v3->v4:
- For patch 1, add the DIO_SKIP_DIO_COUNT flag to dax_do_io() calls
only to address issue raised by Dave Chinner.
v2->v3:
- Remove the percpu_stats helper functions and use percpu_counters
instead.
v1->v2:
- Remove percpu_stats_reset() which is not really needed in this
patchset.
- Move some percpu_stats* functions to the newly created
lib/percpu_stats.c.
- Add a new patch to support 64-bit statistics counts in 32-bit
architectures.
- Rearrange the patches by moving the percpu_stats patches to the
front followed by the ext4 patches.
This patchset aims to improve parallel I/O performance of the ext4
filesystem on DAX.
Patch 1 eliminates duplicated inode_dio_begin()/inode_dio_end()
calls in dax_do_io().
Patch 2 converts some ext4 statistics counts into percpu counts using
the helper functions.
Waiman Long (2):
ext4: Add DIO_SKIP_DIO_COUNT flag to dax_do_io()
ext4: Make cache hits/misses per-cpu counts
fs/ext4/extents_status.c | 38 +++++++++++++++++++++++++++++---------
fs/ext4/extents_status.h | 4 ++--
fs/ext4/indirect.c | 9 ++++++++-
fs/ext4/inode.c | 11 ++++++++---
4 files changed, 47 insertions(+), 15 deletions(-)
When performing direct I/O on DAX, the current ext4 code does not pass
in the DIO_SKIP_DIO_COUNT flag to dax_do_io() when inode_dio_begin()
has, in fact, been called. This causes dax_do_io() to invoke the
inode_dio_begin()/inode_dio_end() pair internally. This doubling of
inode_dio_begin()/inode_dio_end() calls are wasteful.
For __blockdev_direct_IO(), however, the inode_dio_end() call can be
deferred for AIO. So setting DIO_SKIP_DIO_COUNT may not be appropriate.
This patch removes the extra internal inode_dio_begin()/inode_dio_end()
calls for DAX when those calls are being issued by the caller
directly. For really fast storage systems like NVDIMM, the removal
of the extra inode_dio_begin()/inode_dio_end() can give a meaningful
boost to I/O performance.
On a 4-socket Haswell-EX system (72 cores) running 4.6-rc1 kernel,
fio with 38 threads doing parallel I/O on two shared files on an
NVDIMM with DAX gave the following aggregrate bandwidth with and
without the patch:
Test W/O patch With patch % change
---- --------- ---------- --------
Read-only 8688MB/s 10173MB/s +17.1%
Read-write 2687MB/s 2830MB/s +5.3%
Signed-off-by: Waiman Long <[email protected]>
---
fs/ext4/indirect.c | 9 ++++++++-
fs/ext4/inode.c | 11 ++++++++---
2 files changed, 16 insertions(+), 4 deletions(-)
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 3027fa6..1dfc280 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -706,9 +706,16 @@ retry:
inode_dio_end(inode);
goto locked;
}
+ /*
+ * Need to pass in DIO_SKIP_DIO_COUNT to dax_do_io() to prevent
+ * duplicated inode_dio_begin/inode_dio_end pair. The flag
+ * isn't used in __blockdev_direct_IO() as the inode_dio_end()
+ * call can be deferred for AIO.
+ */
if (IS_DAX(inode))
ret = dax_do_io(iocb, inode, iter, offset,
- ext4_dio_get_block, NULL, 0);
+ ext4_dio_get_block, NULL,
+ DIO_SKIP_DIO_COUNT);
else
ret = __blockdev_direct_IO(iocb, inode,
inode->i_sb->s_bdev, iter,
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index dab84a2..b18ee2f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3358,9 +3358,14 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
* Make all waiters for direct IO properly wait also for extent
* conversion. This also disallows race between truncate() and
* overwrite DIO as i_dio_count needs to be incremented under i_mutex.
+ *
+ * The dax_do_io() will unnecessarily call inode_dio_begin() &
+ * inode_dio_end() again if the DIO_SKIP_DIO_COUNT flag is not set.
*/
- if (iov_iter_rw(iter) == WRITE)
+ if (iov_iter_rw(iter) == WRITE) {
+ dio_flags = IS_DAX(inode) ? DIO_SKIP_DIO_COUNT : 0;
inode_dio_begin(inode);
+ }
/* If we do a overwrite dio, i_mutex locking can be released */
overwrite = *((int *)iocb->private);
@@ -3393,10 +3398,10 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
get_block_func = ext4_dio_get_block_overwrite;
else if (is_sync_kiocb(iocb)) {
get_block_func = ext4_dio_get_block_unwritten_sync;
- dio_flags = DIO_LOCKING;
+ dio_flags |= DIO_LOCKING;
} else {
get_block_func = ext4_dio_get_block_unwritten_async;
- dio_flags = DIO_LOCKING;
+ dio_flags |= DIO_LOCKING;
}
#ifdef CONFIG_EXT4_FS_ENCRYPTION
BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode));
--
1.7.1
This patch changes the es_stats_cache_hits and es_stats_cache_misses
statistics counts to per-cpu variables to reduce cacheline contention
issues whem multiple threads are trying to update those counts
simultaneously. It uses the new per-cpu stats APIs provided by the
percpu_stats.h header file.
With a 38-threads fio I/O test with 2 shared files (on DAX-mount
NVDIMM) running on a 4-socket Haswell-EX server with 4.6-rc1 kernel,
the aggregated bandwidths before and after the patch were:
Test W/O patch With patch % change
---- --------- ---------- --------
Read-only 10173MB/s 16141MB/s +58.7%
Read-write 2830MB/s 4315MB/s +52.5%
Signed-off-by: Waiman Long <[email protected]>
---
fs/ext4/extents_status.c | 38 +++++++++++++++++++++++++++++---------
fs/ext4/extents_status.h | 4 ++--
2 files changed, 31 insertions(+), 11 deletions(-)
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index e38b987..92ca56d 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -770,6 +770,15 @@ void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk,
}
/*
+ * For pure statistics count, use a large batch size to make sure that
+ * it does percpu update as much as possible.
+ */
+static inline void ext4_es_stats_inc(struct percpu_counter *fbc)
+{
+ __percpu_counter_add(fbc, 1, (1 << 30));
+}
+
+/*
* ext4_es_lookup_extent() looks up an extent in extent status tree.
*
* ext4_es_lookup_extent is called by ext4_map_blocks/ext4_da_map_blocks.
@@ -825,9 +834,9 @@ out:
es->es_pblk = es1->es_pblk;
if (!ext4_es_is_referenced(es1))
ext4_es_set_referenced(es1);
- stats->es_stats_cache_hits++;
+ ext4_es_stats_inc(&stats->es_stats_cache_hits);
} else {
- stats->es_stats_cache_misses++;
+ ext4_es_stats_inc(&stats->es_stats_cache_misses);
}
read_unlock(&EXT4_I(inode)->i_es_lock);
@@ -1113,9 +1122,9 @@ int ext4_seq_es_shrinker_info_show(struct seq_file *seq, void *v)
seq_printf(seq, "stats:\n %lld objects\n %lld reclaimable objects\n",
percpu_counter_sum_positive(&es_stats->es_stats_all_cnt),
percpu_counter_sum_positive(&es_stats->es_stats_shk_cnt));
- seq_printf(seq, " %lu/%lu cache hits/misses\n",
- es_stats->es_stats_cache_hits,
- es_stats->es_stats_cache_misses);
+ seq_printf(seq, " %lld/%lld cache hits/misses\n",
+ percpu_counter_sum_positive(&es_stats->es_stats_cache_hits),
+ percpu_counter_sum_positive(&es_stats->es_stats_cache_misses));
if (inode_cnt)
seq_printf(seq, " %d inodes on list\n", inode_cnt);
@@ -1142,8 +1151,6 @@ int ext4_es_register_shrinker(struct ext4_sb_info *sbi)
sbi->s_es_nr_inode = 0;
spin_lock_init(&sbi->s_es_lock);
sbi->s_es_stats.es_stats_shrunk = 0;
- sbi->s_es_stats.es_stats_cache_hits = 0;
- sbi->s_es_stats.es_stats_cache_misses = 0;
sbi->s_es_stats.es_stats_scan_time = 0;
sbi->s_es_stats.es_stats_max_scan_time = 0;
err = percpu_counter_init(&sbi->s_es_stats.es_stats_all_cnt, 0, GFP_KERNEL);
@@ -1153,15 +1160,26 @@ int ext4_es_register_shrinker(struct ext4_sb_info *sbi)
if (err)
goto err1;
+ err = percpu_counter_init(&sbi->s_es_stats.es_stats_cache_hits, 0, GFP_KERNEL);
+ if (err)
+ goto err2;
+
+ err = percpu_counter_init(&sbi->s_es_stats.es_stats_cache_misses, 0, GFP_KERNEL);
+ if (err)
+ goto err3;
+
sbi->s_es_shrinker.scan_objects = ext4_es_scan;
sbi->s_es_shrinker.count_objects = ext4_es_count;
sbi->s_es_shrinker.seeks = DEFAULT_SEEKS;
err = register_shrinker(&sbi->s_es_shrinker);
if (err)
- goto err2;
+ goto err4;
return 0;
-
+err4:
+ percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_misses);
+err3:
+ percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_hits);
err2:
percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt);
err1:
@@ -1173,6 +1191,8 @@ void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi)
{
percpu_counter_destroy(&sbi->s_es_stats.es_stats_all_cnt);
percpu_counter_destroy(&sbi->s_es_stats.es_stats_shk_cnt);
+ percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_hits);
+ percpu_counter_destroy(&sbi->s_es_stats.es_stats_cache_misses);
unregister_shrinker(&sbi->s_es_shrinker);
}
diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h
index f7aa24f..d537868 100644
--- a/fs/ext4/extents_status.h
+++ b/fs/ext4/extents_status.h
@@ -69,10 +69,10 @@ struct ext4_es_tree {
struct ext4_es_stats {
unsigned long es_stats_shrunk;
- unsigned long es_stats_cache_hits;
- unsigned long es_stats_cache_misses;
u64 es_stats_scan_time;
u64 es_stats_max_scan_time;
+ struct percpu_counter es_stats_cache_hits;
+ struct percpu_counter es_stats_cache_misses;
struct percpu_counter es_stats_all_cnt;
struct percpu_counter es_stats_shk_cnt;
};
--
1.7.1