This set is based on the earlier delayed extent tree, but has
been renamed to a "status extent" scheme. The plan is that the
tree will be expanded to track allocated extents and also
support extent locks. Thus status extents seemed like a
more appropriate name.
Allison Henderson (6):
ext4: add two structures supporting status extent tree
ext4: add operations on status extent tree
ext4: initialize status extent tree
ext4: let ext4 maintian status extent trees
ext4: reimplement fiemap on status extent tree
ext4: reimplement ext4_find_delay_alloc_range on status extent tree
fs/ext4/Makefile | 2 +-
fs/ext4/ext4.h | 9 +-
fs/ext4/ext4_extents.h | 3 +-
fs/ext4/extents.c | 297 ++++-----------------------------
fs/ext4/indirect.c | 3 +
fs/ext4/inode.c | 83 ++++------
fs/ext4/status_extents.c | 417 ++++++++++++++++++++++++++++++++++++++++++++++
fs/ext4/status_extents.h | 40 +++++
fs/ext4/super.c | 13 ++-
9 files changed, 545 insertions(+), 322 deletions(-)
create mode 100644 fs/ext4/status_extents.c
create mode 100644 fs/ext4/status_extents.h
Let ext4 initialize status extent tree of a inode.
Signed-off-by: Yongqiang Yang <[email protected]>
Signed-off-by: Allison Henderson <[email protected]>
---
:100644 100644 db2cd3f... da223a1... M fs/ext4/super.c
fs/ext4/super.c | 1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index db2cd3f..da223a1 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -898,6 +898,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
memset(&ei->i_cached_extent, 0, sizeof(struct ext4_ext_cache));
INIT_LIST_HEAD(&ei->i_prealloc_list);
spin_lock_init(&ei->i_prealloc_lock);
+ ext4_se_init_tree(&ei->i_se_tree);
ei->i_reserved_data_blocks = 0;
ei->i_reserved_meta_blocks = 0;
ei->i_allocated_meta_blocks = 0;
--
1.7.1
This patch adds operations on a status extent tree.
Signed-off-by: Yongqiang Yang <[email protected]>
Signed-off-by: Allison Henderson <[email protected]>
---
:100644 100644 56fd8f86.. 55482c1... M fs/ext4/Makefile
:000000 100644 0000000... 938e935... A fs/ext4/status_extents.c
:100644 100644 cbf96ed... 415befd... M fs/ext4/status_extents.h
fs/ext4/Makefile | 2 +-
fs/ext4/status_extents.c | 417 ++++++++++++++++++++++++++++++++++++++++++++++
fs/ext4/status_extents.h | 18 ++
3 files changed, 436 insertions(+), 1 deletions(-)
diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index 56fd8f8..55482c1 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -7,7 +7,7 @@ obj-$(CONFIG_EXT4_FS) += ext4.o
ext4-y := balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.o \
ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o \
- mmp.o indirect.o
+ mmp.o indirect.o status_extents.o
ext4-$(CONFIG_EXT4_FS_XATTR) += xattr.o xattr_user.o xattr_trusted.o
ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o
diff --git a/fs/ext4/status_extents.c b/fs/ext4/status_extents.c
new file mode 100644
index 0000000..938e935
--- /dev/null
+++ b/fs/ext4/status_extents.c
@@ -0,0 +1,417 @@
+/*
+ * fs/ext4/status_extents.c
+ *
+ * Written by Yongqiang Yang <[email protected]>
+ *
+ * Ext4 status extents core functions.
+ */
+#include <linux/rbtree.h>
+#include "ext4.h"
+#include "status_extents.h"
+#include "ext4_extents.h"
+
+/*
+ * status extent implementation for ext4.
+ *
+ *
+ * ==========================================================================
+ * Status extents encompass delayed extents and extent locks
+ *
+ * 1. Why delayed extent implementation ?
+ *
+ * Without delayed extent, ext4 identifies a delayed extent by looking up
+ * page cache, this has several deficiencies - complicated, buggy, and
+ * inefficient code.
+ *
+ * FIEMAP, SEEK_HOLE/DATA, bigalloc, punch hole and writeout all need to know if
+ * a block or a range of blocks are belonged to a delayed extent.
+ *
+ * Let us have a look at how they do without delayed extents implementation.
+ * -- FIEMAP
+ * FIEMAP looks up page cache to identify delayed allocations from holes.
+ *
+ * -- SEEK_HOLE/DATA
+ * SEEK_HOLE/DATA has the same problem as FIEMAP.
+ *
+ * -- bigalloc
+ * bigalloc looks up page cache to figure out if a block is already
+ * under delayed allocation or not to determine whether quota reserving
+ * is needed for the cluster.
+ *
+ * -- punch hole
+ * punch hole looks up page cache to identify a delayed extent.
+ *
+ * -- writeout
+ * Writeout looks up whole page cache to see if a buffer is mapped, If
+ * there are not very many delayed buffers, then it is time comsuming.
+ *
+ * With delayed extents implementation, FIEMAP, SEEK_HOLE/DATA, bigalloc and
+ * writeout can figure out if a block or a range of blocks is under delayed
+ * allocation(belonged to a delayed extent) or not by searching the delayed
+ * extent tree.
+ *
+ *
+ * ==========================================================================
+ * 2. ext4 delayed extents impelmentation
+ *
+ * -- delayed extent
+ * A delayed extent is a range of blocks which are contiguous logically and
+ * under delayed allocation. Unlike extent in ext4, delayed extent in ext4
+ * is a in-memory struct, there is no corresponding on-disk data. There is
+ * no limit on length of delayed extent, so a delayed extent can contain as
+ * many blocks as they are contiguous logically.
+ *
+ * -- delayed extent tree
+ * Every inode has a delayed extent tree and all under delayed allocation
+ * blocks are added to the tree as dealyed extents. Delayed extents in
+ * the tree are ordered by logical block no.
+ *
+ * -- operations on a delayed extent tree
+ * There are three operations on a delayed extent tree: find next delayed
+ * extent, adding a space(a range of blocks) and removing a space.
+ *
+ * -- race on a delayed extent tree
+ * Delayed extent tree is protected inode->i_data_sem like extent tree.
+ *
+ *
+ * ==========================================================================
+ * 3. performance analysis
+ * -- overhead
+ * 1. Apart from operations on a delayed extent tree, we need to
+ * down_write(inode->i_data_sem) in delayed write path to maintain delayed
+ * extent tree, this can have impact on parallel read-write and write-write
+ *
+ * 2. There is a cache extent for write access, so if writes are not very
+ * random, adding space operaions are in O(1) time.
+ *
+ * -- gain
+ * 3. Code is much simpler, more readable, more maintainable and
+ * more efficient.
+ */
+
+static struct kmem_cache *ext4_se_cachep;
+
+int __init ext4_init_se(void)
+{
+ ext4_se_cachep = KMEM_CACHE(status_extent, SLAB_RECLAIM_ACCOUNT);
+ if (ext4_se_cachep == NULL)
+ return -ENOMEM;
+ return 0;
+}
+
+void ext4_exit_se(void)
+{
+ if (ext4_se_cachep)
+ kmem_cache_destroy(ext4_se_cachep);
+}
+
+void ext4_se_init_tree(struct ext4_se_tree *tree)
+{
+ tree->root = RB_ROOT;
+ tree->cache_se = NULL;
+}
+
+#ifdef SE_DEBUG
+static void ext4_se_print_tree(struct inode *inode)
+{
+ struct ext4_se_tree *tree;
+ struct rb_node *node;
+
+ printk(KERN_DEBUG "status extents for inode %lu:", inode->i_ino);
+ tree = &EXT4_I(inode)->i_se_tree;
+ node = rb_first(&tree->root);
+ while (node) {
+ struct status_extent *se;
+ se = rb_entry(node, struct status_extent, rb_node);
+ printk(KERN_DEBUG " [%u/%u)", se->start, se->len);
+ node = rb_next(node);
+ }
+ printk(KERN_DEBUG "\n");
+}
+#else
+#define ext4_se_print_tree(inode)
+#endif
+
+static inline ext4_lblk_t status_extent_end(struct status_extent *se)
+{
+ if (se->start + se->len < se->start)
+ return (ext4_lblk_t)-1;
+ return se->start + se->len;
+}
+
+/*
+ * search through the tree for an delayed_extent with a given offset. If
+ * it can't be found, try to find next extent.
+ */
+static struct status_extent *__se_tree_search(struct rb_root *root,
+ ext4_lblk_t offset)
+{
+ struct rb_node *node = root->rb_node;
+ struct status_extent *se = NULL;
+
+ while (node) {
+ se = rb_entry(node, struct status_extent, rb_node);
+ if (offset < se->start)
+ node = node->rb_left;
+ else if (offset >= status_extent_end(se))
+ node = node->rb_right;
+ else
+ return se;
+ }
+
+ if (se && offset < se->start)
+ return se;
+
+ if (se && offset >= status_extent_end(se)) {
+ node = rb_next(&se->rb_node);
+ return node ? rb_entry(node, struct status_extent, rb_node) :
+ NULL;
+ }
+
+ return NULL;
+}
+
+/*
+ * ext4_se_find_extent: find the 1st delayed extent covering @se->start
+ * if it exists, otherwise, the next extent after @se->start.
+ *
+ * @inode: the inode which owns delayed extents
+ * @se:
+ *
+ * Returns next block beyond the found extent.
+ * Delayed extent is returned via @se.
+ */
+ext4_lblk_t ext4_se_find_extent(struct inode *inode, struct status_extent *se)
+{
+ struct ext4_se_tree *tree;
+ struct status_extent *se1;
+ struct rb_node *node;
+
+ se->len = 0;
+ tree = &EXT4_I(inode)->i_se_tree;
+ se1 = __se_tree_search(&tree->root, se->start);
+ if (se1) {
+ tree->cache_se = se1;
+ se->start = se1->start;
+ se->len = se1->len;
+ node = rb_next(&se1->rb_node);
+ if (node) {
+ se1 = rb_entry(node, struct status_extent, rb_node);
+ return se1->start;
+ }
+ }
+
+ return EXT_MAX_BLOCKS;
+}
+
+static struct status_extent *
+ext4_se_alloc_extent(ext4_lblk_t start, ext4_lblk_t len)
+{
+ struct status_extent *se;
+ se = kmem_cache_alloc(ext4_se_cachep, GFP_NOFS);
+ if (se == NULL)
+ return NULL;
+ se->start = start;
+ se->len = len;
+ return se;
+}
+
+static void ext4_se_free_extent(struct status_extent *se)
+{
+ kmem_cache_free(ext4_se_cachep, se);
+}
+
+static void ext4_se_try_to_merge_left(struct ext4_se_tree *tree,
+ struct status_extent *se)
+{
+ struct status_extent *se1;
+ struct rb_node *node;
+
+ node = rb_prev(&se->rb_node);
+ if (!node)
+ return;
+
+ se1 = rb_entry(node, struct status_extent, rb_node);
+ if (status_extent_end(se1) == se->start) {
+ se1->len += se->len;
+ rb_erase(&se->rb_node, &tree->root);
+ if (se == tree->cache_se)
+ tree->cache_se = se1;
+ ext4_se_free_extent(se);
+ }
+}
+
+static void ext4_se_try_to_merge_right(struct ext4_se_tree *tree,
+ struct status_extent *se)
+{
+ struct status_extent *se1;
+ struct rb_node *node;
+
+ node = rb_next(&se->rb_node);
+ if (!node)
+ return;
+
+ se1 = rb_entry(node, struct status_extent, rb_node);
+ if (se1->start == status_extent_end(se)) {
+ se->len += se1->len;
+ rb_erase(node, &tree->root);
+ if (se1 == tree->cache_se)
+ tree->cache_se = se;
+ ext4_se_free_extent(se1);
+ }
+}
+
+/*
+ * ext4_se_add_space: adds a space to a delayed extent tree.
+ * Caller holds inode->i_data_sem.
+ *
+ * ext4_se_add_space is callyed by ext4_dealyed_write_begin and
+ * ext4_se_remove_space.
+ *
+ * Return 0 on success, error code on failure.
+ */
+int ext4_se_add_space(struct inode *inode, ext4_lblk_t offset, ext4_lblk_t len)
+{
+ struct ext4_se_tree *tree = &EXT4_I(inode)->i_se_tree;
+ struct rb_node **p = &tree->root.rb_node;
+ struct rb_node *parent = NULL;
+ struct status_extent *se;
+ ext4_lblk_t end = offset + len;
+
+ BUG_ON(end <= offset);
+
+ se = tree->cache_se;
+ se_debug("add [%u/%u) to status extent tree of inode %lu\n",
+ offset, len, inode->i_ino);
+
+ if (se && status_extent_end(se) == offset) {
+ se_debug("cached by [%u/%u)\n", se->start, se->len);
+ se->len += len;
+ ext4_se_try_to_merge_right(tree, se);
+ goto out;
+ } else if (se && se->start == end) {
+ se_debug("cached by [%u/%u)\n", se->start, se->len);
+ se->start = offset;
+ se->len += len;
+ ext4_se_try_to_merge_left(tree, se);
+ goto out;
+ } else if (se && se->start <= offset &&
+ status_extent_end(se) >= end) {
+ se_debug("cached by [%u/%u)\n", se->start, se->len);
+ goto out;
+ }
+
+ while (*p) {
+ parent = *p;
+ se = rb_entry(parent, struct status_extent, rb_node);
+
+ if (offset < se->start) {
+ if (end == se->start) {
+ se->len += len;
+ se->start = offset;
+ goto out;
+ }
+ p = &(*p)->rb_left;
+ } else if (offset >= status_extent_end(se)) {
+ if (status_extent_end(se) == offset) {
+ se->len += len;
+ goto out;
+ }
+ p = &(*p)->rb_right;
+ } else
+ goto out;
+ }
+
+ se = ext4_se_alloc_extent(offset, len);
+ if (!se)
+ return -ENOMEM;
+ rb_link_node(&se->rb_node, parent, p);
+ rb_insert_color(&se->rb_node, &tree->root);
+
+out:
+ tree->cache_se = se;
+ ext4_se_print_tree(inode);
+
+ return 0;
+}
+
+/*
+ * ext4_se_remove_space() removes a space from a delayed extent tree.
+ * Caller holds inode->i_data_sem.
+ *
+ * Return 0 on success, error code on failure.
+ */
+int ext4_se_remove_space(struct inode *inode, ext4_lblk_t offset,
+ ext4_lblk_t len)
+{
+ struct rb_node *node;
+ struct ext4_se_tree *tree;
+ struct status_extent *se;
+ struct status_extent orig_se;
+ ext4_lblk_t len1, len2, end;
+
+ se_debug("remove [%u/%u) from status extent tree of inode %lu\n",
+ offset, len, inode->i_ino);
+
+ end = offset + len;
+ BUG_ON(end <= offset);
+ tree = &EXT4_I(inode)->i_se_tree;
+ se = __se_tree_search(&tree->root, offset);
+ if (!se)
+ goto out;
+
+ /* Simply invalidate cache_se. */
+ tree->cache_se = NULL;
+
+ orig_se.start = se->start;
+ orig_se.len = se->len;
+ len1 = offset > se->start ? offset - se->start : 0;
+ len2 = status_extent_end(se) > end ?
+ status_extent_end(se) - end : 0;
+ if (len1 > 0)
+ se->len = len1;
+ if (len2 > 0) {
+ if (len1 > 0) {
+ int err;
+ err = ext4_se_add_space(inode, end, len2);
+ if (err) {
+ se->start = orig_se.start;
+ se->len = orig_se.len;
+ return err;
+ }
+ } else {
+ se->start = end;
+ se->len = len2;
+ }
+ goto out;
+ }
+
+ if (len1 > 0) {
+ node = rb_next(&se->rb_node);
+ if (!node)
+ se = rb_entry(node, struct status_extent, rb_node);
+ else
+ se = NULL;
+ }
+
+ while (se && status_extent_end(se) <= end) {
+ node = rb_next(&se->rb_node);
+ rb_erase(&se->rb_node, &tree->root);
+ ext4_se_free_extent(se);
+ if (!node) {
+ se = NULL;
+ break;
+ }
+ se = rb_entry(node, struct status_extent, rb_node);
+ }
+
+ if (se && se->start < end) {
+ len1 = status_extent_end(se) - end;
+ se->start = end;
+ se->len = len1;
+ }
+
+out:
+ ext4_se_print_tree(inode);
+ return 0;
+}
diff --git a/fs/ext4/status_extents.h b/fs/ext4/status_extents.h
index cbf96ed..415befd 100644
--- a/fs/ext4/status_extents.h
+++ b/fs/ext4/status_extents.h
@@ -8,6 +8,13 @@
#ifndef _EXT4_STATUS_EXTENTS_H
#define _EXT4_STATUS_EXTENTS_H
+#define SE_DEBUG
+#ifdef SE_DEBUG
+#define se_debug(a...) printk(a)
+#else
+#define se_debug(a...)
+#endif
+
struct status_extent {
struct rb_node rb_node;
ext4_lblk_t start; /* first block extent covers */
@@ -19,4 +26,15 @@ struct ext4_se_tree {
struct status_extent *cache_se; /* recently accessed extent */
};
+extern int __init ext4_init_se(void);
+extern void ext4_exit_se(void);
+extern void ext4_se_init_tree(struct ext4_se_tree *tree);
+
+extern int ext4_se_add_space(struct inode *inode, ext4_lblk_t start,
+ ext4_lblk_t len);
+extern int ext4_se_remove_space(struct inode *inode, ext4_lblk_t start,
+ ext4_lblk_t len);
+extern ext4_lblk_t ext4_se_find_extent(struct inode *inode,
+ struct status_extent *se);
+
#endif /* _EXT4_STATUS_EXTENTS_H */
--
1.7.1
This patch let ext4 maintain status extent trees.
Signed-off-by: Yongqiang Yang <[email protected]>
Signed-off-by: Allison Henderson <[email protected]>
---
:100644 100644 ad39627... 2322ff8... M fs/ext4/extents.c
:100644 100644 3cfc73f... 47d78b8... M fs/ext4/indirect.c
:100644 100644 1380cd2... adeae2f... M fs/ext4/inode.c
:100644 100644 da223a1... d1a438b... M fs/ext4/super.c
fs/ext4/extents.c | 2 ++
fs/ext4/indirect.c | 3 +++
fs/ext4/inode.c | 30 ++++++++++++++++++++++++++++--
fs/ext4/super.c | 12 +++++++++++-
4 files changed, 44 insertions(+), 3 deletions(-)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index ad39627..2322ff8 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4227,6 +4227,8 @@ void ext4_ext_truncate(struct inode *inode)
last_block = (inode->i_size + sb->s_blocksize - 1)
>> EXT4_BLOCK_SIZE_BITS(sb);
+ err = ext4_se_remove_space(inode, last_block,
+ EXT_MAX_BLOCKS - last_block);
err = ext4_ext_remove_space(inode, last_block);
/* In a multi-transaction truncate, we only make the final
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 3cfc73f..47d78b8 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -22,6 +22,7 @@
#include <linux/module.h>
#include "ext4_jbd2.h"
+#include "ext4_extents.h"
#include "truncate.h"
#include <trace/events/ext4.h>
@@ -1399,6 +1400,8 @@ void ext4_ind_truncate(struct inode *inode)
down_write(&ei->i_data_sem);
ext4_discard_preallocations(inode);
+ ext4_se_remove_space(inode, last_block,
+ EXT_MAX_BLOCKS - last_block);
/*
* The orphan list entry will now protect us from any crash which
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 1380cd2..adeae2f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -484,7 +484,16 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
up_read((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
- int ret = check_block_validity(inode, map);
+ int ret;
+ if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
+ /* delayed alloc may be allocated by fallocate and
+ * coverted to initialized by directIO.
+ * we need to handle delayed extent here.
+ */
+ down_write((&EXT4_I(inode)->i_data_sem));
+ goto delayed_mapped;
+ }
+ ret = check_block_validity(inode, map);
if (ret != 0)
return ret;
}
@@ -566,8 +575,16 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
* set the BH_Da_Mapped bit on them. Its important to do this
* under the protection of i_data_sem.
*/
- if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
+ if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
+ int ret;
set_buffers_da_mapped(inode, map);
+delayed_mapped:
+ /* delayed allocation blocks has been allocated */
+ ret = ext4_se_remove_space(inode, map->m_lblk,
+ map->m_len);
+ if (ret < 0)
+ retval = ret;
+ }
}
up_write((&EXT4_I(inode)->i_data_sem));
@@ -1668,6 +1685,7 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
struct buffer_head *bh)
{
int retval;
+ int ret;
sector_t invalid_block = ~((sector_t) 0xffff);
if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
@@ -1714,6 +1732,14 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
out_unlock:
up_read((&EXT4_I(inode)->i_data_sem));
+ if (retval == 0) {
+ down_write((&EXT4_I(inode)->i_data_sem));
+ ret = ext4_se_add_space(inode, map->m_lblk, map->m_len);
+ up_write((&EXT4_I(inode)->i_data_sem));
+ if (ret)
+ return ret;
+ }
+
return retval;
}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index da223a1..d1a438b 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -49,6 +49,7 @@
#include "xattr.h"
#include "acl.h"
#include "mballoc.h"
+#include "ext4_extents.h"
#define CREATE_TRACE_POINTS
#include <trace/events/ext4.h>
@@ -983,6 +984,7 @@ void ext4_clear_inode(struct inode *inode)
end_writeback(inode);
dquot_drop(inode);
ext4_discard_preallocations(inode);
+ ext4_se_remove_space(inode, 0, EXT_MAX_BLOCKS);
if (EXT4_I(inode)->jinode) {
jbd2_journal_release_jbd_inode(EXT4_JOURNAL(inode),
EXT4_I(inode)->jinode);
@@ -5066,9 +5068,14 @@ static int __init ext4_init_fs(void)
init_waitqueue_head(&ext4__ioend_wq[i]);
}
- err = ext4_init_pageio();
+ err = ext4_init_se();
if (err)
return err;
+
+ err = ext4_init_pageio();
+ if (err)
+ goto out8;
+
err = ext4_init_system_zone();
if (err)
goto out7;
@@ -5120,6 +5127,9 @@ out6:
ext4_exit_system_zone();
out7:
ext4_exit_pageio();
+out8:
+ ext4_exit_se();
+
return err;
}
--
1.7.1
ext4_find_delay_alloc_range is reimplemented on status extent tree.
Signed-off-by: Yongqiang Yang <[email protected]>
Signed-off-by: Allison Henderson <[email protected]>
---
:100644 100644 704021e... 896f2fb... M fs/ext4/ext4.h
:100644 100644 a52db3a... 14ef9f5... M fs/ext4/ext4_extents.h
:100644 100644 cee94ce... bfcbde3... M fs/ext4/extents.c
:100644 100644 adeae2f... 8970254... M fs/ext4/inode.c
fs/ext4/ext4.h | 4 --
fs/ext4/ext4_extents.h | 3 +-
fs/ext4/extents.c | 109 +++++------------------------------------------
fs/ext4/inode.c | 53 +-----------------------
4 files changed, 14 insertions(+), 155 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 704021e..896f2fb 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2304,14 +2304,10 @@ enum ext4_state_bits {
* never, ever appear in a buffer_head's state
* flag. See EXT4_MAP_FROM_CLUSTER to see where
* this is used. */
- BH_Da_Mapped, /* Delayed allocated block that now has a mapping. This
- * flag is set when ext4_map_blocks is called on a
- * delayed allocated block to get its real mapping. */
};
BUFFER_FNS(Uninit, uninit)
TAS_BUFFER_FNS(Uninit, uninit)
-BUFFER_FNS(Da_Mapped, da_mapped)
/*
* Add new method to test wether block and inode bitmaps are properly
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index a52db3a..14ef9f5 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -290,7 +290,6 @@ extern struct ext4_ext_path *ext4_ext_find_extent(struct inode *, ext4_lblk_t,
struct ext4_ext_path *);
extern void ext4_ext_drop_refs(struct ext4_ext_path *);
extern int ext4_ext_check_inode(struct inode *inode);
-extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk,
- int search_hint_reverse);
+extern int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk);
#endif /* _EXT4_EXTENTS */
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index cee94ce..bfcbde3 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3262,112 +3262,27 @@ static int check_eofblocks_fl(handle_t *handle, struct inode *inode,
/**
* ext4_find_delalloc_range: find delayed allocated block in the given range.
*
- * Goes through the buffer heads in the range [lblk_start, lblk_end] and returns
- * whether there are any buffers marked for delayed allocation. It returns '1'
- * on the first delalloc'ed buffer head found. If no buffer head in the given
- * range is marked for delalloc, it returns 0.
- * lblk_start should always be <= lblk_end.
- * search_hint_reverse is to indicate that searching in reverse from lblk_end to
- * lblk_start might be more efficient (i.e., we will likely hit the delalloc'ed
- * block sooner). This is useful when blocks are truncated sequentially from
- * lblk_start towards lblk_end.
+ * Return 1 if there is a delalloc block in the range, otherwise 0.
*/
static int ext4_find_delalloc_range(struct inode *inode,
ext4_lblk_t lblk_start,
- ext4_lblk_t lblk_end,
- int search_hint_reverse)
+ ext4_lblk_t lblk_end)
{
- struct address_space *mapping = inode->i_mapping;
- struct buffer_head *head, *bh = NULL;
- struct page *page;
- ext4_lblk_t i, pg_lblk;
- pgoff_t index;
-
- /* reverse search wont work if fs block size is less than page size */
- if (inode->i_blkbits < PAGE_CACHE_SHIFT)
- search_hint_reverse = 0;
-
- if (search_hint_reverse)
- i = lblk_end;
- else
- i = lblk_start;
-
- index = i >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
-
- while ((i >= lblk_start) && (i <= lblk_end)) {
- page = find_get_page(mapping, index);
- if (!page)
- goto nextpage;
-
- if (!page_has_buffers(page))
- goto nextpage;
-
- head = page_buffers(page);
- if (!head)
- goto nextpage;
-
- bh = head;
- pg_lblk = index << (PAGE_CACHE_SHIFT -
- inode->i_blkbits);
- do {
- if (unlikely(pg_lblk < lblk_start)) {
- /*
- * This is possible when fs block size is less
- * than page size and our cluster starts/ends in
- * middle of the page. So we need to skip the
- * initial few blocks till we reach the 'lblk'
- */
- pg_lblk++;
- continue;
- }
-
- /* Check if the buffer is delayed allocated and that it
- * is not yet mapped. (when da-buffers are mapped during
- * their writeout, their da_mapped bit is set.)
- */
- if (buffer_delay(bh) && !buffer_da_mapped(bh)) {
- page_cache_release(page);
- trace_ext4_find_delalloc_range(inode,
- lblk_start, lblk_end,
- search_hint_reverse,
- 1, i);
- return 1;
- }
- if (search_hint_reverse)
- i--;
- else
- i++;
- } while ((i >= lblk_start) && (i <= lblk_end) &&
- ((bh = bh->b_this_page) != head));
-nextpage:
- if (page)
- page_cache_release(page);
- /*
- * Move to next page. 'i' will be the first lblk in the next
- * page.
- */
- if (search_hint_reverse)
- index--;
- else
- index++;
- i = index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
- }
+ struct status_extent se;
- trace_ext4_find_delalloc_range(inode, lblk_start, lblk_end,
- search_hint_reverse, 0, 0);
- return 0;
+ se.start = lblk_start;
+ ext4_se_find_extent(inode, &se);
+ return (se.start + se.len) >= lblk_end && se.start <= lblk_start;
}
-int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk,
- int search_hint_reverse)
+int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
ext4_lblk_t lblk_start, lblk_end;
lblk_start = lblk & (~(sbi->s_cluster_ratio - 1));
lblk_end = lblk_start + sbi->s_cluster_ratio - 1;
- return ext4_find_delalloc_range(inode, lblk_start, lblk_end,
- search_hint_reverse);
+ return ext4_find_delalloc_range(inode, lblk_start, lblk_end);
}
/**
@@ -3428,7 +3343,7 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start,
lblk_from = lblk_start & (~(sbi->s_cluster_ratio - 1));
lblk_to = lblk_from + c_offset - 1;
- if (ext4_find_delalloc_range(inode, lblk_from, lblk_to, 0))
+ if (ext4_find_delalloc_range(inode, lblk_from, lblk_to))
allocated_clusters--;
}
@@ -3438,7 +3353,7 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start,
lblk_from = lblk_start + num_blks;
lblk_to = lblk_from + (sbi->s_cluster_ratio - c_offset) - 1;
- if (ext4_find_delalloc_range(inode, lblk_from, lblk_to, 0))
+ if (ext4_find_delalloc_range(inode, lblk_from, lblk_to))
allocated_clusters--;
}
@@ -3728,7 +3643,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
ext4_ext_in_cache(inode, map->m_lblk, &newex)) {
if (!newex.ee_start_lo && !newex.ee_start_hi) {
if ((sbi->s_cluster_ratio > 1) &&
- ext4_find_delalloc_cluster(inode, map->m_lblk, 0))
+ ext4_find_delalloc_cluster(inode, map->m_lblk))
map->m_flags |= EXT4_MAP_FROM_CLUSTER;
if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
@@ -3903,7 +3818,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
}
if ((sbi->s_cluster_ratio > 1) &&
- ext4_find_delalloc_cluster(inode, map->m_lblk, 0))
+ ext4_find_delalloc_cluster(inode, map->m_lblk))
map->m_flags |= EXT4_MAP_FROM_CLUSTER;
/*
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index adeae2f..8970254 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -398,49 +398,6 @@ static pgoff_t ext4_num_dirty_pages(struct inode *inode, pgoff_t idx,
}
/*
- * Sets the BH_Da_Mapped bit on the buffer heads corresponding to the given map.
- */
-static void set_buffers_da_mapped(struct inode *inode,
- struct ext4_map_blocks *map)
-{
- struct address_space *mapping = inode->i_mapping;
- struct pagevec pvec;
- int i, nr_pages;
- pgoff_t index, end;
-
- index = map->m_lblk >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
- end = (map->m_lblk + map->m_len - 1) >>
- (PAGE_CACHE_SHIFT - inode->i_blkbits);
-
- pagevec_init(&pvec, 0);
- while (index <= end) {
- nr_pages = pagevec_lookup(&pvec, mapping, index,
- min(end - index + 1,
- (pgoff_t)PAGEVEC_SIZE));
- if (nr_pages == 0)
- break;
- for (i = 0; i < nr_pages; i++) {
- struct page *page = pvec.pages[i];
- struct buffer_head *bh, *head;
-
- if (unlikely(page->mapping != mapping) ||
- !PageDirty(page))
- break;
-
- if (page_has_buffers(page)) {
- bh = head = page_buffers(page);
- do {
- set_buffer_da_mapped(bh);
- bh = bh->b_this_page;
- } while (bh != head);
- }
- index++;
- }
- pagevec_release(&pvec);
- }
-}
-
-/*
* The ext4_map_blocks() function tries to look up the requested blocks,
* and returns if the blocks are already mapped.
*
@@ -571,13 +528,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) {
ext4_clear_inode_state(inode, EXT4_STATE_DELALLOC_RESERVED);
- /* If we have successfully mapped the delayed allocated blocks,
- * set the BH_Da_Mapped bit on them. Its important to do this
- * under the protection of i_data_sem.
- */
if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) {
int ret;
- set_buffers_da_mapped(inode, map);
delayed_mapped:
/* delayed allocation blocks has been allocated */
ret = ext4_se_remove_space(inode, map->m_lblk,
@@ -1221,7 +1173,6 @@ static void ext4_da_page_release_reservation(struct page *page,
if ((offset <= curr_off) && (buffer_delay(bh))) {
to_release++;
clear_buffer_delay(bh);
- clear_buffer_da_mapped(bh);
}
curr_off = next_off;
} while ((bh = bh->b_this_page) != head);
@@ -1234,7 +1185,7 @@ static void ext4_da_page_release_reservation(struct page *page,
lblk = (page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits)) +
((num_clusters - 1) << sbi->s_cluster_bits);
if (sbi->s_cluster_ratio == 1 ||
- !ext4_find_delalloc_cluster(inode, lblk, 1))
+ !ext4_find_delalloc_cluster(inode, lblk))
ext4_da_release_space(inode, 1);
num_clusters--;
@@ -1340,8 +1291,6 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
clear_buffer_delay(bh);
bh->b_blocknr = pblock;
}
- if (buffer_da_mapped(bh))
- clear_buffer_da_mapped(bh);
if (buffer_unwritten(bh) ||
buffer_mapped(bh))
BUG_ON(bh->b_blocknr != pblock);
--
1.7.1
This patch reimplements fiemap on status extent tree.
Signed-off-by: Yongqiang Yang <[email protected]>
Signed-off-by: Allison Henderson <[email protected]>
---
:100644 100644 2322ff8... cee94ce... M fs/ext4/extents.c
fs/ext4/extents.c | 186 +++++++----------------------------------------------
1 files changed, 23 insertions(+), 163 deletions(-)
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 2322ff8..cee94ce 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4448,193 +4448,53 @@ static int ext4_ext_fiemap_cb(struct inode *inode, ext4_lblk_t next,
struct ext4_ext_cache *newex, struct ext4_extent *ex,
void *data)
{
+ struct status_extent se;
__u64 logical;
__u64 physical;
__u64 length;
__u32 flags = 0;
+ ext4_lblk_t next_del;
int ret = 0;
struct fiemap_extent_info *fieinfo = data;
unsigned char blksize_bits;
- blksize_bits = inode->i_sb->s_blocksize_bits;
- logical = (__u64)newex->ec_block << blksize_bits;
+ se.start = newex->ec_block;
+ down_read(&EXT4_I(inode)->i_data_sem);
+ next_del = ext4_se_find_extent(inode, &se);
+ up_read(&EXT4_I(inode)->i_data_sem);
+ next = min(next_del, next);
if (newex->ec_start == 0) {
/*
* No extent in extent-tree contains block @newex->ec_start,
* then the block may stay in 1)a hole or 2)delayed-extent.
- *
- * Holes or delayed-extents are processed as follows.
- * 1. lookup dirty pages with specified range in pagecache.
- * If no page is got, then there is no delayed-extent and
- * return with EXT_CONTINUE.
- * 2. find the 1st mapped buffer,
- * 3. check if the mapped buffer is both in the request range
- * and a delayed buffer. If not, there is no delayed-extent,
- * then return.
- * 4. a delayed-extent is found, the extent will be collected.
*/
- ext4_lblk_t end = 0;
- pgoff_t last_offset;
- pgoff_t offset;
- pgoff_t index;
- pgoff_t start_index = 0;
- struct page **pages = NULL;
- struct buffer_head *bh = NULL;
- struct buffer_head *head = NULL;
- unsigned int nr_pages = PAGE_SIZE / sizeof(struct page *);
-
- pages = kmalloc(PAGE_SIZE, GFP_KERNEL);
- if (pages == NULL)
- return -ENOMEM;
-
- offset = logical >> PAGE_SHIFT;
-repeat:
- last_offset = offset;
- head = NULL;
- ret = find_get_pages_tag(inode->i_mapping, &offset,
- PAGECACHE_TAG_DIRTY, nr_pages, pages);
-
- if (!(flags & FIEMAP_EXTENT_DELALLOC)) {
- /* First time, try to find a mapped buffer. */
- if (ret == 0) {
-out:
- for (index = 0; index < ret; index++)
- page_cache_release(pages[index]);
- /* just a hole. */
- kfree(pages);
- return EXT_CONTINUE;
- }
- index = 0;
-
-next_page:
- /* Try to find the 1st mapped buffer. */
- end = ((__u64)pages[index]->index << PAGE_SHIFT) >>
- blksize_bits;
- if (!page_has_buffers(pages[index]))
- goto out;
- head = page_buffers(pages[index]);
- if (!head)
- goto out;
-
- index++;
- bh = head;
- do {
- if (end >= newex->ec_block +
- newex->ec_len)
- /* The buffer is out of
- * the request range.
- */
- goto out;
-
- if (buffer_mapped(bh) &&
- end >= newex->ec_block) {
- start_index = index - 1;
- /* get the 1st mapped buffer. */
- goto found_mapped_buffer;
- }
-
- bh = bh->b_this_page;
- end++;
- } while (bh != head);
-
- /* No mapped buffer in the range found in this page,
- * We need to look up next page.
- */
- if (index >= ret) {
- /* There is no page left, but we need to limit
- * newex->ec_len.
- */
- newex->ec_len = end - newex->ec_block;
- goto out;
- }
- goto next_page;
- } else {
- /*Find contiguous delayed buffers. */
- if (ret > 0 && pages[0]->index == last_offset)
- head = page_buffers(pages[0]);
- bh = head;
- index = 1;
- start_index = 0;
+ if (se.len == 0)
+ /* A hole found. */
+ return EXT_CONTINUE;
+
+ if (se.start > newex->ec_block) {
+ /* A hole found. */
+ newex->ec_len = min(se.start - newex->ec_block,
+ newex->ec_len);
+ return EXT_CONTINUE;
}
-found_mapped_buffer:
- if (bh != NULL && buffer_delay(bh)) {
- /* 1st or contiguous delayed buffer found. */
- if (!(flags & FIEMAP_EXTENT_DELALLOC)) {
- /*
- * 1st delayed buffer found, record
- * the start of extent.
- */
- flags |= FIEMAP_EXTENT_DELALLOC;
- newex->ec_block = end;
- logical = (__u64)end << blksize_bits;
- }
- /* Find contiguous delayed buffers. */
- do {
- if (!buffer_delay(bh))
- goto found_delayed_extent;
- bh = bh->b_this_page;
- end++;
- } while (bh != head);
-
- for (; index < ret; index++) {
- if (!page_has_buffers(pages[index])) {
- bh = NULL;
- break;
- }
- head = page_buffers(pages[index]);
- if (!head) {
- bh = NULL;
- break;
- }
-
- if (pages[index]->index !=
- pages[start_index]->index + index
- - start_index) {
- /* Blocks are not contiguous. */
- bh = NULL;
- break;
- }
- bh = head;
- do {
- if (!buffer_delay(bh))
- /* Delayed-extent ends. */
- goto found_delayed_extent;
- bh = bh->b_this_page;
- end++;
- } while (bh != head);
- }
- } else if (!(flags & FIEMAP_EXTENT_DELALLOC))
- /* a hole found. */
- goto out;
-
-found_delayed_extent:
- newex->ec_len = min(end - newex->ec_block,
- (ext4_lblk_t)EXT_INIT_MAX_LEN);
- if (ret == nr_pages && bh != NULL &&
- newex->ec_len < EXT_INIT_MAX_LEN &&
- buffer_delay(bh)) {
- /* Have not collected an extent and continue. */
- for (index = 0; index < ret; index++)
- page_cache_release(pages[index]);
- goto repeat;
- }
-
- for (index = 0; index < ret; index++)
- page_cache_release(pages[index]);
- kfree(pages);
+ flags |= FIEMAP_EXTENT_DELALLOC;
+ newex->ec_len = se.start + se.len - newex->ec_block;
}
- physical = (__u64)newex->ec_start << blksize_bits;
- length = (__u64)newex->ec_len << blksize_bits;
This patch adds two structures that supports status extent tree and
status_extent_info to inode_info.
Signed-off-by: Yongqiang Yang <[email protected]>
Signed-off-by: Allison Henderson <[email protected]>
---
:100644 100644 1bbd2ca... 704021e... M fs/ext4/ext4.h
:000000 100644 0000000... cbf96ed... A fs/ext4/status_extents.h
fs/ext4/ext4.h | 5 +++++
fs/ext4/status_extents.h | 22 ++++++++++++++++++++++
2 files changed, 27 insertions(+), 0 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 1bbd2ca..704021e 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -782,6 +782,8 @@ struct ext4_ext_cache {
__u32 ec_len; /* must be 32bit to return holes */
};
+#include "status_extents.h"
+
/*
* fourth extended file system inode data in memory
*/
@@ -859,6 +861,9 @@ struct ext4_inode_info {
struct list_head i_prealloc_list;
spinlock_t i_prealloc_lock;
+ /* delayed extents */
+ struct ext4_se_tree i_se_tree;
+
/* ialloc */
ext4_group_t i_last_alloc_group;
diff --git a/fs/ext4/status_extents.h b/fs/ext4/status_extents.h
new file mode 100644
index 0000000..cbf96ed
--- /dev/null
+++ b/fs/ext4/status_extents.h
@@ -0,0 +1,22 @@
+/*
+ * fs/ext4/status_extents.h
+ *
+ * Written by Yongqiang Yang <[email protected]>
+ *
+ */
+
+#ifndef _EXT4_STATUS_EXTENTS_H
+#define _EXT4_STATUS_EXTENTS_H
+
+struct status_extent {
+ struct rb_node rb_node;
+ ext4_lblk_t start; /* first block extent covers */
+ ext4_lblk_t len; /* length of extent in block */
+};
+
+struct ext4_se_tree {
+ struct rb_root root;
+ struct status_extent *cache_se; /* recently accessed extent */
+};
+
+#endif /* _EXT4_STATUS_EXTENTS_H */
--
1.7.1
On Wed, Apr 18, 2012 at 12:07:12AM -0700, Allison Henderson wrote:
> This set is based on the earlier delayed extent tree, but has
> been renamed to a "status extent" scheme. The plan is that the
> tree will be expanded to track allocated extents and also
> support extent locks. Thus status extents seemed like a
> more appropriate name.
How about "extent status tree" ?
>
> Allison Henderson (6):
> ext4: add two structures supporting status extent tree
> ext4: add operations on status extent tree
> ext4: initialize status extent tree
> ext4: let ext4 maintian status extent trees
"maintain".
--D
> ext4: reimplement fiemap on status extent tree
> ext4: reimplement ext4_find_delay_alloc_range on status extent tree
>
> fs/ext4/Makefile | 2 +-
> fs/ext4/ext4.h | 9 +-
> fs/ext4/ext4_extents.h | 3 +-
> fs/ext4/extents.c | 297 ++++-----------------------------
> fs/ext4/indirect.c | 3 +
> fs/ext4/inode.c | 83 ++++------
> fs/ext4/status_extents.c | 417 ++++++++++++++++++++++++++++++++++++++++++++++
> fs/ext4/status_extents.h | 40 +++++
> fs/ext4/super.c | 13 ++-
> 9 files changed, 545 insertions(+), 322 deletions(-)
> create mode 100644 fs/ext4/status_extents.c
> create mode 100644 fs/ext4/status_extents.h
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>