Linux-Fsdevel Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Ming Lei <ming.lei@redhat.com>
To: Brian Foster <bfoster@redhat.com>
Cc: Dave Chinner <david@fromorbit.com>,
	Christoph Hellwig <hch@infradead.org>,
	Ritesh Harjani <riteshh@linux.ibm.com>,
	Anju T Sudhakar <anju@linux.vnet.ibm.com>,
	darrick.wong@oracle.com, linux-xfs@vger.kernel.org,
	linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
	willy@infradead.org, minlei@redhat.com
Subject: Re: [PATCH] iomap: Fix the write_count in iomap_add_to_ioend().
Date: Mon, 31 Aug 2020 12:01:07 +0800	[thread overview]
Message-ID: <20200831040107.GB257809@T590> (raw)
In-Reply-To: <20200825144917.GA321765@bfoster>

On Tue, Aug 25, 2020 at 10:49:17AM -0400, Brian Foster wrote:
> cc Ming
> 
> On Tue, Aug 25, 2020 at 10:42:03AM +1000, Dave Chinner wrote:
> > On Mon, Aug 24, 2020 at 11:48:41AM -0400, Brian Foster wrote:
> > > On Mon, Aug 24, 2020 at 04:04:17PM +0100, Christoph Hellwig wrote:
> > > > On Mon, Aug 24, 2020 at 10:28:23AM -0400, Brian Foster wrote:
> > > > > Do I understand the current code (__bio_try_merge_page() ->
> > > > > page_is_mergeable()) correctly in that we're checking for physical page
> > > > > contiguity and not necessarily requiring a new bio_vec per physical
> > > > > page?
> > > > 
> > > > 
> > > > Yes.
> > > > 
> > > 
> > > Ok. I also realize now that this occurs on a kernel without commit
> > > 07173c3ec276 ("block: enable multipage bvecs"). That is probably a
> > > contributing factor, but it's not clear to me whether it's feasible to
> > > backport whatever supporting infrastructure is required for that
> > > mechanism to work (I suspect not).
> > > 
> > > > > With regard to Dave's earlier point around seeing excessively sized bio
> > > > > chains.. If I set up a large memory box with high dirty mem ratios and
> > > > > do contiguous buffered overwrites over a 32GB range followed by fsync, I
> > > > > can see upwards of 1GB per bio and thus chains on the order of 32+ bios
> > > > > for the entire write. If I play games with how the buffered overwrite is
> > > > > submitted (i.e., in reverse) however, then I can occasionally reproduce
> > > > > a ~32GB chain of ~32k bios, which I think is what leads to problems in
> > > > > I/O completion on some systems. Granted, I don't reproduce soft lockup
> > > > > issues on my system with that behavior, so perhaps there's more to that
> > > > > particular issue.
> > > > > 
> > > > > Regardless, it seems reasonable to me to at least have a conservative
> > > > > limit on the length of an ioend bio chain. Would anybody object to
> > > > > iomap_ioend growing a chain counter and perhaps forcing into a new ioend
> > > > > if we chain something like more than 1k bios at once?
> > > > 
> > > > So what exactly is the problem of processing a long chain in the
> > > > workqueue vs multiple small chains?  Maybe we need a cond_resched()
> > > > here and there, but I don't see how we'd substantially change behavior.
> > > > 
> > > 
> > > The immediate problem is a watchdog lockup detection in bio completion:
> > > 
> > >   NMI watchdog: Watchdog detected hard LOCKUP on cpu 25
> > > 
> > > This effectively lands at the following segment of iomap_finish_ioend():
> > > 
> > > 		...
> > >                /* walk each page on bio, ending page IO on them */
> > >                 bio_for_each_segment_all(bv, bio, iter_all)
> > >                         iomap_finish_page_writeback(inode, bv->bv_page, error);
> > > 
> > > I suppose we could add a cond_resched(), but is that safe directly
> > > inside of a ->bi_end_io() handler? Another option could be to dump large
> > > chains into the completion workqueue, but we may still need to track the
> > > length to do that. Thoughts?
> > 
> > We have ioend completion merging that will run the compeltion once
> > for all the pending ioend completions on that inode. IOWs, we do not
> > need to build huge chains at submission time to batch up completions
> > efficiently. However, huge bio chains at submission time do cause
> > issues with writeback fairness, pinning GBs of ram as unreclaimable
> > for seconds because they are queued for completion while we are
> > still submitting the bio chain and submission is being throttled by
> > the block layer writeback throttle, etc. Not to mention the latency
> > of stable pages in a situation like this - a mmap() write fault
> > could stall for many seconds waiting for a huge bio chain to finish
> > submission and run completion processing even when the IO for the
> > given page we faulted on was completed before the page fault
> > occurred...
> > 
> > Hence I think we really do need to cap the length of the bio
> > chains here so that we start completing and ending page writeback on
> > large writeback ranges long before the writeback code finishes
> > submitting the range it was asked to write back.
> > 
> 
> Ming pointed out separately that limiting the bio chain itself might not
> be enough because with multipage bvecs, we can effectively capture the
> same number of pages in much fewer bios. Given that, what do you think
> about something like the patch below to limit ioend size? This
> effectively limits the number of pages per ioend regardless of whether
> in-core state results in a small chain of dense bios or a large chain of
> smaller bios, without requiring any new explicit page count tracking.

Hello Brian,

This patch looks fine.

However, I am wondering why iomap has to chain bios in one ioend, and why not
submit each bio in usual way just like what fs/direct-io.c does? Then each bio
can complete the pages in its own .bi_end_io().


thanks,
Ming


  reply	other threads:[~2020-08-31  4:01 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-08-19 10:28 Anju T Sudhakar
2020-08-20 23:11 ` Dave Chinner
2020-08-21  4:45   ` Ritesh Harjani
2020-08-21  6:00     ` Christoph Hellwig
2020-08-21  9:09       ` Ritesh Harjani
2020-08-21 21:53     ` Dave Chinner
2020-08-22 13:13       ` Christoph Hellwig
2020-08-24 14:28         ` Brian Foster
2020-08-24 15:04           ` Christoph Hellwig
2020-08-24 15:48             ` Brian Foster
2020-08-25  0:42               ` Dave Chinner
2020-08-25 14:49                 ` Brian Foster
2020-08-31  4:01                   ` Ming Lei [this message]
2020-08-31 14:35                     ` Brian Foster
2020-09-16  0:12                   ` Darrick J. Wong
2020-09-16  8:45                     ` Christoph Hellwig
2020-09-16 13:07                       ` Brian Foster
2020-09-17  8:04                         ` Christoph Hellwig
2020-09-17 10:42                           ` Brian Foster
2020-09-17 14:48                             ` Christoph Hellwig
2020-09-17 21:33                               ` Darrick J. Wong
2020-09-17 23:13                           ` Ming Lei
2020-08-21  6:01   ` Christoph Hellwig
2020-08-21  6:07 ` Christoph Hellwig
2020-08-21  8:53   ` Ritesh Harjani
2020-08-21 14:49   ` Jens Axboe
2020-08-21 13:31 ` Matthew Wilcox

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200831040107.GB257809@T590 \
    --to=ming.lei@redhat.com \
    --cc=anju@linux.vnet.ibm.com \
    --cc=bfoster@redhat.com \
    --cc=darrick.wong@oracle.com \
    --cc=david@fromorbit.com \
    --cc=hch@infradead.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=minlei@redhat.com \
    --cc=riteshh@linux.ibm.com \
    --cc=willy@infradead.org \
    --subject='Re: [PATCH] iomap: Fix the write_count in iomap_add_to_ioend().' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).