From: Wang Shilong <wshilong@xxxxxxx>
While running number of creating file threads concurrently,
we found heavy lock contention on group spinlock:
FUNC TOTAL_TIME(us) COUNT AVG(us)
ext4_create 1707443399 1440000 1185.72
_raw_spin_lock 1317641501 180899929 7.28
jbd2__journal_start 287821030 1453950 197.96
jbd2_journal_get_write_access 33441470 73077185 0.46
ext4_add_nondir 29435963 1440000 20.44
ext4_add_entry 26015166 1440049 18.07
ext4_dx_add_entry 25729337 1432814 17.96
ext4_mark_inode_dirty 12302433 5774407 2.13
most of cpu time blames to _raw_spin_lock, here is some testing
numbers with/without patch.
Test environment:
Server : SuperMicro Sever (2 x E5-2690 v3@2.60GHz, 128GB 2133MHz
DDR4 Memory, 8GbFC)
Storage : 2 x RAID1 (DDN SFA7700X, 4 x Toshiba PX02SMU020 200GB
Read Intensive SSD)
format command:
mkfs.ext4 -J size=4096
test command:
mpirun -np 48 mdtest -n 30000 -d /ext4/mdtest.out -F -C \
-r -i 5 -v -p 10 -u
Kernel version: 4.13.0-rc3
Test 1,440,000 files with 48 directories by 48 processes:
Without patch:
File Creation File removal
79,033 289,569 ops/per second
81,463 285,359
79,875 288,475
79,917 284,624
79,420 290,91
With patch:
File Creation File removal
302,600 312,813 ops/per second
295,644 316,557
288,125 306,961
302,960 310,517
295,175 311,927
Now create and removal performaces are similar, and creation
performaces are improved more than 3x with large journal size.
In default journal size, performances are improved by 50%.
Tested-by: Shuichi Ihara <sihara@xxxxxxx>
Signed-off-by: Wang Shilong <wshilong@xxxxxxx>
---
fs/ext4/ialloc.c | 13 ++++++++++++-
1 file changed, 12 insertions(+), 1 deletion(-)
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 507bfb3..18aeaf4 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -761,6 +761,7 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
ext4_group_t flex_group;
struct ext4_group_info *grp;
int encrypt = 0;
+ unsigned attemp;
/* Cannot create files in a deleted directory */
if (!dir || !dir->i_nlink)
@@ -917,6 +918,7 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
continue;
}
+ attemp = 0;
repeat_in_this_group:
ino = ext4_find_next_zero_bit((unsigned long *)
inode_bitmap_bh->b_data,
@@ -933,6 +935,9 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
ino++;
goto next_inode;
}
+
+ attemp++;
+
if (!handle) {
BUG_ON(nblocks <= 0);
handle = __ext4_journal_start_sb(dir->i_sb, line_no,
@@ -957,8 +962,14 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
if (!ret2)
goto got; /* we grabbed the inode! */
next_inode:
- if (ino < EXT4_INODES_PER_GROUP(sb))
+ if (ino < EXT4_INODES_PER_GROUP(sb)) {
+ /* Lock contention, relax a bit */
+ if (attemp >= 2) {
+ schedule_timeout_uninterruptible(msecs_to_jiffies(1));
+ attemp = 0;
+ }
goto repeat_in_this_group;
+ }
next_group:
if (++group == ngroups)
group = 0;
--
2.9.3
