sluggish writeback fixes
cover sluggish writeback fixes
Andrew,
The following patches fix the sluggish writeback behavior. They are well understood and well tested - but not yet widely tested.
The first patch reverts the debugging -mm only check_dirty_inode_list.patch - which is no longer necessary.
The following 4 patches do the real jobs:
[PATCH 2/5] writeback: fix time ordering of the per superblock inode lists 8 [PATCH 3/5] writeback: fix ntfs with sb_has_dirty_inodes()
[PATCH 4/5] writeback: remove pages_skipped accounting in __block_write_full_page() [PATCH 5/5] writeback: introduce writeback_control.more_io to indicate more io
They share the same goal as the following patches in -mm. Therefore I'd recommend to put the last 4 new ones after them:
writeback-fix-time-ordering-of-the-per-superblock-dirty-inode-lists.patch writeback-fix-time-ordering-of-the-per-superblock-dirty-inode-lists-2.patch writeback-fix-time-ordering-of-the-per-superblock-dirty-inode-lists-3.patch writeback-fix-time-ordering-of-the-per-superblock-dirty-inode-lists-4.patch writeback-fix-comment-use-helper-function.patch writeback-fix-time-ordering-of-the-per-superblock-dirty-inode-lists-5.patch writeback-fix-time-ordering-of-the-per-superblock-dirty-inode-lists-6.patch writeback-fix-time-ordering-of-the-per-superblock-dirty-inode-lists-7.patch writeback-fix-periodic-superblock-dirty-inode-flushing.patch
Regards,
Fengguang
--
Quoted 19 lines · --- Fengguang Wu
Andrew,
The following patches fix the sluggish writeback behavior. They are well understood and well tested - but not yet widely tested.
The first patch reverts the debugging -mm only
check_dirty_inode_list.patch -
which is no longer necessary.The following 4 patches do the real jobs:
[PATCH 2/5] writeback: fix time ordering of the per superblock inode lists 8
[PATCH 3/5] writeback: fix ntfs withsb_has_dirty_inodes()[PATCH 4/5] writeback: removepages_skippedaccounting in__block_write_full_page()
[PATCH 5/5] writeback: introduce writeback_control.more_io to indicate more io
Quoted 5 lines
They share the same goal as the following patches in -mm. Therefore I'd
recommend to put the last 4 new ones after them:
writeback-fix-time-ordering-of-the-per-superblock-dirty-inode-lists.patch
Quoted 1 line
writeback-fix-time-ordering-of-the-per-superblock-dirty-inode-lists-2.patch
Quoted 1 line
writeback-fix-time-ordering-of-the-per-superblock-dirty-inode-lists-3.patch
Quoted 1 line
writeback-fix-time-ordering-of-the-per-superblock-dirty-inode-lists-4.patch
Quoted 2 lines
writeback-fix-comment-use-helper-function.patch
writeback-fix-time-ordering-of-the-per-superblock-dirty-inode-lists-5.patch
Quoted 1 line
writeback-fix-time-ordering-of-the-per-superblock-dirty-inode-lists-6.patch
Quoted 1 line
writeback-fix-time-ordering-of-the-per-superblock-dirty-inode-lists-7.patch
Quoted 4 lines
writeback-fix-periodic-superblock-dirty-inode-flushing.patch
Regards,
Fengguang
Hi Fenguang,
now that Peters stuff seems to make it into mainline, do you think
your fixes should go in as well? Would definitely help to broaden the tester base. Definitely by one very interested tester :-)
Keep on the good work
Martin
------------------------------------------------------
Martin Knoblauch
email: k n o b i AT knobisoft DOT de www: http://www.knobisoft.de