Messages in this thread | | | From | Chandan Babu R <> | Subject | Re: [PATCH V3] xfs: use roundup_pow_of_two instead of ffs during xlog_find_tail | Date | Tue, 19 Sep 2023 12:04:44 +0530 |
| |
On Mon, Sep 18, 2023 at 08:21:38 PM -0700, Darrick J. Wong wrote: > On Tue, Sep 19, 2023 at 10:06:56AM +0800, Wang Jianchao wrote: >> Ping ? Do I need other update on this patch ? > > Nope, I think this is ok... > >> Thanks >> Jianchao >> >> On 2023/9/13 09:38, Wang Jianchao wrote: >> > >> > In our production environment, we find that mounting a 500M /boot >> > which is umount cleanly needs ~6s. One cause is that ffs() is >> > used by xlog_write_log_records() to decide the buffer size. It >> > can cause a lot of small IO easily when xlog_clear_stale_blocks() >> > needs to wrap around the end of log area and log head block is >> > not power of two. Things are similar in xlog_find_verify_cycle(). >> > >> > The code is able to handed bigger buffer very well, we can use >> > roundup_pow_of_two() to replace ffs() directly to avoid small >> > and sychronous IOs. >> > >> > Reviewed-by: Dave Chinner <dchinner@redhat.com> >> > Signed-off-by: Wang Jianchao <wangjc136@midea.com> > > ...so let's see if the release manager will take this patch. > > Chandan? Could you pull in the various one-off patches floating around > on the list that have passed review? ;)
I had picked this patch along with others sometime last week.
I have pushed the new set of commits to official xfs-linux git repository and sent the announcement mail around 30 mins ago.
> > Reviewed-by: Darrick J. Wong <djwong@kernel.org> > > PS: If you'd like to send a pull request to push things along, please do >
-- Chandan
| |