summaryrefslogtreecommitdiffstats
path: root/fs/ext4/super.c
diff options
context:
space:
mode:
authorZheng Liu <wenqing.lz@taobao.com>2013-07-01 08:12:37 -0400
committerTheodore Ts'o <tytso@mit.edu>2013-07-01 08:12:37 -0400
commitd3922a777f9b4c4df898d326fa940f239af4f9b6 (patch)
tree76f63123d146bb7bbc4a3478e301bff68ab08ed7 /fs/ext4/super.c
parent2c00ef3ee309142041c7395f42aa1d49fc9f44b9 (diff)
downloadlinux-d3922a777f9b4c4df898d326fa940f239af4f9b6.tar.bz2
ext4: improve extent cache shrink mechanism to avoid to burn CPU time
Now we maintain an proper in-order LRU list in ext4 to reclaim entries from extent status tree when we are under heavy memory pressure. For keeping this order, a spin lock is used to protect this list. But this lock burns a lot of CPU time. We can use the following steps to trigger it. % cd /dev/shm % dd if=/dev/zero of=ext4-img bs=1M count=2k % mkfs.ext4 ext4-img % mount -t ext4 -o loop ext4-img /mnt % cd /mnt % for ((i=0;i<160;i++)); do truncate -s 64g $i; done % for ((i=0;i<160;i++)); do cp $i /dev/null &; done % perf record -a -g % perf report This commit tries to fix this problem. Now a new member called i_touch_when is added into ext4_inode_info to record the last access time for an inode. Meanwhile we never need to keep a proper in-order LRU list. So this can avoid to burns some CPU time. When we try to reclaim some entries from extent status tree, we use list_sort() to get a proper in-order list. Then we traverse this list to discard some entries. In ext4_sb_info, we use s_es_last_sorted to record the last time of sorting this list. When we traverse the list, we skip the inode that is newer than this time, and move this inode to the tail of LRU list. When the head of the list is newer than s_es_last_sorted, we will sort the LRU list again. In this commit, we break the loop if s_extent_cache_cnt == 0 because that means that all extents in extent status tree have been reclaimed. Meanwhile in this commit, ext4_es_{un}register_shrinker()'s prototype is changed to save a local variable in these functions. Reported-by: Dave Hansen <dave.hansen@intel.com> Signed-off-by: Zheng Liu <wenqing.lz@taobao.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Diffstat (limited to 'fs/ext4/super.c')
-rw-r--r--fs/ext4/super.c7
1 files changed, 4 insertions, 3 deletions
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 54701fca4515..cc8201180b30 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -773,7 +773,7 @@ static void ext4_put_super(struct super_block *sb)
ext4_abort(sb, "Couldn't clean up the journal");
}
- ext4_es_unregister_shrinker(sb);
+ ext4_es_unregister_shrinker(sbi);
del_timer(&sbi->s_err_report);
ext4_release_system_zone(sb);
ext4_mb_release(sb);
@@ -862,6 +862,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
rwlock_init(&ei->i_es_lock);
INIT_LIST_HEAD(&ei->i_es_lru);
ei->i_es_lru_nr = 0;
+ ei->i_touch_when = 0;
ei->i_reserved_data_blocks = 0;
ei->i_reserved_meta_blocks = 0;
ei->i_allocated_meta_blocks = 0;
@@ -3799,7 +3800,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_err_report.data = (unsigned long) sb;
/* Register extent status tree shrinker */
- ext4_es_register_shrinker(sb);
+ ext4_es_register_shrinker(sbi);
err = percpu_counter_init(&sbi->s_freeclusters_counter,
ext4_count_free_clusters(sb));
@@ -4127,7 +4128,7 @@ failed_mount_wq:
sbi->s_journal = NULL;
}
failed_mount3:
- ext4_es_unregister_shrinker(sb);
+ ext4_es_unregister_shrinker(sbi);
del_timer(&sbi->s_err_report);
if (sbi->s_flex_groups)
ext4_kvfree(sbi->s_flex_groups);