From: kernel test robot <oliver.sang@intel.com>
To: Boris Burkov <boris@bur.io>
Cc: <oe-lkp@lists.linux.dev>, <lkp@intel.com>,
Andrew Morton <akpm@linux-foundation.org>,
Shakeel Butt <shakeel.butt@linux.dev>,
"Johannes Weiner" <hannes@cmpxchg.org>,
Matthew Wilcox <willy@infradead.org>,
"Michal Hocko" <mhocko@kernel.org>,
Muchun Song <muchun.song@linux.dev>, Qu Wenruo <wqu@suse.com>,
Roman Gushchin <roman.gushchin@linux.dev>,
<linux-btrfs@vger.kernel.org>, <oliver.sang@intel.com>
Subject: [akpm-mm:mm-stable] [btrfs] b55102826d: filebench.sum_operations/s 12.4% regression
Date: Thu, 25 Sep 2025 15:24:03 +0800 [thread overview]
Message-ID: <202509251432.59b331b7-lkp@intel.com> (raw)
Hello,
kernel test robot noticed a 12.4% regression of filebench.sum_operations/s on:
commit: b55102826d7d3d41a5777931689c746207308c95 ("btrfs: set AS_KERNEL_FILE on the btree_inode")
https://git.kernel.org/cgit/linux/kernel/git/akpm/mm.git mm-stable
testcase: filebench
config: x86_64-rhel-9.4
compiler: gcc-14
test machine: 192 threads 4 sockets Intel(R) Xeon(R) Platinum 9242 CPU @ 2.30GHz (Cascade Lake) with 176G memory
parameters:
disk: 1SSD
fs: btrfs
test: randomwrite.f
cpufreq_governor: performance
If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <oliver.sang@intel.com>
| Closes: https://lore.kernel.org/oe-lkp/202509251432.59b331b7-lkp@intel.com
Details are as below:
-------------------------------------------------------------------------------------------------->
The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20250925/202509251432.59b331b7-lkp@intel.com
=========================================================================================
compiler/cpufreq_governor/disk/fs/kconfig/rootfs/tbox_group/test/testcase:
gcc-14/performance/1SSD/btrfs/x86_64-rhel-9.4/debian-13-x86_64-20250902.cgz/lkp-csl-2sp10/randomwrite.f/filebench
commit:
e3a9ac4e86 ("mm: add vmstat for kernel_file pages")
b55102826d ("btrfs: set AS_KERNEL_FILE on the btree_inode")
e3a9ac4e866ea746 b55102826d7d3d41a5777931689
---------------- ---------------------------
%stddev %change %stddev
\ | \
2.90 +2.2% 2.96 iostat.cpu.system
1293622 -21.8% 1011948 meminfo.Dirty
111179 +22.7% 136404 ± 2% meminfo.Shmem
0.02 ± 4% -0.0 0.02 ± 6% mpstat.cpu.all.iowait%
0.39 +0.1 0.47 mpstat.cpu.all.sys%
1300 +2.7% 1335 turbostat.Bzy_MHz
0.16 ± 3% +0.1 0.23 ± 4% turbostat.C1%
24580 ± 18% +368.5% 115156 ± 97% numa-meminfo.node0.Active
24573 ± 18% +368.6% 115148 ± 97% numa-meminfo.node0.Active(anon)
80724 ± 25% +33.1% 107431 ± 9% numa-meminfo.node3.Shmem
9462 ± 4% +48.2% 14025 ± 3% sched_debug.cpu.nr_switches.avg
104544 ± 9% +42.0% 148483 ± 22% sched_debug.cpu.nr_switches.max
18711 ± 6% +40.0% 26196 ± 7% sched_debug.cpu.nr_switches.stddev
6144 ± 18% +368.1% 28763 ± 97% numa-vmstat.node0.nr_active_anon
609471 ±216% +427.6% 3215506 ± 68% numa-vmstat.node0.nr_dirtied
602202 ±217% +429.1% 3186249 ± 68% numa-vmstat.node0.nr_written
6144 ± 18% +368.1% 28762 ± 97% numa-vmstat.node0.nr_zone_active_anon
20153 ± 26% +33.3% 26862 ± 9% numa-vmstat.node3.nr_shmem
800.20 -12.4% 701.12 filebench.sum_bytes_mb/s
6146050 -12.4% 5384959 filebench.sum_operations
102425 -12.4% 89741 filebench.sum_operations/s
0.01 ± 4% +13.8% 0.01 filebench.sum_time_ms/op
102425 -12.4% 89741 filebench.sum_writes/s
28873566 ± 2% +32.2% 38160857 ± 2% filebench.time.file_system_outputs
4.01 ± 29% +4383.5% 180.01 ±203% perf-sched.sch_delay.max.ms.[unknown].[unknown].[unknown].[unknown].[unknown]
4.01 ± 29% +4383.5% 180.01 ±203% perf-sched.total_sch_delay.max.ms
179.61 ± 6% -78.9% 37.91 ± 10% perf-sched.total_wait_and_delay.average.ms
7539 ± 6% +412.6% 38652 ± 9% perf-sched.total_wait_and_delay.count.ms
4983 -25.5% 3713 ± 13% perf-sched.total_wait_and_delay.max.ms
179.60 ± 6% -78.9% 37.89 ± 10% perf-sched.total_wait_time.average.ms
4983 -25.5% 3713 ± 13% perf-sched.total_wait_time.max.ms
179.61 ± 6% -78.9% 37.91 ± 10% perf-sched.wait_and_delay.avg.ms.[unknown].[unknown].[unknown].[unknown].[unknown]
7539 ± 6% +412.6% 38652 ± 9% perf-sched.wait_and_delay.count.[unknown].[unknown].[unknown].[unknown].[unknown]
4983 -25.5% 3713 ± 13% perf-sched.wait_and_delay.max.ms.[unknown].[unknown].[unknown].[unknown].[unknown]
179.60 ± 6% -78.9% 37.89 ± 10% perf-sched.wait_time.avg.ms.[unknown].[unknown].[unknown].[unknown].[unknown]
4983 -25.5% 3713 ± 13% perf-sched.wait_time.max.ms.[unknown].[unknown].[unknown].[unknown].[unknown]
191802 +3.3% 198131 proc-vmstat.nr_active_anon
3666016 ± 2% +33.5% 4895484 ± 2% proc-vmstat.nr_dirtied
324179 -21.8% 253508 proc-vmstat.nr_dirty
2228424 +1.9% 2271558 proc-vmstat.nr_file_pages
1283451 +2.9% 1320253 proc-vmstat.nr_inactive_file
27774 +22.7% 34080 ± 2% proc-vmstat.nr_shmem
35203 +1.7% 35786 proc-vmstat.nr_slab_reclaimable
97029 +2.5% 99413 proc-vmstat.nr_slab_unreclaimable
3628151 ± 2% +33.4% 4838878 ± 2% proc-vmstat.nr_written
191802 +3.3% 198131 proc-vmstat.nr_zone_active_anon
1283451 +2.9% 1320253 proc-vmstat.nr_zone_inactive_file
325032 -21.8% 254299 proc-vmstat.nr_zone_write_pending
2438711 +4.5% 2548843 proc-vmstat.numa_hit
2140583 +5.2% 2250864 proc-vmstat.numa_local
2587325 +5.2% 2722312 proc-vmstat.pgalloc_normal
2441172 +1.9% 2488658 proc-vmstat.pgfree
14693823 ± 2% +34.6% 19777902 ± 2% proc-vmstat.pgpgout
5.99 -2.4% 5.84 perf-stat.i.MPKI
7.594e+08 +12.2% 8.523e+08 perf-stat.i.branch-instructions
7.74 ± 2% +0.6 8.37 ± 3% perf-stat.i.cache-miss-rate%
12470451 +11.0% 13837828 perf-stat.i.cache-misses
1.627e+08 +2.6% 1.67e+08 perf-stat.i.cache-references
17709 ± 3% +42.7% 25268 ± 3% perf-stat.i.context-switches
1.189e+10 +3.9% 1.236e+10 perf-stat.i.cpu-cycles
3.777e+09 +14.4% 4.323e+09 perf-stat.i.instructions
0.28 +7.5% 0.30 perf-stat.i.ipc
5.53 -0.5 5.00 perf-stat.overall.branch-miss-rate%
7.66 ± 2% +0.6 8.28 ± 2% perf-stat.overall.cache-miss-rate%
3.15 ± 2% -9.2% 2.86 perf-stat.overall.cpi
954.54 ± 3% -6.3% 894.29 ± 3% perf-stat.overall.cycles-between-cache-misses
0.32 ± 2% +10.1% 0.35 perf-stat.overall.ipc
7.538e+08 +12.2% 8.459e+08 perf-stat.ps.branch-instructions
12385908 +10.9% 13741541 perf-stat.ps.cache-misses
1.618e+08 +2.6% 1.66e+08 perf-stat.ps.cache-references
17574 ± 3% +42.6% 25062 ± 3% perf-stat.ps.context-switches
1.182e+10 +3.9% 1.228e+10 perf-stat.ps.cpu-cycles
3.749e+09 +14.4% 4.29e+09 perf-stat.ps.instructions
6.365e+11 ± 2% +15.1% 7.326e+11 perf-stat.total.instructions
Disclaimer:
Results have been estimated based on internal Intel analysis and are provided
for informational purposes only. Any difference in system hardware or software
design or configuration may affect actual performance.
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki
reply other threads:[~2025-09-25 7:24 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
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=202509251432.59b331b7-lkp@intel.com \
--to=oliver.sang@intel.com \
--cc=akpm@linux-foundation.org \
--cc=boris@bur.io \
--cc=hannes@cmpxchg.org \
--cc=linux-btrfs@vger.kernel.org \
--cc=lkp@intel.com \
--cc=mhocko@kernel.org \
--cc=muchun.song@linux.dev \
--cc=oe-lkp@lists.linux.dev \
--cc=roman.gushchin@linux.dev \
--cc=shakeel.butt@linux.dev \
--cc=willy@infradead.org \
--cc=wqu@suse.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).