Greeting, FYI, we noticed a -100.0% improvement of xfstests.xfs.004.pass due to commit: commit: 8bbb6aa20ae7032991a4738ceb26c3672c8f607b ("xfs: bump up reserved blocks in xfs_alloc_set_aside") https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git master in testcase: xfstests on test machine: 4 threads Intel(R) Core(TM) i5-2500K CPU @ 3.30GHz with 6G memory with following parameters: disk: 4HDD fs: xfs test: xfs-quick1 test-description: xfstests is a regression test suite for xfs and other files ystems. test-url: git://git.kernel.org/pub/scm/fs/xfs/xfstests-dev.git Details are as below: --------------------------------------------------------------------------------------------------> To reproduce: git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git cd lkp-tests bin/lkp install job.yaml # job file is attached in this email bin/lkp run job.yaml testcase/path_params/tbox_group/run: xfstests/4HDD-xfs-xfs-quick1/snb-drag ed40875dd4b4c7b5 8bbb6aa20ae7032991a4738ceb ---------------- -------------------------- %stddev change %stddev \ | \ 1 100% 2 xfstests.time.exit_status fail:runs %reproduction fail:runs | | | :4 100% 4:4 xfstests.xfs.004.fail 1 -100% 0 xfstests.xfs.004.pass :4 25% 1:4 kmsg.DHCP/BOOTP:Reply_not_for_us_on_eth#,op[#]xid[ca#c3] 2:4 -50% :4 kmsg.DHCP/BOOTP:Reply_not_for_us_on_eth#,op[#]xid[#] 1:4 -25% :4 kmsg.DHCP/BOOTP:Reply_not_for_us_on_eth#,op[#]xid[#da5] xfs/003 0s xfs/004 [failed, exit status 1] - output mismatch (see /lkp/benchmarks/xfstests/results//xfs/004.out.bad) --- tests/xfs/004.out 2016-11-10 09:18:29.000000000 +0800 +++ /lkp/benchmarks/xfstests/results//xfs/004.out.bad 2017-01-15 05:20:02.458741598 +0800 @@ -5,5 +5,13 @@ naming =VERN bsize=XXX log =LDEV bsize=XXX blocks=XXX realtime =RDEV extsz=XXX blocks=XXX, rtextents=XXX -Checking blocks column same as df: yes +Checking blocks column same as df: no (214637608960 != 214637559808) +Error: /dev/sda8: freesp mismatch: no (214637608960 != 214637559808) +xfs_db output ... ... (Run 'diff -u tests/xfs/004.out /lkp/benchmarks/xfstests/results//xfs/004.out.bad' to see the entire diff) xfs/005 2s 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. Thanks, Xiaolong