On Fri, May 31, 2024 at 7:54 AM Christoph Hellwig <hch@xxxxxx> wrote:
>
> On Thu, May 30, 2024 at 09:48:06PM +0200, Ilya Dryomov wrote:
> > For rbd, this change effectively lowers max_sectors from 4M to 64K or
> > less and that is definitely not desirable. From previous interactions
> > with users we want max_sectors to match max_hw_sectors -- this has come
> > up a quite a few times over the years. Some people just aren't aware
> > of the soft cap and the fact that it's adjustable and get frustrated
> > over the time poured into debugging their iostat numbers for workloads
> > that can send object (set) size I/Os.
> >
> > Looking at the git history, we lowered io_opt from objset_bytes to
> > opts->alloc_size in commit [1], but I guess io_opt was lowered just
> > along for the ride. What that commit was concerned with is really
> > discard_granularity and to a smaller extent io_min.
> >
> > How much difference does io_opt make in the real world? If what rbd
> > does stands in the way of a tree-wide cleanup, I would much rather bump
> > io_opt back to objset_bytes (i.e. what max_user_sectors is currently
> > set to).
>
> The only existing in-kernel usage is to set the readahead size.
> Based on your comments I seems like we should revert io_opt to
> objset to ->alloc_size in a prep patch?
We should revert io_opt from opts->alloc_size to objset_bytes (I think
it's what you meant to say but typoed).
How do you want to handle it? I can put together a patch, send it to
ceph-devel and it will be picked by linux-next sometime next week. Then
this patch would grow a contextual conflict and the description would
need to be updated to not mention a behavior change for rbd anymore.
Thanks,
Ilya
