[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <ZDkNTJfu83DrecW1@yujie-X299>
Date: Fri, 14 Apr 2023 16:22:36 +0800
From: Yujie Liu <yujie.liu@...el.com>
To: Christoph Hellwig <hch@....de>
CC: <oe-lkp@...ts.linux.dev>, <lkp@...el.com>,
<linux-kernel@...r.kernel.org>, David Sterba <dsterba@...e.com>,
Johannes Thumshirn <johannes.thumshirn@....com>,
Anand Jain <anand.jain@...cle.com>,
<linux-btrfs@...r.kernel.org>, <ying.huang@...el.com>,
<feng.tang@...el.com>, <fengwei.yin@...el.com>
Subject: Re: [linus:master] [btrfs] 4ae2edf12d: fio.write_iops -11.9%
regression
On Fri, Apr 14, 2023 at 07:24:58AM +0200, Christoph Hellwig wrote:
> On Fri, Apr 14, 2023 at 10:01:51AM +0800, kernel test robot wrote:
> > Hello,
> >
> > kernel test robot noticed a -11.9% regression of fio.write_iops on:
> >
> > commit: 4ae2edf12d49fdbaea2dfda0bb2ec06501bd3493 ("btrfs: simplify parameters of btrfs_lookup_bio_sums")
> > https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
>
> Can you revalidate this? The patch is purely a parameter passing
> cleanup, so a large reduction in IOPS looks very suspicious.
Sorry this is a false positive report.
The environment was inconsistent when testing this commit and its
parent. We've revalidated under same environment and confirmed there is
no regression:
=========================================================================================
bs/compiler/cpufreq_governor/direct/disk/fs/ioengine/kconfig/nr_task/rootfs/runtime/rw/tbox_group/test_size/testcase:
4k/gcc-11/performance/direct/1HDD/btrfs/io_uring/x86_64-rhel-8.3/100%/debian-11.1-x86_64-20220510.cgz/300s/write/lkp-icl-2sp1/128G/fio-basic
commit:
5fa356531e33e ("btrfs: remove the direct I/O read checksum lookup optimization")
4ae2edf12d49f ("btrfs: simplify parameters of btrfs_lookup_bio_sums")
5fa356531e33e7c7 4ae2edf12d49fdbaea2dfda0bb2
---------------- ---------------------------
%stddev %change %stddev
\ | \
9370 -0.7% 9309 fio.write_iops
Sorry again for the inconvenience. We will improve our workflow to
reduce false positives.
--
Best Regards,
Yujie
Powered by blists - more mailing lists