Writeback code cleanup & improvements
Jan Kara
reviewerHi,
here's one suggestion for discussion at LSF/VM summit:
It seems to me that the current writeback code has outlived it's days. The code is rather complex as various tweaks accumulated over years, filesystems workaround MAX_WRITEBACK_PAGES limitation to get better performance, inode writeback is suboptimal for filesystems doing delayed allocation (we end up writing inodes twice), sync writeback is (at least in theory) livelockable. So I think it would be worthwhile to sit down and get to some agreement on how do we improve this situation.
Honza
Signature · 2 lines
Jan Kara <[email protected]> SUSE Labs, CR