From: Trond Myklebust <trondmy@hammerspace.com>
To: "neilb@suse.de" <neilb@suse.de>
Cc: "bfields@fieldses.org" <bfields@fieldses.org>,
"smayhew@redhat.com" <smayhew@redhat.com>,
"tpearson@raptorengineering.com" <tpearson@raptorengineering.com>,
"linux-nfs@vger.kernel.org" <linux-nfs@vger.kernel.org>,
"chuck.lever@oracle.com" <chuck.lever@oracle.com>
Subject: Re: CPU stall, eventual host hang with BTRFS + NFS under heavy load
Date: Fri, 15 Oct 2021 08:05:45 +0000 [thread overview]
Message-ID: <8bc8cad158234aca0448ab1c8410880daff3c278.camel@hammerspace.com> (raw)
In-Reply-To: <f2ebce6afe1d01b529a9373ecfba1dc8b3009b4c.camel@hammerspace.com>
On Fri, 2021-10-15 at 08:03 +0000, Trond Myklebust wrote:
> On Fri, 2021-10-15 at 09:51 +1100, NeilBrown wrote:
> > On Fri, 15 Oct 2021, Trond Myklebust wrote:
> > > On Tue, 2021-10-12 at 08:57 +1100, NeilBrown wrote:
> > > > On Tue, 12 Oct 2021, Chuck Lever III wrote:
> > > > >
> > > > > Scott seems well positioned to identify a reproducer. Maybe
> > > > > we
> > > > > can give him some likely candidates for possible bugs to
> > > > > explore
> > > > > first.
> > > >
> > > > Has this patch been tried?
> > > >
> > > > NeilBrown
> > > >
> > > >
> > > > diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
> > > > index c045f63d11fa..308f5961cb78 100644
> > > > --- a/net/sunrpc/sched.c
> > > > +++ b/net/sunrpc/sched.c
> > > > @@ -814,6 +814,7 @@ rpc_reset_task_statistics(struct rpc_task
> > > > *task)
> > > > {
> > > > task->tk_timeouts = 0;
> > > > task->tk_flags &= ~(RPC_CALL_MAJORSEEN|RPC_TASK_SENT);
> > > > + clear_bit(RPC_TASK_SIGNALLED, &task->tk_runstate);
> > > > rpc_init_task_st
> > >
> > > We shouldn't automatically "unsignal" a task once it has been
> > > told
> > > to
> > > die. The correct thing to do here should rather be to change
> > > rpc_restart_call() to exit early if the task was signalled.
> > >
> >
> > Maybe. It depends on exactly what the signal meant
> > (rpc_killall_tasks()
> > is a bit different from getting a SIGKILL), and exactly what the
> > task
> > is
> > trying to achieve.
> >
> > Before Commit ae67bd3821bb ("SUNRPC: Fix up task signalling")
> > that is exactly what we did.
> > If we want to change the behaviour of a task responding to
> > rpc_killall_tasks(), we should clearly justify it in a patch doing
> > exactly that.
> >
>
> The intention behind rpc_killall_tasks() never changed, which is why
> it
("it" being the error ERESTARTSYS)
> is listed in nfs_error_is_fatal(). I'm not aware of any case where we
> deliberately override in order to restart the RPC call on an
> ERESTARTSYS error.
>
>
--
Trond Myklebust
Linux NFS client maintainer, Hammerspace
trond.myklebust@hammerspace.com
next prev parent reply other threads:[~2021-10-15 8:05 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-05 9:44 CPU stall, eventual host hang with BTRFS + NFS under heavy load Timothy Pearson
2021-07-05 9:47 ` Timothy Pearson
2021-07-23 21:01 ` J. Bruce Fields
[not found] ` <B4D8C4B7-EE8C-456C-A6C5-D25FF1F3608E@rutgers.edu>
[not found] ` <3A4DF3BB-955C-4301-BBED-4D5F02959F71@rutgers.edu>
2021-08-09 17:06 ` Timothy Pearson
2021-08-09 17:15 ` hedrick
2021-08-09 17:25 ` Timothy Pearson
2021-08-09 17:37 ` Chuck Lever III
[not found] ` <F5179A41-FB9A-4AB1-BE58-C2859DB7EC06@rutgers.edu>
2021-08-09 18:30 ` Timothy Pearson
2021-08-09 18:38 ` hedrick
2021-08-09 18:44 ` Timothy Pearson
2021-08-09 18:49 ` J. Bruce Fields
[not found] ` <15AD846A-4638-4ACF-B47C-8EF655AD6E85@rutgers.edu>
2021-08-09 18:56 ` Timothy Pearson
2021-08-09 20:54 ` Charles Hedrick
2021-08-09 21:49 ` Timothy Pearson
2021-08-09 22:01 ` Charles Hedrick
[not found] ` <1119B476-171F-4C5A-9DEF-184F211A6A98@rutgers.edu>
2021-08-10 16:22 ` Timothy Pearson
2021-08-16 14:43 ` hedrick
2021-08-09 18:30 ` J. Bruce Fields
2021-08-09 18:34 ` hedrick
[not found] ` <413163A6-8484-4170-9877-C0C2D50B13C0@rutgers.edu>
2021-08-10 14:58 ` J. Bruce Fields
2021-07-23 21:00 ` J. Bruce Fields
2021-07-23 21:22 ` Timothy Pearson
2021-07-28 19:51 ` Timothy Pearson
2021-08-02 19:28 ` J. Bruce Fields
2021-08-10 0:43 ` NeilBrown
2021-08-10 0:54 ` J. Bruce Fields
2021-08-12 14:44 ` J. Bruce Fields
2021-08-12 21:36 ` NeilBrown
2021-10-08 20:27 ` Scott Mayhew
2021-10-08 20:53 ` Timothy Pearson
2021-10-08 21:11 ` J. Bruce Fields
2021-10-09 17:33 ` Chuck Lever III
2021-10-11 14:30 ` Bruce Fields
2021-10-11 16:36 ` Chuck Lever III
2021-10-11 21:57 ` NeilBrown
2021-10-14 22:36 ` Trond Myklebust
2021-10-14 22:51 ` NeilBrown
2021-10-15 8:03 ` Trond Myklebust
2021-10-15 8:05 ` Trond Myklebust [this message]
2021-12-01 18:36 ` Scott Mayhew
2021-12-01 19:35 ` Trond Myklebust
2021-12-01 20:13 ` Scott Mayhew
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=8bc8cad158234aca0448ab1c8410880daff3c278.camel@hammerspace.com \
--to=trondmy@hammerspace.com \
--cc=bfields@fieldses.org \
--cc=chuck.lever@oracle.com \
--cc=linux-nfs@vger.kernel.org \
--cc=neilb@suse.de \
--cc=smayhew@redhat.com \
--cc=tpearson@raptorengineering.com \
/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).