Home
last modified time | relevance | path

Searched hist:"687 de7f1010cb819d04b768556960d3689abe02b" (Results 1 – 3 of 3) sorted by relevance

/openbmc/linux/fs/f2fs/
H A Dsuper.cdiff 687de7f1010cb819d04b768556960d3689abe02b Tue Mar 28 20:07:38 CDT 2017 Jaegeuk Kim <jaegeuk@kernel.org> f2fs: avoid IO split due to mixed WB_SYNC_ALL and WB_SYNC_NONE

If two threads try to flush dirty pages in different inodes respectively,
f2fs_write_data_pages() will produce WRITE and WRITE_SYNC one at a time,
resulting in a lot of 4KB seperated IOs.

So, this patch gives higher priority to WB_SYNC_ALL IOs and gathers write
IOs with a big WRITE_SYNC'ed bio.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
H A Ddata.cdiff 687de7f1010cb819d04b768556960d3689abe02b Tue Mar 28 20:07:38 CDT 2017 Jaegeuk Kim <jaegeuk@kernel.org> f2fs: avoid IO split due to mixed WB_SYNC_ALL and WB_SYNC_NONE

If two threads try to flush dirty pages in different inodes respectively,
f2fs_write_data_pages() will produce WRITE and WRITE_SYNC one at a time,
resulting in a lot of 4KB seperated IOs.

So, this patch gives higher priority to WB_SYNC_ALL IOs and gathers write
IOs with a big WRITE_SYNC'ed bio.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
H A Df2fs.hdiff 687de7f1010cb819d04b768556960d3689abe02b Tue Mar 28 20:07:38 CDT 2017 Jaegeuk Kim <jaegeuk@kernel.org> f2fs: avoid IO split due to mixed WB_SYNC_ALL and WB_SYNC_NONE

If two threads try to flush dirty pages in different inodes respectively,
f2fs_write_data_pages() will produce WRITE and WRITE_SYNC one at a time,
resulting in a lot of 4KB seperated IOs.

So, this patch gives higher priority to WB_SYNC_ALL IOs and gathers write
IOs with a big WRITE_SYNC'ed bio.

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>