Hi,
This is the 18th release of the writeback patchset. Changes since
v17 include:
- Change the naming of sync_sb_inodes() and sync_sb_inodes_wait(). It's
now writeback_inodes_sb() to start writeback on dirty sb inodes, and
sync_inodes_sb() to start and wait on writeback. Suggestion from Jan
Kara, and I agree it better explains what the code does.
- Fix compile error in pohmelfs.
- Update Ted's MAX_WRITEBACK_PAGES patch to be MB based instead of in
pages.
- Integrate the suggestions from Christoph:
- Move wakeup_flusher_threads() into fs/fs-writeback.c, it fits
better there and allows us to make bdi_writeback_all() static.
- Get rid of generic_sync_sb_inodes(). Move the issue and wait
into the two callers instead, making the old function now
wait_sb_inodes() and only concerned with waiting on already
issued IO.
- wbc->nr_to_write was mistakenly set to LLONG_MAX instead of
LONG_MAX.
Please review, thanks!
b/block/blk-core.c | 1
b/drivers/block/aoe/aoeblk.c | 1
b/drivers/char/mem.c | 1
b/drivers/staging/pohmelfs/inode.c | 9
b/fs/btrfs/disk-io.c | 1
b/fs/buffer.c | 2
b/fs/char_dev.c | 1
b/fs/configfs/inode.c | 1
b/fs/fs-writeback.c | 1042 +++++++++++++++++++++--------
b/fs/fuse/inode.c | 1
b/fs/hugetlbfs/inode.c | 1
b/fs/nfs/client.c | 1
b/fs/ocfs2/dlm/dlmfs.c | 1
b/fs/ramfs/inode.c | 1
b/fs/super.c | 3
b/fs/sync.c | 20
b/fs/sysfs/inode.c | 1
b/fs/ubifs/budget.c | 16
b/fs/ubifs/super.c | 9
b/include/linux/backing-dev.h | 55 +
b/include/linux/fs.h | 8
b/include/linux/writeback.h | 24
b/kernel/cgroup.c | 1
b/kernel/sysctl.c | 8
b/mm/Makefile | 2
b/mm/backing-dev.c | 379 ++++++++++
b/mm/page-writeback.c | 183 -----
b/mm/swap_state.c | 1
b/mm/vmscan.c | 2
mm/pdflush.c | 269 -------
30 files changed, 1267 insertions(+), 778 deletions(-)
--
Jens Axboe
This adds two new exported functions:
- writeback_inodes_sb(), which only attempts to writeback dirty inodes on
this super_block, for WB_SYNC_NONE writeout.
- sync_inodes_sbt(), which writes out all dirty inodes on this super_block
and also waits for the IO to complete.
Signed-off-by: Jens Axboe <[email protected]>
---
drivers/staging/pohmelfs/inode.c | 9 +----
fs/fs-writeback.c | 70 ++++++++++++++++++++++---------------
fs/sync.c | 18 +++++----
fs/ubifs/budget.c | 16 +-------
fs/ubifs/super.c | 8 +----
include/linux/fs.h | 2 -
include/linux/writeback.h | 3 +-
7 files changed, 58 insertions(+), 68 deletions(-)
diff --git a/drivers/staging/pohmelfs/inode.c b/drivers/staging/pohmelfs/inode.c
index 7b60579..e63c9be 100644
--- a/drivers/staging/pohmelfs/inode.c
+++ b/drivers/staging/pohmelfs/inode.c
@@ -1950,14 +1950,7 @@ static int pohmelfs_get_sb(struct file_system_type *fs_type,
*/
static void pohmelfs_kill_super(struct super_block *sb)
{
- struct writeback_control wbc = {
- .sync_mode = WB_SYNC_ALL,
- .range_start = 0,
- .range_end = LLONG_MAX,
- .nr_to_write = LONG_MAX,
- };
- generic_sync_sb_inodes(sb, &wbc);
-
+ sync_inodes_sb(sb);
kill_anon_super(sb);
}
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index c54226b..271e5f4 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -458,8 +458,8 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
* on the writer throttling path, and we get decent balancing between many
* throttled threads: we don't want them all piling up on inode_sync_wait.
*/
-void generic_sync_sb_inodes(struct super_block *sb,
- struct writeback_control *wbc)
+static void generic_sync_sb_inodes(struct super_block *sb,
+ struct writeback_control *wbc)
{
const unsigned long start = jiffies; /* livelock avoidance */
int sync = wbc->sync_mode == WB_SYNC_ALL;
@@ -593,13 +593,6 @@ void generic_sync_sb_inodes(struct super_block *sb,
return; /* Leave any unwritten inodes on s_io */
}
-EXPORT_SYMBOL_GPL(generic_sync_sb_inodes);
-
-static void sync_sb_inodes(struct super_block *sb,
- struct writeback_control *wbc)
-{
- generic_sync_sb_inodes(sb, wbc);
-}
/*
* Start writeback of dirty pagecache data against all unlocked inodes.
@@ -640,7 +633,7 @@ restart:
*/
if (down_read_trylock(&sb->s_umount)) {
if (sb->s_root)
- sync_sb_inodes(sb, wbc);
+ generic_sync_sb_inodes(sb, wbc);
up_read(&sb->s_umount);
}
spin_lock(&sb_lock);
@@ -653,35 +646,56 @@ restart:
spin_unlock(&sb_lock);
}
-/*
- * writeback and wait upon the filesystem's dirty inodes. The caller will
- * do this in two passes - one to write, and one to wait.
- *
- * A finite limit is set on the number of pages which will be written.
- * To prevent infinite livelock of sys_sync().
+/**
+ * writeback_inodes_sb - writeback dirty inodes from given super_block
+ * @sb: the superblock
*
- * We add in the number of potentially dirty inodes, because each inode write
- * can dirty pagecache in the underlying blockdev.
+ * Start writeback on some inodes on this super_block. No guarantees are made
+ * on how many (if any) will be written, and this function does not wait
+ * for IO completion of submitted IO. The number of pages submitted is
+ * returned.
*/
-void sync_inodes_sb(struct super_block *sb, int wait)
+long writeback_inodes_sb(struct super_block *sb)
{
struct writeback_control wbc = {
- .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE,
+ .sync_mode = WB_SYNC_NONE,
.range_start = 0,
.range_end = LLONG_MAX,
};
+ unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
+ unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
+ long nr_to_write;
- if (!wait) {
- unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
- unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
-
- wbc.nr_to_write = nr_dirty + nr_unstable +
+ nr_to_write = nr_dirty + nr_unstable +
(inodes_stat.nr_inodes - inodes_stat.nr_unused);
- } else
- wbc.nr_to_write = LONG_MAX; /* doesn't actually matter */
- sync_sb_inodes(sb, &wbc);
+ wbc.nr_to_write = nr_to_write;
+ generic_sync_sb_inodes(sb, &wbc);
+ return nr_to_write - wbc.nr_to_write;
+}
+EXPORT_SYMBOL(writeback_inodes_sb);
+
+/**
+ * sync_inodes_sb - sync sb inode pages
+ * @sb: the superblock
+ *
+ * This function writes and waits on any dirty inode belonging to this
+ * super_block. The number of pages synced is returned.
+ */
+long sync_inodes_sb(struct super_block *sb)
+{
+ struct writeback_control wbc = {
+ .sync_mode = WB_SYNC_ALL,
+ .range_start = 0,
+ .range_end = LLONG_MAX,
+ };
+ long nr_to_write = LONG_MAX; /* doesn't actually matter */
+
+ wbc.nr_to_write = nr_to_write;
+ generic_sync_sb_inodes(sb, &wbc);
+ return nr_to_write - wbc.nr_to_write;
}
+EXPORT_SYMBOL(sync_inodes_sb);
/**
* write_inode_now - write an inode to disk
diff --git a/fs/sync.c b/fs/sync.c
index 3422ba6..66f2104 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -19,20 +19,22 @@
SYNC_FILE_RANGE_WAIT_AFTER)
/*
- * Do the filesystem syncing work. For simple filesystems sync_inodes_sb(sb, 0)
- * just dirties buffers with inodes so we have to submit IO for these buffers
- * via __sync_blockdev(). This also speeds up the wait == 1 case since in that
- * case write_inode() functions do sync_dirty_buffer() and thus effectively
- * write one block at a time.
+ * Do the filesystem syncing work. For simple filesystems
+ * writeback_inodes_sb(sb) just dirties buffers with inodes so we have to
+ * submit IO for these buffers via __sync_blockdev(). This also speeds up the
+ * wait == 1 case since in that case write_inode() functions do
+ * sync_dirty_buffer() and thus effectively write one block at a time.
*/
static int __sync_filesystem(struct super_block *sb, int wait)
{
/* Avoid doing twice syncing and cache pruning for quota sync */
- if (!wait)
+ if (!wait) {
writeout_quota_sb(sb, -1);
- else
+ writeback_inodes_sb(sb);
+ } else {
sync_quota_sb(sb, -1);
- sync_inodes_sb(sb, wait);
+ sync_inodes_sb(sb);
+ }
if (sb->s_op->sync_fs)
sb->s_op->sync_fs(sb, wait);
return __sync_blockdev(sb->s_bdev, wait);
diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c
index eaf6d89..1c8991b 100644
--- a/fs/ubifs/budget.c
+++ b/fs/ubifs/budget.c
@@ -65,26 +65,14 @@
static int shrink_liability(struct ubifs_info *c, int nr_to_write)
{
int nr_written;
- struct writeback_control wbc = {
- .sync_mode = WB_SYNC_NONE,
- .range_end = LLONG_MAX,
- .nr_to_write = nr_to_write,
- };
-
- generic_sync_sb_inodes(c->vfs_sb, &wbc);
- nr_written = nr_to_write - wbc.nr_to_write;
+ nr_written = writeback_inodes_sb(c->vfs_sb);
if (!nr_written) {
/*
* Re-try again but wait on pages/inodes which are being
* written-back concurrently (e.g., by pdflush).
*/
- memset(&wbc, 0, sizeof(struct writeback_control));
- wbc.sync_mode = WB_SYNC_ALL;
- wbc.range_end = LLONG_MAX;
- wbc.nr_to_write = nr_to_write;
- generic_sync_sb_inodes(c->vfs_sb, &wbc);
- nr_written = nr_to_write - wbc.nr_to_write;
+ nr_written = sync_inodes_sb(c->vfs_sb);
}
dbg_budg("%d pages were written back", nr_written);
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 26d2e0d..8d6050a 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -438,12 +438,6 @@ static int ubifs_sync_fs(struct super_block *sb, int wait)
{
int i, err;
struct ubifs_info *c = sb->s_fs_info;
- struct writeback_control wbc = {
- .sync_mode = WB_SYNC_ALL,
- .range_start = 0,
- .range_end = LLONG_MAX,
- .nr_to_write = LONG_MAX,
- };
/*
* Zero @wait is just an advisory thing to help the file system shove
@@ -462,7 +456,7 @@ static int ubifs_sync_fs(struct super_block *sb, int wait)
* the user be able to get more accurate results of 'statfs()' after
* they synchronize the file system.
*/
- generic_sync_sb_inodes(sb, &wbc);
+ sync_inodes_sb(sb);
/*
* Synchronize write buffers, because 'ubifs_run_commit()' does not
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 73e9b64..07b0f66 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2070,8 +2070,6 @@ static inline void invalidate_remote_inode(struct inode *inode)
extern int invalidate_inode_pages2(struct address_space *mapping);
extern int invalidate_inode_pages2_range(struct address_space *mapping,
pgoff_t start, pgoff_t end);
-extern void generic_sync_sb_inodes(struct super_block *sb,
- struct writeback_control *wbc);
extern int write_inode_now(struct inode *, int);
extern int filemap_fdatawrite(struct address_space *);
extern int filemap_flush(struct address_space *);
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 3224820..0703929 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -78,7 +78,8 @@ struct writeback_control {
*/
void writeback_inodes(struct writeback_control *wbc);
int inode_wait(void *);
-void sync_inodes_sb(struct super_block *, int wait);
+long writeback_inodes_sb(struct super_block *);
+long sync_inodes_sb(struct super_block *);
/* writeback.h requires fs.h; it, too, is not included from here. */
static inline void wait_on_inode(struct inode *inode)
--
1.6.4.1.207.g68ea
This is a first step at introducing per-bdi flusher threads. We should
have no change in behaviour, although sb_has_dirty_inodes() is now
ridiculously expensive, as there's no easy way to answer that question.
Not a huge problem, since it'll be deleted in subsequent patches.
Signed-off-by: Jens Axboe <[email protected]>
---
fs/fs-writeback.c | 197 ++++++++++++++++++++++++++++---------------
fs/super.c | 3 -
include/linux/backing-dev.h | 9 ++
include/linux/fs.h | 5 +-
mm/backing-dev.c | 24 +++++
mm/page-writeback.c | 11 +--
6 files changed, 165 insertions(+), 84 deletions(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 271e5f4..45ad4bb 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -25,6 +25,7 @@
#include <linux/buffer_head.h>
#include "internal.h"
+#define inode_to_bdi(inode) ((inode)->i_mapping->backing_dev_info)
/**
* writeback_acquire - attempt to get exclusive writeback access to a device
@@ -165,12 +166,13 @@ void __mark_inode_dirty(struct inode *inode, int flags)
goto out;
/*
- * If the inode was already on s_dirty/s_io/s_more_io, don't
- * reposition it (that would break s_dirty time-ordering).
+ * If the inode was already on b_dirty/b_io/b_more_io, don't
+ * reposition it (that would break b_dirty time-ordering).
*/
if (!was_dirty) {
inode->dirtied_when = jiffies;
- list_move(&inode->i_list, &sb->s_dirty);
+ list_move(&inode->i_list,
+ &inode_to_bdi(inode)->b_dirty);
}
}
out:
@@ -191,31 +193,30 @@ static int write_inode(struct inode *inode, int sync)
* furthest end of its superblock's dirty-inode list.
*
* Before stamping the inode's ->dirtied_when, we check to see whether it is
- * already the most-recently-dirtied inode on the s_dirty list. If that is
+ * already the most-recently-dirtied inode on the b_dirty list. If that is
* the case then the inode must have been redirtied while it was being written
* out and we don't reset its dirtied_when.
*/
static void redirty_tail(struct inode *inode)
{
- struct super_block *sb = inode->i_sb;
+ struct backing_dev_info *bdi = inode_to_bdi(inode);
- if (!list_empty(&sb->s_dirty)) {
- struct inode *tail_inode;
+ if (!list_empty(&bdi->b_dirty)) {
+ struct inode *tail;
- tail_inode = list_entry(sb->s_dirty.next, struct inode, i_list);
- if (time_before(inode->dirtied_when,
- tail_inode->dirtied_when))
+ tail = list_entry(bdi->b_dirty.next, struct inode, i_list);
+ if (time_before(inode->dirtied_when, tail->dirtied_when))
inode->dirtied_when = jiffies;
}
- list_move(&inode->i_list, &sb->s_dirty);
+ list_move(&inode->i_list, &bdi->b_dirty);
}
/*
- * requeue inode for re-scanning after sb->s_io list is exhausted.
+ * requeue inode for re-scanning after bdi->b_io list is exhausted.
*/
static void requeue_io(struct inode *inode)
{
- list_move(&inode->i_list, &inode->i_sb->s_more_io);
+ list_move(&inode->i_list, &inode_to_bdi(inode)->b_more_io);
}
static void inode_sync_complete(struct inode *inode)
@@ -262,18 +263,50 @@ static void move_expired_inodes(struct list_head *delaying_queue,
/*
* Queue all expired dirty inodes for io, eldest first.
*/
-static void queue_io(struct super_block *sb,
- unsigned long *older_than_this)
+static void queue_io(struct backing_dev_info *bdi,
+ unsigned long *older_than_this)
+{
+ list_splice_init(&bdi->b_more_io, bdi->b_io.prev);
+ move_expired_inodes(&bdi->b_dirty, &bdi->b_io, older_than_this);
+}
+
+static int sb_on_inode_list(struct super_block *sb, struct list_head *list)
{
- list_splice_init(&sb->s_more_io, sb->s_io.prev);
- move_expired_inodes(&sb->s_dirty, &sb->s_io, older_than_this);
+ struct inode *inode;
+ int ret = 0;
+
+ spin_lock(&inode_lock);
+ list_for_each_entry(inode, list, i_list) {
+ if (inode->i_sb == sb) {
+ ret = 1;
+ break;
+ }
+ }
+ spin_unlock(&inode_lock);
+ return ret;
}
int sb_has_dirty_inodes(struct super_block *sb)
{
- return !list_empty(&sb->s_dirty) ||
- !list_empty(&sb->s_io) ||
- !list_empty(&sb->s_more_io);
+ struct backing_dev_info *bdi;
+ int ret = 0;
+
+ /*
+ * This is REALLY expensive right now, but it'll go away
+ * when the bdi writeback is introduced
+ */
+ mutex_lock(&bdi_lock);
+ list_for_each_entry(bdi, &bdi_list, bdi_list) {
+ if (sb_on_inode_list(sb, &bdi->b_dirty) ||
+ sb_on_inode_list(sb, &bdi->b_io) ||
+ sb_on_inode_list(sb, &bdi->b_more_io)) {
+ ret = 1;
+ break;
+ }
+ }
+ mutex_unlock(&bdi_lock);
+
+ return ret;
}
EXPORT_SYMBOL(sb_has_dirty_inodes);
@@ -322,11 +355,11 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
if (inode->i_state & I_SYNC) {
/*
* If this inode is locked for writeback and we are not doing
- * writeback-for-data-integrity, move it to s_more_io so that
+ * writeback-for-data-integrity, move it to b_more_io so that
* writeback can proceed with the other inodes on s_io.
*
* We'll have another go at writing back this inode when we
- * completed a full scan of s_io.
+ * completed a full scan of b_io.
*/
if (!wait) {
requeue_io(inode);
@@ -371,11 +404,11 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
/*
* We didn't write back all the pages. nfs_writepages()
* sometimes bales out without doing anything. Redirty
- * the inode; Move it from s_io onto s_more_io/s_dirty.
+ * the inode; Move it from b_io onto b_more_io/b_dirty.
*/
/*
* akpm: if the caller was the kupdate function we put
- * this inode at the head of s_dirty so it gets first
+ * this inode at the head of b_dirty so it gets first
* consideration. Otherwise, move it to the tail, for
* the reasons described there. I'm not really sure
* how much sense this makes. Presumably I had a good
@@ -385,7 +418,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
if (wbc->for_kupdate) {
/*
* For the kupdate function we move the inode
- * to s_more_io so it will get more writeout as
+ * to b_more_io so it will get more writeout as
* soon as the queue becomes uncongested.
*/
inode->i_state |= I_DIRTY_PAGES;
@@ -433,51 +466,34 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
return ret;
}
-/*
- * Write out a superblock's list of dirty inodes. A wait will be performed
- * upon no inodes, all inodes or the final one, depending upon sync_mode.
- *
- * If older_than_this is non-NULL, then only write out inodes which
- * had their first dirtying at a time earlier than *older_than_this.
- *
- * If we're a pdflush thread, then implement pdflush collision avoidance
- * against the entire list.
- *
- * If `bdi' is non-zero then we're being asked to writeback a specific queue.
- * This function assumes that the blockdev superblock's inodes are backed by
- * a variety of queues, so all inodes are searched. For other superblocks,
- * assume that all inodes are backed by the same queue.
- *
- * FIXME: this linear search could get expensive with many fileystems. But
- * how to fix? We need to go from an address_space to all inodes which share
- * a queue with that address_space. (Easy: have a global "dirty superblocks"
- * list).
- *
- * The inodes to be written are parked on sb->s_io. They are moved back onto
- * sb->s_dirty as they are selected for writing. This way, none can be missed
- * on the writer throttling path, and we get decent balancing between many
- * throttled threads: we don't want them all piling up on inode_sync_wait.
- */
-static void generic_sync_sb_inodes(struct super_block *sb,
- struct writeback_control *wbc)
+static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
+ struct writeback_control *wbc,
+ struct super_block *sb)
{
+ const int is_blkdev_sb = sb_is_blkdev_sb(sb);
const unsigned long start = jiffies; /* livelock avoidance */
- int sync = wbc->sync_mode == WB_SYNC_ALL;
spin_lock(&inode_lock);
- if (!wbc->for_kupdate || list_empty(&sb->s_io))
- queue_io(sb, wbc->older_than_this);
- while (!list_empty(&sb->s_io)) {
- struct inode *inode = list_entry(sb->s_io.prev,
+ if (!wbc->for_kupdate || list_empty(&bdi->b_io))
+ queue_io(bdi, wbc->older_than_this);
+
+ while (!list_empty(&bdi->b_io)) {
+ struct inode *inode = list_entry(bdi->b_io.prev,
struct inode, i_list);
- struct address_space *mapping = inode->i_mapping;
- struct backing_dev_info *bdi = mapping->backing_dev_info;
long pages_skipped;
+ /*
+ * super block given and doesn't match, skip this inode
+ */
+ if (sb && sb != inode->i_sb) {
+ redirty_tail(inode);
+ continue;
+ }
+
if (!bdi_cap_writeback_dirty(bdi)) {
redirty_tail(inode);
- if (sb_is_blkdev_sb(sb)) {
+ if (is_blkdev_sb) {
/*
* Dirty memory-backed blockdev: the ramdisk
* driver does this. Skip just this inode
@@ -499,14 +515,14 @@ static void generic_sync_sb_inodes(struct super_block *sb,
if (wbc->nonblocking && bdi_write_congested(bdi)) {
wbc->encountered_congestion = 1;
- if (!sb_is_blkdev_sb(sb))
+ if (!is_blkdev_sb)
break; /* Skip a congested fs */
requeue_io(inode);
continue; /* Skip a congested blockdev */
}
if (wbc->bdi && bdi != wbc->bdi) {
- if (!sb_is_blkdev_sb(sb))
+ if (!is_blkdev_sb)
break; /* fs has the wrong queue */
requeue_io(inode);
continue; /* blockdev has wrong queue */
@@ -544,13 +560,57 @@ static void generic_sync_sb_inodes(struct super_block *sb,
wbc->more_io = 1;
break;
}
- if (!list_empty(&sb->s_more_io))
+ if (!list_empty(&bdi->b_more_io))
wbc->more_io = 1;
}
- if (sync) {
+ spin_unlock(&inode_lock);
+ /* Leave any unwritten inodes on b_io */
+}
+
+/*
+ * Write out a superblock's list of dirty inodes. A wait will be performed
+ * upon no inodes, all inodes or the final one, depending upon sync_mode.
+ *
+ * If older_than_this is non-NULL, then only write out inodes which
+ * had their first dirtying at a time earlier than *older_than_this.
+ *
+ * If we're a pdlfush thread, then implement pdflush collision avoidance
+ * against the entire list.
+ *
+ * If `bdi' is non-zero then we're being asked to writeback a specific queue.
+ * This function assumes that the blockdev superblock's inodes are backed by
+ * a variety of queues, so all inodes are searched. For other superblocks,
+ * assume that all inodes are backed by the same queue.
+ *
+ * FIXME: this linear search could get expensive with many fileystems. But
+ * how to fix? We need to go from an address_space to all inodes which share
+ * a queue with that address_space. (Easy: have a global "dirty superblocks"
+ * list).
+ *
+ * The inodes to be written are parked on bdi->b_io. They are moved back onto
+ * bdi->b_dirty as they are selected for writing. This way, none can be missed
+ * on the writer throttling path, and we get decent balancing between many
+ * throttled threads: we don't want them all piling up on inode_sync_wait.
+ */
+static void generic_sync_sb_inodes(struct super_block *sb,
+ struct writeback_control *wbc)
+{
+ struct backing_dev_info *bdi;
+
+ if (!wbc->bdi) {
+ mutex_lock(&bdi_lock);
+ list_for_each_entry(bdi, &bdi_list, bdi_list)
+ generic_sync_bdi_inodes(bdi, wbc, sb);
+ mutex_unlock(&bdi_lock);
+ } else
+ generic_sync_bdi_inodes(wbc->bdi, wbc, sb);
+
+ if (wbc->sync_mode == WB_SYNC_ALL) {
struct inode *inode, *old_inode = NULL;
+ spin_lock(&inode_lock);
+
/*
* Data integrity sync. Must wait for all pages under writeback,
* because there may have been pages dirtied before our sync
@@ -588,10 +648,7 @@ static void generic_sync_sb_inodes(struct super_block *sb,
}
spin_unlock(&inode_lock);
iput(old_inode);
- } else
- spin_unlock(&inode_lock);
-
- return; /* Leave any unwritten inodes on s_io */
+ }
}
/*
@@ -599,8 +656,8 @@ static void generic_sync_sb_inodes(struct super_block *sb,
*
* Note:
* We don't need to grab a reference to superblock here. If it has non-empty
- * ->s_dirty it's hadn't been killed yet and kill_super() won't proceed
- * past sync_inodes_sb() until the ->s_dirty/s_io/s_more_io lists are all
+ * ->b_dirty it's hadn't been killed yet and kill_super() won't proceed
+ * past sync_inodes_sb() until the ->b_dirty/b_io/b_more_io lists are all
* empty. Since __sync_single_inode() regains inode_lock before it finally moves
* inode from superblock lists we are OK.
*
diff --git a/fs/super.c b/fs/super.c
index 2761d3e..0d22ce3 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -62,9 +62,6 @@ static struct super_block *alloc_super(struct file_system_type *type)
s = NULL;
goto out;
}
- INIT_LIST_HEAD(&s->s_dirty);
- INIT_LIST_HEAD(&s->s_io);
- INIT_LIST_HEAD(&s->s_more_io);
INIT_LIST_HEAD(&s->s_files);
INIT_LIST_HEAD(&s->s_instances);
INIT_HLIST_HEAD(&s->s_anon);
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 1d52425..928cd54 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -40,6 +40,8 @@ enum bdi_stat_item {
#define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids)))
struct backing_dev_info {
+ struct list_head bdi_list;
+
unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */
unsigned long state; /* Always use atomic bitops on this */
unsigned int capabilities; /* Device capabilities */
@@ -58,6 +60,10 @@ struct backing_dev_info {
struct device *dev;
+ struct list_head b_dirty; /* dirty inodes */
+ struct list_head b_io; /* parked for writeback */
+ struct list_head b_more_io; /* parked for more writeback */
+
#ifdef CONFIG_DEBUG_FS
struct dentry *debug_dir;
struct dentry *debug_stats;
@@ -72,6 +78,9 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
void bdi_unregister(struct backing_dev_info *bdi);
+extern struct mutex bdi_lock;
+extern struct list_head bdi_list;
+
static inline void __add_bdi_stat(struct backing_dev_info *bdi,
enum bdi_stat_item item, s64 amount)
{
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 07b0f66..97949b7 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -715,7 +715,7 @@ struct posix_acl;
struct inode {
struct hlist_node i_hash;
- struct list_head i_list;
+ struct list_head i_list; /* backing dev IO list */
struct list_head i_sb_list;
struct list_head i_dentry;
unsigned long i_ino;
@@ -1336,9 +1336,6 @@ struct super_block {
struct xattr_handler **s_xattr;
struct list_head s_inodes; /* all inodes */
- struct list_head s_dirty; /* dirty inodes */
- struct list_head s_io; /* parked for writeback */
- struct list_head s_more_io; /* parked for more writeback */
struct hlist_head s_anon; /* anonymous dentries for (nfs) exporting */
struct list_head s_files;
/* s_dentry_lru and s_nr_dentry_unused are protected by dcache_lock */
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index c86edd2..6f163e0 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -22,6 +22,8 @@ struct backing_dev_info default_backing_dev_info = {
EXPORT_SYMBOL_GPL(default_backing_dev_info);
static struct class *bdi_class;
+DEFINE_MUTEX(bdi_lock);
+LIST_HEAD(bdi_list);
#ifdef CONFIG_DEBUG_FS
#include <linux/debugfs.h>
@@ -211,6 +213,10 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
goto exit;
}
+ mutex_lock(&bdi_lock);
+ list_add_tail(&bdi->bdi_list, &bdi_list);
+ mutex_unlock(&bdi_lock);
+
bdi->dev = dev;
bdi_debug_register(bdi, dev_name(dev));
@@ -225,9 +231,17 @@ int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev)
}
EXPORT_SYMBOL(bdi_register_dev);
+static void bdi_remove_from_list(struct backing_dev_info *bdi)
+{
+ mutex_lock(&bdi_lock);
+ list_del(&bdi->bdi_list);
+ mutex_unlock(&bdi_lock);
+}
+
void bdi_unregister(struct backing_dev_info *bdi)
{
if (bdi->dev) {
+ bdi_remove_from_list(bdi);
bdi_debug_unregister(bdi);
device_unregister(bdi->dev);
bdi->dev = NULL;
@@ -245,6 +259,10 @@ int bdi_init(struct backing_dev_info *bdi)
bdi->min_ratio = 0;
bdi->max_ratio = 100;
bdi->max_prop_frac = PROP_FRAC_BASE;
+ INIT_LIST_HEAD(&bdi->bdi_list);
+ INIT_LIST_HEAD(&bdi->b_io);
+ INIT_LIST_HEAD(&bdi->b_dirty);
+ INIT_LIST_HEAD(&bdi->b_more_io);
for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
err = percpu_counter_init(&bdi->bdi_stat[i], 0);
@@ -259,6 +277,8 @@ int bdi_init(struct backing_dev_info *bdi)
err:
while (i--)
percpu_counter_destroy(&bdi->bdi_stat[i]);
+
+ bdi_remove_from_list(bdi);
}
return err;
@@ -269,6 +289,10 @@ void bdi_destroy(struct backing_dev_info *bdi)
{
int i;
+ WARN_ON(!list_empty(&bdi->b_dirty));
+ WARN_ON(!list_empty(&bdi->b_io));
+ WARN_ON(!list_empty(&bdi->b_more_io));
+
bdi_unregister(bdi);
for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 81627eb..f8341b6 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -320,15 +320,13 @@ static void task_dirty_limit(struct task_struct *tsk, unsigned long *pdirty)
/*
*
*/
-static DEFINE_SPINLOCK(bdi_lock);
static unsigned int bdi_min_ratio;
int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
{
int ret = 0;
- unsigned long flags;
- spin_lock_irqsave(&bdi_lock, flags);
+ mutex_lock(&bdi_lock);
if (min_ratio > bdi->max_ratio) {
ret = -EINVAL;
} else {
@@ -340,27 +338,26 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
ret = -EINVAL;
}
}
- spin_unlock_irqrestore(&bdi_lock, flags);
+ mutex_unlock(&bdi_lock);
return ret;
}
int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio)
{
- unsigned long flags;
int ret = 0;
if (max_ratio > 100)
return -EINVAL;
- spin_lock_irqsave(&bdi_lock, flags);
+ mutex_lock(&bdi_lock);
if (bdi->min_ratio > max_ratio) {
ret = -EINVAL;
} else {
bdi->max_ratio = max_ratio;
bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100;
}
- spin_unlock_irqrestore(&bdi_lock, flags);
+ mutex_unlock(&bdi_lock);
return ret;
}
--
1.6.4.1.207.g68ea
This gets rid of pdflush for bdi writeout and kupdated style cleaning.
pdflush writeout suffers from lack of locality and also requires more
threads to handle the same workload, since it has to work in a
non-blocking fashion against each queue. This also introduces lumpy
behaviour and potential request starvation, since pdflush can be starved
for queue access if others are accessing it. A sample ffsb workload that
does random writes to files is about 8% faster here on a simple SATA drive
during the benchmark phase. File layout also seems a LOT more smooth in
vmstat:
r b swpd free buff cache si so bi bo in cs us sy id wa
0 1 0 608848 2652 375372 0 0 0 71024 604 24 1 10 48 42
0 1 0 549644 2712 433736 0 0 0 60692 505 27 1 8 48 44
1 0 0 476928 2784 505192 0 0 4 29540 553 24 0 9 53 37
0 1 0 457972 2808 524008 0 0 0 54876 331 16 0 4 38 58
0 1 0 366128 2928 614284 0 0 4 92168 710 58 0 13 53 34
0 1 0 295092 3000 684140 0 0 0 62924 572 23 0 9 53 37
0 1 0 236592 3064 741704 0 0 4 58256 523 17 0 8 48 44
0 1 0 165608 3132 811464 0 0 0 57460 560 21 0 8 54 38
0 1 0 102952 3200 873164 0 0 4 74748 540 29 1 10 48 41
0 1 0 48604 3252 926472 0 0 0 53248 469 29 0 7 47 45
where vanilla tends to fluctuate a lot in the creation phase:
r b swpd free buff cache si so bi bo in cs us sy id wa
1 1 0 678716 5792 303380 0 0 0 74064 565 50 1 11 52 36
1 0 0 662488 5864 319396 0 0 4 352 302 329 0 2 47 51
0 1 0 599312 5924 381468 0 0 0 78164 516 55 0 9 51 40
0 1 0 519952 6008 459516 0 0 4 78156 622 56 1 11 52 37
1 1 0 436640 6092 541632 0 0 0 82244 622 54 0 11 48 41
0 1 0 436640 6092 541660 0 0 0 8 152 39 0 0 51 49
0 1 0 332224 6200 644252 0 0 4 102800 728 46 1 13 49 36
1 0 0 274492 6260 701056 0 0 4 12328 459 49 0 7 50 43
0 1 0 211220 6324 763356 0 0 0 106940 515 37 1 10 51 39
1 0 0 160412 6376 813468 0 0 0 8224 415 43 0 6 49 45
1 1 0 85980 6452 886556 0 0 4 113516 575 39 1 11 54 34
0 2 0 85968 6452 886620 0 0 0 1640 158 211 0 0 46 54
A 10 disk test with btrfs performs 26% faster with per-bdi flushing. A
SSD based writeback test on XFS performs over 20% better as well, with
the throughput being very stable around 1GB/sec, where pdflush only
manages 750MB/sec and fluctuates wildly while doing so. Random buffered
writes to many files behave a lot better as well, as does random mmap'ed
writes.
A separate thread is added to sync the super blocks. In the long term,
adding sync_supers_bdi() functionality could get rid of this thread again.
Signed-off-by: Jens Axboe <[email protected]>
---
fs/buffer.c | 2 +-
fs/fs-writeback.c | 980 ++++++++++++++++++++++++++++++-------------
fs/sync.c | 2 +-
include/linux/backing-dev.h | 55 +++-
include/linux/fs.h | 1 -
include/linux/writeback.h | 8 +-
mm/backing-dev.c | 340 ++++++++++++++-
mm/page-writeback.c | 174 ++-------
mm/vmscan.c | 2 +-
9 files changed, 1094 insertions(+), 470 deletions(-)
diff --git a/fs/buffer.c b/fs/buffer.c
index 28f320f..90a9886 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -281,7 +281,7 @@ static void free_more_memory(void)
struct zone *zone;
int nid;
- wakeup_pdflush(1024);
+ wakeup_flusher_threads(1024);
yield();
for_each_online_node(nid) {
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 45ad4bb..93aa9a7 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -19,6 +19,8 @@
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/mm.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
@@ -27,165 +29,213 @@
#define inode_to_bdi(inode) ((inode)->i_mapping->backing_dev_info)
-/**
- * writeback_acquire - attempt to get exclusive writeback access to a device
- * @bdi: the device's backing_dev_info structure
- *
- * It is a waste of resources to have more than one pdflush thread blocked on
- * a single request queue. Exclusion at the request_queue level is obtained
- * via a flag in the request_queue's backing_dev_info.state.
- *
- * Non-request_queue-backed address_spaces will share default_backing_dev_info,
- * unless they implement their own. Which is somewhat inefficient, as this
- * may prevent concurrent writeback against multiple devices.
+/*
+ * Work items for the bdi_writeback threads
*/
-static int writeback_acquire(struct backing_dev_info *bdi)
+struct bdi_work {
+ struct list_head list;
+ struct list_head wait_list;
+ struct rcu_head rcu_head;
+
+ unsigned long seen;
+ atomic_t pending;
+
+ struct super_block *sb;
+ unsigned long nr_pages;
+ enum writeback_sync_modes sync_mode;
+
+ unsigned long state;
+};
+
+enum {
+ WS_USED_B = 0,
+ WS_ONSTACK_B,
+};
+
+#define WS_USED (1 << WS_USED_B)
+#define WS_ONSTACK (1 << WS_ONSTACK_B)
+
+static inline bool bdi_work_on_stack(struct bdi_work *work)
+{
+ return test_bit(WS_ONSTACK_B, &work->state);
+}
+
+static inline void bdi_work_init(struct bdi_work *work,
+ struct writeback_control *wbc)
{
- return !test_and_set_bit(BDI_pdflush, &bdi->state);
+ INIT_RCU_HEAD(&work->rcu_head);
+ work->sb = wbc->sb;
+ work->nr_pages = wbc->nr_to_write;
+ work->sync_mode = wbc->sync_mode;
+ work->state = WS_USED;
+}
+
+static inline void bdi_work_init_on_stack(struct bdi_work *work,
+ struct writeback_control *wbc)
+{
+ bdi_work_init(work, wbc);
+ work->state |= WS_ONSTACK;
}
/**
* writeback_in_progress - determine whether there is writeback in progress
* @bdi: the device's backing_dev_info structure.
*
- * Determine whether there is writeback in progress against a backing device.
+ * Determine whether there is writeback waiting to be handled against a
+ * backing device.
*/
int writeback_in_progress(struct backing_dev_info *bdi)
{
- return test_bit(BDI_pdflush, &bdi->state);
+ return !list_empty(&bdi->work_list);
}
-/**
- * writeback_release - relinquish exclusive writeback access against a device.
- * @bdi: the device's backing_dev_info structure
- */
-static void writeback_release(struct backing_dev_info *bdi)
+static void bdi_work_clear(struct bdi_work *work)
{
- BUG_ON(!writeback_in_progress(bdi));
- clear_bit(BDI_pdflush, &bdi->state);
+ clear_bit(WS_USED_B, &work->state);
+ smp_mb__after_clear_bit();
+ wake_up_bit(&work->state, WS_USED_B);
}
-static noinline void block_dump___mark_inode_dirty(struct inode *inode)
+static void bdi_work_free(struct rcu_head *head)
{
- if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
- struct dentry *dentry;
- const char *name = "?";
+ struct bdi_work *work = container_of(head, struct bdi_work, rcu_head);
- dentry = d_find_alias(inode);
- if (dentry) {
- spin_lock(&dentry->d_lock);
- name = (const char *) dentry->d_name.name;
- }
- printk(KERN_DEBUG
- "%s(%d): dirtied inode %lu (%s) on %s\n",
- current->comm, task_pid_nr(current), inode->i_ino,
- name, inode->i_sb->s_id);
- if (dentry) {
- spin_unlock(&dentry->d_lock);
- dput(dentry);
- }
- }
+ if (!bdi_work_on_stack(work))
+ kfree(work);
+ else
+ bdi_work_clear(work);
}
-/**
- * __mark_inode_dirty - internal function
- * @inode: inode to mark
- * @flags: what kind of dirty (i.e. I_DIRTY_SYNC)
- * Mark an inode as dirty. Callers should use mark_inode_dirty or
- * mark_inode_dirty_sync.
- *
- * Put the inode on the super block's dirty list.
- *
- * CAREFUL! We mark it dirty unconditionally, but move it onto the
- * dirty list only if it is hashed or if it refers to a blockdev.
- * If it was not hashed, it will never be added to the dirty list
- * even if it is later hashed, as it will have been marked dirty already.
- *
- * In short, make sure you hash any inodes _before_ you start marking
- * them dirty.
- *
- * This function *must* be atomic for the I_DIRTY_PAGES case -
- * set_page_dirty() is called under spinlock in several places.
- *
- * Note that for blockdevs, inode->dirtied_when represents the dirtying time of
- * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of
- * the kernel-internal blockdev inode represents the dirtying time of the
- * blockdev's pages. This is why for I_DIRTY_PAGES we always use
- * page->mapping->host, so the page-dirtying time is recorded in the internal
- * blockdev inode.
- */
-void __mark_inode_dirty(struct inode *inode, int flags)
+static void wb_work_complete(struct bdi_work *work)
{
- struct super_block *sb = inode->i_sb;
+ const enum writeback_sync_modes sync_mode = work->sync_mode;
/*
- * Don't do this for I_DIRTY_PAGES - that doesn't actually
- * dirty the inode itself
+ * For allocated work, we can clear the done/seen bit right here.
+ * For on-stack work, we need to postpone both the clear and free
+ * to after the RCU grace period, since the stack could be invalidated
+ * as soon as bdi_work_clear() has done the wakeup.
*/
- if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
- if (sb->s_op->dirty_inode)
- sb->s_op->dirty_inode(inode);
- }
+ if (!bdi_work_on_stack(work))
+ bdi_work_clear(work);
+ if (sync_mode == WB_SYNC_NONE || bdi_work_on_stack(work))
+ call_rcu(&work->rcu_head, bdi_work_free);
+}
+static void wb_clear_pending(struct bdi_writeback *wb, struct bdi_work *work)
+{
/*
- * make sure that changes are seen by all cpus before we test i_state
- * -- mikulas
+ * The caller has retrieved the work arguments from this work,
+ * drop our reference. If this is the last ref, delete and free it
*/
- smp_mb();
+ if (atomic_dec_and_test(&work->pending)) {
+ struct backing_dev_info *bdi = wb->bdi;
- /* avoid the locking if we can */
- if ((inode->i_state & flags) == flags)
- return;
+ spin_lock(&bdi->wb_lock);
+ list_del_rcu(&work->list);
+ spin_unlock(&bdi->wb_lock);
- if (unlikely(block_dump))
- block_dump___mark_inode_dirty(inode);
+ wb_work_complete(work);
+ }
+}
- spin_lock(&inode_lock);
- if ((inode->i_state & flags) != flags) {
- const int was_dirty = inode->i_state & I_DIRTY;
+static void wb_start_writeback(struct bdi_writeback *wb, struct bdi_work *work)
+{
+ /*
+ * If we failed allocating the bdi work item, wake up the wb thread
+ * always. As a safety precaution, it'll flush out everything
+ */
+ if (!wb_has_dirty_io(wb) && work)
+ wb_clear_pending(wb, work);
+ else if (wb->task)
+ wake_up_process(wb->task);
+}
- inode->i_state |= flags;
+static void bdi_sched_work(struct backing_dev_info *bdi, struct bdi_work *work)
+{
+ wb_start_writeback(&bdi->wb, work);
+}
- /*
- * If the inode is being synced, just update its dirty state.
- * The unlocker will place the inode on the appropriate
- * superblock list, based upon its state.
- */
- if (inode->i_state & I_SYNC)
- goto out;
+static void bdi_queue_work(struct backing_dev_info *bdi, struct bdi_work *work)
+{
+ if (work) {
+ work->seen = bdi->wb_mask;
+ BUG_ON(!work->seen);
+ atomic_set(&work->pending, bdi->wb_cnt);
+ BUG_ON(!bdi->wb_cnt);
/*
- * Only add valid (hashed) inodes to the superblock's
- * dirty list. Add blockdev inodes as well.
+ * Make sure stores are seen before it appears on the list
*/
- if (!S_ISBLK(inode->i_mode)) {
- if (hlist_unhashed(&inode->i_hash))
- goto out;
- }
- if (inode->i_state & (I_FREEING|I_CLEAR))
- goto out;
+ smp_mb();
- /*
- * If the inode was already on b_dirty/b_io/b_more_io, don't
- * reposition it (that would break b_dirty time-ordering).
- */
- if (!was_dirty) {
- inode->dirtied_when = jiffies;
- list_move(&inode->i_list,
- &inode_to_bdi(inode)->b_dirty);
- }
+ spin_lock(&bdi->wb_lock);
+ list_add_tail_rcu(&work->list, &bdi->work_list);
+ spin_unlock(&bdi->wb_lock);
}
-out:
- spin_unlock(&inode_lock);
+
+ /*
+ * If the default thread isn't there, make sure we add it. When
+ * it gets created and wakes up, we'll run this work.
+ */
+ if (unlikely(list_empty_careful(&bdi->wb_list)))
+ wake_up_process(default_backing_dev_info.wb.task);
+ else
+ bdi_sched_work(bdi, work);
}
-EXPORT_SYMBOL(__mark_inode_dirty);
+/*
+ * Used for on-stack allocated work items. The caller needs to wait until
+ * the wb threads have acked the work before it's safe to continue.
+ */
+static void bdi_wait_on_work_clear(struct bdi_work *work)
+{
+ wait_on_bit(&work->state, WS_USED_B, bdi_sched_wait,
+ TASK_UNINTERRUPTIBLE);
+}
-static int write_inode(struct inode *inode, int sync)
+static struct bdi_work *bdi_alloc_work(struct writeback_control *wbc)
{
- if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode))
- return inode->i_sb->s_op->write_inode(inode, sync);
- return 0;
+ struct bdi_work *work;
+
+ work = kmalloc(sizeof(*work), GFP_ATOMIC);
+ if (work)
+ bdi_work_init(work, wbc);
+
+ return work;
+}
+
+void bdi_start_writeback(struct writeback_control *wbc)
+{
+ const bool must_wait = wbc->sync_mode == WB_SYNC_ALL;
+ struct bdi_work work_stack, *work = NULL;
+
+ if (!must_wait)
+ work = bdi_alloc_work(wbc);
+
+ if (!work) {
+ work = &work_stack;
+ bdi_work_init_on_stack(work, wbc);
+ }
+
+ bdi_queue_work(wbc->bdi, work);
+
+ /*
+ * If the sync mode is WB_SYNC_ALL, block waiting for the work to
+ * complete. If not, we only need to wait for the work to be started,
+ * if we allocated it on-stack. We use the same mechanism, if the
+ * wait bit is set in the bdi_work struct, then threads will not
+ * clear pending until after they are done.
+ *
+ * Note that work == &work_stack if must_wait is true, so we don't
+ * need to do call_rcu() here ever, since the completion path will
+ * have done that for us.
+ */
+ if (must_wait || work == &work_stack) {
+ bdi_wait_on_work_clear(work);
+ if (work != &work_stack)
+ call_rcu(&work->rcu_head, bdi_work_free);
+ }
}
/*
@@ -199,16 +249,16 @@ static int write_inode(struct inode *inode, int sync)
*/
static void redirty_tail(struct inode *inode)
{
- struct backing_dev_info *bdi = inode_to_bdi(inode);
+ struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
- if (!list_empty(&bdi->b_dirty)) {
+ if (!list_empty(&wb->b_dirty)) {
struct inode *tail;
- tail = list_entry(bdi->b_dirty.next, struct inode, i_list);
+ tail = list_entry(wb->b_dirty.next, struct inode, i_list);
if (time_before(inode->dirtied_when, tail->dirtied_when))
inode->dirtied_when = jiffies;
}
- list_move(&inode->i_list, &bdi->b_dirty);
+ list_move(&inode->i_list, &wb->b_dirty);
}
/*
@@ -216,7 +266,9 @@ static void redirty_tail(struct inode *inode)
*/
static void requeue_io(struct inode *inode)
{
- list_move(&inode->i_list, &inode_to_bdi(inode)->b_more_io);
+ struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
+
+ list_move(&inode->i_list, &wb->b_more_io);
}
static void inode_sync_complete(struct inode *inode)
@@ -263,52 +315,18 @@ static void move_expired_inodes(struct list_head *delaying_queue,
/*
* Queue all expired dirty inodes for io, eldest first.
*/
-static void queue_io(struct backing_dev_info *bdi,
- unsigned long *older_than_this)
+static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this)
{
- list_splice_init(&bdi->b_more_io, bdi->b_io.prev);
- move_expired_inodes(&bdi->b_dirty, &bdi->b_io, older_than_this);
-}
-
-static int sb_on_inode_list(struct super_block *sb, struct list_head *list)
-{
- struct inode *inode;
- int ret = 0;
-
- spin_lock(&inode_lock);
- list_for_each_entry(inode, list, i_list) {
- if (inode->i_sb == sb) {
- ret = 1;
- break;
- }
- }
- spin_unlock(&inode_lock);
- return ret;
+ list_splice_init(&wb->b_more_io, wb->b_io.prev);
+ move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
}
-int sb_has_dirty_inodes(struct super_block *sb)
+static int write_inode(struct inode *inode, int sync)
{
- struct backing_dev_info *bdi;
- int ret = 0;
-
- /*
- * This is REALLY expensive right now, but it'll go away
- * when the bdi writeback is introduced
- */
- mutex_lock(&bdi_lock);
- list_for_each_entry(bdi, &bdi_list, bdi_list) {
- if (sb_on_inode_list(sb, &bdi->b_dirty) ||
- sb_on_inode_list(sb, &bdi->b_io) ||
- sb_on_inode_list(sb, &bdi->b_more_io)) {
- ret = 1;
- break;
- }
- }
- mutex_unlock(&bdi_lock);
-
- return ret;
+ if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode))
+ return inode->i_sb->s_op->write_inode(inode, sync);
+ return 0;
}
-EXPORT_SYMBOL(sb_has_dirty_inodes);
/*
* Wait for writeback on an inode to complete.
@@ -466,20 +484,70 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
return ret;
}
-static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
- struct writeback_control *wbc,
- struct super_block *sb)
+/*
+ * For WB_SYNC_NONE writeback, the caller does not have the sb pinned
+ * before calling writeback. So make sure that we do pin it, so it doesn't
+ * go away while we are writing inodes from it.
+ */
+static int pin_sb_for_writeback(struct writeback_control *wbc,
+ struct inode *inode)
{
+ struct super_block *sb = inode->i_sb;
+
+ /*
+ * Caller must already hold the ref for this
+ */
+ if (wbc->sync_mode == WB_SYNC_ALL) {
+ WARN_ON(!rwsem_is_locked(&sb->s_umount));
+ return 0;
+ }
+
+ spin_lock(&sb_lock);
+ sb->s_count++;
+ if (down_read_trylock(&sb->s_umount)) {
+ if (sb->s_root) {
+ spin_unlock(&sb_lock);
+ return 0;
+ }
+ /*
+ * umounted, drop rwsem again and fall through to failure
+ */
+ up_read(&sb->s_umount);
+ }
+
+ __put_super_and_need_restart(sb);
+ spin_unlock(&sb_lock);
+ return 1;
+}
+
+static void unpin_sb_for_writeback(struct writeback_control *wbc,
+ struct inode *inode)
+{
+ struct super_block *sb = inode->i_sb;
+
+ if (wbc->sync_mode == WB_SYNC_ALL)
+ return;
+
+ up_read(&sb->s_umount);
+ spin_lock(&sb_lock);
+ __put_super_and_need_restart(sb);
+ spin_unlock(&sb_lock);
+}
+
+static void writeback_inodes_wb(struct bdi_writeback *wb,
+ struct writeback_control *wbc)
+{
+ struct super_block *sb = wbc->sb;
const int is_blkdev_sb = sb_is_blkdev_sb(sb);
const unsigned long start = jiffies; /* livelock avoidance */
spin_lock(&inode_lock);
- if (!wbc->for_kupdate || list_empty(&bdi->b_io))
- queue_io(bdi, wbc->older_than_this);
+ if (!wbc->for_kupdate || list_empty(&wb->b_io))
+ queue_io(wb, wbc->older_than_this);
- while (!list_empty(&bdi->b_io)) {
- struct inode *inode = list_entry(bdi->b_io.prev,
+ while (!list_empty(&wb->b_io)) {
+ struct inode *inode = list_entry(wb->b_io.prev,
struct inode, i_list);
long pages_skipped;
@@ -491,7 +559,7 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
continue;
}
- if (!bdi_cap_writeback_dirty(bdi)) {
+ if (!bdi_cap_writeback_dirty(wb->bdi)) {
redirty_tail(inode);
if (is_blkdev_sb) {
/*
@@ -513,7 +581,7 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
continue;
}
- if (wbc->nonblocking && bdi_write_congested(bdi)) {
+ if (wbc->nonblocking && bdi_write_congested(wb->bdi)) {
wbc->encountered_congestion = 1;
if (!is_blkdev_sb)
break; /* Skip a congested fs */
@@ -521,13 +589,6 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
continue; /* Skip a congested blockdev */
}
- if (wbc->bdi && bdi != wbc->bdi) {
- if (!is_blkdev_sb)
- break; /* fs has the wrong queue */
- requeue_io(inode);
- continue; /* blockdev has wrong queue */
- }
-
/*
* Was this inode dirtied after sync_sb_inodes was called?
* This keeps sync from extra jobs and livelock.
@@ -535,16 +596,16 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
if (inode_dirtied_after(inode, start))
break;
- /* Is another pdflush already flushing this queue? */
- if (current_is_pdflush() && !writeback_acquire(bdi))
- break;
+ if (pin_sb_for_writeback(wbc, inode)) {
+ requeue_io(inode);
+ continue;
+ }
BUG_ON(inode->i_state & (I_FREEING | I_CLEAR));
__iget(inode);
pages_skipped = wbc->pages_skipped;
writeback_single_inode(inode, wbc);
- if (current_is_pdflush())
- writeback_release(bdi);
+ unpin_sb_for_writeback(wbc, inode);
if (wbc->pages_skipped != pages_skipped) {
/*
* writeback is not making progress due to locked
@@ -560,7 +621,7 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
wbc->more_io = 1;
break;
}
- if (!list_empty(&bdi->b_more_io))
+ if (!list_empty(&wb->b_more_io))
wbc->more_io = 1;
}
@@ -568,139 +629,475 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
/* Leave any unwritten inodes on b_io */
}
+void writeback_inodes_wbc(struct writeback_control *wbc)
+{
+ struct backing_dev_info *bdi = wbc->bdi;
+
+ writeback_inodes_wb(&bdi->wb, wbc);
+}
+
/*
- * Write out a superblock's list of dirty inodes. A wait will be performed
- * upon no inodes, all inodes or the final one, depending upon sync_mode.
- *
- * If older_than_this is non-NULL, then only write out inodes which
- * had their first dirtying at a time earlier than *older_than_this.
- *
- * If we're a pdlfush thread, then implement pdflush collision avoidance
- * against the entire list.
+ * The maximum number of pages to writeout in a single bdi flush/kupdate
+ * operation. We do this so we don't hold I_SYNC against an inode for
+ * enormous amounts of time, which would block a userspace task which has
+ * been forced to throttle against that inode. Also, the code reevaluates
+ * the dirty each time it has written this many pages.
+ */
+#define MAX_WRITEBACK_PAGES 1024
+
+static inline bool over_bground_thresh(void)
+{
+ unsigned long background_thresh, dirty_thresh;
+
+ get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
+
+ return (global_page_state(NR_FILE_DIRTY) +
+ global_page_state(NR_UNSTABLE_NFS) >= background_thresh);
+}
+
+/*
+ * Explicit flushing or periodic writeback of "old" data.
*
- * If `bdi' is non-zero then we're being asked to writeback a specific queue.
- * This function assumes that the blockdev superblock's inodes are backed by
- * a variety of queues, so all inodes are searched. For other superblocks,
- * assume that all inodes are backed by the same queue.
+ * Define "old": the first time one of an inode's pages is dirtied, we mark the
+ * dirtying-time in the inode's address_space. So this periodic writeback code
+ * just walks the superblock inode list, writing back any inodes which are
+ * older than a specific point in time.
*
- * FIXME: this linear search could get expensive with many fileystems. But
- * how to fix? We need to go from an address_space to all inodes which share
- * a queue with that address_space. (Easy: have a global "dirty superblocks"
- * list).
+ * Try to run once per dirty_writeback_interval. But if a writeback event
+ * takes longer than a dirty_writeback_interval interval, then leave a
+ * one-second gap.
*
- * The inodes to be written are parked on bdi->b_io. They are moved back onto
- * bdi->b_dirty as they are selected for writing. This way, none can be missed
- * on the writer throttling path, and we get decent balancing between many
- * throttled threads: we don't want them all piling up on inode_sync_wait.
+ * older_than_this takes precedence over nr_to_write. So we'll only write back
+ * all dirty pages if they are all attached to "old" mappings.
*/
-static void generic_sync_sb_inodes(struct super_block *sb,
- struct writeback_control *wbc)
+static long wb_writeback(struct bdi_writeback *wb, long nr_pages,
+ struct super_block *sb,
+ enum writeback_sync_modes sync_mode, int for_kupdate)
{
- struct backing_dev_info *bdi;
+ struct writeback_control wbc = {
+ .bdi = wb->bdi,
+ .sb = sb,
+ .sync_mode = sync_mode,
+ .older_than_this = NULL,
+ .for_kupdate = for_kupdate,
+ .range_cyclic = 1,
+ };
+ unsigned long oldest_jif;
+ long wrote = 0;
- if (!wbc->bdi) {
- mutex_lock(&bdi_lock);
- list_for_each_entry(bdi, &bdi_list, bdi_list)
- generic_sync_bdi_inodes(bdi, wbc, sb);
- mutex_unlock(&bdi_lock);
- } else
- generic_sync_bdi_inodes(wbc->bdi, wbc, sb);
+ if (wbc.for_kupdate) {
+ wbc.older_than_this = &oldest_jif;
+ oldest_jif = jiffies -
+ msecs_to_jiffies(dirty_expire_interval * 10);
+ }
- if (wbc->sync_mode == WB_SYNC_ALL) {
- struct inode *inode, *old_inode = NULL;
+ for (;;) {
+ if (sync_mode == WB_SYNC_NONE && nr_pages <= 0 &&
+ !over_bground_thresh())
+ break;
- spin_lock(&inode_lock);
+ wbc.more_io = 0;
+ wbc.encountered_congestion = 0;
+ wbc.nr_to_write = MAX_WRITEBACK_PAGES;
+ wbc.pages_skipped = 0;
+ writeback_inodes_wb(wb, &wbc);
+ nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
+ wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write;
/*
- * Data integrity sync. Must wait for all pages under writeback,
- * because there may have been pages dirtied before our sync
- * call, but which had writeout started before we write it out.
- * In which case, the inode may not be on the dirty list, but
- * we still have to wait for that writeout.
+ * If we ran out of stuff to write, bail unless more_io got set
*/
- list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
- struct address_space *mapping;
-
- if (inode->i_state &
- (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
- continue;
- mapping = inode->i_mapping;
- if (mapping->nrpages == 0)
+ if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
+ if (wbc.more_io && !wbc.for_kupdate)
continue;
- __iget(inode);
- spin_unlock(&inode_lock);
+ break;
+ }
+ }
+
+ return wrote;
+}
+
+/*
+ * Return the next bdi_work struct that hasn't been processed by this
+ * wb thread yet
+ */
+static struct bdi_work *get_next_work_item(struct backing_dev_info *bdi,
+ struct bdi_writeback *wb)
+{
+ struct bdi_work *work, *ret = NULL;
+
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(work, &bdi->work_list, list) {
+ if (!test_and_clear_bit(wb->nr, &work->seen))
+ continue;
+
+ ret = work;
+ break;
+ }
+
+ rcu_read_unlock();
+ return ret;
+}
+
+/*
+ * Retrieve work items and do the writeback they describe
+ */
+long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
+{
+ struct backing_dev_info *bdi = wb->bdi;
+ struct bdi_work *work;
+ long nr_pages, wrote = 0;
+
+ while ((work = get_next_work_item(bdi, wb)) != NULL) {
+ enum writeback_sync_modes sync_mode;
+
+ nr_pages = work->nr_pages;
+
+ /*
+ * Override sync mode, in case we must wait for completion
+ */
+ if (force_wait)
+ work->sync_mode = sync_mode = WB_SYNC_ALL;
+ else
+ sync_mode = work->sync_mode;
+
+ /*
+ * If this isn't a data integrity operation, just notify
+ * that we have seen this work and we are now starting it.
+ */
+ if (sync_mode == WB_SYNC_NONE)
+ wb_clear_pending(wb, work);
+
+ wrote += wb_writeback(wb, nr_pages, work->sb, sync_mode, 0);
+
+ /*
+ * This is a data integrity writeback, so only do the
+ * notification when we have completed the work.
+ */
+ if (sync_mode == WB_SYNC_ALL)
+ wb_clear_pending(wb, work);
+ }
+
+ /*
+ * Check for periodic writeback, kupdated() style
+ */
+ if (!wrote) {
+ nr_pages = global_page_state(NR_FILE_DIRTY) +
+ global_page_state(NR_UNSTABLE_NFS) +
+ (inodes_stat.nr_inodes - inodes_stat.nr_unused);
+
+ wrote = wb_writeback(wb, nr_pages, NULL, WB_SYNC_NONE, 1);
+ }
+
+ return wrote;
+}
+
+/*
+ * Handle writeback of dirty data for the device backed by this bdi. Also
+ * wakes up periodically and does kupdated style flushing.
+ */
+int bdi_writeback_task(struct bdi_writeback *wb)
+{
+ unsigned long last_active = jiffies;
+ unsigned long wait_jiffies = -1UL;
+ long pages_written;
+
+ while (!kthread_should_stop()) {
+ pages_written = wb_do_writeback(wb, 0);
+
+ if (pages_written)
+ last_active = jiffies;
+ else if (wait_jiffies != -1UL) {
+ unsigned long max_idle;
+
/*
- * We hold a reference to 'inode' so it couldn't have
- * been removed from s_inodes list while we dropped the
- * inode_lock. We cannot iput the inode now as we can
- * be holding the last reference and we cannot iput it
- * under inode_lock. So we keep the reference and iput
- * it later.
+ * Longest period of inactivity that we tolerate. If we
+ * see dirty data again later, the task will get
+ * recreated automatically.
*/
- iput(old_inode);
- old_inode = inode;
+ max_idle = max(5UL * 60 * HZ, wait_jiffies);
+ if (time_after(jiffies, max_idle + last_active))
+ break;
+ }
+
+ wait_jiffies = msecs_to_jiffies(dirty_writeback_interval * 10);
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(wait_jiffies);
+ try_to_freeze();
+ }
- filemap_fdatawait(mapping);
+ return 0;
+}
- cond_resched();
+/*
+ * Schedule writeback for all backing devices. Expensive! If this is a data
+ * integrity operation, writeback will be complete when this returns. If
+ * we are simply called for WB_SYNC_NONE, then writeback will merely be
+ * scheduled to run.
+ */
+static void bdi_writeback_all(struct writeback_control *wbc)
+{
+ const bool must_wait = wbc->sync_mode == WB_SYNC_ALL;
+ struct backing_dev_info *bdi;
+ struct bdi_work *work;
+ LIST_HEAD(list);
+
+restart:
+ spin_lock(&bdi_lock);
+
+ list_for_each_entry(bdi, &bdi_list, bdi_list) {
+ struct bdi_work *work;
+
+ if (!bdi_has_dirty_io(bdi))
+ continue;
- spin_lock(&inode_lock);
+ /*
+ * If work allocation fails, do the writes inline. We drop
+ * the lock and restart the list writeout. This should be OK,
+ * since this happens rarely and because the writeout should
+ * eventually make more free memory available.
+ */
+ work = bdi_alloc_work(wbc);
+ if (!work) {
+ struct writeback_control __wbc = *wbc;
+
+ /*
+ * Not a data integrity writeout, just continue
+ */
+ if (!must_wait)
+ continue;
+
+ spin_unlock(&bdi_lock);
+ __wbc = *wbc;
+ __wbc.bdi = bdi;
+ writeback_inodes_wbc(&__wbc);
+ goto restart;
}
- spin_unlock(&inode_lock);
- iput(old_inode);
+ if (must_wait)
+ list_add_tail(&work->wait_list, &list);
+
+ bdi_queue_work(bdi, work);
+ }
+
+ spin_unlock(&bdi_lock);
+
+ /*
+ * If this is for WB_SYNC_ALL, wait for pending work to complete
+ * before returning.
+ */
+ while (!list_empty(&list)) {
+ work = list_entry(list.next, struct bdi_work, wait_list);
+ list_del(&work->wait_list);
+ bdi_wait_on_work_clear(work);
+ call_rcu(&work->rcu_head, bdi_work_free);
}
}
/*
- * Start writeback of dirty pagecache data against all unlocked inodes.
+ * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back
+ * the whole world.
+ */
+void wakeup_flusher_threads(long nr_pages)
+{
+ struct writeback_control wbc = {
+ .sync_mode = WB_SYNC_NONE,
+ .older_than_this = NULL,
+ .range_cyclic = 1,
+ };
+
+ if (nr_pages == 0)
+ nr_pages = global_page_state(NR_FILE_DIRTY) +
+ global_page_state(NR_UNSTABLE_NFS);
+ wbc.nr_to_write = nr_pages;
+ bdi_writeback_all(&wbc);
+}
+
+static noinline void block_dump___mark_inode_dirty(struct inode *inode)
+{
+ if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
+ struct dentry *dentry;
+ const char *name = "?";
+
+ dentry = d_find_alias(inode);
+ if (dentry) {
+ spin_lock(&dentry->d_lock);
+ name = (const char *) dentry->d_name.name;
+ }
+ printk(KERN_DEBUG
+ "%s(%d): dirtied inode %lu (%s) on %s\n",
+ current->comm, task_pid_nr(current), inode->i_ino,
+ name, inode->i_sb->s_id);
+ if (dentry) {
+ spin_unlock(&dentry->d_lock);
+ dput(dentry);
+ }
+ }
+}
+
+/**
+ * __mark_inode_dirty - internal function
+ * @inode: inode to mark
+ * @flags: what kind of dirty (i.e. I_DIRTY_SYNC)
+ * Mark an inode as dirty. Callers should use mark_inode_dirty or
+ * mark_inode_dirty_sync.
*
- * Note:
- * We don't need to grab a reference to superblock here. If it has non-empty
- * ->b_dirty it's hadn't been killed yet and kill_super() won't proceed
- * past sync_inodes_sb() until the ->b_dirty/b_io/b_more_io lists are all
- * empty. Since __sync_single_inode() regains inode_lock before it finally moves
- * inode from superblock lists we are OK.
+ * Put the inode on the super block's dirty list.
*
- * If `older_than_this' is non-zero then only flush inodes which have a
- * flushtime older than *older_than_this.
+ * CAREFUL! We mark it dirty unconditionally, but move it onto the
+ * dirty list only if it is hashed or if it refers to a blockdev.
+ * If it was not hashed, it will never be added to the dirty list
+ * even if it is later hashed, as it will have been marked dirty already.
+ *
+ * In short, make sure you hash any inodes _before_ you start marking
+ * them dirty.
+ *
+ * This function *must* be atomic for the I_DIRTY_PAGES case -
+ * set_page_dirty() is called under spinlock in several places.
*
- * If `bdi' is non-zero then we will scan the first inode against each
- * superblock until we find the matching ones. One group will be the dirty
- * inodes against a filesystem. Then when we hit the dummy blockdev superblock,
- * sync_sb_inodes will seekout the blockdev which matches `bdi'. Maybe not
- * super-efficient but we're about to do a ton of I/O...
+ * Note that for blockdevs, inode->dirtied_when represents the dirtying time of
+ * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of
+ * the kernel-internal blockdev inode represents the dirtying time of the
+ * blockdev's pages. This is why for I_DIRTY_PAGES we always use
+ * page->mapping->host, so the page-dirtying time is recorded in the internal
+ * blockdev inode.
*/
-void
-writeback_inodes(struct writeback_control *wbc)
+void __mark_inode_dirty(struct inode *inode, int flags)
{
- struct super_block *sb;
+ struct super_block *sb = inode->i_sb;
- might_sleep();
- spin_lock(&sb_lock);
-restart:
- list_for_each_entry_reverse(sb, &super_blocks, s_list) {
- if (sb_has_dirty_inodes(sb)) {
- /* we're making our own get_super here */
- sb->s_count++;
- spin_unlock(&sb_lock);
- /*
- * If we can't get the readlock, there's no sense in
- * waiting around, most of the time the FS is going to
- * be unmounted by the time it is released.
- */
- if (down_read_trylock(&sb->s_umount)) {
- if (sb->s_root)
- generic_sync_sb_inodes(sb, wbc);
- up_read(&sb->s_umount);
- }
- spin_lock(&sb_lock);
- if (__put_super_and_need_restart(sb))
- goto restart;
+ /*
+ * Don't do this for I_DIRTY_PAGES - that doesn't actually
+ * dirty the inode itself
+ */
+ if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
+ if (sb->s_op->dirty_inode)
+ sb->s_op->dirty_inode(inode);
+ }
+
+ /*
+ * make sure that changes are seen by all cpus before we test i_state
+ * -- mikulas
+ */
+ smp_mb();
+
+ /* avoid the locking if we can */
+ if ((inode->i_state & flags) == flags)
+ return;
+
+ if (unlikely(block_dump))
+ block_dump___mark_inode_dirty(inode);
+
+ spin_lock(&inode_lock);
+ if ((inode->i_state & flags) != flags) {
+ const int was_dirty = inode->i_state & I_DIRTY;
+
+ inode->i_state |= flags;
+
+ /*
+ * If the inode is being synced, just update its dirty state.
+ * The unlocker will place the inode on the appropriate
+ * superblock list, based upon its state.
+ */
+ if (inode->i_state & I_SYNC)
+ goto out;
+
+ /*
+ * Only add valid (hashed) inodes to the superblock's
+ * dirty list. Add blockdev inodes as well.
+ */
+ if (!S_ISBLK(inode->i_mode)) {
+ if (hlist_unhashed(&inode->i_hash))
+ goto out;
+ }
+ if (inode->i_state & (I_FREEING|I_CLEAR))
+ goto out;
+
+ /*
+ * If the inode was already on b_dirty/b_io/b_more_io, don't
+ * reposition it (that would break b_dirty time-ordering).
+ */
+ if (!was_dirty) {
+ struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
+
+ inode->dirtied_when = jiffies;
+ list_move(&inode->i_list, &wb->b_dirty);
}
- if (wbc->nr_to_write <= 0)
- break;
}
- spin_unlock(&sb_lock);
+out:
+ spin_unlock(&inode_lock);
+}
+
+EXPORT_SYMBOL(__mark_inode_dirty);
+
+/*
+ * Write out a superblock's list of dirty inodes. A wait will be performed
+ * upon no inodes, all inodes or the final one, depending upon sync_mode.
+ *
+ * If older_than_this is non-NULL, then only write out inodes which
+ * had their first dirtying at a time earlier than *older_than_this.
+ *
+ * If we're a pdlfush thread, then implement pdflush collision avoidance
+ * against the entire list.
+ *
+ * If `bdi' is non-zero then we're being asked to writeback a specific queue.
+ * This function assumes that the blockdev superblock's inodes are backed by
+ * a variety of queues, so all inodes are searched. For other superblocks,
+ * assume that all inodes are backed by the same queue.
+ *
+ * The inodes to be written are parked on bdi->b_io. They are moved back onto
+ * bdi->b_dirty as they are selected for writing. This way, none can be missed
+ * on the writer throttling path, and we get decent balancing between many
+ * throttled threads: we don't want them all piling up on inode_sync_wait.
+ */
+static void wait_sb_inodes(struct writeback_control *wbc)
+{
+ struct inode *inode, *old_inode = NULL;
+
+ /*
+ * We need to be protected against the filesystem going from
+ * r/o to r/w or vice versa.
+ */
+ WARN_ON(!rwsem_is_locked(&wbc->sb->s_umount));
+
+ spin_lock(&inode_lock);
+
+ /*
+ * Data integrity sync. Must wait for all pages under writeback,
+ * because there may have been pages dirtied before our sync
+ * call, but which had writeout started before we write it out.
+ * In which case, the inode may not be on the dirty list, but
+ * we still have to wait for that writeout.
+ */
+ list_for_each_entry(inode, &wbc->sb->s_inodes, i_sb_list) {
+ struct address_space *mapping;
+
+ if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
+ continue;
+ mapping = inode->i_mapping;
+ if (mapping->nrpages == 0)
+ continue;
+ __iget(inode);
+ spin_unlock(&inode_lock);
+ /*
+ * We hold a reference to 'inode' so it couldn't have
+ * been removed from s_inodes list while we dropped the
+ * inode_lock. We cannot iput the inode now as we can
+ * be holding the last reference and we cannot iput it
+ * under inode_lock. So we keep the reference and iput
+ * it later.
+ */
+ iput(old_inode);
+ old_inode = inode;
+
+ filemap_fdatawait(mapping);
+
+ cond_resched();
+
+ spin_lock(&inode_lock);
+ }
+ spin_unlock(&inode_lock);
+ iput(old_inode);
}
/**
@@ -715,6 +1112,7 @@ restart:
long writeback_inodes_sb(struct super_block *sb)
{
struct writeback_control wbc = {
+ .sb = sb,
.sync_mode = WB_SYNC_NONE,
.range_start = 0,
.range_end = LLONG_MAX,
@@ -727,7 +1125,7 @@ long writeback_inodes_sb(struct super_block *sb)
(inodes_stat.nr_inodes - inodes_stat.nr_unused);
wbc.nr_to_write = nr_to_write;
- generic_sync_sb_inodes(sb, &wbc);
+ bdi_writeback_all(&wbc);
return nr_to_write - wbc.nr_to_write;
}
EXPORT_SYMBOL(writeback_inodes_sb);
@@ -742,6 +1140,7 @@ EXPORT_SYMBOL(writeback_inodes_sb);
long sync_inodes_sb(struct super_block *sb)
{
struct writeback_control wbc = {
+ .sb = sb,
.sync_mode = WB_SYNC_ALL,
.range_start = 0,
.range_end = LLONG_MAX,
@@ -749,7 +1148,8 @@ long sync_inodes_sb(struct super_block *sb)
long nr_to_write = LONG_MAX; /* doesn't actually matter */
wbc.nr_to_write = nr_to_write;
- generic_sync_sb_inodes(sb, &wbc);
+ bdi_writeback_all(&wbc);
+ wait_sb_inodes(&wbc);
return nr_to_write - wbc.nr_to_write;
}
EXPORT_SYMBOL(sync_inodes_sb);
diff --git a/fs/sync.c b/fs/sync.c
index 66f2104..103cc7f 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -120,7 +120,7 @@ restart:
*/
SYSCALL_DEFINE0(sync)
{
- wakeup_pdflush(0);
+ wakeup_flusher_threads(0);
sync_filesystems(0);
sync_filesystems(1);
if (unlikely(laptop_mode))
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 928cd54..ac1d2ba 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -13,6 +13,8 @@
#include <linux/proportions.h>
#include <linux/kernel.h>
#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/writeback.h>
#include <asm/atomic.h>
struct page;
@@ -23,7 +25,8 @@ struct dentry;
* Bits in backing_dev_info.state
*/
enum bdi_state {
- BDI_pdflush, /* A pdflush thread is working this device */
+ BDI_pending, /* On its way to being activated */
+ BDI_wb_alloc, /* Default embedded wb allocated */
BDI_async_congested, /* The async (write) queue is getting full */
BDI_sync_congested, /* The sync queue is getting full */
BDI_unused, /* Available bits start here */
@@ -39,9 +42,22 @@ enum bdi_stat_item {
#define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids)))
+struct bdi_writeback {
+ struct list_head list; /* hangs off the bdi */
+
+ struct backing_dev_info *bdi; /* our parent bdi */
+ unsigned int nr;
+
+ struct task_struct *task; /* writeback task */
+ struct list_head b_dirty; /* dirty inodes */
+ struct list_head b_io; /* parked for writeback */
+ struct list_head b_more_io; /* parked for more writeback */
+};
+
+#define BDI_MAX_FLUSHERS 32
+
struct backing_dev_info {
struct list_head bdi_list;
-
unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */
unsigned long state; /* Always use atomic bitops on this */
unsigned int capabilities; /* Device capabilities */
@@ -58,11 +74,15 @@ struct backing_dev_info {
unsigned int min_ratio;
unsigned int max_ratio, max_prop_frac;
- struct device *dev;
+ struct bdi_writeback wb; /* default writeback info for this bdi */
+ spinlock_t wb_lock; /* protects update side of wb_list */
+ struct list_head wb_list; /* the flusher threads hanging off this bdi */
+ unsigned long wb_mask; /* bitmask of registered tasks */
+ unsigned int wb_cnt; /* number of registered tasks */
- struct list_head b_dirty; /* dirty inodes */
- struct list_head b_io; /* parked for writeback */
- struct list_head b_more_io; /* parked for more writeback */
+ struct list_head work_list;
+
+ struct device *dev;
#ifdef CONFIG_DEBUG_FS
struct dentry *debug_dir;
@@ -77,10 +97,20 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
const char *fmt, ...);
int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
void bdi_unregister(struct backing_dev_info *bdi);
+void bdi_start_writeback(struct writeback_control *wbc);
+int bdi_writeback_task(struct bdi_writeback *wb);
+int bdi_has_dirty_io(struct backing_dev_info *bdi);
-extern struct mutex bdi_lock;
+extern spinlock_t bdi_lock;
extern struct list_head bdi_list;
+static inline int wb_has_dirty_io(struct bdi_writeback *wb)
+{
+ return !list_empty(&wb->b_dirty) ||
+ !list_empty(&wb->b_io) ||
+ !list_empty(&wb->b_more_io);
+}
+
static inline void __add_bdi_stat(struct backing_dev_info *bdi,
enum bdi_stat_item item, s64 amount)
{
@@ -270,6 +300,11 @@ static inline bool bdi_cap_swap_backed(struct backing_dev_info *bdi)
return bdi->capabilities & BDI_CAP_SWAP_BACKED;
}
+static inline bool bdi_cap_flush_forker(struct backing_dev_info *bdi)
+{
+ return bdi == &default_backing_dev_info;
+}
+
static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
{
return bdi_cap_writeback_dirty(mapping->backing_dev_info);
@@ -285,4 +320,10 @@ static inline bool mapping_cap_swap_backed(struct address_space *mapping)
return bdi_cap_swap_backed(mapping->backing_dev_info);
}
+static inline int bdi_sched_wait(void *word)
+{
+ schedule();
+ return 0;
+}
+
#endif /* _LINUX_BACKING_DEV_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 97949b7..53c97ed 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2181,7 +2181,6 @@ extern int bdev_read_only(struct block_device *);
extern int set_blocksize(struct block_device *, int);
extern int sb_set_blocksize(struct super_block *, int);
extern int sb_min_blocksize(struct super_block *, int);
-extern int sb_has_dirty_inodes(struct super_block *);
extern int generic_file_mmap(struct file *, struct vm_area_struct *);
extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 0703929..cef7552 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -40,6 +40,8 @@ enum writeback_sync_modes {
struct writeback_control {
struct backing_dev_info *bdi; /* If !NULL, only write back this
queue */
+ struct super_block *sb; /* if !NULL, only write inodes from
+ this super_block */
enum writeback_sync_modes sync_mode;
unsigned long *older_than_this; /* If !NULL, only write back inodes
older than this */
@@ -76,10 +78,13 @@ struct writeback_control {
/*
* fs/fs-writeback.c
*/
-void writeback_inodes(struct writeback_control *wbc);
+struct bdi_writeback;
int inode_wait(void *);
long writeback_inodes_sb(struct super_block *);
long sync_inodes_sb(struct super_block *);
+void writeback_inodes_wbc(struct writeback_control *wbc);
+long wb_do_writeback(struct bdi_writeback *wb, int force_wait);
+void wakeup_flusher_threads(long nr_pages);
/* writeback.h requires fs.h; it, too, is not included from here. */
static inline void wait_on_inode(struct inode *inode)
@@ -99,7 +104,6 @@ static inline void inode_sync_wait(struct inode *inode)
/*
* mm/page-writeback.c
*/
-int wakeup_pdflush(long nr_pages);
void laptop_io_completion(void);
void laptop_sync_completion(void);
void throttle_vm_writeout(gfp_t gfp_mask);
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 6f163e0..9532c1f 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -1,8 +1,11 @@
#include <linux/wait.h>
#include <linux/backing-dev.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
+#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/writeback.h>
@@ -22,8 +25,18 @@ struct backing_dev_info default_backing_dev_info = {
EXPORT_SYMBOL_GPL(default_backing_dev_info);
static struct class *bdi_class;
-DEFINE_MUTEX(bdi_lock);
+DEFINE_SPINLOCK(bdi_lock);
LIST_HEAD(bdi_list);
+LIST_HEAD(bdi_pending_list);
+
+static struct task_struct *sync_supers_tsk;
+static struct timer_list sync_supers_timer;
+
+static int bdi_sync_supers(void *);
+static void sync_supers_timer_fn(unsigned long);
+static void arm_supers_timer(void);
+
+static void bdi_add_default_flusher_task(struct backing_dev_info *bdi);
#ifdef CONFIG_DEBUG_FS
#include <linux/debugfs.h>
@@ -187,6 +200,13 @@ static int __init default_bdi_init(void)
{
int err;
+ sync_supers_tsk = kthread_run(bdi_sync_supers, NULL, "sync_supers");
+ BUG_ON(IS_ERR(sync_supers_tsk));
+
+ init_timer(&sync_supers_timer);
+ setup_timer(&sync_supers_timer, sync_supers_timer_fn, 0);
+ arm_supers_timer();
+
err = bdi_init(&default_backing_dev_info);
if (!err)
bdi_register(&default_backing_dev_info, NULL, "default");
@@ -195,6 +215,241 @@ static int __init default_bdi_init(void)
}
subsys_initcall(default_bdi_init);
+static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
+{
+ memset(wb, 0, sizeof(*wb));
+
+ wb->bdi = bdi;
+ INIT_LIST_HEAD(&wb->b_dirty);
+ INIT_LIST_HEAD(&wb->b_io);
+ INIT_LIST_HEAD(&wb->b_more_io);
+}
+
+static void bdi_task_init(struct backing_dev_info *bdi,
+ struct bdi_writeback *wb)
+{
+ struct task_struct *tsk = current;
+
+ spin_lock(&bdi->wb_lock);
+ list_add_tail_rcu(&wb->list, &bdi->wb_list);
+ spin_unlock(&bdi->wb_lock);
+
+ tsk->flags |= PF_FLUSHER | PF_SWAPWRITE;
+ set_freezable();
+
+ /*
+ * Our parent may run at a different priority, just set us to normal
+ */
+ set_user_nice(tsk, 0);
+}
+
+static int bdi_start_fn(void *ptr)
+{
+ struct bdi_writeback *wb = ptr;
+ struct backing_dev_info *bdi = wb->bdi;
+ int ret;
+
+ /*
+ * Add us to the active bdi_list
+ */
+ spin_lock(&bdi_lock);
+ list_add(&bdi->bdi_list, &bdi_list);
+ spin_unlock(&bdi_lock);
+
+ bdi_task_init(bdi, wb);
+
+ /*
+ * Clear pending bit and wakeup anybody waiting to tear us down
+ */
+ clear_bit(BDI_pending, &bdi->state);
+ smp_mb__after_clear_bit();
+ wake_up_bit(&bdi->state, BDI_pending);
+
+ ret = bdi_writeback_task(wb);
+
+ /*
+ * Remove us from the list
+ */
+ spin_lock(&bdi->wb_lock);
+ list_del_rcu(&wb->list);
+ spin_unlock(&bdi->wb_lock);
+
+ /*
+ * Flush any work that raced with us exiting. No new work
+ * will be added, since this bdi isn't discoverable anymore.
+ */
+ if (!list_empty(&bdi->work_list))
+ wb_do_writeback(wb, 1);
+
+ wb->task = NULL;
+ return ret;
+}
+
+int bdi_has_dirty_io(struct backing_dev_info *bdi)
+{
+ return wb_has_dirty_io(&bdi->wb);
+}
+
+static void bdi_flush_io(struct backing_dev_info *bdi)
+{
+ struct writeback_control wbc = {
+ .bdi = bdi,
+ .sync_mode = WB_SYNC_NONE,
+ .older_than_this = NULL,
+ .range_cyclic = 1,
+ .nr_to_write = 1024,
+ };
+
+ writeback_inodes_wbc(&wbc);
+}
+
+/*
+ * kupdated() used to do this. We cannot do it from the bdi_forker_task()
+ * or we risk deadlocking on ->s_umount. The longer term solution would be
+ * to implement sync_supers_bdi() or similar and simply do it from the
+ * bdi writeback tasks individually.
+ */
+static int bdi_sync_supers(void *unused)
+{
+ set_user_nice(current, 0);
+
+ while (!kthread_should_stop()) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule();
+
+ /*
+ * Do this periodically, like kupdated() did before.
+ */
+ sync_supers();
+ }
+
+ return 0;
+}
+
+static void arm_supers_timer(void)
+{
+ unsigned long next;
+
+ next = msecs_to_jiffies(dirty_writeback_interval * 10) + jiffies;
+ mod_timer(&sync_supers_timer, round_jiffies_up(next));
+}
+
+static void sync_supers_timer_fn(unsigned long unused)
+{
+ wake_up_process(sync_supers_tsk);
+ arm_supers_timer();
+}
+
+static int bdi_forker_task(void *ptr)
+{
+ struct bdi_writeback *me = ptr;
+
+ bdi_task_init(me->bdi, me);
+
+ for (;;) {
+ struct backing_dev_info *bdi, *tmp;
+ struct bdi_writeback *wb;
+
+ /*
+ * Temporary measure, we want to make sure we don't see
+ * dirty data on the default backing_dev_info
+ */
+ if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list))
+ wb_do_writeback(me, 0);
+
+ spin_lock(&bdi_lock);
+
+ /*
+ * Check if any existing bdi's have dirty data without
+ * a thread registered. If so, set that up.
+ */
+ list_for_each_entry_safe(bdi, tmp, &bdi_list, bdi_list) {
+ if (bdi->wb.task)
+ continue;
+ if (list_empty(&bdi->work_list) &&
+ !bdi_has_dirty_io(bdi))
+ continue;
+
+ bdi_add_default_flusher_task(bdi);
+ }
+
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ if (list_empty(&bdi_pending_list)) {
+ unsigned long wait;
+
+ spin_unlock(&bdi_lock);
+ wait = msecs_to_jiffies(dirty_writeback_interval * 10);
+ schedule_timeout(wait);
+ try_to_freeze();
+ continue;
+ }
+
+ __set_current_state(TASK_RUNNING);
+
+ /*
+ * This is our real job - check for pending entries in
+ * bdi_pending_list, and create the tasks that got added
+ */
+ bdi = list_entry(bdi_pending_list.next, struct backing_dev_info,
+ bdi_list);
+ list_del_init(&bdi->bdi_list);
+ spin_unlock(&bdi_lock);
+
+ wb = &bdi->wb;
+ wb->task = kthread_run(bdi_start_fn, wb, "flush-%s",
+ dev_name(bdi->dev));
+ /*
+ * If task creation fails, then readd the bdi to
+ * the pending list and force writeout of the bdi
+ * from this forker thread. That will free some memory
+ * and we can try again.
+ */
+ if (IS_ERR(wb->task)) {
+ wb->task = NULL;
+
+ /*
+ * Add this 'bdi' to the back, so we get
+ * a chance to flush other bdi's to free
+ * memory.
+ */
+ spin_lock(&bdi_lock);
+ list_add_tail(&bdi->bdi_list, &bdi_pending_list);
+ spin_unlock(&bdi_lock);
+
+ bdi_flush_io(bdi);
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * Add the default flusher task that gets created for any bdi
+ * that has dirty data pending writeout
+ */
+void static bdi_add_default_flusher_task(struct backing_dev_info *bdi)
+{
+ if (!bdi_cap_writeback_dirty(bdi))
+ return;
+
+ /*
+ * Check with the helper whether to proceed adding a task. Will only
+ * abort if we two or more simultanous calls to
+ * bdi_add_default_flusher_task() occured, further additions will block
+ * waiting for previous additions to finish.
+ */
+ if (!test_and_set_bit(BDI_pending, &bdi->state)) {
+ list_move_tail(&bdi->bdi_list, &bdi_pending_list);
+
+ /*
+ * We are now on the pending list, wake up bdi_forker_task()
+ * to finish the job and add us back to the active bdi_list
+ */
+ wake_up_process(default_backing_dev_info.wb.task);
+ }
+}
+
int bdi_register(struct backing_dev_info *bdi, struct device *parent,
const char *fmt, ...)
{
@@ -213,13 +468,34 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
goto exit;
}
- mutex_lock(&bdi_lock);
+ spin_lock(&bdi_lock);
list_add_tail(&bdi->bdi_list, &bdi_list);
- mutex_unlock(&bdi_lock);
+ spin_unlock(&bdi_lock);
bdi->dev = dev;
- bdi_debug_register(bdi, dev_name(dev));
+ /*
+ * Just start the forker thread for our default backing_dev_info,
+ * and add other bdi's to the list. They will get a thread created
+ * on-demand when they need it.
+ */
+ if (bdi_cap_flush_forker(bdi)) {
+ struct bdi_writeback *wb = &bdi->wb;
+
+ wb->task = kthread_run(bdi_forker_task, wb, "bdi-%s",
+ dev_name(dev));
+ if (IS_ERR(wb->task)) {
+ wb->task = NULL;
+ ret = -ENOMEM;
+
+ spin_lock(&bdi_lock);
+ list_del(&bdi->bdi_list);
+ spin_unlock(&bdi_lock);
+ goto exit;
+ }
+ }
+
+ bdi_debug_register(bdi, dev_name(dev));
exit:
return ret;
}
@@ -231,17 +507,42 @@ int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev)
}
EXPORT_SYMBOL(bdi_register_dev);
-static void bdi_remove_from_list(struct backing_dev_info *bdi)
+/*
+ * Remove bdi from the global list and shutdown any threads we have running
+ */
+static void bdi_wb_shutdown(struct backing_dev_info *bdi)
{
- mutex_lock(&bdi_lock);
+ struct bdi_writeback *wb;
+
+ if (!bdi_cap_writeback_dirty(bdi))
+ return;
+
+ /*
+ * If setup is pending, wait for that to complete first
+ */
+ wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait,
+ TASK_UNINTERRUPTIBLE);
+
+ /*
+ * Make sure nobody finds us on the bdi_list anymore
+ */
+ spin_lock(&bdi_lock);
list_del(&bdi->bdi_list);
- mutex_unlock(&bdi_lock);
+ spin_unlock(&bdi_lock);
+
+ /*
+ * Finally, kill the kernel threads. We don't need to be RCU
+ * safe anymore, since the bdi is gone from visibility.
+ */
+ list_for_each_entry(wb, &bdi->wb_list, list)
+ kthread_stop(wb->task);
}
void bdi_unregister(struct backing_dev_info *bdi)
{
if (bdi->dev) {
- bdi_remove_from_list(bdi);
+ if (!bdi_cap_flush_forker(bdi))
+ bdi_wb_shutdown(bdi);
bdi_debug_unregister(bdi);
device_unregister(bdi->dev);
bdi->dev = NULL;
@@ -251,18 +552,25 @@ EXPORT_SYMBOL(bdi_unregister);
int bdi_init(struct backing_dev_info *bdi)
{
- int i;
- int err;
+ int i, err;
bdi->dev = NULL;
bdi->min_ratio = 0;
bdi->max_ratio = 100;
bdi->max_prop_frac = PROP_FRAC_BASE;
+ spin_lock_init(&bdi->wb_lock);
INIT_LIST_HEAD(&bdi->bdi_list);
- INIT_LIST_HEAD(&bdi->b_io);
- INIT_LIST_HEAD(&bdi->b_dirty);
- INIT_LIST_HEAD(&bdi->b_more_io);
+ INIT_LIST_HEAD(&bdi->wb_list);
+ INIT_LIST_HEAD(&bdi->work_list);
+
+ bdi_wb_init(&bdi->wb, bdi);
+
+ /*
+ * Just one thread support for now, hard code mask and count
+ */
+ bdi->wb_mask = 1;
+ bdi->wb_cnt = 1;
for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
err = percpu_counter_init(&bdi->bdi_stat[i], 0);
@@ -277,8 +585,6 @@ int bdi_init(struct backing_dev_info *bdi)
err:
while (i--)
percpu_counter_destroy(&bdi->bdi_stat[i]);
-
- bdi_remove_from_list(bdi);
}
return err;
@@ -289,9 +595,7 @@ void bdi_destroy(struct backing_dev_info *bdi)
{
int i;
- WARN_ON(!list_empty(&bdi->b_dirty));
- WARN_ON(!list_empty(&bdi->b_io));
- WARN_ON(!list_empty(&bdi->b_more_io));
+ WARN_ON(bdi_has_dirty_io(bdi));
bdi_unregister(bdi);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index f8341b6..2c287d9 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -36,15 +36,6 @@
#include <linux/pagevec.h>
/*
- * The maximum number of pages to writeout in a single bdflush/kupdate
- * operation. We do this so we don't hold I_SYNC against an inode for
- * enormous amounts of time, which would block a userspace task which has
- * been forced to throttle against that inode. Also, the code reevaluates
- * the dirty each time it has written this many pages.
- */
-#define MAX_WRITEBACK_PAGES 1024
-
-/*
* After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited
* will look to see if it needs to force writeback or throttling.
*/
@@ -117,8 +108,6 @@ EXPORT_SYMBOL(laptop_mode);
/* End of sysctl-exported parameters */
-static void background_writeout(unsigned long _min_pages);
-
/*
* Scale the writeback cache size proportional to the relative writeout speeds.
*
@@ -326,7 +315,7 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
{
int ret = 0;
- mutex_lock(&bdi_lock);
+ spin_lock(&bdi_lock);
if (min_ratio > bdi->max_ratio) {
ret = -EINVAL;
} else {
@@ -338,7 +327,7 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
ret = -EINVAL;
}
}
- mutex_unlock(&bdi_lock);
+ spin_unlock(&bdi_lock);
return ret;
}
@@ -350,14 +339,14 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio)
if (max_ratio > 100)
return -EINVAL;
- mutex_lock(&bdi_lock);
+ spin_lock(&bdi_lock);
if (bdi->min_ratio > max_ratio) {
ret = -EINVAL;
} else {
bdi->max_ratio = max_ratio;
bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100;
}
- mutex_unlock(&bdi_lock);
+ spin_unlock(&bdi_lock);
return ret;
}
@@ -543,7 +532,7 @@ static void balance_dirty_pages(struct address_space *mapping)
* up.
*/
if (bdi_nr_reclaimable > bdi_thresh) {
- writeback_inodes(&wbc);
+ writeback_inodes_wbc(&wbc);
pages_written += write_chunk - wbc.nr_to_write;
get_dirty_limits(&background_thresh, &dirty_thresh,
&bdi_thresh, bdi);
@@ -572,7 +561,7 @@ static void balance_dirty_pages(struct address_space *mapping)
if (pages_written >= write_chunk)
break; /* We've done our duty */
- congestion_wait(BLK_RW_ASYNC, HZ/10);
+ schedule_timeout(1);
}
if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
@@ -593,8 +582,15 @@ static void balance_dirty_pages(struct address_space *mapping)
if ((laptop_mode && pages_written) ||
(!laptop_mode && (global_page_state(NR_FILE_DIRTY)
+ global_page_state(NR_UNSTABLE_NFS)
- > background_thresh)))
- pdflush_operation(background_writeout, 0);
+ > background_thresh))) {
+ struct writeback_control wbc = {
+ .bdi = bdi,
+ .sync_mode = WB_SYNC_NONE,
+ };
+
+
+ bdi_start_writeback(&wbc);
+ }
}
void set_page_dirty_balance(struct page *page, int page_mkwrite)
@@ -678,153 +674,35 @@ void throttle_vm_writeout(gfp_t gfp_mask)
}
}
-/*
- * writeback at least _min_pages, and keep writing until the amount of dirty
- * memory is less than the background threshold, or until we're all clean.
- */
-static void background_writeout(unsigned long _min_pages)
-{
- long min_pages = _min_pages;
- struct writeback_control wbc = {
- .bdi = NULL,
- .sync_mode = WB_SYNC_NONE,
- .older_than_this = NULL,
- .nr_to_write = 0,
- .nonblocking = 1,
- .range_cyclic = 1,
- };
-
- for ( ; ; ) {
- unsigned long background_thresh;
- unsigned long dirty_thresh;
-
- get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
- if (global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS) < background_thresh
- && min_pages <= 0)
- break;
- wbc.more_io = 0;
- wbc.encountered_congestion = 0;
- wbc.nr_to_write = MAX_WRITEBACK_PAGES;
- wbc.pages_skipped = 0;
- writeback_inodes(&wbc);
- min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
- if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
- /* Wrote less than expected */
- if (wbc.encountered_congestion || wbc.more_io)
- congestion_wait(BLK_RW_ASYNC, HZ/10);
- else
- break;
- }
- }
-}
-
-/*
- * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back
- * the whole world. Returns 0 if a pdflush thread was dispatched. Returns
- * -1 if all pdflush threads were busy.
- */
-int wakeup_pdflush(long nr_pages)
-{
- if (nr_pages == 0)
- nr_pages = global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS);
- return pdflush_operation(background_writeout, nr_pages);
-}
-
-static void wb_timer_fn(unsigned long unused);
static void laptop_timer_fn(unsigned long unused);
-static DEFINE_TIMER(wb_timer, wb_timer_fn, 0, 0);
static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0);
/*
- * Periodic writeback of "old" data.
- *
- * Define "old": the first time one of an inode's pages is dirtied, we mark the
- * dirtying-time in the inode's address_space. So this periodic writeback code
- * just walks the superblock inode list, writing back any inodes which are
- * older than a specific point in time.
- *
- * Try to run once per dirty_writeback_interval. But if a writeback event
- * takes longer than a dirty_writeback_interval interval, then leave a
- * one-second gap.
- *
- * older_than_this takes precedence over nr_to_write. So we'll only write back
- * all dirty pages if they are all attached to "old" mappings.
- */
-static void wb_kupdate(unsigned long arg)
-{
- unsigned long oldest_jif;
- unsigned long start_jif;
- unsigned long next_jif;
- long nr_to_write;
- struct writeback_control wbc = {
- .bdi = NULL,
- .sync_mode = WB_SYNC_NONE,
- .older_than_this = &oldest_jif,
- .nr_to_write = 0,
- .nonblocking = 1,
- .for_kupdate = 1,
- .range_cyclic = 1,
- };
-
- sync_supers();
-
- oldest_jif = jiffies - msecs_to_jiffies(dirty_expire_interval * 10);
- start_jif = jiffies;
- next_jif = start_jif + msecs_to_jiffies(dirty_writeback_interval * 10);
- nr_to_write = global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS) +
- (inodes_stat.nr_inodes - inodes_stat.nr_unused);
- while (nr_to_write > 0) {
- wbc.more_io = 0;
- wbc.encountered_congestion = 0;
- wbc.nr_to_write = MAX_WRITEBACK_PAGES;
- writeback_inodes(&wbc);
- if (wbc.nr_to_write > 0) {
- if (wbc.encountered_congestion || wbc.more_io)
- congestion_wait(BLK_RW_ASYNC, HZ/10);
- else
- break; /* All the old data is written */
- }
- nr_to_write -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
- }
- if (time_before(next_jif, jiffies + HZ))
- next_jif = jiffies + HZ;
- if (dirty_writeback_interval)
- mod_timer(&wb_timer, next_jif);
-}
-
-/*
* sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
*/
int dirty_writeback_centisecs_handler(ctl_table *table, int write,
struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
{
proc_dointvec(table, write, file, buffer, length, ppos);
- if (dirty_writeback_interval)
- mod_timer(&wb_timer, jiffies +
- msecs_to_jiffies(dirty_writeback_interval * 10));
- else
- del_timer(&wb_timer);
return 0;
}
-static void wb_timer_fn(unsigned long unused)
-{
- if (pdflush_operation(wb_kupdate, 0) < 0)
- mod_timer(&wb_timer, jiffies + HZ); /* delay 1 second */
-}
-
-static void laptop_flush(unsigned long unused)
+static void do_laptop_sync(struct work_struct *work)
{
- sys_sync();
+ wakeup_flusher_threads(0);
+ kfree(work);
}
static void laptop_timer_fn(unsigned long unused)
{
- pdflush_operation(laptop_flush, 0);
+ struct work_struct *work;
+
+ work = kmalloc(sizeof(*work), GFP_ATOMIC);
+ if (work) {
+ INIT_WORK(work, do_laptop_sync);
+ schedule_work(work);
+ }
}
/*
@@ -907,8 +785,6 @@ void __init page_writeback_init(void)
{
int shift;
- mod_timer(&wb_timer,
- jiffies + msecs_to_jiffies(dirty_writeback_interval * 10));
writeback_set_ratelimit();
register_cpu_notifier(&ratelimit_nb);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 94e86dd..ba8228e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1720,7 +1720,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
*/
if (total_scanned > sc->swap_cluster_max +
sc->swap_cluster_max / 2) {
- wakeup_pdflush(laptop_mode ? 0 : total_scanned);
+ wakeup_flusher_threads(laptop_mode ? 0 : total_scanned);
sc->may_writepage = 1;
}
--
1.6.4.1.207.g68ea
It is now unused, so kill it off.
Signed-off-by: Jens Axboe <[email protected]>
---
fs/fs-writeback.c | 5 +
include/linux/writeback.h | 12 --
mm/Makefile | 2 +-
mm/pdflush.c | 269 ---------------------------------------------
4 files changed, 6 insertions(+), 282 deletions(-)
delete mode 100644 mm/pdflush.c
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 93aa9a7..6714b38 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -30,6 +30,11 @@
#define inode_to_bdi(inode) ((inode)->i_mapping->backing_dev_info)
/*
+ * We don't actually have pdflush, but this one is exported though /proc...
+ */
+int nr_pdflush_threads;
+
+/*
* Work items for the bdi_writeback threads
*/
struct bdi_work {
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index cef7552..78b1e46 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -14,17 +14,6 @@ extern struct list_head inode_in_use;
extern struct list_head inode_unused;
/*
- * Yes, writeback.h requires sched.h
- * No, sched.h is not included from here.
- */
-static inline int task_is_pdflush(struct task_struct *task)
-{
- return task->flags & PF_FLUSHER;
-}
-
-#define current_is_pdflush() task_is_pdflush(current)
-
-/*
* fs/fs-writeback.c
*/
enum writeback_sync_modes {
@@ -155,7 +144,6 @@ balance_dirty_pages_ratelimited(struct address_space *mapping)
typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc,
void *data);
-int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0);
int generic_writepages(struct address_space *mapping,
struct writeback_control *wbc);
int write_cache_pages(struct address_space *mapping,
diff --git a/mm/Makefile b/mm/Makefile
index 5e0bd64..147a7a7 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -8,7 +8,7 @@ mmu-$(CONFIG_MMU) := fremap.o highmem.o madvise.o memory.o mincore.o \
vmalloc.o
obj-y := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
- maccess.o page_alloc.o page-writeback.o pdflush.o \
+ maccess.o page_alloc.o page-writeback.o \
readahead.o swap.o truncate.o vmscan.o shmem.o \
prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
page_isolation.o mm_init.o $(mmu-y)
diff --git a/mm/pdflush.c b/mm/pdflush.c
deleted file mode 100644
index 235ac44..0000000
--- a/mm/pdflush.c
+++ /dev/null
@@ -1,269 +0,0 @@
-/*
- * mm/pdflush.c - worker threads for writing back filesystem data
- *
- * Copyright (C) 2002, Linus Torvalds.
- *
- * 09Apr2002 Andrew Morton
- * Initial version
- * 29Feb2004 [email protected]
- * Move worker thread creation to kthread to avoid chewing
- * up stack space with nested calls to kernel_thread.
- */
-
-#include <linux/sched.h>
-#include <linux/list.h>
-#include <linux/signal.h>
-#include <linux/spinlock.h>
-#include <linux/gfp.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/fs.h> /* Needed by writeback.h */
-#include <linux/writeback.h> /* Prototypes pdflush_operation() */
-#include <linux/kthread.h>
-#include <linux/cpuset.h>
-#include <linux/freezer.h>
-
-
-/*
- * Minimum and maximum number of pdflush instances
- */
-#define MIN_PDFLUSH_THREADS 2
-#define MAX_PDFLUSH_THREADS 8
-
-static void start_one_pdflush_thread(void);
-
-
-/*
- * The pdflush threads are worker threads for writing back dirty data.
- * Ideally, we'd like one thread per active disk spindle. But the disk
- * topology is very hard to divine at this level. Instead, we take
- * care in various places to prevent more than one pdflush thread from
- * performing writeback against a single filesystem. pdflush threads
- * have the PF_FLUSHER flag set in current->flags to aid in this.
- */
-
-/*
- * All the pdflush threads. Protected by pdflush_lock
- */
-static LIST_HEAD(pdflush_list);
-static DEFINE_SPINLOCK(pdflush_lock);
-
-/*
- * The count of currently-running pdflush threads. Protected
- * by pdflush_lock.
- *
- * Readable by sysctl, but not writable. Published to userspace at
- * /proc/sys/vm/nr_pdflush_threads.
- */
-int nr_pdflush_threads = 0;
-
-/*
- * The time at which the pdflush thread pool last went empty
- */
-static unsigned long last_empty_jifs;
-
-/*
- * The pdflush thread.
- *
- * Thread pool management algorithm:
- *
- * - The minimum and maximum number of pdflush instances are bound
- * by MIN_PDFLUSH_THREADS and MAX_PDFLUSH_THREADS.
- *
- * - If there have been no idle pdflush instances for 1 second, create
- * a new one.
- *
- * - If the least-recently-went-to-sleep pdflush thread has been asleep
- * for more than one second, terminate a thread.
- */
-
-/*
- * A structure for passing work to a pdflush thread. Also for passing
- * state information between pdflush threads. Protected by pdflush_lock.
- */
-struct pdflush_work {
- struct task_struct *who; /* The thread */
- void (*fn)(unsigned long); /* A callback function */
- unsigned long arg0; /* An argument to the callback */
- struct list_head list; /* On pdflush_list, when idle */
- unsigned long when_i_went_to_sleep;
-};
-
-static int __pdflush(struct pdflush_work *my_work)
-{
- current->flags |= PF_FLUSHER | PF_SWAPWRITE;
- set_freezable();
- my_work->fn = NULL;
- my_work->who = current;
- INIT_LIST_HEAD(&my_work->list);
-
- spin_lock_irq(&pdflush_lock);
- for ( ; ; ) {
- struct pdflush_work *pdf;
-
- set_current_state(TASK_INTERRUPTIBLE);
- list_move(&my_work->list, &pdflush_list);
- my_work->when_i_went_to_sleep = jiffies;
- spin_unlock_irq(&pdflush_lock);
- schedule();
- try_to_freeze();
- spin_lock_irq(&pdflush_lock);
- if (!list_empty(&my_work->list)) {
- /*
- * Someone woke us up, but without removing our control
- * structure from the global list. swsusp will do this
- * in try_to_freeze()->refrigerator(). Handle it.
- */
- my_work->fn = NULL;
- continue;
- }
- if (my_work->fn == NULL) {
- printk("pdflush: bogus wakeup\n");
- continue;
- }
- spin_unlock_irq(&pdflush_lock);
-
- (*my_work->fn)(my_work->arg0);
-
- spin_lock_irq(&pdflush_lock);
-
- /*
- * Thread creation: For how long have there been zero
- * available threads?
- *
- * To throttle creation, we reset last_empty_jifs.
- */
- if (time_after(jiffies, last_empty_jifs + 1 * HZ)) {
- if (list_empty(&pdflush_list)) {
- if (nr_pdflush_threads < MAX_PDFLUSH_THREADS) {
- last_empty_jifs = jiffies;
- nr_pdflush_threads++;
- spin_unlock_irq(&pdflush_lock);
- start_one_pdflush_thread();
- spin_lock_irq(&pdflush_lock);
- }
- }
- }
-
- my_work->fn = NULL;
-
- /*
- * Thread destruction: For how long has the sleepiest
- * thread slept?
- */
- if (list_empty(&pdflush_list))
- continue;
- if (nr_pdflush_threads <= MIN_PDFLUSH_THREADS)
- continue;
- pdf = list_entry(pdflush_list.prev, struct pdflush_work, list);
- if (time_after(jiffies, pdf->when_i_went_to_sleep + 1 * HZ)) {
- /* Limit exit rate */
- pdf->when_i_went_to_sleep = jiffies;
- break; /* exeunt */
- }
- }
- nr_pdflush_threads--;
- spin_unlock_irq(&pdflush_lock);
- return 0;
-}
-
-/*
- * Of course, my_work wants to be just a local in __pdflush(). It is
- * separated out in this manner to hopefully prevent the compiler from
- * performing unfortunate optimisations against the auto variables. Because
- * these are visible to other tasks and CPUs. (No problem has actually
- * been observed. This is just paranoia).
- */
-static int pdflush(void *dummy)
-{
- struct pdflush_work my_work;
- cpumask_var_t cpus_allowed;
-
- /*
- * Since the caller doesn't even check kthread_run() worked, let's not
- * freak out too much if this fails.
- */
- if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
- printk(KERN_WARNING "pdflush failed to allocate cpumask\n");
- return 0;
- }
-
- /*
- * pdflush can spend a lot of time doing encryption via dm-crypt. We
- * don't want to do that at keventd's priority.
- */
- set_user_nice(current, 0);
-
- /*
- * Some configs put our parent kthread in a limited cpuset,
- * which kthread() overrides, forcing cpus_allowed == cpu_all_mask.
- * Our needs are more modest - cut back to our cpusets cpus_allowed.
- * This is needed as pdflush's are dynamically created and destroyed.
- * The boottime pdflush's are easily placed w/o these 2 lines.
- */
- cpuset_cpus_allowed(current, cpus_allowed);
- set_cpus_allowed_ptr(current, cpus_allowed);
- free_cpumask_var(cpus_allowed);
-
- return __pdflush(&my_work);
-}
-
-/*
- * Attempt to wake up a pdflush thread, and get it to do some work for you.
- * Returns zero if it indeed managed to find a worker thread, and passed your
- * payload to it.
- */
-int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0)
-{
- unsigned long flags;
- int ret = 0;
-
- BUG_ON(fn == NULL); /* Hard to diagnose if it's deferred */
-
- spin_lock_irqsave(&pdflush_lock, flags);
- if (list_empty(&pdflush_list)) {
- ret = -1;
- } else {
- struct pdflush_work *pdf;
-
- pdf = list_entry(pdflush_list.next, struct pdflush_work, list);
- list_del_init(&pdf->list);
- if (list_empty(&pdflush_list))
- last_empty_jifs = jiffies;
- pdf->fn = fn;
- pdf->arg0 = arg0;
- wake_up_process(pdf->who);
- }
- spin_unlock_irqrestore(&pdflush_lock, flags);
-
- return ret;
-}
-
-static void start_one_pdflush_thread(void)
-{
- struct task_struct *k;
-
- k = kthread_run(pdflush, NULL, "pdflush");
- if (unlikely(IS_ERR(k))) {
- spin_lock_irq(&pdflush_lock);
- nr_pdflush_threads--;
- spin_unlock_irq(&pdflush_lock);
- }
-}
-
-static int __init pdflush_init(void)
-{
- int i;
-
- /*
- * Pre-set nr_pdflush_threads... If we fail to create,
- * the count will be decremented.
- */
- nr_pdflush_threads = MIN_PDFLUSH_THREADS;
-
- for (i = 0; i < MIN_PDFLUSH_THREADS; i++)
- start_one_pdflush_thread();
- return 0;
-}
-
-module_init(pdflush_init);
--
1.6.4.1.207.g68ea
Add some debug entries to be able to inspect the internal state of
the writeback details.
Signed-off-by: Jens Axboe <[email protected]>
---
mm/backing-dev.c | 38 ++++++++++++++++++++++++++++++++++----
1 files changed, 34 insertions(+), 4 deletions(-)
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 9532c1f..70c565f 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -52,9 +52,29 @@ static void bdi_debug_init(void)
static int bdi_debug_stats_show(struct seq_file *m, void *v)
{
struct backing_dev_info *bdi = m->private;
+ struct bdi_writeback *wb;
unsigned long background_thresh;
unsigned long dirty_thresh;
unsigned long bdi_thresh;
+ unsigned long nr_dirty, nr_io, nr_more_io, nr_wb;
+ struct inode *inode;
+
+ /*
+ * inode lock is enough here, the bdi->wb_list is protected by
+ * RCU on the reader side
+ */
+ nr_wb = nr_dirty = nr_io = nr_more_io = 0;
+ spin_lock(&inode_lock);
+ list_for_each_entry(wb, &bdi->wb_list, list) {
+ nr_wb++;
+ list_for_each_entry(inode, &wb->b_dirty, i_list)
+ nr_dirty++;
+ list_for_each_entry(inode, &wb->b_io, i_list)
+ nr_io++;
+ list_for_each_entry(inode, &wb->b_more_io, i_list)
+ nr_more_io++;
+ }
+ spin_unlock(&inode_lock);
get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi);
@@ -64,12 +84,22 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
"BdiReclaimable: %8lu kB\n"
"BdiDirtyThresh: %8lu kB\n"
"DirtyThresh: %8lu kB\n"
- "BackgroundThresh: %8lu kB\n",
+ "BackgroundThresh: %8lu kB\n"
+ "WriteBack threads:%8lu\n"
+ "b_dirty: %8lu\n"
+ "b_io: %8lu\n"
+ "b_more_io: %8lu\n"
+ "bdi_list: %8u\n"
+ "state: %8lx\n"
+ "wb_mask: %8lx\n"
+ "wb_list: %8u\n"
+ "wb_cnt: %8u\n",
(unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)),
(unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)),
- K(bdi_thresh),
- K(dirty_thresh),
- K(background_thresh));
+ K(bdi_thresh), K(dirty_thresh),
+ K(background_thresh), nr_wb, nr_dirty, nr_io, nr_more_io,
+ !list_empty(&bdi->bdi_list), bdi->state, bdi->wb_mask,
+ !list_empty(&bdi->wb_list), bdi->wb_cnt);
#undef K
return 0;
--
1.6.4.1.207.g68ea
This enables us to track who does what and print info. Its main use
is catching dirty inodes on the default_backing_dev_info, so we can
fix that up.
Signed-off-by: Jens Axboe <[email protected]>
---
block/blk-core.c | 1 +
drivers/block/aoe/aoeblk.c | 1 +
drivers/char/mem.c | 1 +
fs/btrfs/disk-io.c | 1 +
fs/char_dev.c | 1 +
fs/configfs/inode.c | 1 +
fs/fuse/inode.c | 1 +
fs/hugetlbfs/inode.c | 1 +
fs/nfs/client.c | 1 +
fs/ocfs2/dlm/dlmfs.c | 1 +
fs/ramfs/inode.c | 1 +
fs/sysfs/inode.c | 1 +
fs/ubifs/super.c | 1 +
include/linux/backing-dev.h | 2 ++
kernel/cgroup.c | 1 +
mm/backing-dev.c | 1 +
mm/swap_state.c | 1 +
17 files changed, 18 insertions(+), 0 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index e3299a7..e695634 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -501,6 +501,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
q->backing_dev_info.state = 0;
q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
+ q->backing_dev_info.name = "block";
err = bdi_init(&q->backing_dev_info);
if (err) {
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index 2307a27..0efb8fc 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -265,6 +265,7 @@ aoeblk_gdalloc(void *vp)
}
blk_queue_make_request(&d->blkq, aoeblk_make_request);
+ d->blkq.backing_dev_info.name = "aoe";
if (bdi_init(&d->blkq.backing_dev_info))
goto err_mempool;
spin_lock_irqsave(&d->lock, flags);
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index afa8813..645237b 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -822,6 +822,7 @@ static const struct file_operations zero_fops = {
* - permits private mappings, "copies" are taken of the source of zeros
*/
static struct backing_dev_info zero_bdi = {
+ .name = "char/mem",
.capabilities = BDI_CAP_MAP_COPY,
};
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index e83be2e..15831d5 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1352,6 +1352,7 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
{
int err;
+ bdi->name = "btrfs";
bdi->capabilities = BDI_CAP_MAP_COPY;
err = bdi_init(bdi);
if (err)
diff --git a/fs/char_dev.c b/fs/char_dev.c
index a173551..7c27a8e 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -31,6 +31,7 @@
* - no readahead or I/O queue unplugging required
*/
struct backing_dev_info directly_mappable_cdev_bdi = {
+ .name = "char",
.capabilities = (
#ifdef CONFIG_MMU
/* permit private copies of the data to be taken */
diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c
index 4921e74..a2f7460 100644
--- a/fs/configfs/inode.c
+++ b/fs/configfs/inode.c
@@ -51,6 +51,7 @@ static const struct address_space_operations configfs_aops = {
};
static struct backing_dev_info configfs_backing_dev_info = {
+ .name = "configfs",
.ra_pages = 0, /* No readahead */
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index f91ccc4..4567db6 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -801,6 +801,7 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb)
{
int err;
+ fc->bdi.name = "fuse";
fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
fc->bdi.unplug_io_fn = default_unplug_io_fn;
/* fuse does it's own writeback accounting */
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index cb88dac..a93b885 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -44,6 +44,7 @@ static const struct inode_operations hugetlbfs_dir_inode_operations;
static const struct inode_operations hugetlbfs_inode_operations;
static struct backing_dev_info hugetlbfs_backing_dev_info = {
+ .name = "hugetlbfs",
.ra_pages = 0, /* No readahead */
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 8d25ccb..c6be84a 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -879,6 +879,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *
server->rsize = NFS_MAX_FILE_IO_SIZE;
server->rpages = (server->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ server->backing_dev_info.name = "nfs";
server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD;
if (server->wsize > max_rpc_payload)
diff --git a/fs/ocfs2/dlm/dlmfs.c b/fs/ocfs2/dlm/dlmfs.c
index 1c9efb4..02bf178 100644
--- a/fs/ocfs2/dlm/dlmfs.c
+++ b/fs/ocfs2/dlm/dlmfs.c
@@ -325,6 +325,7 @@ clear_fields:
}
static struct backing_dev_info dlmfs_backing_dev_info = {
+ .name = "ocfs2-dlmfs",
.ra_pages = 0, /* No readahead */
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index 0ff7566..a7f0110 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -46,6 +46,7 @@ static const struct super_operations ramfs_ops;
static const struct inode_operations ramfs_dir_inode_operations;
static struct backing_dev_info ramfs_backing_dev_info = {
+ .name = "ramfs",
.ra_pages = 0, /* No readahead */
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK |
BDI_CAP_MAP_DIRECT | BDI_CAP_MAP_COPY |
diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c
index 555f0ff..e57f98e 100644
--- a/fs/sysfs/inode.c
+++ b/fs/sysfs/inode.c
@@ -29,6 +29,7 @@ static const struct address_space_operations sysfs_aops = {
};
static struct backing_dev_info sysfs_backing_dev_info = {
+ .name = "sysfs",
.ra_pages = 0, /* No readahead */
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 8d6050a..51763aa 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -1965,6 +1965,7 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
*
* Read-ahead will be disabled because @c->bdi.ra_pages is 0.
*/
+ c->bdi.name = "ubifs",
c->bdi.capabilities = BDI_CAP_MAP_COPY;
c->bdi.unplug_io_fn = default_unplug_io_fn;
err = bdi_init(&c->bdi);
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index ac1d2ba..64c43ef 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -66,6 +66,8 @@ struct backing_dev_info {
void (*unplug_io_fn)(struct backing_dev_info *, struct page *);
void *unplug_io_data;
+ char *name;
+
struct percpu_counter bdi_stat[NR_BDI_STAT_ITEMS];
struct prop_local_percpu completions;
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index b6eadfe..c7ece8f 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -600,6 +600,7 @@ static struct inode_operations cgroup_dir_inode_operations;
static struct file_operations proc_cgroupstats_operations;
static struct backing_dev_info cgroup_backing_dev_info = {
+ .name = "cgroup",
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK,
};
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 70c565f..bfc6ee2 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -17,6 +17,7 @@ void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
EXPORT_SYMBOL(default_unplug_io_fn);
struct backing_dev_info default_backing_dev_info = {
+ .name = "default",
.ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
.state = 0,
.capabilities = BDI_CAP_MAP_COPY,
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 42cd38e..5ae6b8b 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -34,6 +34,7 @@ static const struct address_space_operations swap_aops = {
};
static struct backing_dev_info swap_backing_dev_info = {
+ .name = "swap",
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
.unplug_io_fn = swap_unplug_io_fn,
};
--
1.6.4.1.207.g68ea
Also a debugging aid. We want to catch dirty inodes being added to
backing devices that don't do writeback.
Signed-off-by: Jens Axboe <[email protected]>
---
fs/fs-writeback.c | 7 +++++++
include/linux/backing-dev.h | 1 +
mm/backing-dev.c | 6 ++++++
3 files changed, 14 insertions(+), 0 deletions(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 6714b38..ce68f60 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1024,6 +1024,13 @@ void __mark_inode_dirty(struct inode *inode, int flags)
*/
if (!was_dirty) {
struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
+ struct backing_dev_info *bdi = wb->bdi;
+
+ if (bdi_cap_writeback_dirty(bdi) &&
+ !test_bit(BDI_registered, &bdi->state)) {
+ WARN_ON(1);
+ printk("bdi-%s not registered\n", bdi->name);
+ }
inode->dirtied_when = jiffies;
list_move(&inode->i_list, &wb->b_dirty);
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 64c43ef..293dd69 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -29,6 +29,7 @@ enum bdi_state {
BDI_wb_alloc, /* Default embedded wb allocated */
BDI_async_congested, /* The async (write) queue is getting full */
BDI_sync_congested, /* The sync queue is getting full */
+ BDI_registered, /* bdi_register() was done */
BDI_unused, /* Available bits start here */
};
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index bfc6ee2..1bb8361 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -464,6 +464,11 @@ void static bdi_add_default_flusher_task(struct backing_dev_info *bdi)
if (!bdi_cap_writeback_dirty(bdi))
return;
+ if (WARN_ON(!test_bit(BDI_registered, &bdi->state))) {
+ printk("bdi %p/%s is not registered!\n", bdi, bdi->name);
+ return;
+ }
+
/*
* Check with the helper whether to proceed adding a task. Will only
* abort if we two or more simultanous calls to
@@ -527,6 +532,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
}
bdi_debug_register(bdi, dev_name(dev));
+ set_bit(BDI_registered, &bdi->state);
exit:
return ret;
}
--
1.6.4.1.207.g68ea
From: Theodore Ts'o <[email protected]>
Originally, MAX_WRITEBACK_PAGES was hard-coded to 1024 because of a
concern of not holding I_SYNC for too long. (At least, that was the
comment previously.) This doesn't make sense now because the only
time we wait for I_SYNC is if we are calling sync or fsync, and in
that case we need to write out all of the data anyway. Previously
there may have been other code paths that waited on I_SYNC, but not
any more.
According to Christoph, the current writeback size is way too small,
and XFS had a hack that bumped out nr_to_write to four times the value
sent by the VM to be able to saturate medium-sized RAID arrays. This
value was also problematic for ext4 as well, as it caused large files
to be come interleaved on disk by in 8 megabyte chunks (we bumped up
the nr_to_write by a factor of two).
So, in this patch, we make the MAX_WRITEBACK_PAGES a tunable,
max_writeback_mb, and set it to a default value of 128 megabytes.
http://bugzilla.kernel.org/show_bug.cgi?id=13930
Signed-off-by: "Theodore Ts'o" <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>
---
fs/fs-writeback.c | 9 +--------
include/linux/writeback.h | 1 +
kernel/sysctl.c | 8 ++++++++
mm/page-writeback.c | 6 ++++++
4 files changed, 16 insertions(+), 8 deletions(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index ce68f60..790d379 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -641,14 +641,7 @@ void writeback_inodes_wbc(struct writeback_control *wbc)
writeback_inodes_wb(&bdi->wb, wbc);
}
-/*
- * The maximum number of pages to writeout in a single bdi flush/kupdate
- * operation. We do this so we don't hold I_SYNC against an inode for
- * enormous amounts of time, which would block a userspace task which has
- * been forced to throttle against that inode. Also, the code reevaluates
- * the dirty each time it has written this many pages.
- */
-#define MAX_WRITEBACK_PAGES 1024
+#define MAX_WRITEBACK_PAGES (max_writeback_mb << (20 - PAGE_SHIFT))
static inline bool over_bground_thresh(void)
{
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 78b1e46..fbed759 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -104,6 +104,7 @@ extern int vm_dirty_ratio;
extern unsigned long vm_dirty_bytes;
extern unsigned int dirty_writeback_interval;
extern unsigned int dirty_expire_interval;
+extern unsigned int max_writeback_mb;
extern int vm_highmem_is_dirtyable;
extern int block_dump;
extern int laptop_mode;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 58be760..315fc30 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1104,6 +1104,14 @@ static struct ctl_table vm_table[] = {
.proc_handler = &proc_dointvec,
},
{
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "max_writeback_mb",
+ .data = &max_writeback_mb,
+ .maxlen = sizeof(max_writeback_mb),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
+ {
.ctl_name = VM_NR_PDFLUSH_THREADS,
.procname = "nr_pdflush_threads",
.data = &nr_pdflush_threads,
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 2c287d9..38fe4e8 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -55,6 +55,12 @@ static inline long sync_writeback_pages(void)
/* The following parameters are exported via /proc/sys/vm */
/*
+ * The maximum amount of memory (in megabytes) to write out in a
+ * single bdflush/kupdate operation.
+ */
+unsigned int max_writeback_mb = 128;
+
+/*
* Start background writeback (via pdflush) at this percentage
*/
int dirty_background_ratio = 10;
--
1.6.4.1.207.g68ea
On Fri 04-09-09 09:46:39, Jens Axboe wrote:
> This adds two new exported functions:
>
> - writeback_inodes_sb(), which only attempts to writeback dirty inodes on
> this super_block, for WB_SYNC_NONE writeout.
> - sync_inodes_sbt(), which writes out all dirty inodes on this super_block
> and also waits for the IO to complete.
>
> Signed-off-by: Jens Axboe <[email protected]>
The patch looks good. A nice cleanup.
Acked-by: Jan Kara <[email protected]>
> ---
> drivers/staging/pohmelfs/inode.c | 9 +----
> fs/fs-writeback.c | 70 ++++++++++++++++++++++---------------
> fs/sync.c | 18 +++++----
> fs/ubifs/budget.c | 16 +-------
> fs/ubifs/super.c | 8 +----
> include/linux/fs.h | 2 -
> include/linux/writeback.h | 3 +-
> 7 files changed, 58 insertions(+), 68 deletions(-)
>
> diff --git a/drivers/staging/pohmelfs/inode.c b/drivers/staging/pohmelfs/inode.c
> index 7b60579..e63c9be 100644
> --- a/drivers/staging/pohmelfs/inode.c
> +++ b/drivers/staging/pohmelfs/inode.c
> @@ -1950,14 +1950,7 @@ static int pohmelfs_get_sb(struct file_system_type *fs_type,
> */
> static void pohmelfs_kill_super(struct super_block *sb)
> {
> - struct writeback_control wbc = {
> - .sync_mode = WB_SYNC_ALL,
> - .range_start = 0,
> - .range_end = LLONG_MAX,
> - .nr_to_write = LONG_MAX,
> - };
> - generic_sync_sb_inodes(sb, &wbc);
> -
> + sync_inodes_sb(sb);
> kill_anon_super(sb);
> }
>
> diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
> index c54226b..271e5f4 100644
> --- a/fs/fs-writeback.c
> +++ b/fs/fs-writeback.c
> @@ -458,8 +458,8 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
> * on the writer throttling path, and we get decent balancing between many
> * throttled threads: we don't want them all piling up on inode_sync_wait.
> */
> -void generic_sync_sb_inodes(struct super_block *sb,
> - struct writeback_control *wbc)
> +static void generic_sync_sb_inodes(struct super_block *sb,
> + struct writeback_control *wbc)
> {
> const unsigned long start = jiffies; /* livelock avoidance */
> int sync = wbc->sync_mode == WB_SYNC_ALL;
> @@ -593,13 +593,6 @@ void generic_sync_sb_inodes(struct super_block *sb,
>
> return; /* Leave any unwritten inodes on s_io */
> }
> -EXPORT_SYMBOL_GPL(generic_sync_sb_inodes);
> -
> -static void sync_sb_inodes(struct super_block *sb,
> - struct writeback_control *wbc)
> -{
> - generic_sync_sb_inodes(sb, wbc);
> -}
>
> /*
> * Start writeback of dirty pagecache data against all unlocked inodes.
> @@ -640,7 +633,7 @@ restart:
> */
> if (down_read_trylock(&sb->s_umount)) {
> if (sb->s_root)
> - sync_sb_inodes(sb, wbc);
> + generic_sync_sb_inodes(sb, wbc);
> up_read(&sb->s_umount);
> }
> spin_lock(&sb_lock);
> @@ -653,35 +646,56 @@ restart:
> spin_unlock(&sb_lock);
> }
>
> -/*
> - * writeback and wait upon the filesystem's dirty inodes. The caller will
> - * do this in two passes - one to write, and one to wait.
> - *
> - * A finite limit is set on the number of pages which will be written.
> - * To prevent infinite livelock of sys_sync().
> +/**
> + * writeback_inodes_sb - writeback dirty inodes from given super_block
> + * @sb: the superblock
> *
> - * We add in the number of potentially dirty inodes, because each inode write
> - * can dirty pagecache in the underlying blockdev.
> + * Start writeback on some inodes on this super_block. No guarantees are made
> + * on how many (if any) will be written, and this function does not wait
> + * for IO completion of submitted IO. The number of pages submitted is
> + * returned.
> */
> -void sync_inodes_sb(struct super_block *sb, int wait)
> +long writeback_inodes_sb(struct super_block *sb)
> {
> struct writeback_control wbc = {
> - .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE,
> + .sync_mode = WB_SYNC_NONE,
> .range_start = 0,
> .range_end = LLONG_MAX,
> };
> + unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
> + unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
> + long nr_to_write;
>
> - if (!wait) {
> - unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
> - unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
> -
> - wbc.nr_to_write = nr_dirty + nr_unstable +
> + nr_to_write = nr_dirty + nr_unstable +
> (inodes_stat.nr_inodes - inodes_stat.nr_unused);
> - } else
> - wbc.nr_to_write = LONG_MAX; /* doesn't actually matter */
>
> - sync_sb_inodes(sb, &wbc);
> + wbc.nr_to_write = nr_to_write;
> + generic_sync_sb_inodes(sb, &wbc);
> + return nr_to_write - wbc.nr_to_write;
> +}
> +EXPORT_SYMBOL(writeback_inodes_sb);
> +
> +/**
> + * sync_inodes_sb - sync sb inode pages
> + * @sb: the superblock
> + *
> + * This function writes and waits on any dirty inode belonging to this
> + * super_block. The number of pages synced is returned.
> + */
> +long sync_inodes_sb(struct super_block *sb)
> +{
> + struct writeback_control wbc = {
> + .sync_mode = WB_SYNC_ALL,
> + .range_start = 0,
> + .range_end = LLONG_MAX,
> + };
> + long nr_to_write = LONG_MAX; /* doesn't actually matter */
> +
> + wbc.nr_to_write = nr_to_write;
> + generic_sync_sb_inodes(sb, &wbc);
> + return nr_to_write - wbc.nr_to_write;
> }
> +EXPORT_SYMBOL(sync_inodes_sb);
>
> /**
> * write_inode_now - write an inode to disk
> diff --git a/fs/sync.c b/fs/sync.c
> index 3422ba6..66f2104 100644
> --- a/fs/sync.c
> +++ b/fs/sync.c
> @@ -19,20 +19,22 @@
> SYNC_FILE_RANGE_WAIT_AFTER)
>
> /*
> - * Do the filesystem syncing work. For simple filesystems sync_inodes_sb(sb, 0)
> - * just dirties buffers with inodes so we have to submit IO for these buffers
> - * via __sync_blockdev(). This also speeds up the wait == 1 case since in that
> - * case write_inode() functions do sync_dirty_buffer() and thus effectively
> - * write one block at a time.
> + * Do the filesystem syncing work. For simple filesystems
> + * writeback_inodes_sb(sb) just dirties buffers with inodes so we have to
> + * submit IO for these buffers via __sync_blockdev(). This also speeds up the
> + * wait == 1 case since in that case write_inode() functions do
> + * sync_dirty_buffer() and thus effectively write one block at a time.
> */
> static int __sync_filesystem(struct super_block *sb, int wait)
> {
> /* Avoid doing twice syncing and cache pruning for quota sync */
> - if (!wait)
> + if (!wait) {
> writeout_quota_sb(sb, -1);
> - else
> + writeback_inodes_sb(sb);
> + } else {
> sync_quota_sb(sb, -1);
> - sync_inodes_sb(sb, wait);
> + sync_inodes_sb(sb);
> + }
> if (sb->s_op->sync_fs)
> sb->s_op->sync_fs(sb, wait);
> return __sync_blockdev(sb->s_bdev, wait);
> diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c
> index eaf6d89..1c8991b 100644
> --- a/fs/ubifs/budget.c
> +++ b/fs/ubifs/budget.c
> @@ -65,26 +65,14 @@
> static int shrink_liability(struct ubifs_info *c, int nr_to_write)
> {
> int nr_written;
> - struct writeback_control wbc = {
> - .sync_mode = WB_SYNC_NONE,
> - .range_end = LLONG_MAX,
> - .nr_to_write = nr_to_write,
> - };
> -
> - generic_sync_sb_inodes(c->vfs_sb, &wbc);
> - nr_written = nr_to_write - wbc.nr_to_write;
>
> + nr_written = writeback_inodes_sb(c->vfs_sb);
> if (!nr_written) {
> /*
> * Re-try again but wait on pages/inodes which are being
> * written-back concurrently (e.g., by pdflush).
> */
> - memset(&wbc, 0, sizeof(struct writeback_control));
> - wbc.sync_mode = WB_SYNC_ALL;
> - wbc.range_end = LLONG_MAX;
> - wbc.nr_to_write = nr_to_write;
> - generic_sync_sb_inodes(c->vfs_sb, &wbc);
> - nr_written = nr_to_write - wbc.nr_to_write;
> + nr_written = sync_inodes_sb(c->vfs_sb);
> }
>
> dbg_budg("%d pages were written back", nr_written);
> diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
> index 26d2e0d..8d6050a 100644
> --- a/fs/ubifs/super.c
> +++ b/fs/ubifs/super.c
> @@ -438,12 +438,6 @@ static int ubifs_sync_fs(struct super_block *sb, int wait)
> {
> int i, err;
> struct ubifs_info *c = sb->s_fs_info;
> - struct writeback_control wbc = {
> - .sync_mode = WB_SYNC_ALL,
> - .range_start = 0,
> - .range_end = LLONG_MAX,
> - .nr_to_write = LONG_MAX,
> - };
>
> /*
> * Zero @wait is just an advisory thing to help the file system shove
> @@ -462,7 +456,7 @@ static int ubifs_sync_fs(struct super_block *sb, int wait)
> * the user be able to get more accurate results of 'statfs()' after
> * they synchronize the file system.
> */
> - generic_sync_sb_inodes(sb, &wbc);
> + sync_inodes_sb(sb);
>
> /*
> * Synchronize write buffers, because 'ubifs_run_commit()' does not
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index 73e9b64..07b0f66 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -2070,8 +2070,6 @@ static inline void invalidate_remote_inode(struct inode *inode)
> extern int invalidate_inode_pages2(struct address_space *mapping);
> extern int invalidate_inode_pages2_range(struct address_space *mapping,
> pgoff_t start, pgoff_t end);
> -extern void generic_sync_sb_inodes(struct super_block *sb,
> - struct writeback_control *wbc);
> extern int write_inode_now(struct inode *, int);
> extern int filemap_fdatawrite(struct address_space *);
> extern int filemap_flush(struct address_space *);
> diff --git a/include/linux/writeback.h b/include/linux/writeback.h
> index 3224820..0703929 100644
> --- a/include/linux/writeback.h
> +++ b/include/linux/writeback.h
> @@ -78,7 +78,8 @@ struct writeback_control {
> */
> void writeback_inodes(struct writeback_control *wbc);
> int inode_wait(void *);
> -void sync_inodes_sb(struct super_block *, int wait);
> +long writeback_inodes_sb(struct super_block *);
> +long sync_inodes_sb(struct super_block *);
>
> /* writeback.h requires fs.h; it, too, is not included from here. */
> static inline void wait_on_inode(struct inode *inode)
> --
> 1.6.4.1.207.g68ea
>
--
Jan Kara <[email protected]>
SUSE Labs, CR
On Fri 04-09-09 09:46:41, Jens Axboe wrote:
> diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
> index 45ad4bb..93aa9a7 100644
> --- a/fs/fs-writeback.c
> +++ b/fs/fs-writeback.c
...
> +static void wb_start_writeback(struct bdi_writeback *wb, struct bdi_work *work)
> +{
> + /*
> + * If we failed allocating the bdi work item, wake up the wb thread
> + * always. As a safety precaution, it'll flush out everything
> + */
> + if (!wb_has_dirty_io(wb) && work)
> + wb_clear_pending(wb, work);
> + else if (wb->task)
> + wake_up_process(wb->task);
> +}
>
> - inode->i_state |= flags;
> +static void bdi_sched_work(struct backing_dev_info *bdi, struct bdi_work *work)
> +{
> + wb_start_writeback(&bdi->wb, work);
> +}
wb_start_writeback gets called only from bdi_sched_work() that gets
called only from bdi_queue_work(). I think it might be easier to read if we
put everything in bdi_queue_work().
Also it's not quite clear to me, why wb_start_writeback() wakes up process
even if wb_has_dirty_io() == 0.
> +/*
> + * For WB_SYNC_NONE writeback, the caller does not have the sb pinned
> + * before calling writeback. So make sure that we do pin it, so it doesn't
> + * go away while we are writing inodes from it.
Maybe add here a comment that the function returns 0 if the sb pinned and
1 if it isn't (which seems slightly counterintuitive to me).
> + */
> +static int pin_sb_for_writeback(struct writeback_control *wbc,
> + struct inode *inode)
> {
> + struct super_block *sb = inode->i_sb;
> +
> + /*
> + * Caller must already hold the ref for this
> + */
> + if (wbc->sync_mode == WB_SYNC_ALL) {
> + WARN_ON(!rwsem_is_locked(&sb->s_umount));
> + return 0;
> + }
> +
> + spin_lock(&sb_lock);
> + sb->s_count++;
> + if (down_read_trylock(&sb->s_umount)) {
> + if (sb->s_root) {
> + spin_unlock(&sb_lock);
> + return 0;
> + }
> + /*
> + * umounted, drop rwsem again and fall through to failure
> + */
> + up_read(&sb->s_umount);
> + }
> +
> + __put_super_and_need_restart(sb);
Here, you should be safe to do just sb->s_count-- since you didn't drop
sb_lock in the mean time. Other
> + spin_unlock(&sb_lock);
> + return 1;
> +}
> +
> +static void unpin_sb_for_writeback(struct writeback_control *wbc,
> + struct inode *inode)
> +{
> + struct super_block *sb = inode->i_sb;
> +
> + if (wbc->sync_mode == WB_SYNC_ALL)
> + return;
> +
> + up_read(&sb->s_umount);
> + spin_lock(&sb_lock);
> + __put_super_and_need_restart(sb);
> + spin_unlock(&sb_lock);
Above three lines should be just:
put_super(sb);
> +}
> +
> +static void writeback_inodes_wb(struct bdi_writeback *wb,
> + struct writeback_control *wbc)
> +{
> + struct super_block *sb = wbc->sb;
> const int is_blkdev_sb = sb_is_blkdev_sb(sb);
> const unsigned long start = jiffies; /* livelock avoidance */
>
> spin_lock(&inode_lock);
>
> - if (!wbc->for_kupdate || list_empty(&bdi->b_io))
> - queue_io(bdi, wbc->older_than_this);
> + if (!wbc->for_kupdate || list_empty(&wb->b_io))
> + queue_io(wb, wbc->older_than_this);
>
> - while (!list_empty(&bdi->b_io)) {
> - struct inode *inode = list_entry(bdi->b_io.prev,
> + while (!list_empty(&wb->b_io)) {
> + struct inode *inode = list_entry(wb->b_io.prev,
> struct inode, i_list);
> long pages_skipped;
>
> @@ -491,7 +559,7 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
> continue;
> }
>
> - if (!bdi_cap_writeback_dirty(bdi)) {
> + if (!bdi_cap_writeback_dirty(wb->bdi)) {
> redirty_tail(inode);
> if (is_blkdev_sb) {
> /*
> @@ -513,7 +581,7 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
> continue;
> }
>
> - if (wbc->nonblocking && bdi_write_congested(bdi)) {
> + if (wbc->nonblocking && bdi_write_congested(wb->bdi)) {
> wbc->encountered_congestion = 1;
> if (!is_blkdev_sb)
> break; /* Skip a congested fs */
> @@ -521,13 +589,6 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
> continue; /* Skip a congested blockdev */
> }
>
> - if (wbc->bdi && bdi != wbc->bdi) {
> - if (!is_blkdev_sb)
> - break; /* fs has the wrong queue */
> - requeue_io(inode);
> - continue; /* blockdev has wrong queue */
> - }
> -
> /*
> * Was this inode dirtied after sync_sb_inodes was called?
> * This keeps sync from extra jobs and livelock.
> @@ -535,16 +596,16 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
> if (inode_dirtied_after(inode, start))
> break;
>
> - /* Is another pdflush already flushing this queue? */
> - if (current_is_pdflush() && !writeback_acquire(bdi))
> - break;
> + if (pin_sb_for_writeback(wbc, inode)) {
> + requeue_io(inode);
> + continue;
> + }
>
> BUG_ON(inode->i_state & (I_FREEING | I_CLEAR));
> __iget(inode);
> pages_skipped = wbc->pages_skipped;
> writeback_single_inode(inode, wbc);
> - if (current_is_pdflush())
> - writeback_release(bdi);
> + unpin_sb_for_writeback(wbc, inode);
> if (wbc->pages_skipped != pages_skipped) {
> /*
> * writeback is not making progress due to locked
This looks safe now. Good.
> /*
> - * Write out a superblock's list of dirty inodes. A wait will be performed
> - * upon no inodes, all inodes or the final one, depending upon sync_mode.
> - *
> - * If older_than_this is non-NULL, then only write out inodes which
> - * had their first dirtying at a time earlier than *older_than_this.
> - *
> - * If we're a pdlfush thread, then implement pdflush collision avoidance
> - * against the entire list.
> + * The maximum number of pages to writeout in a single bdi flush/kupdate
> + * operation. We do this so we don't hold I_SYNC against an inode for
> + * enormous amounts of time, which would block a userspace task which has
> + * been forced to throttle against that inode. Also, the code reevaluates
> + * the dirty each time it has written this many pages.
> + */
> +#define MAX_WRITEBACK_PAGES 1024
> +
> +static inline bool over_bground_thresh(void)
> +{
> + unsigned long background_thresh, dirty_thresh;
> +
> + get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
> +
> + return (global_page_state(NR_FILE_DIRTY) +
> + global_page_state(NR_UNSTABLE_NFS) >= background_thresh);
> +}
> +
> +/*
> + * Explicit flushing or periodic writeback of "old" data.
> *
> - * If `bdi' is non-zero then we're being asked to writeback a specific queue.
> - * This function assumes that the blockdev superblock's inodes are backed by
> - * a variety of queues, so all inodes are searched. For other superblocks,
> - * assume that all inodes are backed by the same queue.
> + * Define "old": the first time one of an inode's pages is dirtied, we mark the
> + * dirtying-time in the inode's address_space. So this periodic writeback code
> + * just walks the superblock inode list, writing back any inodes which are
> + * older than a specific point in time.
> *
> - * FIXME: this linear search could get expensive with many fileystems. But
> - * how to fix? We need to go from an address_space to all inodes which share
> - * a queue with that address_space. (Easy: have a global "dirty superblocks"
> - * list).
> + * Try to run once per dirty_writeback_interval. But if a writeback event
> + * takes longer than a dirty_writeback_interval interval, then leave a
> + * one-second gap.
> *
> - * The inodes to be written are parked on bdi->b_io. They are moved back onto
> - * bdi->b_dirty as they are selected for writing. This way, none can be missed
> - * on the writer throttling path, and we get decent balancing between many
> - * throttled threads: we don't want them all piling up on inode_sync_wait.
> + * older_than_this takes precedence over nr_to_write. So we'll only write back
> + * all dirty pages if they are all attached to "old" mappings.
> */
> -static void generic_sync_sb_inodes(struct super_block *sb,
> - struct writeback_control *wbc)
> +static long wb_writeback(struct bdi_writeback *wb, long nr_pages,
> + struct super_block *sb,
> + enum writeback_sync_modes sync_mode, int for_kupdate)
> {
> - struct backing_dev_info *bdi;
> + struct writeback_control wbc = {
> + .bdi = wb->bdi,
> + .sb = sb,
> + .sync_mode = sync_mode,
> + .older_than_this = NULL,
> + .for_kupdate = for_kupdate,
> + .range_cyclic = 1,
> + };
> + unsigned long oldest_jif;
> + long wrote = 0;
>
> - if (!wbc->bdi) {
> - mutex_lock(&bdi_lock);
> - list_for_each_entry(bdi, &bdi_list, bdi_list)
> - generic_sync_bdi_inodes(bdi, wbc, sb);
> - mutex_unlock(&bdi_lock);
> - } else
> - generic_sync_bdi_inodes(wbc->bdi, wbc, sb);
> + if (wbc.for_kupdate) {
> + wbc.older_than_this = &oldest_jif;
> + oldest_jif = jiffies -
> + msecs_to_jiffies(dirty_expire_interval * 10);
> + }
>
> - if (wbc->sync_mode == WB_SYNC_ALL) {
> - struct inode *inode, *old_inode = NULL;
> + for (;;) {
> + if (sync_mode == WB_SYNC_NONE && nr_pages <= 0 &&
> + !over_bground_thresh())
> + break;
I don't understand this - why should this function care about
over_bground_thresh? As I understand it, it should just do what it was
told. For example when someone asks to write-out 20 pages from some
superblock, we may effectively end up writing everyting from the superblock
if the system happens to have another superblock with more than
background_thresh of dirty pages...
I guess you try to join pdflush-like and kupdate-like writeback here.
Then you might want to have conditions like
if (!for_kupdate && nr_pages <= 0 && sync_mode == WB_SYNC_NONE)
break;
if (for_kupdate && nr_pages <= 0 && !over_bground_thresh())
break;
> - spin_lock(&inode_lock);
> + wbc.more_io = 0;
> + wbc.encountered_congestion = 0;
> + wbc.nr_to_write = MAX_WRITEBACK_PAGES;
> + wbc.pages_skipped = 0;
> + writeback_inodes_wb(wb, &wbc);
> + nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
> + wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write;
>
> /*
> - * Data integrity sync. Must wait for all pages under writeback,
> - * because there may have been pages dirtied before our sync
> - * call, but which had writeout started before we write it out.
> - * In which case, the inode may not be on the dirty list, but
> - * we still have to wait for that writeout.
> + * If we ran out of stuff to write, bail unless more_io got set
> */
> - list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
> - struct address_space *mapping;
> -
> - if (inode->i_state &
> - (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
> - continue;
> - mapping = inode->i_mapping;
> - if (mapping->nrpages == 0)
> + if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
> + if (wbc.more_io && !wbc.for_kupdate)
> continue;
> - __iget(inode);
> - spin_unlock(&inode_lock);
> + break;
> + }
> + }
> +
> + return wrote;
> +}
> +
> +/*
> + * Retrieve work items and do the writeback they describe
> + */
> +long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
Why is here force_wait parameter? I don't see it being set anywhere...
> +{
> + struct backing_dev_info *bdi = wb->bdi;
> + struct bdi_work *work;
> + long nr_pages, wrote = 0;
> +
> + while ((work = get_next_work_item(bdi, wb)) != NULL) {
> + enum writeback_sync_modes sync_mode;
> +
> + nr_pages = work->nr_pages;
> +
> + /*
> + * Override sync mode, in case we must wait for completion
> + */
> + if (force_wait)
> + work->sync_mode = sync_mode = WB_SYNC_ALL;
> + else
> + sync_mode = work->sync_mode;
> +
> + /*
> + * If this isn't a data integrity operation, just notify
> + * that we have seen this work and we are now starting it.
> + */
> + if (sync_mode == WB_SYNC_NONE)
> + wb_clear_pending(wb, work);
> +
> + wrote += wb_writeback(wb, nr_pages, work->sb, sync_mode, 0);
> +
> + /*
> + * This is a data integrity writeback, so only do the
> + * notification when we have completed the work.
> + */
> + if (sync_mode == WB_SYNC_ALL)
> + wb_clear_pending(wb, work);
> + }
> +
> + /*
> + * Check for periodic writeback, kupdated() style
> + */
> + if (!wrote) {
Hmm, but who guarantees that old inodes get flushed from dirty list
when someone just periodically submits some work? And similarly who
guarantees we drop below background threshold? I think the logic
here needs some rethinking...
> + nr_pages = global_page_state(NR_FILE_DIRTY) +
> + global_page_state(NR_UNSTABLE_NFS) +
> + (inodes_stat.nr_inodes - inodes_stat.nr_unused);
> +
> + wrote = wb_writeback(wb, nr_pages, NULL, WB_SYNC_NONE, 1);
> + }
> +
> + return wrote;
> +}
> +
> +/*
> + * Handle writeback of dirty data for the device backed by this bdi. Also
> + * wakes up periodically and does kupdated style flushing.
> + */
> +int bdi_writeback_task(struct bdi_writeback *wb)
> +{
> + unsigned long last_active = jiffies;
> + unsigned long wait_jiffies = -1UL;
> + long pages_written;
> +
> + while (!kthread_should_stop()) {
> + pages_written = wb_do_writeback(wb, 0);
> +
> + if (pages_written)
> + last_active = jiffies;
> + else if (wait_jiffies != -1UL) {
> + unsigned long max_idle;
> +
> /*
> - * We hold a reference to 'inode' so it couldn't have
> - * been removed from s_inodes list while we dropped the
> - * inode_lock. We cannot iput the inode now as we can
> - * be holding the last reference and we cannot iput it
> - * under inode_lock. So we keep the reference and iput
> - * it later.
> + * Longest period of inactivity that we tolerate. If we
> + * see dirty data again later, the task will get
> + * recreated automatically.
> */
> - iput(old_inode);
> - old_inode = inode;
> + max_idle = max(5UL * 60 * HZ, wait_jiffies);
> + if (time_after(jiffies, max_idle + last_active))
> + break;
> + }
> +
> + wait_jiffies = msecs_to_jiffies(dirty_writeback_interval * 10);
> + set_current_state(TASK_INTERRUPTIBLE);
> + schedule_timeout(wait_jiffies);
> + try_to_freeze();
> + }
>
> - filemap_fdatawait(mapping);
> + return 0;
> +}
>
> - cond_resched();
> +/*
> + * Schedule writeback for all backing devices. Expensive! If this is a data
> + * integrity operation, writeback will be complete when this returns. If
> + * we are simply called for WB_SYNC_NONE, then writeback will merely be
> + * scheduled to run.
> + */
> +static void bdi_writeback_all(struct writeback_control *wbc)
> +{
> + const bool must_wait = wbc->sync_mode == WB_SYNC_ALL;
> + struct backing_dev_info *bdi;
> + struct bdi_work *work;
> + LIST_HEAD(list);
> +
> +restart:
> + spin_lock(&bdi_lock);
> +
> + list_for_each_entry(bdi, &bdi_list, bdi_list) {
> + struct bdi_work *work;
> +
> + if (!bdi_has_dirty_io(bdi))
> + continue;
>
> - spin_lock(&inode_lock);
> + /*
> + * If work allocation fails, do the writes inline. We drop
> + * the lock and restart the list writeout. This should be OK,
> + * since this happens rarely and because the writeout should
> + * eventually make more free memory available.
> + */
> + work = bdi_alloc_work(wbc);
> + if (!work) {
> + struct writeback_control __wbc = *wbc;
> +
> + /*
> + * Not a data integrity writeout, just continue
> + */
> + if (!must_wait)
> + continue;
> +
> + spin_unlock(&bdi_lock);
> + __wbc = *wbc;
> + __wbc.bdi = bdi;
> + writeback_inodes_wbc(&__wbc);
> + goto restart;
> }
> - spin_unlock(&inode_lock);
> - iput(old_inode);
> + if (must_wait)
> + list_add_tail(&work->wait_list, &list);
> +
> + bdi_queue_work(bdi, work);
> + }
> +
> + spin_unlock(&bdi_lock);
> +
> + /*
> + * If this is for WB_SYNC_ALL, wait for pending work to complete
> + * before returning.
> + */
> + while (!list_empty(&list)) {
> + work = list_entry(list.next, struct bdi_work, wait_list);
> + list_del(&work->wait_list);
> + bdi_wait_on_work_clear(work);
> + call_rcu(&work->rcu_head, bdi_work_free);
> }
> }
...
> @@ -715,6 +1112,7 @@ restart:
> long writeback_inodes_sb(struct super_block *sb)
> {
> struct writeback_control wbc = {
> + .sb = sb,
> .sync_mode = WB_SYNC_NONE,
> .range_start = 0,
> .range_end = LLONG_MAX,
> @@ -727,7 +1125,7 @@ long writeback_inodes_sb(struct super_block *sb)
> (inodes_stat.nr_inodes - inodes_stat.nr_unused);
>
> wbc.nr_to_write = nr_to_write;
> - generic_sync_sb_inodes(sb, &wbc);
> + bdi_writeback_all(&wbc);
> return nr_to_write - wbc.nr_to_write;
> }
> EXPORT_SYMBOL(writeback_inodes_sb);
> @@ -742,6 +1140,7 @@ EXPORT_SYMBOL(writeback_inodes_sb);
> long sync_inodes_sb(struct super_block *sb)
> {
> struct writeback_control wbc = {
> + .sb = sb,
> .sync_mode = WB_SYNC_ALL,
> .range_start = 0,
> .range_end = LLONG_MAX,
> @@ -749,7 +1148,8 @@ long sync_inodes_sb(struct super_block *sb)
> long nr_to_write = LONG_MAX; /* doesn't actually matter */
>
> wbc.nr_to_write = nr_to_write;
> - generic_sync_sb_inodes(sb, &wbc);
> + bdi_writeback_all(&wbc);
> + wait_sb_inodes(&wbc);
> return nr_to_write - wbc.nr_to_write;
> }
> EXPORT_SYMBOL(sync_inodes_sb);
So to writeback or sync inodes in a single superblock, you effectively
scan all the dirty inodes in the system just to find out which ones are on
your superblock? I don't think that's very efficient.
> diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
> index 928cd54..ac1d2ba 100644
> --- a/include/linux/backing-dev.h
> +++ b/include/linux/backing-dev.h
...
> +#define BDI_MAX_FLUSHERS 32
> +
This isn't used anywhere...
> diff --git a/mm/page-writeback.c b/mm/page-writeback.c
> index f8341b6..2c287d9 100644
> --- a/mm/page-writeback.c
> +++ b/mm/page-writeback.c
...
> @@ -593,8 +582,15 @@ static void balance_dirty_pages(struct address_space *mapping)
> if ((laptop_mode && pages_written) ||
> (!laptop_mode && (global_page_state(NR_FILE_DIRTY)
> + global_page_state(NR_UNSTABLE_NFS)
> - > background_thresh)))
> - pdflush_operation(background_writeout, 0);
> + > background_thresh))) {
> + struct writeback_control wbc = {
> + .bdi = bdi,
> + .sync_mode = WB_SYNC_NONE,
> + };
Shouldn't we set nr_pages here? I see that with your old code it wasn't
needed because of that over_bground check but that will probably get
changed.
> +
> +
> + bdi_start_writeback(&wbc);
> + }
> }
>
Honza
--
Jan Kara <[email protected]>
SUSE Labs, CR
On Fri, Sep 04 2009, Jan Kara wrote:
> On Fri 04-09-09 09:46:41, Jens Axboe wrote:
> > diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
> > index 45ad4bb..93aa9a7 100644
> > --- a/fs/fs-writeback.c
> > +++ b/fs/fs-writeback.c
> ...
> > +static void wb_start_writeback(struct bdi_writeback *wb, struct bdi_work *work)
> > +{
> > + /*
> > + * If we failed allocating the bdi work item, wake up the wb thread
> > + * always. As a safety precaution, it'll flush out everything
> > + */
> > + if (!wb_has_dirty_io(wb) && work)
> > + wb_clear_pending(wb, work);
> > + else if (wb->task)
> > + wake_up_process(wb->task);
> > +}
> >
> > - inode->i_state |= flags;
> > +static void bdi_sched_work(struct backing_dev_info *bdi, struct bdi_work *work)
> > +{
> > + wb_start_writeback(&bdi->wb, work);
> > +}
> wb_start_writeback gets called only from bdi_sched_work() that gets
> called only from bdi_queue_work(). I think it might be easier to read if we
> put everything in bdi_queue_work().
> Also it's not quite clear to me, why wb_start_writeback() wakes up process
> even if wb_has_dirty_io() == 0.
Indeed, mostly left-overs from the more complicated multi thread
support. I folded everything into bdi_queue_work() now.
Not sure why the wakeup statement looks as odd as it does, I changed it
as below now:
if (!wb_has_dirty_io(wb)) {
if (work)
wb_clear_pending(wb, work);
} else if (wb->task)
wake_up_process(wb->task);
so that we only wake the thread if it has dirty IO.
> > +/*
> > + * For WB_SYNC_NONE writeback, the caller does not have the sb pinned
> > + * before calling writeback. So make sure that we do pin it, so it doesn't
> > + * go away while we are writing inodes from it.
> Maybe add here a comment that the function returns 0 if the sb pinned and
> 1 if it isn't (which seems slightly counterintuitive to me).
0 on success is the usual calling convention, so I think that is fine. I
have added a comment about the return value.
> > + */
> > +static int pin_sb_for_writeback(struct writeback_control *wbc,
> > + struct inode *inode)
> > {
> > + struct super_block *sb = inode->i_sb;
> > +
> > + /*
> > + * Caller must already hold the ref for this
> > + */
> > + if (wbc->sync_mode == WB_SYNC_ALL) {
> > + WARN_ON(!rwsem_is_locked(&sb->s_umount));
> > + return 0;
> > + }
> > +
> > + spin_lock(&sb_lock);
> > + sb->s_count++;
> > + if (down_read_trylock(&sb->s_umount)) {
> > + if (sb->s_root) {
> > + spin_unlock(&sb_lock);
> > + return 0;
> > + }
> > + /*
> > + * umounted, drop rwsem again and fall through to failure
> > + */
> > + up_read(&sb->s_umount);
> > + }
> > +
> > + __put_super_and_need_restart(sb);
> Here, you should be safe to do just sb->s_count-- since you didn't drop
> sb_lock in the mean time. Other
Indeed, thanks!
> > + spin_unlock(&sb_lock);
> > + return 1;
> > +}
> > +
> > +static void unpin_sb_for_writeback(struct writeback_control *wbc,
> > + struct inode *inode)
> > +{
> > + struct super_block *sb = inode->i_sb;
> > +
> > + if (wbc->sync_mode == WB_SYNC_ALL)
> > + return;
> > +
> > + up_read(&sb->s_umount);
> > + spin_lock(&sb_lock);
> > + __put_super_and_need_restart(sb);
> > + spin_unlock(&sb_lock);
> Above three lines should be just:
> put_super(sb);
Just trying to avoid making put_super() non-static, but I've made that
change now too.
> > @@ -535,16 +596,16 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
> > if (inode_dirtied_after(inode, start))
> > break;
> >
> > - /* Is another pdflush already flushing this queue? */
> > - if (current_is_pdflush() && !writeback_acquire(bdi))
> > - break;
> > + if (pin_sb_for_writeback(wbc, inode)) {
> > + requeue_io(inode);
> > + continue;
> > + }
> >
> > BUG_ON(inode->i_state & (I_FREEING | I_CLEAR));
> > __iget(inode);
> > pages_skipped = wbc->pages_skipped;
> > writeback_single_inode(inode, wbc);
> > - if (current_is_pdflush())
> > - writeback_release(bdi);
> > + unpin_sb_for_writeback(wbc, inode);
> > if (wbc->pages_skipped != pages_skipped) {
> > /*
> > * writeback is not making progress due to locked
> This looks safe now. Good.
I'm relieved you're happy with that now, thanks! :-)
> > /*
> > - * Write out a superblock's list of dirty inodes. A wait will be performed
> > - * upon no inodes, all inodes or the final one, depending upon sync_mode.
> > - *
> > - * If older_than_this is non-NULL, then only write out inodes which
> > - * had their first dirtying at a time earlier than *older_than_this.
> > - *
> > - * If we're a pdlfush thread, then implement pdflush collision avoidance
> > - * against the entire list.
> > + * The maximum number of pages to writeout in a single bdi flush/kupdate
> > + * operation. We do this so we don't hold I_SYNC against an inode for
> > + * enormous amounts of time, which would block a userspace task which has
> > + * been forced to throttle against that inode. Also, the code reevaluates
> > + * the dirty each time it has written this many pages.
> > + */
> > +#define MAX_WRITEBACK_PAGES 1024
> > +
> > +static inline bool over_bground_thresh(void)
> > +{
> > + unsigned long background_thresh, dirty_thresh;
> > +
> > + get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
> > +
> > + return (global_page_state(NR_FILE_DIRTY) +
> > + global_page_state(NR_UNSTABLE_NFS) >= background_thresh);
> > +}
> > +
> > +/*
> > + * Explicit flushing or periodic writeback of "old" data.
> > *
> > - * If `bdi' is non-zero then we're being asked to writeback a specific queue.
> > - * This function assumes that the blockdev superblock's inodes are backed by
> > - * a variety of queues, so all inodes are searched. For other superblocks,
> > - * assume that all inodes are backed by the same queue.
> > + * Define "old": the first time one of an inode's pages is dirtied, we mark the
> > + * dirtying-time in the inode's address_space. So this periodic writeback code
> > + * just walks the superblock inode list, writing back any inodes which are
> > + * older than a specific point in time.
> > *
> > - * FIXME: this linear search could get expensive with many fileystems. But
> > - * how to fix? We need to go from an address_space to all inodes which share
> > - * a queue with that address_space. (Easy: have a global "dirty superblocks"
> > - * list).
> > + * Try to run once per dirty_writeback_interval. But if a writeback event
> > + * takes longer than a dirty_writeback_interval interval, then leave a
> > + * one-second gap.
> > *
> > - * The inodes to be written are parked on bdi->b_io. They are moved back onto
> > - * bdi->b_dirty as they are selected for writing. This way, none can be missed
> > - * on the writer throttling path, and we get decent balancing between many
> > - * throttled threads: we don't want them all piling up on inode_sync_wait.
> > + * older_than_this takes precedence over nr_to_write. So we'll only write back
> > + * all dirty pages if they are all attached to "old" mappings.
> > */
> > -static void generic_sync_sb_inodes(struct super_block *sb,
> > - struct writeback_control *wbc)
> > +static long wb_writeback(struct bdi_writeback *wb, long nr_pages,
> > + struct super_block *sb,
> > + enum writeback_sync_modes sync_mode, int for_kupdate)
> > {
> > - struct backing_dev_info *bdi;
> > + struct writeback_control wbc = {
> > + .bdi = wb->bdi,
> > + .sb = sb,
> > + .sync_mode = sync_mode,
> > + .older_than_this = NULL,
> > + .for_kupdate = for_kupdate,
> > + .range_cyclic = 1,
> > + };
> > + unsigned long oldest_jif;
> > + long wrote = 0;
> >
> > - if (!wbc->bdi) {
> > - mutex_lock(&bdi_lock);
> > - list_for_each_entry(bdi, &bdi_list, bdi_list)
> > - generic_sync_bdi_inodes(bdi, wbc, sb);
> > - mutex_unlock(&bdi_lock);
> > - } else
> > - generic_sync_bdi_inodes(wbc->bdi, wbc, sb);
> > + if (wbc.for_kupdate) {
> > + wbc.older_than_this = &oldest_jif;
> > + oldest_jif = jiffies -
> > + msecs_to_jiffies(dirty_expire_interval * 10);
> > + }
> >
> > - if (wbc->sync_mode == WB_SYNC_ALL) {
> > - struct inode *inode, *old_inode = NULL;
> > + for (;;) {
> > + if (sync_mode == WB_SYNC_NONE && nr_pages <= 0 &&
> > + !over_bground_thresh())
> > + break;
> I don't understand this - why should this function care about
> over_bground_thresh? As I understand it, it should just do what it was
> told. For example when someone asks to write-out 20 pages from some
> superblock, we may effectively end up writing everyting from the superblock
> if the system happens to have another superblock with more than
> background_thresh of dirty pages...
> I guess you try to join pdflush-like and kupdate-like writeback here.
> Then you might want to have conditions like
> if (!for_kupdate && nr_pages <= 0 && sync_mode == WB_SYNC_NONE)
> break;
> if (for_kupdate && nr_pages <= 0 && !over_bground_thresh())
> break;
Good spotting, yes that looks correct!
>
> > - spin_lock(&inode_lock);
> > + wbc.more_io = 0;
> > + wbc.encountered_congestion = 0;
> > + wbc.nr_to_write = MAX_WRITEBACK_PAGES;
> > + wbc.pages_skipped = 0;
> > + writeback_inodes_wb(wb, &wbc);
> > + nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
> > + wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write;
> >
> > /*
> > - * Data integrity sync. Must wait for all pages under writeback,
> > - * because there may have been pages dirtied before our sync
> > - * call, but which had writeout started before we write it out.
> > - * In which case, the inode may not be on the dirty list, but
> > - * we still have to wait for that writeout.
> > + * If we ran out of stuff to write, bail unless more_io got set
> > */
> > - list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
> > - struct address_space *mapping;
> > -
> > - if (inode->i_state &
> > - (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
> > - continue;
> > - mapping = inode->i_mapping;
> > - if (mapping->nrpages == 0)
> > + if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
> > + if (wbc.more_io && !wbc.for_kupdate)
> > continue;
> > - __iget(inode);
> > - spin_unlock(&inode_lock);
> > + break;
> > + }
> > + }
> > +
> > + return wrote;
> > +}
> > +
> > +/*
> > + * Retrieve work items and do the writeback they describe
> > + */
> > +long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
> Why is here force_wait parameter? I don't see it being set anywhere...
It's used on thread exit, to ensure that we flush and wait any pending
IO before exiting the thread.
> > +{
> > + struct backing_dev_info *bdi = wb->bdi;
> > + struct bdi_work *work;
> > + long nr_pages, wrote = 0;
> > +
> > + while ((work = get_next_work_item(bdi, wb)) != NULL) {
> > + enum writeback_sync_modes sync_mode;
> > +
> > + nr_pages = work->nr_pages;
> > +
> > + /*
> > + * Override sync mode, in case we must wait for completion
> > + */
> > + if (force_wait)
> > + work->sync_mode = sync_mode = WB_SYNC_ALL;
> > + else
> > + sync_mode = work->sync_mode;
> > +
> > + /*
> > + * If this isn't a data integrity operation, just notify
> > + * that we have seen this work and we are now starting it.
> > + */
> > + if (sync_mode == WB_SYNC_NONE)
> > + wb_clear_pending(wb, work);
> > +
> > + wrote += wb_writeback(wb, nr_pages, work->sb, sync_mode, 0);
> > +
> > + /*
> > + * This is a data integrity writeback, so only do the
> > + * notification when we have completed the work.
> > + */
> > + if (sync_mode == WB_SYNC_ALL)
> > + wb_clear_pending(wb, work);
> > + }
> > +
> > + /*
> > + * Check for periodic writeback, kupdated() style
> > + */
> > + if (!wrote) {
> Hmm, but who guarantees that old inodes get flushed from dirty list
> when someone just periodically submits some work? And similarly who
> guarantees we drop below background threshold? I think the logic
> here needs some rethinking...
Good point, I guess it is possible to get into a situation where it
periodically does explicit work and thus never seems idle enough to
flush old data. I'll add a check for 'last periodic old sync' for that.
> > @@ -749,7 +1148,8 @@ long sync_inodes_sb(struct super_block *sb)
> > long nr_to_write = LONG_MAX; /* doesn't actually matter */
> >
> > wbc.nr_to_write = nr_to_write;
> > - generic_sync_sb_inodes(sb, &wbc);
> > + bdi_writeback_all(&wbc);
> > + wait_sb_inodes(&wbc);
> > return nr_to_write - wbc.nr_to_write;
> > }
> > EXPORT_SYMBOL(sync_inodes_sb);
> So to writeback or sync inodes in a single superblock, you effectively
> scan all the dirty inodes in the system just to find out which ones are on
> your superblock? I don't think that's very efficient.
Yes I know, I'll provide some lookup functionality for that.
> > diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
> > index 928cd54..ac1d2ba 100644
> > --- a/include/linux/backing-dev.h
> > +++ b/include/linux/backing-dev.h
> ...
> > +#define BDI_MAX_FLUSHERS 32
> > +
> This isn't used anywhere...
Good catch, leftover as well. Killed.
> > diff --git a/mm/page-writeback.c b/mm/page-writeback.c
> > index f8341b6..2c287d9 100644
> > --- a/mm/page-writeback.c
> > +++ b/mm/page-writeback.c
> ...
> > @@ -593,8 +582,15 @@ static void balance_dirty_pages(struct address_space *mapping)
> > if ((laptop_mode && pages_written) ||
> > (!laptop_mode && (global_page_state(NR_FILE_DIRTY)
> > + global_page_state(NR_UNSTABLE_NFS)
> > - > background_thresh)))
> > - pdflush_operation(background_writeout, 0);
> > + > background_thresh))) {
> > + struct writeback_control wbc = {
> > + .bdi = bdi,
> > + .sync_mode = WB_SYNC_NONE,
> > + };
> Shouldn't we set nr_pages here? I see that with your old code it wasn't
> needed because of that over_bground check but that will probably get
> changed.
Sure, we may as well set it explicitly to the total dirty count.
Thanks for your review Jan, I'll post a new round shortly...
--
Jens Axboe
On Fri, Sep 04 2009, Jan Kara wrote:
> On Fri 04-09-09 09:46:39, Jens Axboe wrote:
> > This adds two new exported functions:
> >
> > - writeback_inodes_sb(), which only attempts to writeback dirty inodes on
> > this super_block, for WB_SYNC_NONE writeout.
> > - sync_inodes_sbt(), which writes out all dirty inodes on this super_block
> > and also waits for the IO to complete.
> >
> > Signed-off-by: Jens Axboe <[email protected]>
> The patch looks good. A nice cleanup.
> Acked-by: Jan Kara <[email protected]>
Thanks, ack added.
--
Jens Axboe
On Fri, Sep 04 2009, Jens Axboe wrote:
> Thanks for your review Jan, I'll post a new round shortly...
Since I just changed that one patch (and since I'm posting this patchset
a lot), I'll just include the updated patch below.
>From ec9603fe6f4d9026f282dc8945e977ea293bed57 Mon Sep 17 00:00:00 2001
From: Jens Axboe <[email protected]>
Date: Fri, 4 Sep 2009 14:01:16 +0200
Subject: [PATCH 3/8] writeback: switch to per-bdi threads for flushing data
This gets rid of pdflush for bdi writeout and kupdated style cleaning.
pdflush writeout suffers from lack of locality and also requires more
threads to handle the same workload, since it has to work in a
non-blocking fashion against each queue. This also introduces lumpy
behaviour and potential request starvation, since pdflush can be starved
for queue access if others are accessing it. A sample ffsb workload that
does random writes to files is about 8% faster here on a simple SATA drive
during the benchmark phase. File layout also seems a LOT more smooth in
vmstat:
r b swpd free buff cache si so bi bo in cs us sy id wa
0 1 0 608848 2652 375372 0 0 0 71024 604 24 1 10 48 42
0 1 0 549644 2712 433736 0 0 0 60692 505 27 1 8 48 44
1 0 0 476928 2784 505192 0 0 4 29540 553 24 0 9 53 37
0 1 0 457972 2808 524008 0 0 0 54876 331 16 0 4 38 58
0 1 0 366128 2928 614284 0 0 4 92168 710 58 0 13 53 34
0 1 0 295092 3000 684140 0 0 0 62924 572 23 0 9 53 37
0 1 0 236592 3064 741704 0 0 4 58256 523 17 0 8 48 44
0 1 0 165608 3132 811464 0 0 0 57460 560 21 0 8 54 38
0 1 0 102952 3200 873164 0 0 4 74748 540 29 1 10 48 41
0 1 0 48604 3252 926472 0 0 0 53248 469 29 0 7 47 45
where vanilla tends to fluctuate a lot in the creation phase:
r b swpd free buff cache si so bi bo in cs us sy id wa
1 1 0 678716 5792 303380 0 0 0 74064 565 50 1 11 52 36
1 0 0 662488 5864 319396 0 0 4 352 302 329 0 2 47 51
0 1 0 599312 5924 381468 0 0 0 78164 516 55 0 9 51 40
0 1 0 519952 6008 459516 0 0 4 78156 622 56 1 11 52 37
1 1 0 436640 6092 541632 0 0 0 82244 622 54 0 11 48 41
0 1 0 436640 6092 541660 0 0 0 8 152 39 0 0 51 49
0 1 0 332224 6200 644252 0 0 4 102800 728 46 1 13 49 36
1 0 0 274492 6260 701056 0 0 4 12328 459 49 0 7 50 43
0 1 0 211220 6324 763356 0 0 0 106940 515 37 1 10 51 39
1 0 0 160412 6376 813468 0 0 0 8224 415 43 0 6 49 45
1 1 0 85980 6452 886556 0 0 4 113516 575 39 1 11 54 34
0 2 0 85968 6452 886620 0 0 0 1640 158 211 0 0 46 54
A 10 disk test with btrfs performs 26% faster with per-bdi flushing. A
SSD based writeback test on XFS performs over 20% better as well, with
the throughput being very stable around 1GB/sec, where pdflush only
manages 750MB/sec and fluctuates wildly while doing so. Random buffered
writes to many files behave a lot better as well, as does random mmap'ed
writes.
A separate thread is added to sync the super blocks. In the long term,
adding sync_supers_bdi() functionality could get rid of this thread again.
Signed-off-by: Jens Axboe <[email protected]>
---
fs/buffer.c | 2 +-
fs/fs-writeback.c | 997 ++++++++++++++++++++++++++++++-------------
fs/super.c | 2 +-
fs/sync.c | 2 +-
include/linux/backing-dev.h | 55 ++-
include/linux/fs.h | 2 +-
include/linux/writeback.h | 8 +-
mm/backing-dev.c | 341 ++++++++++++++-
mm/page-writeback.c | 179 ++-------
mm/vmscan.c | 2 +-
10 files changed, 1118 insertions(+), 472 deletions(-)
diff --git a/fs/buffer.c b/fs/buffer.c
index 28f320f..90a9886 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -281,7 +281,7 @@ static void free_more_memory(void)
struct zone *zone;
int nid;
- wakeup_pdflush(1024);
+ wakeup_flusher_threads(1024);
yield();
for_each_online_node(nid) {
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 45ad4bb..c86492c 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -19,6 +19,8 @@
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/mm.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
@@ -27,165 +29,208 @@
#define inode_to_bdi(inode) ((inode)->i_mapping->backing_dev_info)
-/**
- * writeback_acquire - attempt to get exclusive writeback access to a device
- * @bdi: the device's backing_dev_info structure
- *
- * It is a waste of resources to have more than one pdflush thread blocked on
- * a single request queue. Exclusion at the request_queue level is obtained
- * via a flag in the request_queue's backing_dev_info.state.
- *
- * Non-request_queue-backed address_spaces will share default_backing_dev_info,
- * unless they implement their own. Which is somewhat inefficient, as this
- * may prevent concurrent writeback against multiple devices.
+/*
+ * Work items for the bdi_writeback threads
*/
-static int writeback_acquire(struct backing_dev_info *bdi)
+struct bdi_work {
+ struct list_head list;
+ struct list_head wait_list;
+ struct rcu_head rcu_head;
+
+ unsigned long seen;
+ atomic_t pending;
+
+ struct super_block *sb;
+ unsigned long nr_pages;
+ enum writeback_sync_modes sync_mode;
+
+ unsigned long state;
+};
+
+enum {
+ WS_USED_B = 0,
+ WS_ONSTACK_B,
+};
+
+#define WS_USED (1 << WS_USED_B)
+#define WS_ONSTACK (1 << WS_ONSTACK_B)
+
+static inline bool bdi_work_on_stack(struct bdi_work *work)
+{
+ return test_bit(WS_ONSTACK_B, &work->state);
+}
+
+static inline void bdi_work_init(struct bdi_work *work,
+ struct writeback_control *wbc)
{
- return !test_and_set_bit(BDI_pdflush, &bdi->state);
+ INIT_RCU_HEAD(&work->rcu_head);
+ work->sb = wbc->sb;
+ work->nr_pages = wbc->nr_to_write;
+ work->sync_mode = wbc->sync_mode;
+ work->state = WS_USED;
+}
+
+static inline void bdi_work_init_on_stack(struct bdi_work *work,
+ struct writeback_control *wbc)
+{
+ bdi_work_init(work, wbc);
+ work->state |= WS_ONSTACK;
}
/**
* writeback_in_progress - determine whether there is writeback in progress
* @bdi: the device's backing_dev_info structure.
*
- * Determine whether there is writeback in progress against a backing device.
+ * Determine whether there is writeback waiting to be handled against a
+ * backing device.
*/
int writeback_in_progress(struct backing_dev_info *bdi)
{
- return test_bit(BDI_pdflush, &bdi->state);
+ return !list_empty(&bdi->work_list);
}
-/**
- * writeback_release - relinquish exclusive writeback access against a device.
- * @bdi: the device's backing_dev_info structure
- */
-static void writeback_release(struct backing_dev_info *bdi)
+static void bdi_work_clear(struct bdi_work *work)
{
- BUG_ON(!writeback_in_progress(bdi));
- clear_bit(BDI_pdflush, &bdi->state);
+ clear_bit(WS_USED_B, &work->state);
+ smp_mb__after_clear_bit();
+ wake_up_bit(&work->state, WS_USED_B);
}
-static noinline void block_dump___mark_inode_dirty(struct inode *inode)
+static void bdi_work_free(struct rcu_head *head)
{
- if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
- struct dentry *dentry;
- const char *name = "?";
+ struct bdi_work *work = container_of(head, struct bdi_work, rcu_head);
- dentry = d_find_alias(inode);
- if (dentry) {
- spin_lock(&dentry->d_lock);
- name = (const char *) dentry->d_name.name;
- }
- printk(KERN_DEBUG
- "%s(%d): dirtied inode %lu (%s) on %s\n",
- current->comm, task_pid_nr(current), inode->i_ino,
- name, inode->i_sb->s_id);
- if (dentry) {
- spin_unlock(&dentry->d_lock);
- dput(dentry);
- }
- }
+ if (!bdi_work_on_stack(work))
+ kfree(work);
+ else
+ bdi_work_clear(work);
}
-/**
- * __mark_inode_dirty - internal function
- * @inode: inode to mark
- * @flags: what kind of dirty (i.e. I_DIRTY_SYNC)
- * Mark an inode as dirty. Callers should use mark_inode_dirty or
- * mark_inode_dirty_sync.
- *
- * Put the inode on the super block's dirty list.
- *
- * CAREFUL! We mark it dirty unconditionally, but move it onto the
- * dirty list only if it is hashed or if it refers to a blockdev.
- * If it was not hashed, it will never be added to the dirty list
- * even if it is later hashed, as it will have been marked dirty already.
- *
- * In short, make sure you hash any inodes _before_ you start marking
- * them dirty.
- *
- * This function *must* be atomic for the I_DIRTY_PAGES case -
- * set_page_dirty() is called under spinlock in several places.
- *
- * Note that for blockdevs, inode->dirtied_when represents the dirtying time of
- * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of
- * the kernel-internal blockdev inode represents the dirtying time of the
- * blockdev's pages. This is why for I_DIRTY_PAGES we always use
- * page->mapping->host, so the page-dirtying time is recorded in the internal
- * blockdev inode.
- */
-void __mark_inode_dirty(struct inode *inode, int flags)
+static void wb_work_complete(struct bdi_work *work)
{
- struct super_block *sb = inode->i_sb;
+ const enum writeback_sync_modes sync_mode = work->sync_mode;
/*
- * Don't do this for I_DIRTY_PAGES - that doesn't actually
- * dirty the inode itself
+ * For allocated work, we can clear the done/seen bit right here.
+ * For on-stack work, we need to postpone both the clear and free
+ * to after the RCU grace period, since the stack could be invalidated
+ * as soon as bdi_work_clear() has done the wakeup.
*/
- if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
- if (sb->s_op->dirty_inode)
- sb->s_op->dirty_inode(inode);
- }
+ if (!bdi_work_on_stack(work))
+ bdi_work_clear(work);
+ if (sync_mode == WB_SYNC_NONE || bdi_work_on_stack(work))
+ call_rcu(&work->rcu_head, bdi_work_free);
+}
+static void wb_clear_pending(struct bdi_writeback *wb, struct bdi_work *work)
+{
/*
- * make sure that changes are seen by all cpus before we test i_state
- * -- mikulas
+ * The caller has retrieved the work arguments from this work,
+ * drop our reference. If this is the last ref, delete and free it
*/
- smp_mb();
+ if (atomic_dec_and_test(&work->pending)) {
+ struct backing_dev_info *bdi = wb->bdi;
- /* avoid the locking if we can */
- if ((inode->i_state & flags) == flags)
- return;
-
- if (unlikely(block_dump))
- block_dump___mark_inode_dirty(inode);
+ spin_lock(&bdi->wb_lock);
+ list_del_rcu(&work->list);
+ spin_unlock(&bdi->wb_lock);
- spin_lock(&inode_lock);
- if ((inode->i_state & flags) != flags) {
- const int was_dirty = inode->i_state & I_DIRTY;
+ wb_work_complete(work);
+ }
+}
- inode->i_state |= flags;
+static void bdi_queue_work(struct backing_dev_info *bdi, struct bdi_work *work)
+{
+ if (work) {
+ work->seen = bdi->wb_mask;
+ BUG_ON(!work->seen);
+ atomic_set(&work->pending, bdi->wb_cnt);
+ BUG_ON(!bdi->wb_cnt);
/*
- * If the inode is being synced, just update its dirty state.
- * The unlocker will place the inode on the appropriate
- * superblock list, based upon its state.
+ * Make sure stores are seen before it appears on the list
*/
- if (inode->i_state & I_SYNC)
- goto out;
+ smp_mb();
- /*
- * Only add valid (hashed) inodes to the superblock's
- * dirty list. Add blockdev inodes as well.
- */
- if (!S_ISBLK(inode->i_mode)) {
- if (hlist_unhashed(&inode->i_hash))
- goto out;
- }
- if (inode->i_state & (I_FREEING|I_CLEAR))
- goto out;
+ spin_lock(&bdi->wb_lock);
+ list_add_tail_rcu(&work->list, &bdi->work_list);
+ spin_unlock(&bdi->wb_lock);
+ }
+
+ /*
+ * If the default thread isn't there, make sure we add it. When
+ * it gets created and wakes up, we'll run this work.
+ */
+ if (unlikely(list_empty_careful(&bdi->wb_list)))
+ wake_up_process(default_backing_dev_info.wb.task);
+ else {
+ struct bdi_writeback *wb = &bdi->wb;
/*
- * If the inode was already on b_dirty/b_io/b_more_io, don't
- * reposition it (that would break b_dirty time-ordering).
+ * If we failed allocating the bdi work item, wake up the wb
+ * thread always. As a safety precaution, it'll flush out
+ * everything
*/
- if (!was_dirty) {
- inode->dirtied_when = jiffies;
- list_move(&inode->i_list,
- &inode_to_bdi(inode)->b_dirty);
- }
+ if (!wb_has_dirty_io(wb)) {
+ if (work)
+ wb_clear_pending(wb, work);
+ } else if (wb->task);
+ wake_up_process(wb->task);
}
-out:
- spin_unlock(&inode_lock);
}
-EXPORT_SYMBOL(__mark_inode_dirty);
+/*
+ * Used for on-stack allocated work items. The caller needs to wait until
+ * the wb threads have acked the work before it's safe to continue.
+ */
+static void bdi_wait_on_work_clear(struct bdi_work *work)
+{
+ wait_on_bit(&work->state, WS_USED_B, bdi_sched_wait,
+ TASK_UNINTERRUPTIBLE);
+}
-static int write_inode(struct inode *inode, int sync)
+static struct bdi_work *bdi_alloc_work(struct writeback_control *wbc)
{
- if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode))
- return inode->i_sb->s_op->write_inode(inode, sync);
- return 0;
+ struct bdi_work *work;
+
+ work = kmalloc(sizeof(*work), GFP_ATOMIC);
+ if (work)
+ bdi_work_init(work, wbc);
+
+ return work;
+}
+
+void bdi_start_writeback(struct writeback_control *wbc)
+{
+ const bool must_wait = wbc->sync_mode == WB_SYNC_ALL;
+ struct bdi_work work_stack, *work = NULL;
+
+ if (!must_wait)
+ work = bdi_alloc_work(wbc);
+
+ if (!work) {
+ work = &work_stack;
+ bdi_work_init_on_stack(work, wbc);
+ }
+
+ bdi_queue_work(wbc->bdi, work);
+
+ /*
+ * If the sync mode is WB_SYNC_ALL, block waiting for the work to
+ * complete. If not, we only need to wait for the work to be started,
+ * if we allocated it on-stack. We use the same mechanism, if the
+ * wait bit is set in the bdi_work struct, then threads will not
+ * clear pending until after they are done.
+ *
+ * Note that work == &work_stack if must_wait is true, so we don't
+ * need to do call_rcu() here ever, since the completion path will
+ * have done that for us.
+ */
+ if (must_wait || work == &work_stack) {
+ bdi_wait_on_work_clear(work);
+ if (work != &work_stack)
+ call_rcu(&work->rcu_head, bdi_work_free);
+ }
}
/*
@@ -199,16 +244,16 @@ static int write_inode(struct inode *inode, int sync)
*/
static void redirty_tail(struct inode *inode)
{
- struct backing_dev_info *bdi = inode_to_bdi(inode);
+ struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
- if (!list_empty(&bdi->b_dirty)) {
+ if (!list_empty(&wb->b_dirty)) {
struct inode *tail;
- tail = list_entry(bdi->b_dirty.next, struct inode, i_list);
+ tail = list_entry(wb->b_dirty.next, struct inode, i_list);
if (time_before(inode->dirtied_when, tail->dirtied_when))
inode->dirtied_when = jiffies;
}
- list_move(&inode->i_list, &bdi->b_dirty);
+ list_move(&inode->i_list, &wb->b_dirty);
}
/*
@@ -216,7 +261,9 @@ static void redirty_tail(struct inode *inode)
*/
static void requeue_io(struct inode *inode)
{
- list_move(&inode->i_list, &inode_to_bdi(inode)->b_more_io);
+ struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
+
+ list_move(&inode->i_list, &wb->b_more_io);
}
static void inode_sync_complete(struct inode *inode)
@@ -263,52 +310,18 @@ static void move_expired_inodes(struct list_head *delaying_queue,
/*
* Queue all expired dirty inodes for io, eldest first.
*/
-static void queue_io(struct backing_dev_info *bdi,
- unsigned long *older_than_this)
+static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this)
{
- list_splice_init(&bdi->b_more_io, bdi->b_io.prev);
- move_expired_inodes(&bdi->b_dirty, &bdi->b_io, older_than_this);
+ list_splice_init(&wb->b_more_io, wb->b_io.prev);
+ move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
}
-static int sb_on_inode_list(struct super_block *sb, struct list_head *list)
-{
- struct inode *inode;
- int ret = 0;
-
- spin_lock(&inode_lock);
- list_for_each_entry(inode, list, i_list) {
- if (inode->i_sb == sb) {
- ret = 1;
- break;
- }
- }
- spin_unlock(&inode_lock);
- return ret;
-}
-
-int sb_has_dirty_inodes(struct super_block *sb)
+static int write_inode(struct inode *inode, int sync)
{
- struct backing_dev_info *bdi;
- int ret = 0;
-
- /*
- * This is REALLY expensive right now, but it'll go away
- * when the bdi writeback is introduced
- */
- mutex_lock(&bdi_lock);
- list_for_each_entry(bdi, &bdi_list, bdi_list) {
- if (sb_on_inode_list(sb, &bdi->b_dirty) ||
- sb_on_inode_list(sb, &bdi->b_io) ||
- sb_on_inode_list(sb, &bdi->b_more_io)) {
- ret = 1;
- break;
- }
- }
- mutex_unlock(&bdi_lock);
-
- return ret;
+ if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode))
+ return inode->i_sb->s_op->write_inode(inode, sync);
+ return 0;
}
-EXPORT_SYMBOL(sb_has_dirty_inodes);
/*
* Wait for writeback on an inode to complete.
@@ -466,20 +479,71 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
return ret;
}
-static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
- struct writeback_control *wbc,
- struct super_block *sb)
+/*
+ * For WB_SYNC_NONE writeback, the caller does not have the sb pinned
+ * before calling writeback. So make sure that we do pin it, so it doesn't
+ * go away while we are writing inodes from it.
+ *
+ * Returns 0 if the super was successfully pinned (or pinning wasn't needed),
+ * 1 if we failed.
+ */
+static int pin_sb_for_writeback(struct writeback_control *wbc,
+ struct inode *inode)
+{
+ struct super_block *sb = inode->i_sb;
+
+ /*
+ * Caller must already hold the ref for this
+ */
+ if (wbc->sync_mode == WB_SYNC_ALL) {
+ WARN_ON(!rwsem_is_locked(&sb->s_umount));
+ return 0;
+ }
+
+ spin_lock(&sb_lock);
+ sb->s_count++;
+ if (down_read_trylock(&sb->s_umount)) {
+ if (sb->s_root) {
+ spin_unlock(&sb_lock);
+ return 0;
+ }
+ /*
+ * umounted, drop rwsem again and fall through to failure
+ */
+ up_read(&sb->s_umount);
+ }
+
+ sb->s_count--;
+ spin_unlock(&sb_lock);
+ return 1;
+}
+
+static void unpin_sb_for_writeback(struct writeback_control *wbc,
+ struct inode *inode)
{
+ struct super_block *sb = inode->i_sb;
+
+ if (wbc->sync_mode == WB_SYNC_ALL)
+ return;
+
+ up_read(&sb->s_umount);
+ put_super(sb);
+}
+
+static void writeback_inodes_wb(struct bdi_writeback *wb,
+ struct writeback_control *wbc)
+{
+ struct super_block *sb = wbc->sb;
const int is_blkdev_sb = sb_is_blkdev_sb(sb);
const unsigned long start = jiffies; /* livelock avoidance */
spin_lock(&inode_lock);
- if (!wbc->for_kupdate || list_empty(&bdi->b_io))
- queue_io(bdi, wbc->older_than_this);
+ if (!wbc->for_kupdate || list_empty(&wb->b_io))
+ queue_io(wb, wbc->older_than_this);
- while (!list_empty(&bdi->b_io)) {
- struct inode *inode = list_entry(bdi->b_io.prev,
+ while (!list_empty(&wb->b_io)) {
+ struct inode *inode = list_entry(wb->b_io.prev,
struct inode, i_list);
long pages_skipped;
@@ -491,7 +555,7 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
continue;
}
- if (!bdi_cap_writeback_dirty(bdi)) {
+ if (!bdi_cap_writeback_dirty(wb->bdi)) {
redirty_tail(inode);
if (is_blkdev_sb) {
/*
@@ -513,7 +577,7 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
continue;
}
- if (wbc->nonblocking && bdi_write_congested(bdi)) {
+ if (wbc->nonblocking && bdi_write_congested(wb->bdi)) {
wbc->encountered_congestion = 1;
if (!is_blkdev_sb)
break; /* Skip a congested fs */
@@ -521,13 +585,6 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
continue; /* Skip a congested blockdev */
}
- if (wbc->bdi && bdi != wbc->bdi) {
- if (!is_blkdev_sb)
- break; /* fs has the wrong queue */
- requeue_io(inode);
- continue; /* blockdev has wrong queue */
- }
-
/*
* Was this inode dirtied after sync_sb_inodes was called?
* This keeps sync from extra jobs and livelock.
@@ -535,16 +592,16 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
if (inode_dirtied_after(inode, start))
break;
- /* Is another pdflush already flushing this queue? */
- if (current_is_pdflush() && !writeback_acquire(bdi))
- break;
+ if (pin_sb_for_writeback(wbc, inode)) {
+ requeue_io(inode);
+ continue;
+ }
BUG_ON(inode->i_state & (I_FREEING | I_CLEAR));
__iget(inode);
pages_skipped = wbc->pages_skipped;
writeback_single_inode(inode, wbc);
- if (current_is_pdflush())
- writeback_release(bdi);
+ unpin_sb_for_writeback(wbc, inode);
if (wbc->pages_skipped != pages_skipped) {
/*
* writeback is not making progress due to locked
@@ -560,7 +617,7 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
wbc->more_io = 1;
break;
}
- if (!list_empty(&bdi->b_more_io))
+ if (!list_empty(&wb->b_more_io))
wbc->more_io = 1;
}
@@ -568,139 +625,498 @@ static void generic_sync_bdi_inodes(struct backing_dev_info *bdi,
/* Leave any unwritten inodes on b_io */
}
+void writeback_inodes_wbc(struct writeback_control *wbc)
+{
+ struct backing_dev_info *bdi = wbc->bdi;
+
+ writeback_inodes_wb(&bdi->wb, wbc);
+}
+
/*
- * Write out a superblock's list of dirty inodes. A wait will be performed
- * upon no inodes, all inodes or the final one, depending upon sync_mode.
- *
- * If older_than_this is non-NULL, then only write out inodes which
- * had their first dirtying at a time earlier than *older_than_this.
- *
- * If we're a pdlfush thread, then implement pdflush collision avoidance
- * against the entire list.
+ * The maximum number of pages to writeout in a single bdi flush/kupdate
+ * operation. We do this so we don't hold I_SYNC against an inode for
+ * enormous amounts of time, which would block a userspace task which has
+ * been forced to throttle against that inode. Also, the code reevaluates
+ * the dirty each time it has written this many pages.
+ */
+#define MAX_WRITEBACK_PAGES 1024
+
+static inline bool over_bground_thresh(void)
+{
+ unsigned long background_thresh, dirty_thresh;
+
+ get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
+
+ return (global_page_state(NR_FILE_DIRTY) +
+ global_page_state(NR_UNSTABLE_NFS) >= background_thresh);
+}
+
+/*
+ * Explicit flushing or periodic writeback of "old" data.
*
- * If `bdi' is non-zero then we're being asked to writeback a specific queue.
- * This function assumes that the blockdev superblock's inodes are backed by
- * a variety of queues, so all inodes are searched. For other superblocks,
- * assume that all inodes are backed by the same queue.
+ * Define "old": the first time one of an inode's pages is dirtied, we mark the
+ * dirtying-time in the inode's address_space. So this periodic writeback code
+ * just walks the superblock inode list, writing back any inodes which are
+ * older than a specific point in time.
*
- * FIXME: this linear search could get expensive with many fileystems. But
- * how to fix? We need to go from an address_space to all inodes which share
- * a queue with that address_space. (Easy: have a global "dirty superblocks"
- * list).
+ * Try to run once per dirty_writeback_interval. But if a writeback event
+ * takes longer than a dirty_writeback_interval interval, then leave a
+ * one-second gap.
*
- * The inodes to be written are parked on bdi->b_io. They are moved back onto
- * bdi->b_dirty as they are selected for writing. This way, none can be missed
- * on the writer throttling path, and we get decent balancing between many
- * throttled threads: we don't want them all piling up on inode_sync_wait.
+ * older_than_this takes precedence over nr_to_write. So we'll only write back
+ * all dirty pages if they are all attached to "old" mappings.
*/
-static void generic_sync_sb_inodes(struct super_block *sb,
- struct writeback_control *wbc)
+static long wb_writeback(struct bdi_writeback *wb, long nr_pages,
+ struct super_block *sb,
+ enum writeback_sync_modes sync_mode, int for_kupdate)
{
- struct backing_dev_info *bdi;
-
- if (!wbc->bdi) {
- mutex_lock(&bdi_lock);
- list_for_each_entry(bdi, &bdi_list, bdi_list)
- generic_sync_bdi_inodes(bdi, wbc, sb);
- mutex_unlock(&bdi_lock);
- } else
- generic_sync_bdi_inodes(wbc->bdi, wbc, sb);
+ struct writeback_control wbc = {
+ .bdi = wb->bdi,
+ .sb = sb,
+ .sync_mode = sync_mode,
+ .older_than_this = NULL,
+ .for_kupdate = for_kupdate,
+ .range_cyclic = 1,
+ };
+ unsigned long oldest_jif;
+ long wrote = 0;
- if (wbc->sync_mode == WB_SYNC_ALL) {
- struct inode *inode, *old_inode = NULL;
+ if (wbc.for_kupdate) {
+ wbc.older_than_this = &oldest_jif;
+ oldest_jif = jiffies -
+ msecs_to_jiffies(dirty_expire_interval * 10);
+ }
- spin_lock(&inode_lock);
+ for (;;) {
+ /*
+ * Don't flush anything for non-integrity writeback where
+ * no nr_pages was given
+ */
+ if (!for_kupdate && nr_pages <= 0 && sync_mode == WB_SYNC_NONE)
+ break;
/*
- * Data integrity sync. Must wait for all pages under writeback,
- * because there may have been pages dirtied before our sync
- * call, but which had writeout started before we write it out.
- * In which case, the inode may not be on the dirty list, but
- * we still have to wait for that writeout.
+ * If no specific pages were given and this is just a
+ * periodic background writeout and we are below the
+ * background dirty threshold, don't do anything
*/
- list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
- struct address_space *mapping;
+ if (for_kupdate && nr_pages <= 0 && !over_bground_thresh())
+ break;
- if (inode->i_state &
- (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
- continue;
- mapping = inode->i_mapping;
- if (mapping->nrpages == 0)
+ wbc.more_io = 0;
+ wbc.encountered_congestion = 0;
+ wbc.nr_to_write = MAX_WRITEBACK_PAGES;
+ wbc.pages_skipped = 0;
+ writeback_inodes_wb(wb, &wbc);
+ nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
+ wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write;
+
+ /*
+ * If we ran out of stuff to write, bail unless more_io got set
+ */
+ if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
+ if (wbc.more_io && !wbc.for_kupdate)
continue;
- __iget(inode);
- spin_unlock(&inode_lock);
+ break;
+ }
+ }
+
+ return wrote;
+}
+
+/*
+ * Return the next bdi_work struct that hasn't been processed by this
+ * wb thread yet
+ */
+static struct bdi_work *get_next_work_item(struct backing_dev_info *bdi,
+ struct bdi_writeback *wb)
+{
+ struct bdi_work *work, *ret = NULL;
+
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(work, &bdi->work_list, list) {
+ if (!test_and_clear_bit(wb->nr, &work->seen))
+ continue;
+
+ ret = work;
+ break;
+ }
+
+ rcu_read_unlock();
+ return ret;
+}
+
+static long wb_check_old_data_flush(struct bdi_writeback *wb)
+{
+ unsigned long expired;
+ long nr_pages;
+
+ expired = wb->last_old_flush +
+ msecs_to_jiffies(dirty_writeback_interval * 10);
+ if (time_before(jiffies, expired))
+ return 0;
+
+ nr_pages = global_page_state(NR_FILE_DIRTY) +
+ global_page_state(NR_UNSTABLE_NFS) +
+ (inodes_stat.nr_inodes - inodes_stat.nr_unused);
+
+ return wb_writeback(wb, nr_pages, NULL, WB_SYNC_NONE, 1);
+}
+
+/*
+ * Retrieve work items and do the writeback they describe
+ */
+long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
+{
+ struct backing_dev_info *bdi = wb->bdi;
+ struct bdi_work *work;
+ long nr_pages, wrote = 0;
+
+ while ((work = get_next_work_item(bdi, wb)) != NULL) {
+ enum writeback_sync_modes sync_mode;
+
+ nr_pages = work->nr_pages;
+
+ /*
+ * Override sync mode, in case we must wait for completion
+ */
+ if (force_wait)
+ work->sync_mode = sync_mode = WB_SYNC_ALL;
+ else
+ sync_mode = work->sync_mode;
+
+ /*
+ * If this isn't a data integrity operation, just notify
+ * that we have seen this work and we are now starting it.
+ */
+ if (sync_mode == WB_SYNC_NONE)
+ wb_clear_pending(wb, work);
+
+ wrote += wb_writeback(wb, nr_pages, work->sb, sync_mode, 0);
+
+ /*
+ * This is a data integrity writeback, so only do the
+ * notification when we have completed the work.
+ */
+ if (sync_mode == WB_SYNC_ALL)
+ wb_clear_pending(wb, work);
+ }
+
+ /*
+ * Check for periodic writeback, kupdated() style
+ */
+ if (!wrote)
+ wrote = wb_check_old_data_flush(wb);
+
+ return wrote;
+}
+
+/*
+ * Handle writeback of dirty data for the device backed by this bdi. Also
+ * wakes up periodically and does kupdated style flushing.
+ */
+int bdi_writeback_task(struct bdi_writeback *wb)
+{
+ unsigned long last_active = jiffies;
+ unsigned long wait_jiffies = -1UL;
+ long pages_written;
+
+ while (!kthread_should_stop()) {
+ pages_written = wb_do_writeback(wb, 0);
+
+ if (pages_written)
+ last_active = jiffies;
+ else if (wait_jiffies != -1UL) {
+ unsigned long max_idle;
+
/*
- * We hold a reference to 'inode' so it couldn't have
- * been removed from s_inodes list while we dropped the
- * inode_lock. We cannot iput the inode now as we can
- * be holding the last reference and we cannot iput it
- * under inode_lock. So we keep the reference and iput
- * it later.
+ * Longest period of inactivity that we tolerate. If we
+ * see dirty data again later, the task will get
+ * recreated automatically.
*/
- iput(old_inode);
- old_inode = inode;
+ max_idle = max(5UL * 60 * HZ, wait_jiffies);
+ if (time_after(jiffies, max_idle + last_active))
+ break;
+ }
+
+ wait_jiffies = msecs_to_jiffies(dirty_writeback_interval * 10);
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(wait_jiffies);
+ try_to_freeze();
+ }
+
+ return 0;
+}
+
+/*
+ * Schedule writeback for all backing devices. Expensive! If this is a data
+ * integrity operation, writeback will be complete when this returns. If
+ * we are simply called for WB_SYNC_NONE, then writeback will merely be
+ * scheduled to run.
+ */
+static void bdi_writeback_all(struct writeback_control *wbc)
+{
+ const bool must_wait = wbc->sync_mode == WB_SYNC_ALL;
+ struct backing_dev_info *bdi;
+ struct bdi_work *work;
+ LIST_HEAD(list);
+
+restart:
+ spin_lock(&bdi_lock);
- filemap_fdatawait(mapping);
+ list_for_each_entry(bdi, &bdi_list, bdi_list) {
+ struct bdi_work *work;
+
+ if (!bdi_has_dirty_io(bdi))
+ continue;
+
+ /*
+ * If work allocation fails, do the writes inline. We drop
+ * the lock and restart the list writeout. This should be OK,
+ * since this happens rarely and because the writeout should
+ * eventually make more free memory available.
+ */
+ work = bdi_alloc_work(wbc);
+ if (!work) {
+ struct writeback_control __wbc = *wbc;
- cond_resched();
+ /*
+ * Not a data integrity writeout, just continue
+ */
+ if (!must_wait)
+ continue;
- spin_lock(&inode_lock);
+ spin_unlock(&bdi_lock);
+ __wbc = *wbc;
+ __wbc.bdi = bdi;
+ writeback_inodes_wbc(&__wbc);
+ goto restart;
}
- spin_unlock(&inode_lock);
- iput(old_inode);
+ if (must_wait)
+ list_add_tail(&work->wait_list, &list);
+
+ bdi_queue_work(bdi, work);
+ }
+
+ spin_unlock(&bdi_lock);
+
+ /*
+ * If this is for WB_SYNC_ALL, wait for pending work to complete
+ * before returning.
+ */
+ while (!list_empty(&list)) {
+ work = list_entry(list.next, struct bdi_work, wait_list);
+ list_del(&work->wait_list);
+ bdi_wait_on_work_clear(work);
+ call_rcu(&work->rcu_head, bdi_work_free);
}
}
/*
- * Start writeback of dirty pagecache data against all unlocked inodes.
+ * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back
+ * the whole world.
+ */
+void wakeup_flusher_threads(long nr_pages)
+{
+ struct writeback_control wbc = {
+ .sync_mode = WB_SYNC_NONE,
+ .older_than_this = NULL,
+ .range_cyclic = 1,
+ };
+
+ if (nr_pages == 0)
+ nr_pages = global_page_state(NR_FILE_DIRTY) +
+ global_page_state(NR_UNSTABLE_NFS);
+ wbc.nr_to_write = nr_pages;
+ bdi_writeback_all(&wbc);
+}
+
+static noinline void block_dump___mark_inode_dirty(struct inode *inode)
+{
+ if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
+ struct dentry *dentry;
+ const char *name = "?";
+
+ dentry = d_find_alias(inode);
+ if (dentry) {
+ spin_lock(&dentry->d_lock);
+ name = (const char *) dentry->d_name.name;
+ }
+ printk(KERN_DEBUG
+ "%s(%d): dirtied inode %lu (%s) on %s\n",
+ current->comm, task_pid_nr(current), inode->i_ino,
+ name, inode->i_sb->s_id);
+ if (dentry) {
+ spin_unlock(&dentry->d_lock);
+ dput(dentry);
+ }
+ }
+}
+
+/**
+ * __mark_inode_dirty - internal function
+ * @inode: inode to mark
+ * @flags: what kind of dirty (i.e. I_DIRTY_SYNC)
+ * Mark an inode as dirty. Callers should use mark_inode_dirty or
+ * mark_inode_dirty_sync.
+ *
+ * Put the inode on the super block's dirty list.
*
- * Note:
- * We don't need to grab a reference to superblock here. If it has non-empty
- * ->b_dirty it's hadn't been killed yet and kill_super() won't proceed
- * past sync_inodes_sb() until the ->b_dirty/b_io/b_more_io lists are all
- * empty. Since __sync_single_inode() regains inode_lock before it finally moves
- * inode from superblock lists we are OK.
+ * CAREFUL! We mark it dirty unconditionally, but move it onto the
+ * dirty list only if it is hashed or if it refers to a blockdev.
+ * If it was not hashed, it will never be added to the dirty list
+ * even if it is later hashed, as it will have been marked dirty already.
+ *
+ * In short, make sure you hash any inodes _before_ you start marking
+ * them dirty.
*
- * If `older_than_this' is non-zero then only flush inodes which have a
- * flushtime older than *older_than_this.
+ * This function *must* be atomic for the I_DIRTY_PAGES case -
+ * set_page_dirty() is called under spinlock in several places.
*
- * If `bdi' is non-zero then we will scan the first inode against each
- * superblock until we find the matching ones. One group will be the dirty
- * inodes against a filesystem. Then when we hit the dummy blockdev superblock,
- * sync_sb_inodes will seekout the blockdev which matches `bdi'. Maybe not
- * super-efficient but we're about to do a ton of I/O...
+ * Note that for blockdevs, inode->dirtied_when represents the dirtying time of
+ * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of
+ * the kernel-internal blockdev inode represents the dirtying time of the
+ * blockdev's pages. This is why for I_DIRTY_PAGES we always use
+ * page->mapping->host, so the page-dirtying time is recorded in the internal
+ * blockdev inode.
*/
-void
-writeback_inodes(struct writeback_control *wbc)
+void __mark_inode_dirty(struct inode *inode, int flags)
{
- struct super_block *sb;
+ struct super_block *sb = inode->i_sb;
- might_sleep();
- spin_lock(&sb_lock);
-restart:
- list_for_each_entry_reverse(sb, &super_blocks, s_list) {
- if (sb_has_dirty_inodes(sb)) {
- /* we're making our own get_super here */
- sb->s_count++;
- spin_unlock(&sb_lock);
- /*
- * If we can't get the readlock, there's no sense in
- * waiting around, most of the time the FS is going to
- * be unmounted by the time it is released.
- */
- if (down_read_trylock(&sb->s_umount)) {
- if (sb->s_root)
- generic_sync_sb_inodes(sb, wbc);
- up_read(&sb->s_umount);
- }
- spin_lock(&sb_lock);
- if (__put_super_and_need_restart(sb))
- goto restart;
+ /*
+ * Don't do this for I_DIRTY_PAGES - that doesn't actually
+ * dirty the inode itself
+ */
+ if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
+ if (sb->s_op->dirty_inode)
+ sb->s_op->dirty_inode(inode);
+ }
+
+ /*
+ * make sure that changes are seen by all cpus before we test i_state
+ * -- mikulas
+ */
+ smp_mb();
+
+ /* avoid the locking if we can */
+ if ((inode->i_state & flags) == flags)
+ return;
+
+ if (unlikely(block_dump))
+ block_dump___mark_inode_dirty(inode);
+
+ spin_lock(&inode_lock);
+ if ((inode->i_state & flags) != flags) {
+ const int was_dirty = inode->i_state & I_DIRTY;
+
+ inode->i_state |= flags;
+
+ /*
+ * If the inode is being synced, just update its dirty state.
+ * The unlocker will place the inode on the appropriate
+ * superblock list, based upon its state.
+ */
+ if (inode->i_state & I_SYNC)
+ goto out;
+
+ /*
+ * Only add valid (hashed) inodes to the superblock's
+ * dirty list. Add blockdev inodes as well.
+ */
+ if (!S_ISBLK(inode->i_mode)) {
+ if (hlist_unhashed(&inode->i_hash))
+ goto out;
+ }
+ if (inode->i_state & (I_FREEING|I_CLEAR))
+ goto out;
+
+ /*
+ * If the inode was already on b_dirty/b_io/b_more_io, don't
+ * reposition it (that would break b_dirty time-ordering).
+ */
+ if (!was_dirty) {
+ struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
+
+ inode->dirtied_when = jiffies;
+ list_move(&inode->i_list, &wb->b_dirty);
}
- if (wbc->nr_to_write <= 0)
- break;
}
- spin_unlock(&sb_lock);
+out:
+ spin_unlock(&inode_lock);
+}
+
+EXPORT_SYMBOL(__mark_inode_dirty);
+
+/*
+ * Write out a superblock's list of dirty inodes. A wait will be performed
+ * upon no inodes, all inodes or the final one, depending upon sync_mode.
+ *
+ * If older_than_this is non-NULL, then only write out inodes which
+ * had their first dirtying at a time earlier than *older_than_this.
+ *
+ * If we're a pdlfush thread, then implement pdflush collision avoidance
+ * against the entire list.
+ *
+ * If `bdi' is non-zero then we're being asked to writeback a specific queue.
+ * This function assumes that the blockdev superblock's inodes are backed by
+ * a variety of queues, so all inodes are searched. For other superblocks,
+ * assume that all inodes are backed by the same queue.
+ *
+ * The inodes to be written are parked on bdi->b_io. They are moved back onto
+ * bdi->b_dirty as they are selected for writing. This way, none can be missed
+ * on the writer throttling path, and we get decent balancing between many
+ * throttled threads: we don't want them all piling up on inode_sync_wait.
+ */
+static void wait_sb_inodes(struct writeback_control *wbc)
+{
+ struct inode *inode, *old_inode = NULL;
+
+ /*
+ * We need to be protected against the filesystem going from
+ * r/o to r/w or vice versa.
+ */
+ WARN_ON(!rwsem_is_locked(&wbc->sb->s_umount));
+
+ spin_lock(&inode_lock);
+
+ /*
+ * Data integrity sync. Must wait for all pages under writeback,
+ * because there may have been pages dirtied before our sync
+ * call, but which had writeout started before we write it out.
+ * In which case, the inode may not be on the dirty list, but
+ * we still have to wait for that writeout.
+ */
+ list_for_each_entry(inode, &wbc->sb->s_inodes, i_sb_list) {
+ struct address_space *mapping;
+
+ if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
+ continue;
+ mapping = inode->i_mapping;
+ if (mapping->nrpages == 0)
+ continue;
+ __iget(inode);
+ spin_unlock(&inode_lock);
+ /*
+ * We hold a reference to 'inode' so it couldn't have
+ * been removed from s_inodes list while we dropped the
+ * inode_lock. We cannot iput the inode now as we can
+ * be holding the last reference and we cannot iput it
+ * under inode_lock. So we keep the reference and iput
+ * it later.
+ */
+ iput(old_inode);
+ old_inode = inode;
+
+ filemap_fdatawait(mapping);
+
+ cond_resched();
+
+ spin_lock(&inode_lock);
+ }
+ spin_unlock(&inode_lock);
+ iput(old_inode);
}
/**
@@ -715,6 +1131,7 @@ restart:
long writeback_inodes_sb(struct super_block *sb)
{
struct writeback_control wbc = {
+ .sb = sb,
.sync_mode = WB_SYNC_NONE,
.range_start = 0,
.range_end = LLONG_MAX,
@@ -727,7 +1144,7 @@ long writeback_inodes_sb(struct super_block *sb)
(inodes_stat.nr_inodes - inodes_stat.nr_unused);
wbc.nr_to_write = nr_to_write;
- generic_sync_sb_inodes(sb, &wbc);
+ bdi_writeback_all(&wbc);
return nr_to_write - wbc.nr_to_write;
}
EXPORT_SYMBOL(writeback_inodes_sb);
@@ -742,6 +1159,7 @@ EXPORT_SYMBOL(writeback_inodes_sb);
long sync_inodes_sb(struct super_block *sb)
{
struct writeback_control wbc = {
+ .sb = sb,
.sync_mode = WB_SYNC_ALL,
.range_start = 0,
.range_end = LLONG_MAX,
@@ -749,7 +1167,8 @@ long sync_inodes_sb(struct super_block *sb)
long nr_to_write = LONG_MAX; /* doesn't actually matter */
wbc.nr_to_write = nr_to_write;
- generic_sync_sb_inodes(sb, &wbc);
+ bdi_writeback_all(&wbc);
+ wait_sb_inodes(&wbc);
return nr_to_write - wbc.nr_to_write;
}
EXPORT_SYMBOL(sync_inodes_sb);
diff --git a/fs/super.c b/fs/super.c
index 0d22ce3..9cda337 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -168,7 +168,7 @@ int __put_super_and_need_restart(struct super_block *sb)
* Drops a temporary reference, frees superblock if there's no
* references left.
*/
-static void put_super(struct super_block *sb)
+void put_super(struct super_block *sb)
{
spin_lock(&sb_lock);
__put_super(sb);
diff --git a/fs/sync.c b/fs/sync.c
index 66f2104..103cc7f 100644
--- a/fs/sync.c
+++ b/fs/sync.c
@@ -120,7 +120,7 @@ restart:
*/
SYSCALL_DEFINE0(sync)
{
- wakeup_pdflush(0);
+ wakeup_flusher_threads(0);
sync_filesystems(0);
sync_filesystems(1);
if (unlikely(laptop_mode))
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 928cd54..d045f5f 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -13,6 +13,8 @@
#include <linux/proportions.h>
#include <linux/kernel.h>
#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/writeback.h>
#include <asm/atomic.h>
struct page;
@@ -23,7 +25,8 @@ struct dentry;
* Bits in backing_dev_info.state
*/
enum bdi_state {
- BDI_pdflush, /* A pdflush thread is working this device */
+ BDI_pending, /* On its way to being activated */
+ BDI_wb_alloc, /* Default embedded wb allocated */
BDI_async_congested, /* The async (write) queue is getting full */
BDI_sync_congested, /* The sync queue is getting full */
BDI_unused, /* Available bits start here */
@@ -39,9 +42,22 @@ enum bdi_stat_item {
#define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids)))
+struct bdi_writeback {
+ struct list_head list; /* hangs off the bdi */
+
+ struct backing_dev_info *bdi; /* our parent bdi */
+ unsigned int nr;
+
+ unsigned long last_old_flush; /* last old data flush */
+
+ struct task_struct *task; /* writeback task */
+ struct list_head b_dirty; /* dirty inodes */
+ struct list_head b_io; /* parked for writeback */
+ struct list_head b_more_io; /* parked for more writeback */
+};
+
struct backing_dev_info {
struct list_head bdi_list;
-
unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */
unsigned long state; /* Always use atomic bitops on this */
unsigned int capabilities; /* Device capabilities */
@@ -58,11 +74,15 @@ struct backing_dev_info {
unsigned int min_ratio;
unsigned int max_ratio, max_prop_frac;
- struct device *dev;
+ struct bdi_writeback wb; /* default writeback info for this bdi */
+ spinlock_t wb_lock; /* protects update side of wb_list */
+ struct list_head wb_list; /* the flusher threads hanging off this bdi */
+ unsigned long wb_mask; /* bitmask of registered tasks */
+ unsigned int wb_cnt; /* number of registered tasks */
- struct list_head b_dirty; /* dirty inodes */
- struct list_head b_io; /* parked for writeback */
- struct list_head b_more_io; /* parked for more writeback */
+ struct list_head work_list;
+
+ struct device *dev;
#ifdef CONFIG_DEBUG_FS
struct dentry *debug_dir;
@@ -77,10 +97,20 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
const char *fmt, ...);
int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
void bdi_unregister(struct backing_dev_info *bdi);
+void bdi_start_writeback(struct writeback_control *wbc);
+int bdi_writeback_task(struct bdi_writeback *wb);
+int bdi_has_dirty_io(struct backing_dev_info *bdi);
-extern struct mutex bdi_lock;
+extern spinlock_t bdi_lock;
extern struct list_head bdi_list;
+static inline int wb_has_dirty_io(struct bdi_writeback *wb)
+{
+ return !list_empty(&wb->b_dirty) ||
+ !list_empty(&wb->b_io) ||
+ !list_empty(&wb->b_more_io);
+}
+
static inline void __add_bdi_stat(struct backing_dev_info *bdi,
enum bdi_stat_item item, s64 amount)
{
@@ -270,6 +300,11 @@ static inline bool bdi_cap_swap_backed(struct backing_dev_info *bdi)
return bdi->capabilities & BDI_CAP_SWAP_BACKED;
}
+static inline bool bdi_cap_flush_forker(struct backing_dev_info *bdi)
+{
+ return bdi == &default_backing_dev_info;
+}
+
static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
{
return bdi_cap_writeback_dirty(mapping->backing_dev_info);
@@ -285,4 +320,10 @@ static inline bool mapping_cap_swap_backed(struct address_space *mapping)
return bdi_cap_swap_backed(mapping->backing_dev_info);
}
+static inline int bdi_sched_wait(void *word)
+{
+ schedule();
+ return 0;
+}
+
#endif /* _LINUX_BACKING_DEV_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 97949b7..8fe571f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1785,6 +1785,7 @@ extern int get_sb_pseudo(struct file_system_type *, char *,
struct vfsmount *mnt);
extern void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb);
int __put_super_and_need_restart(struct super_block *sb);
+void put_super(struct super_block *sb);
/* Alas, no aliases. Too much hassle with bringing module.h everywhere */
#define fops_get(fops) \
@@ -2181,7 +2182,6 @@ extern int bdev_read_only(struct block_device *);
extern int set_blocksize(struct block_device *, int);
extern int sb_set_blocksize(struct super_block *, int);
extern int sb_min_blocksize(struct super_block *, int);
-extern int sb_has_dirty_inodes(struct super_block *);
extern int generic_file_mmap(struct file *, struct vm_area_struct *);
extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 0703929..cef7552 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -40,6 +40,8 @@ enum writeback_sync_modes {
struct writeback_control {
struct backing_dev_info *bdi; /* If !NULL, only write back this
queue */
+ struct super_block *sb; /* if !NULL, only write inodes from
+ this super_block */
enum writeback_sync_modes sync_mode;
unsigned long *older_than_this; /* If !NULL, only write back inodes
older than this */
@@ -76,10 +78,13 @@ struct writeback_control {
/*
* fs/fs-writeback.c
*/
-void writeback_inodes(struct writeback_control *wbc);
+struct bdi_writeback;
int inode_wait(void *);
long writeback_inodes_sb(struct super_block *);
long sync_inodes_sb(struct super_block *);
+void writeback_inodes_wbc(struct writeback_control *wbc);
+long wb_do_writeback(struct bdi_writeback *wb, int force_wait);
+void wakeup_flusher_threads(long nr_pages);
/* writeback.h requires fs.h; it, too, is not included from here. */
static inline void wait_on_inode(struct inode *inode)
@@ -99,7 +104,6 @@ static inline void inode_sync_wait(struct inode *inode)
/*
* mm/page-writeback.c
*/
-int wakeup_pdflush(long nr_pages);
void laptop_io_completion(void);
void laptop_sync_completion(void);
void throttle_vm_writeout(gfp_t gfp_mask);
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 6f163e0..7f3fa79 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -1,8 +1,11 @@
#include <linux/wait.h>
#include <linux/backing-dev.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
+#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/writeback.h>
@@ -22,8 +25,18 @@ struct backing_dev_info default_backing_dev_info = {
EXPORT_SYMBOL_GPL(default_backing_dev_info);
static struct class *bdi_class;
-DEFINE_MUTEX(bdi_lock);
+DEFINE_SPINLOCK(bdi_lock);
LIST_HEAD(bdi_list);
+LIST_HEAD(bdi_pending_list);
+
+static struct task_struct *sync_supers_tsk;
+static struct timer_list sync_supers_timer;
+
+static int bdi_sync_supers(void *);
+static void sync_supers_timer_fn(unsigned long);
+static void arm_supers_timer(void);
+
+static void bdi_add_default_flusher_task(struct backing_dev_info *bdi);
#ifdef CONFIG_DEBUG_FS
#include <linux/debugfs.h>
@@ -187,6 +200,13 @@ static int __init default_bdi_init(void)
{
int err;
+ sync_supers_tsk = kthread_run(bdi_sync_supers, NULL, "sync_supers");
+ BUG_ON(IS_ERR(sync_supers_tsk));
+
+ init_timer(&sync_supers_timer);
+ setup_timer(&sync_supers_timer, sync_supers_timer_fn, 0);
+ arm_supers_timer();
+
err = bdi_init(&default_backing_dev_info);
if (!err)
bdi_register(&default_backing_dev_info, NULL, "default");
@@ -195,6 +215,242 @@ static int __init default_bdi_init(void)
}
subsys_initcall(default_bdi_init);
+static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
+{
+ memset(wb, 0, sizeof(*wb));
+
+ wb->bdi = bdi;
+ wb->last_old_flush = jiffies;
+ INIT_LIST_HEAD(&wb->b_dirty);
+ INIT_LIST_HEAD(&wb->b_io);
+ INIT_LIST_HEAD(&wb->b_more_io);
+}
+
+static void bdi_task_init(struct backing_dev_info *bdi,
+ struct bdi_writeback *wb)
+{
+ struct task_struct *tsk = current;
+
+ spin_lock(&bdi->wb_lock);
+ list_add_tail_rcu(&wb->list, &bdi->wb_list);
+ spin_unlock(&bdi->wb_lock);
+
+ tsk->flags |= PF_FLUSHER | PF_SWAPWRITE;
+ set_freezable();
+
+ /*
+ * Our parent may run at a different priority, just set us to normal
+ */
+ set_user_nice(tsk, 0);
+}
+
+static int bdi_start_fn(void *ptr)
+{
+ struct bdi_writeback *wb = ptr;
+ struct backing_dev_info *bdi = wb->bdi;
+ int ret;
+
+ /*
+ * Add us to the active bdi_list
+ */
+ spin_lock(&bdi_lock);
+ list_add(&bdi->bdi_list, &bdi_list);
+ spin_unlock(&bdi_lock);
+
+ bdi_task_init(bdi, wb);
+
+ /*
+ * Clear pending bit and wakeup anybody waiting to tear us down
+ */
+ clear_bit(BDI_pending, &bdi->state);
+ smp_mb__after_clear_bit();
+ wake_up_bit(&bdi->state, BDI_pending);
+
+ ret = bdi_writeback_task(wb);
+
+ /*
+ * Remove us from the list
+ */
+ spin_lock(&bdi->wb_lock);
+ list_del_rcu(&wb->list);
+ spin_unlock(&bdi->wb_lock);
+
+ /*
+ * Flush any work that raced with us exiting. No new work
+ * will be added, since this bdi isn't discoverable anymore.
+ */
+ if (!list_empty(&bdi->work_list))
+ wb_do_writeback(wb, 1);
+
+ wb->task = NULL;
+ return ret;
+}
+
+int bdi_has_dirty_io(struct backing_dev_info *bdi)
+{
+ return wb_has_dirty_io(&bdi->wb);
+}
+
+static void bdi_flush_io(struct backing_dev_info *bdi)
+{
+ struct writeback_control wbc = {
+ .bdi = bdi,
+ .sync_mode = WB_SYNC_NONE,
+ .older_than_this = NULL,
+ .range_cyclic = 1,
+ .nr_to_write = 1024,
+ };
+
+ writeback_inodes_wbc(&wbc);
+}
+
+/*
+ * kupdated() used to do this. We cannot do it from the bdi_forker_task()
+ * or we risk deadlocking on ->s_umount. The longer term solution would be
+ * to implement sync_supers_bdi() or similar and simply do it from the
+ * bdi writeback tasks individually.
+ */
+static int bdi_sync_supers(void *unused)
+{
+ set_user_nice(current, 0);
+
+ while (!kthread_should_stop()) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule();
+
+ /*
+ * Do this periodically, like kupdated() did before.
+ */
+ sync_supers();
+ }
+
+ return 0;
+}
+
+static void arm_supers_timer(void)
+{
+ unsigned long next;
+
+ next = msecs_to_jiffies(dirty_writeback_interval * 10) + jiffies;
+ mod_timer(&sync_supers_timer, round_jiffies_up(next));
+}
+
+static void sync_supers_timer_fn(unsigned long unused)
+{
+ wake_up_process(sync_supers_tsk);
+ arm_supers_timer();
+}
+
+static int bdi_forker_task(void *ptr)
+{
+ struct bdi_writeback *me = ptr;
+
+ bdi_task_init(me->bdi, me);
+
+ for (;;) {
+ struct backing_dev_info *bdi, *tmp;
+ struct bdi_writeback *wb;
+
+ /*
+ * Temporary measure, we want to make sure we don't see
+ * dirty data on the default backing_dev_info
+ */
+ if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list))
+ wb_do_writeback(me, 0);
+
+ spin_lock(&bdi_lock);
+
+ /*
+ * Check if any existing bdi's have dirty data without
+ * a thread registered. If so, set that up.
+ */
+ list_for_each_entry_safe(bdi, tmp, &bdi_list, bdi_list) {
+ if (bdi->wb.task)
+ continue;
+ if (list_empty(&bdi->work_list) &&
+ !bdi_has_dirty_io(bdi))
+ continue;
+
+ bdi_add_default_flusher_task(bdi);
+ }
+
+ set_current_state(TASK_INTERRUPTIBLE);
+
+ if (list_empty(&bdi_pending_list)) {
+ unsigned long wait;
+
+ spin_unlock(&bdi_lock);
+ wait = msecs_to_jiffies(dirty_writeback_interval * 10);
+ schedule_timeout(wait);
+ try_to_freeze();
+ continue;
+ }
+
+ __set_current_state(TASK_RUNNING);
+
+ /*
+ * This is our real job - check for pending entries in
+ * bdi_pending_list, and create the tasks that got added
+ */
+ bdi = list_entry(bdi_pending_list.next, struct backing_dev_info,
+ bdi_list);
+ list_del_init(&bdi->bdi_list);
+ spin_unlock(&bdi_lock);
+
+ wb = &bdi->wb;
+ wb->task = kthread_run(bdi_start_fn, wb, "flush-%s",
+ dev_name(bdi->dev));
+ /*
+ * If task creation fails, then readd the bdi to
+ * the pending list and force writeout of the bdi
+ * from this forker thread. That will free some memory
+ * and we can try again.
+ */
+ if (IS_ERR(wb->task)) {
+ wb->task = NULL;
+
+ /*
+ * Add this 'bdi' to the back, so we get
+ * a chance to flush other bdi's to free
+ * memory.
+ */
+ spin_lock(&bdi_lock);
+ list_add_tail(&bdi->bdi_list, &bdi_pending_list);
+ spin_unlock(&bdi_lock);
+
+ bdi_flush_io(bdi);
+ }
+ }
+
+ return 0;
+}
+
+/*
+ * Add the default flusher task that gets created for any bdi
+ * that has dirty data pending writeout
+ */
+void static bdi_add_default_flusher_task(struct backing_dev_info *bdi)
+{
+ if (!bdi_cap_writeback_dirty(bdi))
+ return;
+
+ /*
+ * Check with the helper whether to proceed adding a task. Will only
+ * abort if we two or more simultanous calls to
+ * bdi_add_default_flusher_task() occured, further additions will block
+ * waiting for previous additions to finish.
+ */
+ if (!test_and_set_bit(BDI_pending, &bdi->state)) {
+ list_move_tail(&bdi->bdi_list, &bdi_pending_list);
+
+ /*
+ * We are now on the pending list, wake up bdi_forker_task()
+ * to finish the job and add us back to the active bdi_list
+ */
+ wake_up_process(default_backing_dev_info.wb.task);
+ }
+}
+
int bdi_register(struct backing_dev_info *bdi, struct device *parent,
const char *fmt, ...)
{
@@ -213,13 +469,34 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
goto exit;
}
- mutex_lock(&bdi_lock);
+ spin_lock(&bdi_lock);
list_add_tail(&bdi->bdi_list, &bdi_list);
- mutex_unlock(&bdi_lock);
+ spin_unlock(&bdi_lock);
bdi->dev = dev;
- bdi_debug_register(bdi, dev_name(dev));
+ /*
+ * Just start the forker thread for our default backing_dev_info,
+ * and add other bdi's to the list. They will get a thread created
+ * on-demand when they need it.
+ */
+ if (bdi_cap_flush_forker(bdi)) {
+ struct bdi_writeback *wb = &bdi->wb;
+
+ wb->task = kthread_run(bdi_forker_task, wb, "bdi-%s",
+ dev_name(dev));
+ if (IS_ERR(wb->task)) {
+ wb->task = NULL;
+ ret = -ENOMEM;
+
+ spin_lock(&bdi_lock);
+ list_del(&bdi->bdi_list);
+ spin_unlock(&bdi_lock);
+ goto exit;
+ }
+ }
+
+ bdi_debug_register(bdi, dev_name(dev));
exit:
return ret;
}
@@ -231,17 +508,42 @@ int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev)
}
EXPORT_SYMBOL(bdi_register_dev);
-static void bdi_remove_from_list(struct backing_dev_info *bdi)
+/*
+ * Remove bdi from the global list and shutdown any threads we have running
+ */
+static void bdi_wb_shutdown(struct backing_dev_info *bdi)
{
- mutex_lock(&bdi_lock);
+ struct bdi_writeback *wb;
+
+ if (!bdi_cap_writeback_dirty(bdi))
+ return;
+
+ /*
+ * If setup is pending, wait for that to complete first
+ */
+ wait_on_bit(&bdi->state, BDI_pending, bdi_sched_wait,
+ TASK_UNINTERRUPTIBLE);
+
+ /*
+ * Make sure nobody finds us on the bdi_list anymore
+ */
+ spin_lock(&bdi_lock);
list_del(&bdi->bdi_list);
- mutex_unlock(&bdi_lock);
+ spin_unlock(&bdi_lock);
+
+ /*
+ * Finally, kill the kernel threads. We don't need to be RCU
+ * safe anymore, since the bdi is gone from visibility.
+ */
+ list_for_each_entry(wb, &bdi->wb_list, list)
+ kthread_stop(wb->task);
}
void bdi_unregister(struct backing_dev_info *bdi)
{
if (bdi->dev) {
- bdi_remove_from_list(bdi);
+ if (!bdi_cap_flush_forker(bdi))
+ bdi_wb_shutdown(bdi);
bdi_debug_unregister(bdi);
device_unregister(bdi->dev);
bdi->dev = NULL;
@@ -251,18 +553,25 @@ EXPORT_SYMBOL(bdi_unregister);
int bdi_init(struct backing_dev_info *bdi)
{
- int i;
- int err;
+ int i, err;
bdi->dev = NULL;
bdi->min_ratio = 0;
bdi->max_ratio = 100;
bdi->max_prop_frac = PROP_FRAC_BASE;
+ spin_lock_init(&bdi->wb_lock);
INIT_LIST_HEAD(&bdi->bdi_list);
- INIT_LIST_HEAD(&bdi->b_io);
- INIT_LIST_HEAD(&bdi->b_dirty);
- INIT_LIST_HEAD(&bdi->b_more_io);
+ INIT_LIST_HEAD(&bdi->wb_list);
+ INIT_LIST_HEAD(&bdi->work_list);
+
+ bdi_wb_init(&bdi->wb, bdi);
+
+ /*
+ * Just one thread support for now, hard code mask and count
+ */
+ bdi->wb_mask = 1;
+ bdi->wb_cnt = 1;
for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
err = percpu_counter_init(&bdi->bdi_stat[i], 0);
@@ -277,8 +586,6 @@ int bdi_init(struct backing_dev_info *bdi)
err:
while (i--)
percpu_counter_destroy(&bdi->bdi_stat[i]);
-
- bdi_remove_from_list(bdi);
}
return err;
@@ -289,9 +596,7 @@ void bdi_destroy(struct backing_dev_info *bdi)
{
int i;
- WARN_ON(!list_empty(&bdi->b_dirty));
- WARN_ON(!list_empty(&bdi->b_io));
- WARN_ON(!list_empty(&bdi->b_more_io));
+ WARN_ON(bdi_has_dirty_io(bdi));
bdi_unregister(bdi);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index f8341b6..25e7770 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -36,15 +36,6 @@
#include <linux/pagevec.h>
/*
- * The maximum number of pages to writeout in a single bdflush/kupdate
- * operation. We do this so we don't hold I_SYNC against an inode for
- * enormous amounts of time, which would block a userspace task which has
- * been forced to throttle against that inode. Also, the code reevaluates
- * the dirty each time it has written this many pages.
- */
-#define MAX_WRITEBACK_PAGES 1024
-
-/*
* After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited
* will look to see if it needs to force writeback or throttling.
*/
@@ -117,8 +108,6 @@ EXPORT_SYMBOL(laptop_mode);
/* End of sysctl-exported parameters */
-static void background_writeout(unsigned long _min_pages);
-
/*
* Scale the writeback cache size proportional to the relative writeout speeds.
*
@@ -326,7 +315,7 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
{
int ret = 0;
- mutex_lock(&bdi_lock);
+ spin_lock(&bdi_lock);
if (min_ratio > bdi->max_ratio) {
ret = -EINVAL;
} else {
@@ -338,7 +327,7 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
ret = -EINVAL;
}
}
- mutex_unlock(&bdi_lock);
+ spin_unlock(&bdi_lock);
return ret;
}
@@ -350,14 +339,14 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio)
if (max_ratio > 100)
return -EINVAL;
- mutex_lock(&bdi_lock);
+ spin_lock(&bdi_lock);
if (bdi->min_ratio > max_ratio) {
ret = -EINVAL;
} else {
bdi->max_ratio = max_ratio;
bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100;
}
- mutex_unlock(&bdi_lock);
+ spin_unlock(&bdi_lock);
return ret;
}
@@ -543,7 +532,7 @@ static void balance_dirty_pages(struct address_space *mapping)
* up.
*/
if (bdi_nr_reclaimable > bdi_thresh) {
- writeback_inodes(&wbc);
+ writeback_inodes_wbc(&wbc);
pages_written += write_chunk - wbc.nr_to_write;
get_dirty_limits(&background_thresh, &dirty_thresh,
&bdi_thresh, bdi);
@@ -572,7 +561,7 @@ static void balance_dirty_pages(struct address_space *mapping)
if (pages_written >= write_chunk)
break; /* We've done our duty */
- congestion_wait(BLK_RW_ASYNC, HZ/10);
+ schedule_timeout(1);
}
if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
@@ -591,10 +580,18 @@ static void balance_dirty_pages(struct address_space *mapping)
* background_thresh, to keep the amount of dirty memory low.
*/
if ((laptop_mode && pages_written) ||
- (!laptop_mode && (global_page_state(NR_FILE_DIRTY)
- + global_page_state(NR_UNSTABLE_NFS)
- > background_thresh)))
- pdflush_operation(background_writeout, 0);
+ (!laptop_mode && ((nr_writeback = global_page_state(NR_FILE_DIRTY)
+ + global_page_state(NR_UNSTABLE_NFS))
+ > background_thresh))) {
+ struct writeback_control wbc = {
+ .bdi = bdi,
+ .sync_mode = WB_SYNC_NONE,
+ .nr_to_write = nr_writeback,
+ };
+
+
+ bdi_start_writeback(&wbc);
+ }
}
void set_page_dirty_balance(struct page *page, int page_mkwrite)
@@ -678,153 +675,35 @@ void throttle_vm_writeout(gfp_t gfp_mask)
}
}
-/*
- * writeback at least _min_pages, and keep writing until the amount of dirty
- * memory is less than the background threshold, or until we're all clean.
- */
-static void background_writeout(unsigned long _min_pages)
-{
- long min_pages = _min_pages;
- struct writeback_control wbc = {
- .bdi = NULL,
- .sync_mode = WB_SYNC_NONE,
- .older_than_this = NULL,
- .nr_to_write = 0,
- .nonblocking = 1,
- .range_cyclic = 1,
- };
-
- for ( ; ; ) {
- unsigned long background_thresh;
- unsigned long dirty_thresh;
-
- get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
- if (global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS) < background_thresh
- && min_pages <= 0)
- break;
- wbc.more_io = 0;
- wbc.encountered_congestion = 0;
- wbc.nr_to_write = MAX_WRITEBACK_PAGES;
- wbc.pages_skipped = 0;
- writeback_inodes(&wbc);
- min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
- if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
- /* Wrote less than expected */
- if (wbc.encountered_congestion || wbc.more_io)
- congestion_wait(BLK_RW_ASYNC, HZ/10);
- else
- break;
- }
- }
-}
-
-/*
- * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back
- * the whole world. Returns 0 if a pdflush thread was dispatched. Returns
- * -1 if all pdflush threads were busy.
- */
-int wakeup_pdflush(long nr_pages)
-{
- if (nr_pages == 0)
- nr_pages = global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS);
- return pdflush_operation(background_writeout, nr_pages);
-}
-
-static void wb_timer_fn(unsigned long unused);
static void laptop_timer_fn(unsigned long unused);
-static DEFINE_TIMER(wb_timer, wb_timer_fn, 0, 0);
static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0);
/*
- * Periodic writeback of "old" data.
- *
- * Define "old": the first time one of an inode's pages is dirtied, we mark the
- * dirtying-time in the inode's address_space. So this periodic writeback code
- * just walks the superblock inode list, writing back any inodes which are
- * older than a specific point in time.
- *
- * Try to run once per dirty_writeback_interval. But if a writeback event
- * takes longer than a dirty_writeback_interval interval, then leave a
- * one-second gap.
- *
- * older_than_this takes precedence over nr_to_write. So we'll only write back
- * all dirty pages if they are all attached to "old" mappings.
- */
-static void wb_kupdate(unsigned long arg)
-{
- unsigned long oldest_jif;
- unsigned long start_jif;
- unsigned long next_jif;
- long nr_to_write;
- struct writeback_control wbc = {
- .bdi = NULL,
- .sync_mode = WB_SYNC_NONE,
- .older_than_this = &oldest_jif,
- .nr_to_write = 0,
- .nonblocking = 1,
- .for_kupdate = 1,
- .range_cyclic = 1,
- };
-
- sync_supers();
-
- oldest_jif = jiffies - msecs_to_jiffies(dirty_expire_interval * 10);
- start_jif = jiffies;
- next_jif = start_jif + msecs_to_jiffies(dirty_writeback_interval * 10);
- nr_to_write = global_page_state(NR_FILE_DIRTY) +
- global_page_state(NR_UNSTABLE_NFS) +
- (inodes_stat.nr_inodes - inodes_stat.nr_unused);
- while (nr_to_write > 0) {
- wbc.more_io = 0;
- wbc.encountered_congestion = 0;
- wbc.nr_to_write = MAX_WRITEBACK_PAGES;
- writeback_inodes(&wbc);
- if (wbc.nr_to_write > 0) {
- if (wbc.encountered_congestion || wbc.more_io)
- congestion_wait(BLK_RW_ASYNC, HZ/10);
- else
- break; /* All the old data is written */
- }
- nr_to_write -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
- }
- if (time_before(next_jif, jiffies + HZ))
- next_jif = jiffies + HZ;
- if (dirty_writeback_interval)
- mod_timer(&wb_timer, next_jif);
-}
-
-/*
* sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
*/
int dirty_writeback_centisecs_handler(ctl_table *table, int write,
struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
{
proc_dointvec(table, write, file, buffer, length, ppos);
- if (dirty_writeback_interval)
- mod_timer(&wb_timer, jiffies +
- msecs_to_jiffies(dirty_writeback_interval * 10));
- else
- del_timer(&wb_timer);
return 0;
}
-static void wb_timer_fn(unsigned long unused)
-{
- if (pdflush_operation(wb_kupdate, 0) < 0)
- mod_timer(&wb_timer, jiffies + HZ); /* delay 1 second */
-}
-
-static void laptop_flush(unsigned long unused)
+static void do_laptop_sync(struct work_struct *work)
{
- sys_sync();
+ wakeup_flusher_threads(0);
+ kfree(work);
}
static void laptop_timer_fn(unsigned long unused)
{
- pdflush_operation(laptop_flush, 0);
+ struct work_struct *work;
+
+ work = kmalloc(sizeof(*work), GFP_ATOMIC);
+ if (work) {
+ INIT_WORK(work, do_laptop_sync);
+ schedule_work(work);
+ }
}
/*
@@ -907,8 +786,6 @@ void __init page_writeback_init(void)
{
int shift;
- mod_timer(&wb_timer,
- jiffies + msecs_to_jiffies(dirty_writeback_interval * 10));
writeback_set_ratelimit();
register_cpu_notifier(&ratelimit_nb);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 94e86dd..ba8228e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1720,7 +1720,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
*/
if (total_scanned > sc->swap_cluster_max +
sc->swap_cluster_max / 2) {
- wakeup_pdflush(laptop_mode ? 0 : total_scanned);
+ wakeup_flusher_threads(laptop_mode ? 0 : total_scanned);
sc->may_writepage = 1;
}
--
1.6.4.1.207.g68ea
--
Jens Axboe
On Fri, Sep 04 2009, Jens Axboe wrote:
> +static long wb_check_old_data_flush(struct bdi_writeback *wb)
> +{
> + unsigned long expired;
> + long nr_pages;
> +
> + expired = wb->last_old_flush +
> + msecs_to_jiffies(dirty_writeback_interval * 10);
> + if (time_before(jiffies, expired))
> + return 0;
> +
> + nr_pages = global_page_state(NR_FILE_DIRTY) +
> + global_page_state(NR_UNSTABLE_NFS) +
> + (inodes_stat.nr_inodes - inodes_stat.nr_unused);
> +
> + return wb_writeback(wb, nr_pages, NULL, WB_SYNC_NONE, 1);
> +}
Needs to set ->last_old_flush of course. I also made it check for
nr_pages > 0 before calling into wb_writeback().
--
Jens Axboe
On 04/09/09 08:46, Jens Axboe wrote:
> From: Theodore Ts'o<[email protected]>
>
> Originally, MAX_WRITEBACK_PAGES was hard-coded to 1024 because of a
> concern of not holding I_SYNC for too long. (At least, that was the
> comment previously.) This doesn't make sense now because the only
> time we wait for I_SYNC is if we are calling sync or fsync, and in
> that case we need to write out all of the data anyway. Previously
> there may have been other code paths that waited on I_SYNC, but not
> any more.
>
> According to Christoph, the current writeback size is way too small,
> and XFS had a hack that bumped out nr_to_write to four times the value
> sent by the VM to be able to saturate medium-sized RAID arrays. This
> value was also problematic for ext4 as well, as it caused large files
> to be come interleaved on disk by in 8 megabyte chunks (we bumped up
> the nr_to_write by a factor of two).
>
> So, in this patch, we make the MAX_WRITEBACK_PAGES a tunable,
> max_writeback_mb, and set it to a default value of 128 megabytes.
>
> http://bugzilla.kernel.org/show_bug.cgi?id=13930
>
> Signed-off-by: "Theodore Ts'o"<[email protected]>
> Signed-off-by: Jens Axboe<[email protected]>
> ---
> fs/fs-writeback.c | 9 +--------
> include/linux/writeback.h | 1 +
> kernel/sysctl.c | 8 ++++++++
> mm/page-writeback.c | 6 ++++++
> 4 files changed, 16 insertions(+), 8 deletions(-)
>
> diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
> index ce68f60..790d379 100644
> --- a/fs/fs-writeback.c
> +++ b/fs/fs-writeback.c
> @@ -641,14 +641,7 @@ void writeback_inodes_wbc(struct writeback_control *wbc)
> writeback_inodes_wb(&bdi->wb, wbc);
> }
>
> -/*
> - * The maximum number of pages to writeout in a single bdi flush/kupdate
> - * operation. We do this so we don't hold I_SYNC against an inode for
> - * enormous amounts of time, which would block a userspace task which has
> - * been forced to throttle against that inode. Also, the code reevaluates
> - * the dirty each time it has written this many pages.
> - */
> -#define MAX_WRITEBACK_PAGES 1024
> +#define MAX_WRITEBACK_PAGES (max_writeback_mb<< (20 - PAGE_SHIFT))
>
> static inline bool over_bground_thresh(void)
> {
> diff --git a/include/linux/writeback.h b/include/linux/writeback.h
> index 78b1e46..fbed759 100644
> --- a/include/linux/writeback.h
> +++ b/include/linux/writeback.h
> @@ -104,6 +104,7 @@ extern int vm_dirty_ratio;
> extern unsigned long vm_dirty_bytes;
> extern unsigned int dirty_writeback_interval;
> extern unsigned int dirty_expire_interval;
> +extern unsigned int max_writeback_mb;
> extern int vm_highmem_is_dirtyable;
> extern int block_dump;
> extern int laptop_mode;
> diff --git a/kernel/sysctl.c b/kernel/sysctl.c
> index 58be760..315fc30 100644
> --- a/kernel/sysctl.c
> +++ b/kernel/sysctl.c
> @@ -1104,6 +1104,14 @@ static struct ctl_table vm_table[] = {
> .proc_handler =&proc_dointvec,
> },
> {
> + .ctl_name = CTL_UNNUMBERED,
> + .procname = "max_writeback_mb",
> + .data =&max_writeback_mb,
> + .maxlen = sizeof(max_writeback_mb),
> + .mode = 0644,
> + .proc_handler =&proc_dointvec,
> + },
> + {
> .ctl_name = VM_NR_PDFLUSH_THREADS,
> .procname = "nr_pdflush_threads",
> .data =&nr_pdflush_threads,
> diff --git a/mm/page-writeback.c b/mm/page-writeback.c
> index 2c287d9..38fe4e8 100644
> --- a/mm/page-writeback.c
> +++ b/mm/page-writeback.c
> @@ -55,6 +55,12 @@ static inline long sync_writeback_pages(void)
> /* The following parameters are exported via /proc/sys/vm */
>
> /*
> + * The maximum amount of memory (in megabytes) to write out in a
> + * single bdflush/kupdate operation.
> + */
> +unsigned int max_writeback_mb = 128;
> +
> +/*
> * Start background writeback (via pdflush) at this percentage
> */
> int dirty_background_ratio = 10;
Hi Jens,
I've been testing this & it works pretty well here, but setting
max_writeback_mb to 128 seems much too large for normal desktop machines.
Because it is so large the background writes don't stop when they get
down to the background threshold, but just keep on writing.
background_threshold on my machine is only about 300Mb so it can
undershoot by quite a bit. This could impact random write workloads
significantly.
Would making the tunable a percentage of dirty_threshold be better for
most people? At least it would scale with the size of the system memory.
I'm guessing that machines with RAID arrays also have large memories.
Or can the check for the background threshold be pushed further down
into writeback_inodes_wb and just check it every N pages? I think this
would do a better job but make the code even more complex.
regards
Richard
Richard Kennedy wrote:
> I've been testing this & it works pretty well here, but setting
> max_writeback_mb to 128 seems much too large for normal desktop machines.
>
> Because it is so large the background writes don't stop when they get
> down to the background threshold, but just keep on writing.
> background_threshold on my machine is only about 300Mb so it can
> undershoot by quite a bit. This could impact random write workloads
> significantly.
If that's true, would it be even worse for embedded devices with, say,
just 32MB RAM? It sounds like writeback undershoot might be rather
extreme in that case.
Also on this topic, should max_writeback be smaller for slow disks? I
have a small device here with a hard disk that can only be written at
2-10MB/s due to limitations of the built-in IDE controller.
I know that's unusual, but it shows there is quite a wide range of
speeds at which disks can be written, even just counting hard disks.
-- Jamie
On Sat, 2009-09-05 at 14:26 +0100, Jamie Lokier wrote:
> Richard Kennedy wrote:
> > I've been testing this & it works pretty well here, but setting
> > max_writeback_mb to 128 seems much too large for normal desktop machines.
> >
> > Because it is so large the background writes don't stop when they get
> > down to the background threshold, but just keep on writing.
> > background_threshold on my machine is only about 300Mb so it can
> > undershoot by quite a bit. This could impact random write workloads
> > significantly.
>
> If that's true, would it be even worse for embedded devices with, say,
> just 32MB RAM? It sounds like writeback undershoot might be rather
> extreme in that case.
Well, on a machine that small I don't think it will be any worse. The
current code tries to write 1024 pages so its undershoot will be about
100% anyway.
> Also on this topic, should max_writeback be smaller for slow disks? I
> have a small device here with a hard disk that can only be written at
> 2-10MB/s due to limitations of the built-in IDE controller.
>
> I know that's unusual, but it shows there is quite a wide range of
> speeds at which disks can be written, even just counting hard disks.
>
> -- Jamie
I'm not sure about that, it will depend on how the background threshold
issue gets fixed.
regards
Richard
On Fri, Sep 04, 2009 at 04:28:50PM +0100, Richard Kennedy wrote:
>
> I've been testing this & it works pretty well here, but setting
> max_writeback_mb to 128 seems much too large for normal desktop machines.
>
> Because it is so large the background writes don't stop when they get
> down to the background threshold, but just keep on writing.
> background_threshold on my machine is only about 300Mb so it can
> undershoot by quite a bit. This could impact random write workloads
> significantly.
Keep in mind that the threshold has always been on a per-inode basis.
So on a desktop machine where KDE or GNOME decides to dirty (and
write) a few hundred or thousand small files in ~/.gnome or ~/.kde the
1024 MAX_WRITEBACK_PAGES threshold wuldn't stop it.
It doesn't seem likely to me that a desktop machine is likely to have
a random write workload where multiple megabytes worth of random
writes to a single file. That's more of a heavy database workload,
which tends not to show up on desktop machines.
What is much more likely is that a desktop machine, we might be trying
to write a 800 mb ISO image, and there, stopping after 4mb (1024
pages) is pathetically short place to stall just to seek over to some
other random part of the disk because firefox wants to record that the
user just clicked on some URL, or some KDE app wants to record to disk
the fact that someone just moved or resized a KDE window.
You're right that the amount of time that we might spend doing
background writes does very greatly depending on whether we are doing
lots of small seeky writes, or a big contiguous writes (such as an iso
image or a large mp3 file). But that's always a problem that we've
had with the current writeout algorithm, and we're not making that
problem any worse with respect to the typical desktop workload, since
the small seeky writes tend to be hundreds of different small dot
files, and changing the max_writeback_{mb,pages} threshold isn't going
to change that.
> Or can the check for the background threshold be pushed further down
> into writeback_inodes_wb and just check it every N pages? I think this
> would do a better job but make the code even more complex.
In the long run if we want to cap the amount of work being done in the
threshold, it needs to be a global limit, instead of a per-file limit,
and it needs to take into account whether it is a large contiguous
writeback, or lots of small seeky writes. But that's a previously
unsolved problem, and I don't think we'll be making that problem any worse.
After all, the workloads that do lots of random writes to a single
file also tend to intersperse those writes with fsync()'s, since
that's also characteristic of database workloads.
- Ted
Hi Jens,
now I've found just two minor things (see below). Besides them the only
thing which is blocking my ack is a way to effectively lookup a BDI from a
superblock so that we can reasonably effectively fsync a superblock...
Honza
On Fri 04-09-09 14:04:07, Jens Axboe wrote:
> diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
> index 45ad4bb..c86492c 100644
> --- a/fs/fs-writeback.c
> +++ b/fs/fs-writeback.c
> +static long wb_check_old_data_flush(struct bdi_writeback *wb)
> +{
> + unsigned long expired;
> + long nr_pages;
> +
> + expired = wb->last_old_flush +
> + msecs_to_jiffies(dirty_writeback_interval * 10);
> + if (time_before(jiffies, expired))
> + return 0;
> +
> + nr_pages = global_page_state(NR_FILE_DIRTY) +
> + global_page_state(NR_UNSTABLE_NFS) +
> + (inodes_stat.nr_inodes - inodes_stat.nr_unused);
> +
> + return wb_writeback(wb, nr_pages, NULL, WB_SYNC_NONE, 1);
> +}
> +
> +/*
> + * Retrieve work items and do the writeback they describe
> + */
> +long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
> +{
> + struct backing_dev_info *bdi = wb->bdi;
> + struct bdi_work *work;
> + long nr_pages, wrote = 0;
> +
> + while ((work = get_next_work_item(bdi, wb)) != NULL) {
> + enum writeback_sync_modes sync_mode;
> +
> + nr_pages = work->nr_pages;
> +
> + /*
> + * Override sync mode, in case we must wait for completion
> + */
> + if (force_wait)
> + work->sync_mode = sync_mode = WB_SYNC_ALL;
> + else
> + sync_mode = work->sync_mode;
> +
> + /*
> + * If this isn't a data integrity operation, just notify
> + * that we have seen this work and we are now starting it.
> + */
> + if (sync_mode == WB_SYNC_NONE)
> + wb_clear_pending(wb, work);
> +
> + wrote += wb_writeback(wb, nr_pages, work->sb, sync_mode, 0);
> +
> + /*
> + * This is a data integrity writeback, so only do the
> + * notification when we have completed the work.
> + */
> + if (sync_mode == WB_SYNC_ALL)
> + wb_clear_pending(wb, work);
> + }
> +
> + /*
> + * Check for periodic writeback, kupdated() style
> + */
> + if (!wrote)
> + wrote = wb_check_old_data_flush(wb);
Why is here the !wrote check? It would feel safer if we just did
wrote += wb_check_old_data_flush(wb);
Otherwise we cannot guarantee syncing of inodes every writeback_interval.
> +/*
> + * Schedule writeback for all backing devices. Expensive! If this is a data
> + * integrity operation, writeback will be complete when this returns. If
> + * we are simply called for WB_SYNC_NONE, then writeback will merely be
> + * scheduled to run.
> + */
> +static void bdi_writeback_all(struct writeback_control *wbc)
> +{
> + const bool must_wait = wbc->sync_mode == WB_SYNC_ALL;
> + struct backing_dev_info *bdi;
> + struct bdi_work *work;
> + LIST_HEAD(list);
> +
> +restart:
> + spin_lock(&bdi_lock);
>
> - filemap_fdatawait(mapping);
> + list_for_each_entry(bdi, &bdi_list, bdi_list) {
> + struct bdi_work *work;
> +
> + if (!bdi_has_dirty_io(bdi))
> + continue;
> +
> + /*
> + * If work allocation fails, do the writes inline. We drop
> + * the lock and restart the list writeout. This should be OK,
> + * since this happens rarely and because the writeout should
> + * eventually make more free memory available.
> + */
> + work = bdi_alloc_work(wbc);
> + if (!work) {
> + struct writeback_control __wbc = *wbc;
>
> - cond_resched();
> + /*
> + * Not a data integrity writeout, just continue
> + */
> + if (!must_wait)
> + continue;
>
> - spin_lock(&inode_lock);
> + spin_unlock(&bdi_lock);
> + __wbc = *wbc;
You initialize the variable twice...
--
Jan Kara <[email protected]>
SUSE Labs, CR
On Mon, Sep 07 2009, Jan Kara wrote:
> Hi Jens,
>
> now I've found just two minor things (see below). Besides them the only
> thing which is blocking my ack is a way to effectively lookup a BDI from a
> superblock so that we can reasonably effectively fsync a superblock...
Can we side step that as an inclusion criteria, please? I'd really like
to work on adding that quick lookup, but I'd also hate to potentiall
destabilize anything at this point. So we can probably quite easily make
.32 as well for that, but I'd rather not risk doing a version and
include that from the beginning. OK?
> > + /*
> > + * Check for periodic writeback, kupdated() style
> > + */
> > + if (!wrote)
> > + wrote = wb_check_old_data_flush(wb);
> Why is here the !wrote check? It would feel safer if we just did
> wrote += wb_check_old_data_flush(wb);
> Otherwise we cannot guarantee syncing of inodes every writeback_interval.
Yes good point, that check should not be there or the logic is still
broken wrt old data flushing. Will fix that, thanks!
> > + /*
> > + * If work allocation fails, do the writes inline. We drop
> > + * the lock and restart the list writeout. This should be OK,
> > + * since this happens rarely and because the writeout should
> > + * eventually make more free memory available.
> > + */
> > + work = bdi_alloc_work(wbc);
> > + if (!work) {
> > + struct writeback_control __wbc = *wbc;
> >
> > - cond_resched();
> > + /*
> > + * Not a data integrity writeout, just continue
> > + */
> > + if (!must_wait)
> > + continue;
> >
> > - spin_lock(&inode_lock);
> > + spin_unlock(&bdi_lock);
> > + __wbc = *wbc;
> You initialize the variable twice...
Indeed, the latter should just go. Good spotting, fixed.
--
Jens Axboe
On Fri 04-09-09 09:46:46, Jens Axboe wrote:
> From: Theodore Ts'o <[email protected]>
>
> Originally, MAX_WRITEBACK_PAGES was hard-coded to 1024 because of a
> concern of not holding I_SYNC for too long. (At least, that was the
> comment previously.) This doesn't make sense now because the only
> time we wait for I_SYNC is if we are calling sync or fsync, and in
> that case we need to write out all of the data anyway. Previously
> there may have been other code paths that waited on I_SYNC, but not
> any more.
Well, I've always though that MAX_WRITEBACK_PAGES is there because
of a situation when a thread is forced to throttle on a BDI and
we'd like pdflush to yield to this thread so that it can do its duty
(otherwise it may be basically forced to wait until pdflush writes
enough for a system to drop below dirty_limit instead of writing
just sync_writeback_pages()).
What also seemed suboptimal to me (on a simple SATA drive) is that
this writeout from a throttled thread is interleaved with a writeout
from pdflush when there are more dirty inodes. So what we might
want to do once we have more threads per-bdi and thus won't hit CPU
bottleneck on high-end storage is that we'd leave writeout completely
to per-BDI threads and just make throttled thread wait until enough
IO is done on the BDI....
> According to Christoph, the current writeback size is way too small,
> and XFS had a hack that bumped out nr_to_write to four times the value
> sent by the VM to be able to saturate medium-sized RAID arrays. This
> value was also problematic for ext4 as well, as it caused large files
> to be come interleaved on disk by in 8 megabyte chunks (we bumped up
> the nr_to_write by a factor of two).
>
> So, in this patch, we make the MAX_WRITEBACK_PAGES a tunable,
> max_writeback_mb, and set it to a default value of 128 megabytes.
>
> http://bugzilla.kernel.org/show_bug.cgi?id=13930
>
> Signed-off-by: "Theodore Ts'o" <[email protected]>
> Signed-off-by: Jens Axboe <[email protected]>
Honza
--
Jan Kara <[email protected]>
SUSE Labs, CR
On Mon 07-09-09 20:45:18, Jens Axboe wrote:
> On Mon, Sep 07 2009, Jan Kara wrote:
> > Hi Jens,
> >
> > now I've found just two minor things (see below). Besides them the only
> > thing which is blocking my ack is a way to effectively lookup a BDI from a
> > superblock so that we can reasonably effectively fsync a superblock...
>
> Can we side step that as an inclusion criteria, please? I'd really like
> to work on adding that quick lookup, but I'd also hate to potentiall
> destabilize anything at this point. So we can probably quite easily make
> .32 as well for that, but I'd rather not risk doing a version and
> include that from the beginning. OK?
Well, for now I thought about a simple hack like a pointer to
backing_dev_info in a superblock. That should work for every filesystem
right now and shouldn't be too complex...
But if you promise you'll fix that up before 2.6.32 is released, I'm OK
with your patch as is. I'll give your patches some testing with some less
usual benchmarks this week and if that works out fine you have my ack.
Honza
--
Jan Kara <[email protected]>
SUSE Labs, CR
On Mon, Sep 07 2009, Jan Kara wrote:
> On Mon 07-09-09 20:45:18, Jens Axboe wrote:
> > On Mon, Sep 07 2009, Jan Kara wrote:
> > > Hi Jens,
> > >
> > > now I've found just two minor things (see below). Besides them the only
> > > thing which is blocking my ack is a way to effectively lookup a BDI from a
> > > superblock so that we can reasonably effectively fsync a superblock...
> >
> > Can we side step that as an inclusion criteria, please? I'd really like
> > to work on adding that quick lookup, but I'd also hate to potentiall
> > destabilize anything at this point. So we can probably quite easily make
> > .32 as well for that, but I'd rather not risk doing a version and
> > include that from the beginning. OK?
> Well, for now I thought about a simple hack like a pointer to
> backing_dev_info in a superblock. That should work for every filesystem
> right now and shouldn't be too complex...
Oh certainly, it wont be complex. But there's still a risk with
operations such as that, referencing to something new...
> But if you promise you'll fix that up before 2.6.32 is released, I'm OK
> with your patch as is. I'll give your patches some testing with some less
> usual benchmarks this week and if that works out fine you have my ack.
I promise :-)
Let me post a new version tomorrow, and you can base your tests off
that.
--
Jens Axboe