Compare with Ext3/4, the performance of file creation and deletion on btrfs is
very poor. the reason is that btrfs must do a lot of b+ tree insertions, such as
inode item, directory name item, directory name index and so on.
If we can do some delayed b+ tree insertion or deletion, we can improve the
performance, so we made this patch which implemented delayed directory name
index insertion and deletion.
Beside that, we found we must map the page every time we want to set a member
variable of the inode item, it is inefficient. We just do it at first to reduce
the times of mmap(). By this way, we can also improve the performance of file
creation and deletion.
I did a quick test by the benchmark tool[1] and found we can improve the
performance of file creation by ~11%, and file deletion by ~14%.
Before applying this patch:
Create files:
Total files: 50000
Total time: 1.188547
Average time: 0.000024
Delete files:
Total files: 50000
Total time: 1.662012
Average time: 0.000033
After applying this patch:
Create files:
Total files: 50000
Total time: 1.057432
Average time: 0.000021
Delete files:
Total files: 50000
Total time: 1.422851
Average time: 0.000028
You can also try out the patchset by pulling:
git://repo.or.cz/linux-btrfs-devel.git perf-improve
[1] http://marc.info/?l=linux-btrfs&m=128212635122920&q=p3
---
fs/btrfs/Makefile | 2 +-
fs/btrfs/btrfs_inode.h | 2 +
fs/btrfs/ctree.c | 13 +-
fs/btrfs/ctree.h | 21 +-
fs/btrfs/delayed-dir-index.c | 790 ++++++++++++++++++++++++++++++++++++++++++
fs/btrfs/delayed-dir-index.h | 92 +++++
fs/btrfs/dir-item.c | 61 +++-
fs/btrfs/extent-tree.c | 21 ++
fs/btrfs/inode.c | 189 +++++++---
fs/btrfs/transaction.c | 9 +
fs/btrfs/transaction.h | 2 +
11 files changed, 1117 insertions(+), 85 deletions(-)
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
