Greeting, FYI, we noticed a -36.4% regression of stress-ng.loop.ops_per_sec due to commit: commit: 34db6459c6ff08d993fa1b9f0ef75aca2b2017ee ("watchdog: iTCO: Drop vendor support") https://git.kernel.org/cgit/linux/kernel/git/groeck/linux-staging.git watchdog-next in testcase: stress-ng on test machine: 96 threads 2 sockets Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 512G memory with following parameters: nr_threads: 100% disk: 1HDD testtime: 60s class: device test: loop cpufreq_governor: performance ucode: 0x5003006 If you fix the issue, kindly add following tag Reported-by: kernel test robot <oliver.sang(a)intel.com&gt; Details are as below: --------------------------------------------------------------------------------------------------> To reproduce: git clone https://github.com/intel/lkp-tests.git cd lkp-tests sudo bin/lkp install job.yaml # job file is attached in this email bin/lkp split-job --compatible job.yaml # generate the yaml file for lkp run sudo bin/lkp run generated-yaml-file # if come across any failure that blocks the test, # please remove ~/.lkp and /lkp dir to run from a clean state. ========================================================================================= class/compiler/cpufreq_governor/disk/kconfig/nr_threads/rootfs/tbox_group/test/testcase/testtime/ucode: device/gcc-9/performance/1HDD/x86_64-rhel-8.3/100%/debian-10.4-x86_64-20200603.cgz/lkp-csl-2sp7/loop/stress-ng/60s/0x5003006 commit: 9545ed1a62 ("watchdog: iTCO_wdt: No need to stop the timer in probe") 34db6459c6 ("watchdog: iTCO: Drop vendor support") 9545ed1a6217fef3 34db6459c6ff08d993fa1b9f0ef ---------------- --------------------------- fail:runs %reproduction fail:runs | | | :10 100% 10:10 kmsg.iTCO_wdt_iTCO_wdt:failed_to_reset_NO_REBOOT_flag,reboot_disabled_by_hardware/BIOS %stddev %change %stddev \ | \ 3642 -34.7% 2380 ± 5% stress-ng.loop.ops 59.11 -36.4% 37.60 ± 4% stress-ng.loop.ops_per_sec 5478 ± 2% -23.9% 4169 ± 5% stress-ng.time.involuntary_context_switches 206.80 ± 4% -43.2% 117.40 ± 19% stress-ng.time.percent_of_cpu_this_job_got 134.28 ± 5% -41.0% 79.29 ± 20% stress-ng.time.system_time 236439 ± 8% -28.0% 170186 ± 11% stress-ng.time.voluntary_context_switches 0.43 ± 3% -0.1 0.31 ± 7% mpstat.cpu.all.usr% 3841 ± 3% -28.7% 2737 ± 9% vmstat.io.bi 22294 ± 3% -27.5% 16156 ± 5% vmstat.system.cs 32034 ± 3% -25.9% 23739 ± 10% softirqs.BLOCK 269102 ± 6% -16.7% 224266 ± 5% softirqs.RCU 31077 ± 3% -14.8% 26463 ± 7% softirqs.TIMER 718284 -12.6% 627767 ± 2% proc-vmstat.numa_hit 627378 -14.4% 536904 ± 2% proc-vmstat.numa_local 27597 ± 2% -23.8% 21038 ± 6% proc-vmstat.pgactivate 762921 -13.0% 664122 ± 2% proc-vmstat.pgalloc_normal 631716 -16.4% 528351 ± 3% proc-vmstat.pgfree 260814 ± 3% -25.9% 193161 ± 11% proc-vmstat.pgpgin 32689 ± 4% -24.2% 24771 ± 10% proc-vmstat.unevictable_pgs_culled 0.00 ± 13% -44.4% 0.00 perf-sched.sch_delay.avg.ms.worker_thread.kthread.ret_from_fork 10.33 ± 25% +1109.1% 124.91 ±156% perf-sched.total_wait_and_delay.max.ms 9.66 ± 26% +912.2% 97.80 ±148% perf-sched.total_wait_time.max.ms 22.10 ± 21% +328.5% 94.70 ±139% perf-sched.wait_and_delay.count.do_task_dead.do_exit.do_group_exit.__x64_sys_exit_group.do_syscall_64 18.80 ± 40% +201.6% 56.70 ± 20% perf-sched.wait_and_delay.count.do_wait.kernel_wait4.__do_sys_wait4.do_syscall_64 19.50 ± 20% +384.1% 94.40 ±149% perf-sched.wait_and_delay.count.worker_thread.kthread.ret_from_fork 9.29 ± 28% +1244.9% 124.91 ±156% perf-sched.wait_and_delay.max.ms.smpboot_thread_fn.kthread.ret_from_fork 2.17 ± 31% +53.1% 3.33 ± 17% perf-sched.wait_time.avg.ms.schedule_timeout.rcu_gp_fqs_loop.rcu_gp_kthread.kthread 9.28 ± 28% +953.5% 97.80 ±148% perf-sched.wait_time.max.ms.smpboot_thread_fn.kthread.ret_from_fork 2406 ± 6% +32.4% 3186 ± 20% perf-stat.i.cycles-between-cache-misses 2.52 ± 6% +14.4% 2.89 ± 6% perf-stat.overall.cpi 2296 ± 5% +17.7% 2703 ± 7% perf-stat.overall.cycles-between-cache-misses 72.20 +1.3 73.52 perf-stat.overall.node-load-miss-rate% 9.606e+08 ± 3% -22.2% 7.475e+08 ± 7% perf-stat.ps.branch-instructions 4806075 ± 7% -23.2% 3689732 ± 10% perf-stat.ps.cache-misses 22083 ± 3% -28.8% 15728 ± 6% perf-stat.ps.context-switches 432.07 ± 3% -28.0% 311.23 ± 9% perf-stat.ps.cpu-migrations 1.055e+09 ± 2% -21.4% 8.299e+08 ± 6% perf-stat.ps.dTLB-loads 4.494e+08 ± 2% -27.6% 3.254e+08 ± 6% perf-stat.ps.dTLB-stores 1266757 ± 4% -22.6% 980124 ± 7% perf-stat.ps.iTLB-load-misses 4.366e+09 ± 2% -21.2% 3.442e+09 ± 6% perf-stat.ps.instructions 4190 ± 2% -9.3% 3799 ± 6% perf-stat.ps.minor-faults 1056859 ± 2% -24.8% 795272 ± 4% perf-stat.ps.node-load-misses 406905 -29.7% 286074 ± 3% perf-stat.ps.node-loads 772814 -23.9% 588285 ± 3% perf-stat.ps.node-store-misses 405848 ± 2% -28.5% 290312 ± 2% perf-stat.ps.node-stores 4287 ± 2% -9.7% 3872 ± 6% perf-stat.ps.page-faults 2.834e+11 ± 2% -18.4% 2.312e+11 ± 8% perf-stat.total.instructions 49289 ± 2% -24.3% 37318 ± 5% slabinfo.filp.active_objs 1544 ± 2% -24.0% 1174 ± 5% slabinfo.filp.active_slabs 49432 ± 2% -23.9% 37595 ± 5% slabinfo.filp.num_objs 1544 ± 2% -24.0% 1174 ± 5% slabinfo.filp.num_slabs 7311 ± 2% +77.8% 13002 ± 3% slabinfo.kmalloc-1k.active_objs 256.60 ± 2% +59.2% 408.50 ± 3% slabinfo.kmalloc-1k.active_slabs 8225 ± 2% +59.1% 13084 ± 3% slabinfo.kmalloc-1k.num_objs 256.60 ± 2% +59.2% 408.50 ± 3% slabinfo.kmalloc-1k.num_slabs 4109 ± 6% -16.7% 3424 ± 6% slabinfo.kmalloc-cg-1k.active_objs 4261 ± 6% -19.6% 3425 ± 6% slabinfo.kmalloc-cg-1k.num_objs 1108 ± 11% -47.7% 579.30 ± 7% slabinfo.kmalloc-cg-2k.active_objs 1178 ± 10% -50.8% 580.20 ± 7% slabinfo.kmalloc-cg-2k.num_objs 17607 ± 12% -34.7% 11492 ± 5% slabinfo.kmalloc-rcl-64.active_objs 17612 ± 12% -34.7% 11492 ± 5% slabinfo.kmalloc-rcl-64.num_objs 4265 ± 11% -27.6% 3089 ± 9% slabinfo.kmalloc-rcl-96.active_objs 4265 ± 11% -27.6% 3089 ± 9% slabinfo.kmalloc-rcl-96.num_objs 6313 ± 7% +62.7% 10273 ± 3% slabinfo.skbuff_head_cache.active_objs 200.60 ± 7% +60.0% 321.00 ± 3% slabinfo.skbuff_head_cache.active_slabs 6432 ± 7% +60.0% 10290 ± 3% slabinfo.skbuff_head_cache.num_objs 200.60 ± 7% +60.0% 321.00 ± 3% slabinfo.skbuff_head_cache.num_slabs 134085 ± 3% +38.6% 185862 ± 5% interrupts.CAL:Function_call_interrupts 1538 ± 24% +48.9% 2290 ± 10% interrupts.CPU0.CAL:Function_call_interrupts 1360 ± 11% +38.5% 1884 ± 10% interrupts.CPU10.CAL:Function_call_interrupts 1411 ± 8% +41.6% 1998 ± 8% interrupts.CPU11.CAL:Function_call_interrupts 1420 ± 6% +35.4% 1923 ± 9% interrupts.CPU13.CAL:Function_call_interrupts 1352 ± 11% +39.9% 1891 ± 10% interrupts.CPU14.CAL:Function_call_interrupts 1354 ± 9% +37.1% 1856 ± 10% interrupts.CPU15.CAL:Function_call_interrupts 1397 ± 7% +46.6% 2048 ± 10% interrupts.CPU16.CAL:Function_call_interrupts 1392 ± 7% +42.6% 1985 ± 7% interrupts.CPU17.CAL:Function_call_interrupts 1307 ± 11% +50.5% 1967 ± 6% interrupts.CPU18.CAL:Function_call_interrupts 1366 ± 4% +41.6% 1934 ± 6% interrupts.CPU19.CAL:Function_call_interrupts 1420 ± 10% +36.0% 1930 ± 11% interrupts.CPU20.CAL:Function_call_interrupts 1388 ± 6% +34.8% 1870 ± 6% interrupts.CPU21.CAL:Function_call_interrupts 1358 ± 6% +37.4% 1866 ± 7% interrupts.CPU23.CAL:Function_call_interrupts 1312 ± 8% +46.1% 1916 ± 6% interrupts.CPU24.CAL:Function_call_interrupts 1311 ± 9% +57.8% 2069 ± 17% interrupts.CPU25.CAL:Function_call_interrupts 1330 ± 5% +47.6% 1964 ± 8% interrupts.CPU26.CAL:Function_call_interrupts 1340 ± 9% +41.7% 1899 ± 8% interrupts.CPU27.CAL:Function_call_interrupts 1469 ± 10% +32.9% 1952 ± 4% interrupts.CPU28.CAL:Function_call_interrupts 1364 ± 5% +42.9% 1950 ± 9% interrupts.CPU29.CAL:Function_call_interrupts 1451 ± 9% +29.6% 1881 ± 6% interrupts.CPU32.CAL:Function_call_interrupts 1381 ± 6% +36.9% 1890 ± 6% interrupts.CPU33.CAL:Function_call_interrupts 1310 ± 5% +43.4% 1878 ± 5% interrupts.CPU34.CAL:Function_call_interrupts 1397 ± 9% +38.4% 1933 ± 6% interrupts.CPU35.CAL:Function_call_interrupts 1317 ± 7% +49.4% 1968 ± 6% interrupts.CPU36.CAL:Function_call_interrupts 1380 ± 8% +38.4% 1911 ± 8% interrupts.CPU37.CAL:Function_call_interrupts 1298 ± 8% +47.5% 1915 ± 6% interrupts.CPU38.CAL:Function_call_interrupts 1347 ± 8% +42.5% 1920 ± 4% interrupts.CPU39.CAL:Function_call_interrupts 1367 ± 7% +47.6% 2017 ± 9% interrupts.CPU4.CAL:Function_call_interrupts 1380 ± 10% +39.1% 1921 ± 7% interrupts.CPU40.CAL:Function_call_interrupts 1366 ± 6% +38.7% 1895 ± 6% interrupts.CPU41.CAL:Function_call_interrupts 1390 ± 5% +37.1% 1906 ± 8% interrupts.CPU42.CAL:Function_call_interrupts 1344 ± 12% +42.6% 1917 ± 7% interrupts.CPU43.CAL:Function_call_interrupts 1349 ± 10% +41.1% 1903 ± 8% interrupts.CPU44.CAL:Function_call_interrupts 1376 ± 8% +35.1% 1860 ± 9% interrupts.CPU45.CAL:Function_call_interrupts 1368 ± 9% +39.4% 1906 ± 5% interrupts.CPU46.CAL:Function_call_interrupts 1429 ± 10% +38.1% 1974 ± 8% interrupts.CPU47.CAL:Function_call_interrupts 1471 ± 10% +28.1% 1883 ± 9% interrupts.CPU48.CAL:Function_call_interrupts 1403 ± 8% +35.6% 1902 ± 10% interrupts.CPU49.CAL:Function_call_interrupts 1376 ± 10% +39.8% 1923 ± 9% interrupts.CPU50.CAL:Function_call_interrupts 1463 ± 12% +33.1% 1948 ± 11% interrupts.CPU51.CAL:Function_call_interrupts 1446 ± 14% +28.0% 1851 ± 6% interrupts.CPU52.CAL:Function_call_interrupts 1311 ± 9% +54.0% 2020 ± 11% interrupts.CPU53.CAL:Function_call_interrupts 1373 ± 8% +40.2% 1925 ± 8% interrupts.CPU54.CAL:Function_call_interrupts 1373 ± 9% +42.1% 1950 ± 8% interrupts.CPU55.CAL:Function_call_interrupts 1313 ± 9% +43.6% 1885 ± 6% interrupts.CPU56.CAL:Function_call_interrupts 1370 ± 8% +40.3% 1922 ± 9% interrupts.CPU57.CAL:Function_call_interrupts 1361 ± 6% +39.5% 1898 ± 8% interrupts.CPU58.CAL:Function_call_interrupts 1380 ± 8% +39.2% 1921 ± 9% interrupts.CPU59.CAL:Function_call_interrupts 1440 ± 11% +48.6% 2141 ± 21% interrupts.CPU6.CAL:Function_call_interrupts 1365 ± 11% +41.0% 1924 ± 7% interrupts.CPU60.CAL:Function_call_interrupts 1394 ± 8% +41.1% 1968 ± 9% interrupts.CPU62.CAL:Function_call_interrupts 1388 ± 8% +39.7% 1939 ± 5% interrupts.CPU63.CAL:Function_call_interrupts 1400 ± 10% +36.9% 1917 ± 8% interrupts.CPU64.CAL:Function_call_interrupts 1432 ± 9% +40.4% 2010 ± 12% interrupts.CPU66.CAL:Function_call_interrupts 1392 ± 7% +39.0% 1936 ± 7% interrupts.CPU67.CAL:Function_call_interrupts 1413 ± 8% +37.3% 1940 ± 8% interrupts.CPU68.CAL:Function_call_interrupts 1420 ± 11% +45.7% 2069 ± 11% interrupts.CPU69.CAL:Function_call_interrupts 1397 ± 7% +49.3% 2086 ± 13% interrupts.CPU7.CAL:Function_call_interrupts 1396 ± 10% +39.4% 1947 ± 9% interrupts.CPU71.CAL:Function_call_interrupts 1387 ± 6% +35.8% 1883 ± 5% interrupts.CPU72.CAL:Function_call_interrupts 1373 ± 9% +34.2% 1843 ± 7% interrupts.CPU73.CAL:Function_call_interrupts 1390 ± 9% +38.7% 1928 ± 7% interrupts.CPU74.CAL:Function_call_interrupts 1368 ± 7% +43.0% 1957 ± 11% interrupts.CPU75.CAL:Function_call_interrupts 1361 ± 8% +39.7% 1902 ± 6% interrupts.CPU76.CAL:Function_call_interrupts 1263 ± 12% +52.0% 1919 ± 10% interrupts.CPU78.CAL:Function_call_interrupts 1288 ± 13% +49.5% 1926 ± 9% interrupts.CPU79.CAL:Function_call_interrupts 1474 ± 12% +32.8% 1958 ± 9% interrupts.CPU8.CAL:Function_call_interrupts 1425 ± 6% +34.2% 1912 ± 8% interrupts.CPU80.CAL:Function_call_interrupts 1454 ± 7% +34.1% 1950 ± 7% interrupts.CPU81.CAL:Function_call_interrupts 1344 ± 5% +42.8% 1921 ± 10% interrupts.CPU82.CAL:Function_call_interrupts 1375 ± 8% +45.9% 2007 ± 6% interrupts.CPU83.CAL:Function_call_interrupts 1442 ± 5% +41.4% 2039 ± 9% interrupts.CPU84.CAL:Function_call_interrupts 1374 ± 9% +40.9% 1937 ± 9% interrupts.CPU85.CAL:Function_call_interrupts 1393 ± 11% +38.8% 1934 ± 7% interrupts.CPU86.CAL:Function_call_interrupts 1391 ± 10% +36.2% 1894 ± 6% interrupts.CPU87.CAL:Function_call_interrupts 1303 ± 5% +48.6% 1937 ± 4% interrupts.CPU89.CAL:Function_call_interrupts 1437 ± 9% +37.7% 1979 ± 6% interrupts.CPU9.CAL:Function_call_interrupts 1344 ± 7% +42.9% 1922 ± 8% interrupts.CPU90.CAL:Function_call_interrupts 1385 ± 10% +45.4% 2014 ± 8% interrupts.CPU91.CAL:Function_call_interrupts 1296 ± 13% +43.7% 1861 ± 6% interrupts.CPU92.CAL:Function_call_interrupts 1380 ± 10% +37.8% 1903 ± 11% interrupts.CPU93.CAL:Function_call_interrupts 1354 ± 7% +40.6% 1905 ± 4% interrupts.CPU94.CAL:Function_call_interrupts 42.50 ± 7% -24.6 17.87 ± 39% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.ioctl 42.50 ± 7% -24.6 17.87 ± 39% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.ioctl 42.51 ± 7% -24.6 17.88 ± 39% perf-profile.calltrace.cycles-pp.ioctl 42.50 ± 7% -24.6 17.87 ± 39% perf-profile.calltrace.cycles-pp.__x64_sys_ioctl.do_syscall_64.entry_SYSCALL_64_after_hwframe.ioctl 19.49 ± 9% -18.9 0.55 ± 57% perf-profile.calltrace.cycles-pp.uart_console_write.serial8250_console_write.console_unlock.vprintk_emit._printk 15.38 ± 38% -13.7 1.67 ± 48% perf-profile.calltrace.cycles-pp.block_ioctl.__x64_sys_ioctl.do_syscall_64.entry_SYSCALL_64_after_hwframe.ioctl 15.38 ± 38% -13.7 1.67 ± 48% perf-profile.calltrace.cycles-pp.blkdev_ioctl.block_ioctl.__x64_sys_ioctl.do_syscall_64.entry_SYSCALL_64_after_hwframe 15.32 ± 38% -13.7 1.62 ± 48% perf-profile.calltrace.cycles-pp.lo_ioctl.blkdev_ioctl.block_ioctl.__x64_sys_ioctl.do_syscall_64 13.84 ± 43% -13.3 0.51 ± 72% perf-profile.calltrace.cycles-pp.console_unlock.vprintk_emit._printk.set_capacity_and_notify.cold.loop_set_size 13.83 ± 43% -13.3 0.51 ± 72% perf-profile.calltrace.cycles-pp.serial8250_console_write.console_unlock.vprintk_emit._printk.set_capacity_and_notify.cold 12.88 ± 43% -12.7 0.19 ±152% perf-profile.calltrace.cycles-pp.loop_configure.lo_ioctl.blkdev_ioctl.block_ioctl.__x64_sys_ioctl 12.82 ± 43% -12.7 0.17 ±152% perf-profile.calltrace.cycles-pp.vprintk_emit._printk.set_capacity_and_notify.cold.loop_set_size.loop_configure 12.82 ± 43% -12.7 0.17 ±152% perf-profile.calltrace.cycles-pp._printk.set_capacity_and_notify.cold.loop_set_size.loop_configure.lo_ioctl 12.82 ± 43% -12.7 0.17 ±152% perf-profile.calltrace.cycles-pp.loop_set_size.loop_configure.lo_ioctl.blkdev_ioctl.block_ioctl 12.82 ± 43% -12.7 0.17 ±152% perf-profile.calltrace.cycles-pp.set_capacity_and_notify.cold.loop_set_size.loop_configure.lo_ioctl.blkdev_ioctl 11.60 ± 13% -4.6 7.02 ± 40% perf-profile.calltrace.cycles-pp.mntput_no_expire.simple_recursive_removal.debugfs_remove.blk_mq_debugfs_unregister_hctx.blk_mq_exit_queue 10.63 ± 14% -4.3 6.30 ± 40% perf-profile.calltrace.cycles-pp._raw_spin_lock.mntput_no_expire.simple_recursive_removal.debugfs_remove.blk_mq_debugfs_unregister_hctx 10.50 ± 14% -4.3 6.21 ± 40% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock.mntput_no_expire.simple_recursive_removal.debugfs_remove 2.58 ± 42% -2.2 0.42 ±100% perf-profile.calltrace.cycles-pp.blkdev_open.do_dentry_open.do_open.path_openat.do_filp_open 2.58 ± 42% -2.2 0.42 ±100% perf-profile.calltrace.cycles-pp.blkdev_get_by_dev.blkdev_open.do_dentry_open.do_open.path_openat 0.00 +4.8 4.76 ± 37% perf-profile.calltrace.cycles-pp.osq_lock.__mutex_lock.misc_open.chrdev_open.do_dentry_open 0.00 +7.4 7.44 ± 85% perf-profile.calltrace.cycles-pp.mutex_spin_on_owner.__mutex_lock.misc_open.chrdev_open.do_dentry_open 0.00 +12.2 12.20 ± 54% perf-profile.calltrace.cycles-pp.__mutex_lock.misc_open.chrdev_open.do_dentry_open.do_open 0.00 +17.6 17.65 ± 24% perf-profile.calltrace.cycles-pp.uart_console_write.serial8250_console_write.console_unlock.vprintk_emit.dev_vprintk_emit 0.00 +18.3 18.30 ± 24% perf-profile.calltrace.cycles-pp.serial8250_console_write.console_unlock.vprintk_emit.dev_vprintk_emit.dev_printk_emit 0.00 +18.3 18.31 ± 24% perf-profile.calltrace.cycles-pp.console_unlock.vprintk_emit.dev_vprintk_emit.dev_printk_emit._dev_err 0.00 +19.2 19.19 ± 22% perf-profile.calltrace.cycles-pp.vprintk_emit.dev_vprintk_emit.dev_printk_emit._dev_err.iTCO_wdt_start 0.00 +19.2 19.19 ± 22% perf-profile.calltrace.cycles-pp._dev_err.iTCO_wdt_start.watchdog_start.watchdog_open.misc_open 0.00 +19.2 19.19 ± 22% perf-profile.calltrace.cycles-pp.dev_printk_emit._dev_err.iTCO_wdt_start.watchdog_start.watchdog_open 0.00 +19.2 19.19 ± 22% perf-profile.calltrace.cycles-pp.dev_vprintk_emit.dev_printk_emit._dev_err.iTCO_wdt_start.watchdog_start 0.00 +19.2 19.19 ± 22% perf-profile.calltrace.cycles-pp.watchdog_open.misc_open.chrdev_open.do_dentry_open.do_open 0.00 +19.2 19.19 ± 22% perf-profile.calltrace.cycles-pp.watchdog_start.watchdog_open.misc_open.chrdev_open.do_dentry_open 0.00 +19.2 19.19 ± 22% perf-profile.calltrace.cycles-pp.iTCO_wdt_start.watchdog_start.watchdog_open.misc_open.chrdev_open 3.86 ± 34% +28.6 32.48 ± 20% perf-profile.calltrace.cycles-pp.do_filp_open.do_sys_openat2.do_sys_open.do_syscall_64.entry_SYSCALL_64_after_hwframe 3.86 ± 34% +28.6 32.48 ± 20% perf-profile.calltrace.cycles-pp.path_openat.do_filp_open.do_sys_openat2.do_sys_open.do_syscall_64 3.28 ± 34% +29.2 32.52 ± 20% perf-profile.calltrace.cycles-pp.open64 3.27 ± 34% +29.2 32.51 ± 20% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.open64 3.27 ± 34% +29.2 32.51 ± 20% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.open64 3.25 ± 34% +29.2 32.50 ± 20% perf-profile.calltrace.cycles-pp.do_sys_open.do_syscall_64.entry_SYSCALL_64_after_hwframe.open64 3.24 ± 34% +29.3 32.50 ± 20% perf-profile.calltrace.cycles-pp.do_sys_openat2.do_sys_open.do_syscall_64.entry_SYSCALL_64_after_hwframe.open64 2.62 ± 41% +29.4 32.05 ± 21% perf-profile.calltrace.cycles-pp.do_open.path_openat.do_filp_open.do_sys_openat2.do_sys_open 2.60 ± 42% +29.4 32.03 ± 21% perf-profile.calltrace.cycles-pp.do_dentry_open.do_open.path_openat.do_filp_open.do_sys_openat2 0.00 +31.4 31.40 ± 22% perf-profile.calltrace.cycles-pp.chrdev_open.do_dentry_open.do_open.path_openat.do_filp_open 0.00 +31.4 31.40 ± 22% perf-profile.calltrace.cycles-pp.misc_open.chrdev_open.do_dentry_open.do_open.path_openat 42.51 ± 7% -24.6 17.92 ± 39% perf-profile.children.cycles-pp.ioctl 42.50 ± 7% -24.6 17.91 ± 39% perf-profile.children.cycles-pp.__x64_sys_ioctl 22.52 ± 10% -20.5 2.01 ± 36% perf-profile.children.cycles-pp._printk 15.38 ± 38% -13.7 1.67 ± 48% perf-profile.children.cycles-pp.block_ioctl 15.38 ± 38% -13.7 1.67 ± 48% perf-profile.children.cycles-pp.blkdev_ioctl 15.32 ± 38% -13.7 1.62 ± 48% perf-profile.children.cycles-pp.lo_ioctl 15.02 ± 39% -13.7 1.32 ± 51% perf-profile.children.cycles-pp.loop_set_size 15.02 ± 39% -13.7 1.32 ± 51% perf-profile.children.cycles-pp.set_capacity_and_notify.cold 12.88 ± 43% -12.5 0.36 ± 65% perf-profile.children.cycles-pp.loop_configure 7.25 ± 87% -6.8 0.40 ± 69% perf-profile.children.cycles-pp.loop_control_ioctl.cold 11.88 ± 14% -4.7 7.21 ± 39% perf-profile.children.cycles-pp.mntput_no_expire 2.58 ± 42% -2.0 0.61 ± 43% perf-profile.children.cycles-pp.blkdev_open 2.58 ± 42% -2.0 0.61 ± 43% perf-profile.children.cycles-pp.blkdev_get_by_dev 1.54 ± 53% -1.2 0.37 ± 37% perf-profile.children.cycles-pp.blkdev_get_whole 1.54 ± 53% -1.2 0.37 ± 37% perf-profile.children.cycles-pp.lo_open 1.22 ± 32% -1.1 0.10 ± 78% perf-profile.children.cycles-pp.unit_file_find_dropin_paths 1.13 ± 28% -0.9 0.25 ± 37% perf-profile.children.cycles-pp.openat64 1.43 ± 21% -0.8 0.64 ± 36% perf-profile.children.cycles-pp.path_lookupat 0.67 ± 24% -0.4 0.30 ± 39% perf-profile.children.cycles-pp.path_init 0.75 ± 15% -0.3 0.43 ± 38% perf-profile.children.cycles-pp.walk_component 0.47 ± 23% -0.3 0.18 ± 38% perf-profile.children.cycles-pp.__legitimize_mnt 0.33 ± 24% -0.2 0.11 ± 37% perf-profile.children.cycles-pp.try_to_unlazy 0.33 ± 24% -0.2 0.11 ± 38% perf-profile.children.cycles-pp.__legitimize_path 0.30 ± 31% -0.2 0.10 ± 48% perf-profile.children.cycles-pp.alloc_empty_file 0.36 ± 24% -0.2 0.17 ± 43% perf-profile.children.cycles-pp.__close 0.29 ± 31% -0.2 0.10 ± 48% perf-profile.children.cycles-pp.__alloc_file 0.45 ± 16% -0.2 0.28 ± 37% perf-profile.children.cycles-pp.kmem_cache_alloc 0.35 ± 25% -0.2 0.18 ± 44% perf-profile.children.cycles-pp.syscall_exit_to_user_mode 0.50 ± 18% -0.2 0.33 ± 41% perf-profile.children.cycles-pp.rcu_do_batch 0.40 ± 18% -0.2 0.24 ± 39% perf-profile.children.cycles-pp.step_into 0.21 ± 26% -0.2 0.05 ± 36% perf-profile.children.cycles-pp.complete_walk 0.35 ± 17% -0.1 0.22 ± 42% perf-profile.children.cycles-pp.kmem_cache_free 0.29 ± 19% -0.1 0.17 ± 43% perf-profile.children.cycles-pp.__traverse_mounts 0.28 ± 19% -0.1 0.16 ± 43% perf-profile.children.cycles-pp.lookup_mnt 0.28 ± 12% -0.1 0.17 ± 40% perf-profile.children.cycles-pp.lookup_fast 0.17 ± 20% -0.1 0.06 ± 39% perf-profile.children.cycles-pp.__fxstat64 0.17 ± 23% -0.1 0.09 ± 52% perf-profile.children.cycles-pp.legitimize_mnt 0.13 ± 18% -0.1 0.04 ± 82% perf-profile.children.cycles-pp.____sys_sendmsg 0.13 ± 19% -0.1 0.05 ± 68% perf-profile.children.cycles-pp.__sys_sendmsg 0.12 ± 22% -0.1 0.04 ± 67% perf-profile.children.cycles-pp.__do_sys_newfstat 0.13 ± 20% -0.1 0.05 ± 68% perf-profile.children.cycles-pp.___sys_sendmsg 0.13 ± 14% -0.1 0.07 ± 43% perf-profile.children.cycles-pp.__wake_up_common_lock 0.11 ± 20% -0.1 0.05 ± 52% perf-profile.children.cycles-pp.__wake_up_common 0.09 ± 19% -0.1 0.04 ± 65% perf-profile.children.cycles-pp.vfs_fstat 0.08 ± 16% -0.0 0.04 ±102% perf-profile.children.cycles-pp.obj_cgroup_uncharge_pages 2.86 ± 12% +5.0 7.82 ± 28% perf-profile.children.cycles-pp.osq_lock 2.93 ± 39% +10.2 13.12 ± 49% perf-profile.children.cycles-pp.__mutex_lock 0.00 +19.2 19.19 ± 22% perf-profile.children.cycles-pp._dev_err 0.00 +19.2 19.19 ± 22% perf-profile.children.cycles-pp.dev_printk_emit 0.00 +19.2 19.19 ± 22% perf-profile.children.cycles-pp.dev_vprintk_emit 0.00 +19.2 19.19 ± 22% perf-profile.children.cycles-pp.watchdog_open 0.00 +19.2 19.19 ± 22% perf-profile.children.cycles-pp.watchdog_start 0.00 +19.2 19.19 ± 22% perf-profile.children.cycles-pp.iTCO_wdt_start 4.50 ± 29% +28.3 32.77 ± 20% perf-profile.children.cycles-pp.do_sys_open 4.50 ± 29% +28.3 32.77 ± 20% perf-profile.children.cycles-pp.do_sys_openat2 4.34 ± 29% +28.4 32.74 ± 20% perf-profile.children.cycles-pp.do_filp_open 4.33 ± 29% +28.4 32.73 ± 20% perf-profile.children.cycles-pp.path_openat 3.48 ± 33% +29.1 32.54 ± 20% perf-profile.children.cycles-pp.open64 2.63 ± 41% +29.4 32.05 ± 21% perf-profile.children.cycles-pp.do_open 2.62 ± 41% +29.4 32.04 ± 21% perf-profile.children.cycles-pp.do_dentry_open 0.00 +31.4 31.40 ± 22% perf-profile.children.cycles-pp.chrdev_open 0.00 +31.4 31.40 ± 22% perf-profile.children.cycles-pp.misc_open 0.60 ± 24% -0.3 0.28 ± 39% perf-profile.self.cycles-pp.path_init 0.13 ± 26% -0.1 0.06 ± 53% perf-profile.self.cycles-pp.kmem_cache_alloc 2.84 ± 12% +4.9 7.76 ± 28% perf-profile.self.cycles-pp.osq_lock stress-ng.loop.ops_per_sec 70 +----------------------------------------------------------------------+ | +. | 60 |-+ +.+ .++.+++.+ ++.++.+ .+ +.++. .++.+| |+.+ + + ++.++ + +.+ ++ ++ + + + ++ | 50 |-+ : : : : : : : :: :: : | | : : : : : : : :: :: : | 40 |-+ : :: : : :: : : : :O: O: : O | |O OO O :O:: :O O :O::O: :O:O: :O :O: O | 30 |-+ O: ::O: : :: : : : : : : : | | :: :: :: :: :: :: :: | 20 |-+ :: :: :: :: :: :: :: | | :: :: :: :: :: :: :: | 10 |-+ : : : : : : : | | : : : : : : : | 0 +----------------------------------------------------------------------+ [*] bisect-good sample [O] bisect-bad sample 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. --- 0DAY/LKP+ Test Infrastructure Open Source Technology Center https://lists.01.org/hyperkitty/list/lkp@lists.01.org Intel Corporation Thanks, Oliver Sang