linux-kernel - [linus:master] [jbd2] 6a3afb6ac6: fileio.latency_95th

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-next>] [day] [month] [year] [list]

Message-ID: <202401021525.a27b9444-oliver.sang@intel.com>
Date: Tue, 2 Jan 2024 15:31:00 +0800
From: kernel test robot <oliver.sang@...el.com>
To: Zhang Yi <yi.zhang@...wei.com>
CC: <oe-lkp@...ts.linux.dev>, <lkp@...el.com>, <linux-kernel@...r.kernel.org>,
	Theodore Ts'o <tytso@....edu>, Jan Kara <jack@...e.cz>,
	<linux-ext4@...r.kernel.org>, <ying.huang@...el.com>, <feng.tang@...el.com>,
	<fengwei.yin@...el.com>, <oliver.sang@...el.com>
Subject: [linus:master] [jbd2]  6a3afb6ac6:  fileio.latency_95th_ms 92.5%
 regression



Hello,

kernel test robot noticed a 92.5% regression of fileio.latency_95th_ms on:


commit: 6a3afb6ac6dfab158ebdd4b87941178f58c8939f ("jbd2: increase the journal IO's priority")
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master

testcase: fileio
test machine: 128 threads 2 sockets Intel(R) Xeon(R) Platinum 8358 CPU @ 2.60GHz (Ice Lake) with 128G memory
parameters:

	period: 600s
	nr_threads: 100%
	disk: 1HDD
	fs: ext4
	size: 64G
	filenum: 1024f
	rwmode: seqwr
	iomode: sync
	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@...el.com>
| Closes: https://lore.kernel.org/oe-lkp/202401021525.a27b9444-oliver.sang@intel.com


Details are as below:
-------------------------------------------------------------------------------------------------->


The kernel config and materials to reproduce are available at:
https://download.01.org/0day-ci/archive/20240102/202401021525.a27b9444-oliver.sang@intel.com

=========================================================================================
compiler/cpufreq_governor/disk/filenum/fs/iomode/kconfig/nr_threads/period/rootfs/rwmode/size/tbox_group/testcase:
  gcc-12/performance/1HDD/1024f/ext4/sync/x86_64-rhel-8.3/100%/600s/debian-11.1-x86_64-20220510.cgz/seqwr/64G/lkp-icl-2sp5/fileio

commit: 
  8555922721 ("jbd2: correct the printing of write_flags in jbd2_write_superblock()")
  6a3afb6ac6 ("jbd2: increase the journal IO's priority")

85559227211020b2 6a3afb6ac6dfab158ebdd4b8794 
---------------- --------------------------- 
         %stddev     %change         %stddev
             \          |                \  
     37.99 ±  9%     +92.5%      73.13        fileio.latency_95th_ms
     19872 ± 16%     -24.1%      15078 ± 21%  numa-meminfo.node1.Active(file)
     24.74 ±  6%     +97.3%      48.81 ±  2%  perf-sched.wait_time.avg.ms.kjournald2.kthread.ret_from_fork.ret_from_fork_asm
   8157448            -5.7%    7691858 ±  2%  proc-vmstat.pgpgout
     13464            -5.7%      12700 ±  2%  vmstat.io.bo
      4968 ± 16%     -24.1%       3768 ± 21%  numa-vmstat.node1.nr_active_file
      4968 ± 16%     -24.1%       3768 ± 21%  numa-vmstat.node1.nr_zone_active_file
      1413            +2.8%       1452 ±  2%  perf-stat.i.cycles-between-cache-misses
      1.59            -2.9%       1.54        perf-stat.overall.MPKI
      1368            +2.5%       1402        perf-stat.overall.cycles-between-cache-misses
    161.13 ±  9%     +17.4%     189.23 ± 10%  sched_debug.cpu.curr->pid.avg
     25531 ±  6%     -12.4%      22376 ±  8%  sched_debug.cpu.nr_switches.stddev
    -93.66           +38.8%    -130.00        sched_debug.cpu.nr_uninterruptible.min




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