linux-nfs.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Mike Javorski <mike.javorski@gmail.com>
To: Chuck Lever III <chuck.lever@oracle.com>
Cc: Neil Brown <neilb@suse.de>, Mel Gorman <mgorman@suse.com>,
	Linux NFS Mailing List <linux-nfs@vger.kernel.org>
Subject: Re: NFS server regression in kernel 5.13 (tested w/ 5.13.9)
Date: Fri, 27 Aug 2021 10:07:36 -0700	[thread overview]
Message-ID: <CAOv1SKAiPB62sQcnDCKC5vYbbmakfbe80KRu3JEVZVO7Trk8cw@mail.gmail.com> (raw)
In-Reply-To: <6CC9C852-CEE3-4657-86AD-9D5759E2BE1C@oracle.com>

Chuck:
I just booted a 5.13.13 kernel with your suggested patch. No freezes
on the first test, but that sometimes happens so I will let the server
settle some and try it again later in the day (which also would align
with Neil's comment on memory fragmentation being a contributor).

Neil:
I have started a compile with the above kernel + your patch to test
next unless you or Chuck determine that it isn't needed, or that I
should test both patches discreetly. As the above is already merged to
5.14 it seemed logical to just add your patch on top.

I will also try to set up a vm to test your md5sum scenario with the
various kernels since it's a much faster thing to test.

- mike

On Fri, Aug 27, 2021 at 7:13 AM Chuck Lever III <chuck.lever@oracle.com> wrote:
>
>
> > On Aug 27, 2021, at 3:14 AM, NeilBrown <neilb@suse.de> wrote:
> >
> > Subject: [PATCH] SUNRPC: don't pause on incomplete allocation
> >
> > alloc_pages_bulk_array() attempts to allocate at least one page based on
> > the provided pages, and then opportunistically allocates more if that
> > can be done without dropping the spinlock.
> >
> > So if it returns fewer than requested, that could just mean that it
> > needed to drop the lock.  In that case, try again immediately.
> >
> > Only pause for a time if no progress could be made.
>
> The case I was worried about was "no pages available on the
> pcplist", in which case, alloc_pages_bulk_array() resorts
> to calling __alloc_pages() and returns only one new page.
>
> "No progess" would mean even __alloc_pages() failed.
>
> So this patch would behave essentially like the
> pre-alloc_pages_bulk_array() code: call alloc_page() for
> each empty struct_page in the array without pausing. That
> seems correct to me.
>
>
> I would add
>
> Fixes: f6e70aab9dfe ("SUNRPC: refresh rq_pages using a bulk page allocator")
>
>
> > Signed-off-by: NeilBrown <neilb@suse.de>
> > ---
> > net/sunrpc/svc_xprt.c | 7 +++++--
> > 1 file changed, 5 insertions(+), 2 deletions(-)
> >
> > diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
> > index d66a8e44a1ae..99268dd95519 100644
> > --- a/net/sunrpc/svc_xprt.c
> > +++ b/net/sunrpc/svc_xprt.c
> > @@ -662,7 +662,7 @@ static int svc_alloc_arg(struct svc_rqst *rqstp)
> > {
> >       struct svc_serv *serv = rqstp->rq_server;
> >       struct xdr_buf *arg = &rqstp->rq_arg;
> > -     unsigned long pages, filled;
> > +     unsigned long pages, filled, prev;
> >
> >       pages = (serv->sv_max_mesg + 2 * PAGE_SIZE) >> PAGE_SHIFT;
> >       if (pages > RPCSVC_MAXPAGES) {
> > @@ -672,11 +672,14 @@ static int svc_alloc_arg(struct svc_rqst *rqstp)
> >               pages = RPCSVC_MAXPAGES;
> >       }
> >
> > -     for (;;) {
> > +     for (prev = 0;; prev = filled) {
> >               filled = alloc_pages_bulk_array(GFP_KERNEL, pages,
> >                                               rqstp->rq_pages);
> >               if (filled == pages)
> >                       break;
> > +             if (filled > prev)
> > +                     /* Made progress, don't sleep yet */
> > +                     continue;
> >
> >               set_current_state(TASK_INTERRUPTIBLE);
> >               if (signalled() || kthread_should_stop()) {
>
> --
> Chuck Lever
>
>
>

  reply	other threads:[~2021-08-27 17:07 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-08 22:37 NFS server regression in kernel 5.13 (tested w/ 5.13.9) Mike Javorski
2021-08-08 22:47 ` Chuck Lever III
2021-08-08 23:23   ` Mike Javorski
2021-08-09  0:01 ` NeilBrown
2021-08-09  0:28   ` Mike Javorski
2021-08-10  0:50     ` Mike Javorski
2021-08-10  1:28       ` NeilBrown
2021-08-10 11:54         ` Daire Byrne
2021-08-13  1:51         ` Mike Javorski
2021-08-13  2:39           ` NeilBrown
2021-08-13  2:53             ` Mike Javorski
2021-08-15  1:23               ` Mike Javorski
2021-08-16  1:20                 ` NeilBrown
2021-08-16 13:21                   ` Chuck Lever III
2021-08-16 16:25                     ` Mike Javorski
2021-08-16 23:01                       ` NeilBrown
2021-08-20  0:31                         ` NeilBrown
2021-08-20  0:52                           ` Mike Javorski
2021-08-22  0:17                             ` Mike Javorski
2021-08-22  3:41                               ` NeilBrown
2021-08-22  4:05                                 ` Mike Javorski
2021-08-22 22:00                                   ` NeilBrown
2021-08-26 19:34                                     ` Mike Javorski
2021-08-26 21:44                                       ` NeilBrown
2021-08-27  0:07                                         ` Mike Javorski
2021-08-27  5:27                                           ` NeilBrown
2021-08-27  6:11                                             ` Mike Javorski
2021-08-27  7:14                                               ` NeilBrown
2021-08-27 14:13                                                 ` Chuck Lever III
2021-08-27 17:07                                                   ` Mike Javorski [this message]
2021-08-27 22:00                                                     ` Mike Javorski
2021-08-27 23:49                                                       ` Chuck Lever III
2021-08-28  3:22                                                         ` Mike Javorski
2021-08-28 18:23                                                           ` Chuck Lever III
2021-08-29 22:36                                                             ` [PATCH] SUNRPC: don't pause on incomplete allocation NeilBrown
2021-08-30  9:12                                                               ` Mel Gorman
2021-08-30 20:46                                                               ` J. Bruce Fields
     [not found]                                                             ` <163027609524.7591.4987241695872857175@noble.neil.brown.name>
2021-08-30  9:11                                                               ` [PATCH] MM: clarify effort used in alloc_pages_bulk_*() Mel Gorman
2021-09-04 17:41                                                             ` NFS server regression in kernel 5.13 (tested w/ 5.13.9) Mike Javorski
2021-09-05  2:02                                                               ` Chuck Lever III
2021-09-16  2:45                                                                 ` Mike Javorski
2021-09-16 18:58                                                                   ` Chuck Lever III
2021-09-16 19:21                                                                     ` Mike Javorski
2021-09-17 14:41                                                                       ` J. Bruce Fields
2021-08-16 16:09                   ` Mike Javorski
2021-08-16 23:04                     ` NeilBrown

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=CAOv1SKAiPB62sQcnDCKC5vYbbmakfbe80KRu3JEVZVO7Trk8cw@mail.gmail.com \
    --to=mike.javorski@gmail.com \
    --cc=chuck.lever@oracle.com \
    --cc=linux-nfs@vger.kernel.org \
    --cc=mgorman@suse.com \
    --cc=neilb@suse.de \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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).