linux-kernel - Re: [linus:master] [NFSD] 39d432fc76: fsmark.files_per

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <29dec29c4a776db82406f272557f97cebabca963.camel@kernel.org>
Date:   Thu, 24 Aug 2023 10:26:15 -0400
From:   Jeff Layton <jlayton@...nel.org>
To:     Benjamin Coddington <bcodding@...hat.com>,
        Chuck Lever <chuck.lever@...cle.com>
Cc:     kernel test robot <oliver.sang@...el.com>, oe-lkp@...ts.linux.dev,
        lkp@...el.com, linux-kernel@...r.kernel.org,
        linux-nfs@...r.kernel.org, ying.huang@...el.com,
        feng.tang@...el.com, fengwei.yin@...el.com
Subject: Re: [linus:master] [NFSD]  39d432fc76:  fsmark.files_per_sec
 -100.0% regression

On Thu, 2023-08-24 at 10:12 -0400, Benjamin Coddington wrote:
> On 24 Aug 2023, at 9:23, Chuck Lever wrote:
> 
> > On Thu, Aug 24, 2023 at 01:59:06PM +0800, kernel test robot wrote:
> > > 
> > > 
> > > hi, Chuck Lever,
> > > 
> > > Fengwei (CCed) helped us review this astonishing finding by fsmark tests,
> > > and doubt below part:
> > > -			nfsd4_end_grace(nn);
> > > +			trace_nfsd_end_grace(netns(file));
> > > 
> > > and confirmed if adding back:
> > > 			nfsd4_end_grace(nn);
> > > 
> > > the regression is gone and files_per_sec restore to 61.93.
> > 
> > As always, thanks for the report. However, this result is not
> > plausible. "end_grace" happens only once after a server reboot.
> > 
> > Can you confirm that the NFS server kernel is not crashing
> > during the test?
> 
> Does the removal of nfsd4_end_grace() here disable the ability of nfsdcltrack to
> terminate the grace period early on a first start of the server?
> 
> 

Yes. That should be the only effect (which is why we didn't notice it).
-- 
Jeff Layton <jlayton@...nel.org>