[PATCH v2] fs/dax: Fix pmd vs pte conflict detection

List overview All Threads
Download

newer

older

Request for backporting to 4.4 &...

✅ PASS: Test report for kernel...

Dan Williams

21 Oct 2019 21 Oct '19

4:29 p.m.

Users reported a v5.3 performance regression and inability to establish huge page mappings. A revised version of the ndctl "dax.sh" huge page unit test identifies commit 23c84eb78375 "dax: Fix missed wakeup with PMD faults" as the source.

Update get_unlocked_entry() to check for NULL entries before checking the entry order, otherwise NULL is misinterpreted as a present pte conflict. The 'order' check needs to happen before the locked check as an unlocked entry at the wrong order must fallback to lookup the correct order.

Reported-by: Jeff Smits jeff.smits@intel.com Reported-by: Doug Nelson doug.nelson@intel.com Cc: stable@vger.kernel.org Fixes: 23c84eb78375 ("dax: Fix missed wakeup with PMD faults") Reviewed-by: Jan Kara jack@suse.cz Cc: Jeff Moyer jmoyer@redhat.com Cc: Matthew Wilcox (Oracle) willy@infradead.org Signed-off-by: Dan Williams dan.j.williams@intel.com --- Changes in v2: - Update the changelog to reflect the user visible effects of the bug (Jeff)

fs/dax.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c index 6bf81f931de3..2cc43cd914eb 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -220,10 +220,11 @@ static void *get_unlocked_entry(struct xa_state *xas, unsigned int order)

for (;;) { entry = xas_find_conflict(xas); + if (!entry || WARN_ON_ONCE(!xa_is_value(entry))) + return entry; if (dax_entry_order(entry) < order) return XA_RETRY_ENTRY; - if (!entry || WARN_ON_ONCE(!xa_is_value(entry)) || - !dax_is_locked(entry)) + if (!dax_is_locked(entry)) return entry;

wq = dax_entry_waitqueue(xas, entry, &ewait.key);

Show replies by date

Johannes Thumshirn

22 Oct 22 Oct

7:27 a.m.

Looks good, Reviewed-by: Johannes Thumshirn jthumshirn@suse.de

-- Johannes Thumshirn SUSE Labs Filesystems jthumshirn@suse.de +49 911 74053 689 SUSE Software Solutions Germany GmbH Maxfeldstr. 5 90409 Nürnberg Germany (HRB 36809, AG Nürnberg) Geschäftsführer: Felix Imendörffer Key fingerprint = EC38 9CAB C2C4 F25D 8600 D0D0 0393 969D 2D76 0850

kernel test robot

27 Oct 27 Oct

5:17 a.m.

New subject: [fs/dax] a70e8083a9: fio.read_bw_MBps 523.2% improvement

Greeting,

FYI, we noticed a 523.2% improvement of fio.read_bw_MBps due to commit:

commit: a70e8083a91b17a7c77012f7746dbf29b5050e66 ("[PATCH v2] fs/dax: Fix pmd vs pte conflict detection") url: https://github.com/0day-ci/linux/commits/Dan-Williams/fs-dax-Fix-pmd-vs-pte-...

in testcase: fio-basic on test machine: 96 threads Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 256G memory with following parameters:

disk: 2pmem fs: ext4 mount_option: dax runtime: 200s nr_task: 50% time_based: tb rw: rw bs: 4k ioengine: mmap test_size: 200G ucode: 0x5000021 cpufreq_governor: performance

test-description: Fio is a tool that will spawn a number of threads or processes doing a particular type of I/O action as specified by the user. test-url: https://github.com/axboe/fio

In addition to that, the commit also has significant impact on the following tests:

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

To reproduce:

git clone https://github.com/intel/lkp-tests.git cd lkp-tests bin/lkp install job.yaml # job file is attached in this email bin/lkp run job.yaml

========================================================================================= bs/compiler/cpufreq_governor/disk/fs/ioengine/kconfig/mount_option/nr_task/rootfs/runtime/rw/tbox_group/test_size/testcase/time_based/ucode: 4k/gcc-7/performance/2pmem/ext4/mmap/x86_64-rhel-7.6/dax/50%/debian-x86_64-2019-05-14.cgz/200s/rw/lkp-csl-2sp6/200G/fio-basic/tb/0x5000021

commit: v5.4-rc4 a70e8083a9 ("fs/dax: Fix pmd vs pte conflict detection")

v5.4-rc4 a70e8083a91b17a7c77012f7746 ---------------- fail:runs | 1:5 %stddev \ 0.04 ±103% 0.40 ± 17% 42.23 ± 3% 0.04 ± 48% 0.03 ± 36% 26.56 ± 5% 6660 19072 19993 23475 7134 11158 ± 17% 1704992 227.61 227.61 4.724e+08 4224 8989 626.08 ± 2% 23802 6.821e+08 6662 23526 25779 32665 ± 6% 20398 9815 ± 15% 1705684 40917 ± 70% 41.15 2.87 ± 2% 56.36 40.80 2.85 ± 2% 56.00 2.00 2143726 1156106 ± 19% 1162440 ± 17% 6344 ±193% 916775 ± 23% 941710 ± 21% 498777 7644983 1178141 498777 681978 40679 1246 44.75 56.00 56.20 245.28 128.78 4275 ± 14% 142255 ± 5% 52355 ± 21% 1367388 ± 23% 1360094 ± 23% 150783 ± 7% 72319 ± 16% 738.20 ± 8% 1699 ± 8% 1699 ± 8% 760144 13576 760334 13576 560.40 ± 7% 209548 ± 21% 17189 ± 13% 3707244 ± 4% 572232 ± 5% 209548 ± 21% 308536 ± 16% 289299 ± 15% 3939263 ± 3% 606602 ± 7% 289299 ± 15% 373513 ± 13% 5108 64785 86.00 ± 13% 1028576 2059669 10368676 95519 84.00 ± 2% 96766 292164 124646 45797 5108 95519 84.00 ± 2% 2127714 2096428 3112 ± 7% 2268500 4.731e+08 2172870 666825 129.10 ± 4% 792591 343702 ± 3% 1.00 0.40 ± 2% 791828 343573 ± 3% 549.67 ± 4% 597408 365969 2.73 ± 4% 2.73 ± 4% 1.00 19380 ± 22% 14002 ± 23% 2363 ± 15% 6961 ± 23% 23.40 ± 3% 1191 ± 14% 51.70 ± 4% 441.41 30.50 ± 4% 193.20 ± 2% 0.00 24.20 ±183% 22.00 ±130% 162.60 ±113% 10.40 ±143% 4.40 ± 51% 84.00 ±180% 81.80 ±172% 2.40 ± 62% 3.20 ± 93% 2840 ± 12% 4.00 ± 54% +14525.0% 2.20 ± 66% 2.40 ± 97% 3.20 ± 66% 2.20 ±109% 0.00 11.60 ± 82% 6.20 ± 73% 9.20 ± 67% 13.00 ± 27% 7.60 ± 62% 14.80 ±141% 8.20 ± 56% 9.40 ± 63% 14.80 ± 83% 5.60 ± 96% 8.20 ± 64% 10.20 ± 50% 36.60 ± 50% 8.60 ±136% 3.60 ±132% 7.80 ± 98% 17.40 ± 80% 193.20 ± 2% 14.71 ± 3% 5.704e+09 0.45 ± 8% 23774744 ± 2% 54.74 2.382e+08 ± 3% 4.015e+08 ± 2% 4.39 1.195e+11 896.52 ± 7% 0.05 ± 12% 3096297 6.8e+09 0.24 ± 11% 7425754 ± 11% 2.807e+09 68.54 12855481 ± 3% 2.552e+10 2195 ± 3% 0.27 ± 4% 2077653 31404609 ± 27% 32711606 ± 20% 26979202 ± 24% 25469597 ± 22% 2077670 15.73 ± 2% 0.42 ± 2% 59.33 4.68 501.88 ± 2% 0.05 0.26 ± 11% 70.67 1988 ± 4% 0.21 8446 5.679e+09 23670395 ± 2% 2.372e+08 ± 3% 3.998e+08 ± 2% 1.189e+11 3082720 6.77e+09 7393213 ± 11% 2.795e+09 12799067 ± 3% 2.541e+10 2068549 31266968 ± 27% 32567992 ± 20% 26860938 ± 24% 25357836 ± 22% 2068565 5.762e+12 7535 ± 26% 6126 ± 2% 6381 ± 7% 6087 ± 5% 6287 ± 2% 7342 ± 23% 5947 ± 3% 6407 ± 11% 6614 ± 6% 7221 ± 7% 6926 ± 9% 6566 ± 4% 7679 ± 28% 6611 ± 3% 6726 ± 4% 6571 ± 4% 7565 ± 19% 8353 ± 19% 6097 ± 7% 5926 ± 7% 6096 ± 7% 5783 ± 10% 5998 ± 7% 10929 ± 12% 6860 ± 36% 5811 ± 7% 6107 ± 5% 6072 ± 6% 6014 ± 3% 6002 ± 4% 6323 ± 9% 5893 ± 2% 5894 ± 3% 6129 ± 3% 6155 ± 9% 6324 ± 11% 5909 ± 4% 6131 ± 7% 5907 ± 2% 6020 ± 7% 5859 ± 4% 5877 ± 5% 5826 ± 3% 7221 ± 27% 20592 ± 38% 6200 ± 8% 6992 ± 17% 5929 ± 6% 6678 ± 8% 6522 ± 12% 5935 ± 8% 5873 ± 8% 5938 ± 6% 5727 ± 8% 5878 ± 7% 5787 ± 6% 5925 ± 6% 6262 ± 4% 6107 ± 8% 6101 ± 13% 6414 ± 16% 5835 ± 7% 6121 ± 7% 6790 ± 29% 6139 ± 8% 6002 ± 5% 5766 ± 8% 5780 ± 7% 24983 ± 37% 6216 ± 8% 5838 ± 5% 6131 ± 4% 5992 ± 2% 6138 ± 5% 5888 ± 3% 5961 ± 4% 6367 ± 17% 6033 ± 7% 6364 ± 6% 5892 ± 4% 6732 ± 10% 5826 ± 3% 5906 ± 4% 6215 ± 10% 5892 ± 3% 5738 ± 7% 6017 ± 12% 5960 ± 5% 6085 ± 12% 5808 ± 6% 5887 ± 5% 5755 ± 7% 5865 ± 6% 5962 ± 5% 5914 ± 5% 5940 ± 9% 5715 ± 3% 5820 ± 4% 600723 ± 3% 1744186 ± 3% 66.51 ± 5% 66.47 ± 5% 66.41 ± 5% 66.15 ± 5% 66.02 ± 5% 57.80 ± 5% 55.85 ± 5% 55.26 ± 5% 46.70 ± 6% 46.68 ± 6% 43.98 ± 6% 41.96 ± 6% 41.55 ± 6% 19.15 ± 5% 19.17 ± 5% 17.32 ± 5% 16.42 ± 5% 16.26 ± 5% 0.00 0.00 0.36 ± 81% 0.36 ± 81% 0.37 ± 81% 0.37 ± 81% 0.37 ± 81% 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 30.84 ± 13% 30.84 ± 13% 30.98 ± 12% 30.92 ± 13% 30.92 ± 13% 30.92 ± 13% 31.29 ± 12% 66.53 ± 5% 66.42 ± 5% 66.47 ± 5% 66.16 ± 5% 66.03 ± 5% 65.85 ± 5% 61.30 ± 5% 58.37 ± 5% 57.80 ± 5% 57.80 ± 5% 56.37 ± 5% 55.28 ± 5% 46.70 ± 6% 19.17 ± 5% 2.76 ± 13% 2.67 ± 13% 2.24 ± 14% 1.71 ± 9% 1.32 ± 11% 1.21 ± 11% 1.73 ± 3% 1.70 ± 3% 1.71 ± 3% 1.07 ± 15% 0.79 ± 14% 0.77 ± 15% 0.55 ± 3% 0.27 ± 2% 0.20 ± 6% 0.13 ± 3% 0.10 ± 3% 0.13 ± 5% 0.13 ± 8% 0.11 ± 4% 0.12 ± 6% 0.08 ± 5% 0.16 ± 6% 0.07 ± 5% 0.05 ± 9% 0.01 ±200% 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.01 ±200% 0.01 ±200% 0.00 0.01 ±200% 0.01 ±200% 0.00 0.00 0.00 0.00 0.00 0.08 ± 19% 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.32 ± 17% 0.00 0.00 0.38 ± 18% 0.01 ±200% 0.00 0.00 0.00 0.02 ±122% 0.02 ±122% 0.05 0.02 ±123% 0.02 ±122% 0.02 ±122% 0.02 ±122% 0.02 ±122% 0.02 ±122% 0.02 ±122% 0.02 ±122% 0.10 ± 17% 0.03 ±123% 0.04 ± 51% 0.00 0.00 0.00 0.06 ± 59% 0.04 ± 84% 0.00 0.03 ± 82% 0.07 ± 32% 0.07 ± 32% 0.07 ± 32% 0.00 0.00 0.05 ± 84% 0.07 ± 15% 0.00 0.00 0.09 ± 17% 0.00 0.09 ± 21% 0.09 ± 21% 0.01 ±200% 0.16 ± 17% 0.16 ± 17% 0.37 ± 81% 0.19 ± 15% 0.00 0.06 ± 14% 0.24 ± 14% 0.07 ± 6% 0.08 ± 9% 0.06 ± 12% 0.45 ± 20% 0.00 0.53 ± 26% 0.58 ± 25% 0.27 ± 9% 0.16 ± 7% 0.26 ± 4% 0.00 0.09 ± 4% 30.98 ± 12% 30.92 ± 13% 31.21 ± 12% 31.21 ± 12% 31.29 ± 12% 31.29 ± 12% 31.29 ± 12% 54.97 ± 5% 1.38 ± 16% 1.70 ± 9% 1.18 ± 11% 1.19 ± 3% 1.09 ± 3% 0.73 ± 15% 0.27 ± 2% 0.15 ± 20% 0.20 ± 6% 0.10 ± 3% 0.08 0.04 ± 50% 0.00 0.00 0.00 0.00 0.00 0.00 0.01 ±200% 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.04 ± 50% 0.04 ± 51% 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.02 ±122% 0.00 0.07 ± 6% 0.08 ± 9% 0.06 ± 12% 0.27 ± 9% 0.15 ± 7% 0.25 ± 6% 0.00 0.09 ± 8% 30.98 ± 12% --------------------------- %reproduction fail:runs | | -19% 0:4 perf-profile.children.cycles-pp.error_entry %change %stddev | \ -0.0 0.01 fio.latency_100us% +0.7 1.09 ± 11% fio.latency_10us% -42.0 0.24 ± 30% fio.latency_20us% +58.8 58.84 ± 7% fio.latency_2us% +25.4 25.47 ± 21% fio.latency_4us% -26.3 0.24 ± 13% fio.latency_50us% +523.2% 41507 ± 4% fio.read_bw_MBps -86.6% 2560 ± 4% fio.read_clat_90%_us -85.8% 2840 ± 4% fio.read_clat_95%_us -79.6% 4784 ± 4% fio.read_clat_99%_us -73.5% 1892 ± 5% fio.read_clat_mean_us -84.4% 1738 ± 6% fio.read_clat_stddev +523.2% 10625819 ± 4% fio.read_iops -7.6% 210.23 fio.time.elapsed_time -7.6% 210.23 fio.time.elapsed_time.max -85.0% 70736715 ± 3% fio.time.minor_page_faults +8.3% 4573 fio.time.percent_of_cpu_this_job_got -96.8% 288.96 ± 4% fio.time.system_time +1389.9% 9327 fio.time.user_time -9.7% 21483 fio.time.voluntary_context_switches +523.1% 4.251e+09 ± 4% fio.workload +523.1% 41513 ± 4% fio.write_bw_MBps -90.9% 2150 ± 3% fio.write_clat_90%_us -90.5% 2448 ± 4% fio.write_clat_95%_us -83.9% 5248 ± 5% fio.write_clat_99%_us -92.1% 1612 ± 3% fio.write_clat_mean_us -76.4% 2315 ± 8% fio.write_clat_stddev +523.1% 10627503 ± 4% fio.write_iops -77.1% 9387 ± 57% cpuidle.POLL.usage -39.5 1.63 ± 4% mpstat.cpu.all.sys% +43.9 46.79 mpstat.cpu.all.usr% -7.7% 52.03 iostat.cpu.idle -96.0% 1.62 ± 4% iostat.cpu.system +1528.8% 46.35 iostat.cpu.user -7.1% 52.00 vmstat.cpu.id +2200.0% 46.00 vmstat.cpu.us -19.7% 1720555 vmstat.memory.cache -65.7% 396915 ± 49% numa-numastat.node0.local_node -64.5% 412613 ± 44% numa-numastat.node0.numa_hit +147.5% 15702 ± 98% numa-numastat.node0.other_node -55.2% 410953 ± 48% numa-numastat.node1.local_node -54.7% 426566 ± 43% numa-numastat.node1.numa_hit -80.2% 98859 meminfo.KReclaimable -18.7% 6215641 meminfo.Memused -87.3% 149626 ± 3% meminfo.PageTables -80.2% 98859 meminfo.SReclaimable -58.1% 285710 meminfo.Slab -23.8% 30984 meminfo.max_used_kB +10.7% 1379 turbostat.Avg_MHz +4.7 49.43 turbostat.Busy% +11.2% 62.25 turbostat.CoreTmp +10.3% 62.00 turbostat.PkgTmp +18.0% 289.40 turbostat.PkgWatt +45.3% 187.11 turbostat.RAMWatt +1135.7% 52830 ± 90% numa-vmstat.node0.nr_mapped -86.4% 19293 ± 49% numa-vmstat.node0.nr_page_table_pages -74.2% 13489 ± 13% numa-vmstat.node0.nr_slab_reclaimable -32.4% 924713 ± 22% numa-vmstat.node0.numa_hit -33.2% 908947 ± 22% numa-vmstat.node0.numa_local -88.0% 18133 ± 58% numa-vmstat.node1.nr_page_table_pages -84.5% 11218 ± 17% numa-vmstat.node1.nr_slab_reclaimable +13.8% 840.00 ± 5% slabinfo.blkdev_ioc.num_objs -44.5% 942.75 ± 8% slabinfo.dquot.active_objs -44.5% 942.75 ± 8% slabinfo.dquot.num_objs -92.4% 57717 slabinfo.radix_tree_node.active_objs -92.4% 1031 slabinfo.radix_tree_node.active_slabs -92.4% 57771 slabinfo.radix_tree_node.num_objs -92.4% 1031 slabinfo.radix_tree_node.num_slabs +14.2% 640.25 ± 3% slabinfo.skbuff_ext_cache.active_objs -74.2% 53962 ± 13% numa-meminfo.node0.KReclaimable +1129.1% 211277 ± 90% numa-meminfo.node0.Mapped -13.1% 3221190 ± 3% numa-meminfo.node0.MemUsed -86.5% 77122 ± 49% numa-meminfo.node0.PageTables -74.2% 53962 ± 13% numa-meminfo.node0.SReclaimable -48.4% 159181 ± 7% numa-meminfo.node0.Slab -84.5% 44861 ± 17% numa-meminfo.node1.KReclaimable -24.0% 2994130 ± 4% numa-meminfo.node1.MemUsed -88.0% 72494 ± 58% numa-meminfo.node1.PageTables -84.5% 44861 ± 17% numa-meminfo.node1.SReclaimable -66.1% 126490 ± 9% numa-meminfo.node1.Slab +4.4% 5331 ± 2% proc-vmstat.nr_active_file +1.3% 65642 proc-vmstat.nr_anon_pages +41.6% 121.75 ± 28% proc-vmstat.nr_dirtied +3.4% 1064023 proc-vmstat.nr_dirty_background_threshold +3.4% 2130649 proc-vmstat.nr_dirty_threshold +3.4% 10723419 proc-vmstat.nr_free_pages +8.2% 103375 proc-vmstat.nr_inactive_anon +25.6% 105.50 ± 11% proc-vmstat.nr_inactive_file +8.7% 105168 proc-vmstat.nr_mapped -87.2% 37319 ± 3% proc-vmstat.nr_page_table_pages -80.2% 24716 proc-vmstat.nr_slab_reclaimable +2.0% 46711 proc-vmstat.nr_slab_unreclaimable +4.4% 5331 ± 2% proc-vmstat.nr_zone_active_file +8.2% 103375 proc-vmstat.nr_zone_inactive_anon +25.6% 105.50 ± 11% proc-vmstat.nr_zone_inactive_file -59.4% 864384 proc-vmstat.numa_hit -60.3% 833061 proc-vmstat.numa_local +16.8% 3637 ± 9% proc-vmstat.numa_pte_updates -60.9% 886227 proc-vmstat.pgalloc_normal -84.9% 71307545 ± 3% proc-vmstat.pgfault -62.9% 806246 proc-vmstat.pgfree -88.8% 74786 ± 3% proc-vmstat.thp_fault_fallback +134.2% 302.32 ± 13% sched_debug.cfs_rq:/.exec_clock.min +49.3% 1183484 ± 10% sched_debug.cfs_rq:/.load.max +16.1% 399036 ± 2% sched_debug.cfs_rq:/.load.stddev +31.2% 1.31 ± 8% sched_debug.cfs_rq:/.nr_running.max +9.3% 0.44 sched_debug.cfs_rq:/.nr_running.stddev +49.5% 1183484 ± 10% sched_debug.cfs_rq:/.runnable_weight.max +16.1% 399045 ± 2% sched_debug.cfs_rq:/.runnable_weight.stddev -38.6% 337.58 ± 5% sched_debug.cfs_rq:/.util_est_enqueued.avg +36.4% 814808 sched_debug.cpu.avg_idle.avg -38.5% 225103 ± 2% sched_debug.cpu.avg_idle.stddev +236.1% 9.18 ± 14% sched_debug.cpu.clock.stddev +236.1% 9.18 ± 14% sched_debug.cpu.clock_task.stddev +31.2% 1.31 ± 8% sched_debug.cpu.nr_running.max +78.8% 34650 ± 35% sched_debug.cpu.nr_switches.max +95.1% 27315 ± 33% sched_debug.cpu.sched_count.max +40.3% 3316 ± 23% sched_debug.cpu.sched_count.stddev +95.7% 13623 ± 34% sched_debug.cpu.sched_goidle.max -71.7% 6.62 ± 13% sched_debug.cpu.sched_goidle.min +39.6% 1663 ± 23% sched_debug.cpu.sched_goidle.stddev +51.0% 78.06 ± 24% sched_debug.cpu.ttwu_count.min -12.4% 386.45 ± 2% sched_debug.cpu.ttwu_local.avg +28.1% 39.06 ± 17% sched_debug.cpu.ttwu_local.min -8.1% 177.50 ± 3% interrupts.37:PCI-MSI.31981568-edge.i40e-0000:3d:00.0:misc +6.6e+103% 66.25 ±159% interrupts.88:PCI-MSI.31981619-edge.i40e-eth0-TxRx-50 +3928.9% 975.00 ±126% interrupts.CPU10.RES:Rescheduling_interrupts +284.1% 84.50 ± 59% interrupts.CPU12.RES:Rescheduling_interrupts +408.8% 827.25 ± 98% interrupts.CPU2.RES:Rescheduling_interrupts +1779.8% 195.50 ± 84% interrupts.CPU26.RES:Rescheduling_interrupts +3985.2% 179.75 ±107% interrupts.CPU27.RES:Rescheduling_interrupts +7481.5% 6368 ±163% interrupts.CPU30.RES:Rescheduling_interrupts +368.2% 383.00 ± 98% interrupts.CPU31.RES:Rescheduling_interrupts +6097.9% 148.75 ±145% interrupts.CPU32.RES:Rescheduling_interrupts +4689.1% 153.25 ±111% interrupts.CPU33.RES:Rescheduling_interrupts -18.2% 2324 ± 5% interrupts.CPU35.CAL:Function_call_interrupts 585.00 ±158% interrupts.CPU38.RES:Rescheduling_interrupts +2422.7% 55.50 ± 56% interrupts.CPU39.RES:Rescheduling_interrupts +7660.4% 186.25 ±133% interrupts.CPU42.RES:Rescheduling_interrupts +1642.2% 55.75 ± 88% interrupts.CPU44.RES:Rescheduling_interrupts +4604.5% 103.50 ±102% interrupts.CPU45.RES:Rescheduling_interrupts +6.6e+103% 66.00 ±160% interrupts.CPU50.88:PCI-MSI.31981619-edge.i40e-eth0-TxRx-50 +684.5% 91.00 ± 65% interrupts.CPU50.RES:Rescheduling_interrupts +1545.2% 102.00 ±104% interrupts.CPU51.RES:Rescheduling_interrupts +1416.3% 139.50 ± 61% interrupts.CPU54.RES:Rescheduling_interrupts +503.8% 78.50 ± 73% interrupts.CPU55.RES:Rescheduling_interrupts +962.5% 80.75 ± 83% interrupts.CPU56.RES:Rescheduling_interrupts +416.9% 76.50 ± 41% interrupts.CPU57.RES:Rescheduling_interrupts +1445.7% 126.75 ± 88% interrupts.CPU60.RES:Rescheduling_interrupts +817.6% 86.25 ± 28% interrupts.CPU61.RES:Rescheduling_interrupts +513.2% 90.75 ± 32% interrupts.CPU62.RES:Rescheduling_interrupts +1400.0% 84.00 ± 51% interrupts.CPU63.RES:Rescheduling_interrupts +750.6% 69.75 ± 33% interrupts.CPU65.RES:Rescheduling_interrupts +581.4% 69.50 ± 28% interrupts.CPU68.RES:Rescheduling_interrupts +150.0% 91.50 ± 69% interrupts.CPU70.TLB:TLB_shootdowns +594.8% 59.75 ± 51% interrupts.CPU76.RES:Rescheduling_interrupts +1497.2% 57.50 ± 73% interrupts.CPU78.RES:Rescheduling_interrupts +1582.7% 131.25 ± 91% interrupts.CPU8.RES:Rescheduling_interrupts +293.7% 68.50 ± 60% interrupts.CPU8.TLB:TLB_shootdowns -8.1% 177.50 ± 3% interrupts.CPU9.37:PCI-MSI.31981568-edge.i40e-0000:3d:00.0:misc +81.5% 26.70 perf-stat.i.MPKI +69.4% 9.665e+09 ± 4% perf-stat.i.branch-instructions +0.1 0.54 ± 4% perf-stat.i.branch-miss-rate% +111.4% 50251745 ± 3% perf-stat.i.branch-misses +26.7 81.45 perf-stat.i.cache-miss-rate% +367.4% 1.113e+09 ± 4% perf-stat.i.cache-misses +229.1% 1.321e+09 ± 4% perf-stat.i.cache-references -39.4% 2.66 ± 4% perf-stat.i.cpi +8.0% 1.291e+11 perf-stat.i.cpu-cycles -66.4% 301.06 ± 17% perf-stat.i.cycles-between-cache-misses -0.0 0.01 ± 52% perf-stat.i.dTLB-load-miss-rate% -78.6% 663585 ± 3% perf-stat.i.dTLB-load-misses +97.8% 1.345e+10 ± 5% perf-stat.i.dTLB-loads -0.2 0.01 ± 7% perf-stat.i.dTLB-store-miss-rate% -88.6% 844034 ± 3% perf-stat.i.dTLB-store-misses +185.8% 8.022e+09 ± 4% perf-stat.i.dTLB-stores -30.1 38.46 ± 5% perf-stat.i.iTLB-load-miss-rate% -75.9% 3100419 ± 4% perf-stat.i.iTLB-load-misses +89.4% 4.834e+10 ± 4% perf-stat.i.instructions +618.7% 15776 ± 8% perf-stat.i.instructions-per-iTLB-miss +41.6% 0.38 ± 4% perf-stat.i.ipc -83.5% 342553 ± 3% perf-stat.i.minor-faults +545.5% 2.027e+08 ± 22% perf-stat.i.node-load-misses +625.0% 2.372e+08 ± 26% perf-stat.i.node-loads +446.5% 1.474e+08 ± 18% perf-stat.i.node-store-misses +515.9% 1.569e+08 ± 22% perf-stat.i.node-stores -83.5% 342558 ± 3% perf-stat.i.page-faults +73.7% 27.33 perf-stat.overall.MPKI +0.1 0.52 perf-stat.overall.branch-miss-rate% +24.9 84.27 perf-stat.overall.cache-miss-rate% -42.8% 2.68 ± 4% perf-stat.overall.cpi -76.9% 116.15 ± 4% perf-stat.overall.cycles-between-cache-misses -0.0 0.00 ± 5% perf-stat.overall.dTLB-load-miss-rate% -0.3 0.01 ± 4% perf-stat.overall.dTLB-store-miss-rate% -32.5 38.22 ± 6% perf-stat.overall.iTLB-load-miss-rate% +686.7% 15642 ± 7% perf-stat.overall.instructions-per-iTLB-miss +75.3% 0.37 ± 4% perf-stat.overall.ipc -72.1% 2357 perf-stat.overall.path-length +69.4% 9.622e+09 ± 4% perf-stat.ps.branch-instructions +111.4% 50029998 ± 3% perf-stat.ps.branch-misses +367.4% 1.109e+09 ± 4% perf-stat.ps.cache-misses +229.1% 1.316e+09 ± 4% perf-stat.ps.cache-references +8.1% 1.285e+11 perf-stat.ps.cpu-cycles -78.6% 660373 ± 3% perf-stat.ps.dTLB-load-misses +97.8% 1.339e+10 ± 5% perf-stat.ps.dTLB-loads -88.6% 840338 ± 3% perf-stat.ps.dTLB-store-misses +185.8% 7.987e+09 ± 4% perf-stat.ps.dTLB-stores -75.9% 3086339 ± 4% perf-stat.ps.iTLB-load-misses +89.4% 4.813e+10 ± 4% perf-stat.ps.instructions -83.5% 341065 ± 3% perf-stat.ps.minor-faults +545.7% 2.019e+08 ± 22% perf-stat.ps.node-load-misses +625.0% 2.361e+08 ± 26% perf-stat.ps.node-loads +446.6% 1.468e+08 ± 18% perf-stat.ps.node-store-misses +515.9% 1.562e+08 ± 22% perf-stat.ps.node-stores -83.5% 341071 ± 3% perf-stat.ps.page-faults +73.9% 1.002e+13 ± 4% perf-stat.total.instructions +516.5% 46458 ± 13% softirqs.CPU0.RCU +575.9% 41409 ± 15% softirqs.CPU1.RCU +611.1% 45378 ± 12% softirqs.CPU10.RCU +641.3% 45123 ± 9% softirqs.CPU11.RCU +619.4% 45231 ± 8% softirqs.CPU12.RCU +521.9% 45667 ± 10% softirqs.CPU13.RCU +659.0% 45142 ± 8% softirqs.CPU14.RCU +606.4% 45259 ± 9% softirqs.CPU15.RCU +647.9% 49467 ± 10% softirqs.CPU16.RCU +553.1% 47167 ± 9% softirqs.CPU17.RCU +578.4% 46989 ± 9% softirqs.CPU18.RCU +634.3% 48218 ± 9% softirqs.CPU19.RCU +457.5% 42812 ± 18% softirqs.CPU2.RCU +628.6% 48168 ± 10% softirqs.CPU20.RCU +605.7% 47472 ± 13% softirqs.CPU21.RCU +638.5% 48528 ± 10% softirqs.CPU22.RCU +541.6% 48542 ± 10% softirqs.CPU23.RCU +520.9% 51863 ± 8% softirqs.CPU24.RCU +632.8% 44682 ± 14% softirqs.CPU25.RCU +703.2% 47600 ± 7% softirqs.CPU26.RCU +665.0% 46641 ± 10% softirqs.CPU27.RCU +719.1% 47372 ± 6% softirqs.CPU28.RCU +693.9% 47619 ± 7% softirqs.CPU29.RCU +326.6% 46623 ± 11% softirqs.CPU3.RCU +587.4% 47155 ± 7% softirqs.CPU30.RCU +658.9% 44099 ± 7% softirqs.CPU31.RCU +677.7% 47497 ± 6% softirqs.CPU32.RCU +640.9% 44990 ± 5% softirqs.CPU33.RCU +695.4% 47835 ± 6% softirqs.CPU34.RCU +679.8% 46801 ± 10% softirqs.CPU35.RCU +644.9% 47101 ± 11% softirqs.CPU36.RCU +708.9% 47666 ± 6% softirqs.CPU37.RCU +702.9% 47322 ± 5% softirqs.CPU38.RCU +674.8% 47490 ± 5% softirqs.CPU39.RCU +618.3% 44214 ± 13% softirqs.CPU4.RCU +646.7% 47224 ± 5% softirqs.CPU40.RCU +659.6% 44884 ± 7% softirqs.CPU41.RCU +680.5% 47855 ± 5% softirqs.CPU42.RCU +724.0% 48673 ± 7% softirqs.CPU43.RCU +650.2% 45159 ± 8% softirqs.CPU44.RCU +728.0% 48510 ± 8% softirqs.CPU45.RCU +697.1% 46851 ± 5% softirqs.CPU46.RCU +645.7% 43449 ± 2% softirqs.CPU47.RCU +562.9% 47870 ± 4% softirqs.CPU48.RCU -63.5% 7517 ± 65% softirqs.CPU48.SCHED +597.3% 43232 ± 9% softirqs.CPU49.RCU +532.4% 44217 ± 8% softirqs.CPU5.RCU +686.3% 46619 ± 9% softirqs.CPU50.RCU +558.3% 43964 ± 4% softirqs.CPU51.RCU +623.5% 47186 ± 8% softirqs.CPU52.RCU +680.5% 46325 ± 4% softirqs.CPU53.RCU +674.1% 45468 ± 5% softirqs.CPU54.RCU +673.8% 45947 ± 3% softirqs.CPU55.RCU +693.2% 45435 ± 3% softirqs.CPU56.RCU +684.8% 46133 ± 4% softirqs.CPU57.RCU +651.3% 43475 ± 8% softirqs.CPU58.RCU +673.9% 45855 ± 4% softirqs.CPU59.RCU +619.3% 45045 ± 10% softirqs.CPU6.RCU +619.2% 43923 ± 6% softirqs.CPU60.RCU +638.9% 45082 ± 5% softirqs.CPU61.RCU +582.2% 43759 ± 3% softirqs.CPU62.RCU +712.7% 47419 ± 5% softirqs.CPU63.RCU +694.5% 48633 ± 3% softirqs.CPU64.RCU +605.1% 47880 ± 10% softirqs.CPU65.RCU +678.5% 47797 ± 9% softirqs.CPU66.RCU +681.1% 46887 ± 4% softirqs.CPU67.RCU +720.3% 47306 ± 9% softirqs.CPU68.RCU +802.4% 52160 ± 4% softirqs.CPU69.RCU -59.8% 10032 ±110% softirqs.CPU69.SCHED +592.8% 43066 ± 8% softirqs.CPU7.RCU +732.2% 48584 ± 7% softirqs.CPU70.RCU +695.4% 48767 ± 7% softirqs.CPU71.RCU +688.5% 47249 ± 10% softirqs.CPU72.RCU +666.4% 47042 ± 10% softirqs.CPU73.RCU +692.0% 46641 ± 11% softirqs.CPU74.RCU +649.4% 44673 ± 12% softirqs.CPU75.RCU +632.7% 46652 ± 13% softirqs.CPU76.RCU +675.3% 46776 ± 11% softirqs.CPU77.RCU +634.7% 46759 ± 13% softirqs.CPU78.RCU +650.1% 44198 ± 15% softirqs.CPU79.RCU +558.4% 44328 ± 9% softirqs.CPU8.RCU +659.8% 44272 ± 9% softirqs.CPU80.RCU +663.5% 45095 ± 7% softirqs.CPU81.RCU +621.3% 44831 ± 9% softirqs.CPU82.RCU +636.1% 43371 ± 9% softirqs.CPU83.RCU +690.5% 45364 ± 6% softirqs.CPU84.RCU +634.4% 44190 ± 8% softirqs.CPU85.RCU +644.9% 44398 ± 9% softirqs.CPU86.RCU +635.9% 44782 ± 9% softirqs.CPU87.RCU +662.2% 44277 ± 9% softirqs.CPU88.RCU +634.6% 43246 ± 8% softirqs.CPU89.RCU +666.3% 44105 ± 10% softirqs.CPU9.RCU +663.9% 44804 ± 8% softirqs.CPU90.RCU +660.7% 45354 ± 9% softirqs.CPU91.RCU +624.6% 42854 ± 10% softirqs.CPU92.RCU +646.3% 44333 ± 9% softirqs.CPU93.RCU +673.2% 44188 ± 8% softirqs.CPU94.RCU +659.7% 44215 ± 10% softirqs.CPU95.RCU +635.8% 4420294 ± 3% softirqs.RCU -11.1% 1551273 softirqs.SCHED -62.8 3.73 ± 14% perf-profile.calltrace.cycles-pp.page_fault -62.8 3.71 ± 14% perf-profile.calltrace.cycles-pp.do_page_fault.page_fault -62.7 3.66 ± 15% perf-profile.calltrace.cycles-pp.__do_page_fault.do_page_fault.page_fault -62.7 3.43 ± 15% perf-profile.calltrace.cycles-pp.handle_mm_fault.__do_page_fault.do_page_fault.page_fault -62.7 3.33 ± 15% perf-profile.calltrace.cycles-pp.__handle_mm_fault.handle_mm_fault.__do_page_fault.do_page_fault.page_fault -57.5 0.30 ±173% perf-profile.calltrace.cycles-pp.lookup_memtype.track_pfn_insert.__vm_insert_mixed.dax_iomap_pte_fault.ext4_dax_huge_fault -55.9 0.00 perf-profile.calltrace.cycles-pp._raw_spin_lock.lookup_memtype.track_pfn_insert.__vm_insert_mixed.dax_iomap_pte_fault -55.3 0.00 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock.lookup_memtype.track_pfn_insert.__vm_insert_mixed -45.8 0.89 ± 24% perf-profile.calltrace.cycles-pp.__do_fault.__handle_mm_fault.handle_mm_fault.__do_page_fault.do_page_fault -45.8 0.88 ± 23% perf-profile.calltrace.cycles-pp.ext4_dax_huge_fault.__do_fault.__handle_mm_fault.handle_mm_fault.__do_page_fault -43.2 0.79 ± 24% perf-profile.calltrace.cycles-pp.dax_iomap_pte_fault.ext4_dax_huge_fault.__do_fault.__handle_mm_fault.handle_mm_fault -41.8 0.18 ±173% perf-profile.calltrace.cycles-pp.__vm_insert_mixed.dax_iomap_pte_fault.ext4_dax_huge_fault.__do_fault.__handle_mm_fault -41.4 0.17 ±173% perf-profile.calltrace.cycles-pp.track_pfn_insert.__vm_insert_mixed.dax_iomap_pte_fault.ext4_dax_huge_fault.__do_fault -18.3 0.81 ± 27% perf-profile.calltrace.cycles-pp.ext4_dax_huge_fault.do_wp_page.__handle_mm_fault.handle_mm_fault.__do_page_fault -18.3 0.82 ± 27% perf-profile.calltrace.cycles-pp.do_wp_page.__handle_mm_fault.handle_mm_fault.__do_page_fault.do_page_fault -17.0 0.36 ±100% perf-profile.calltrace.cycles-pp.dax_iomap_pte_fault.ext4_dax_huge_fault.do_wp_page.__handle_mm_fault.handle_mm_fault -16.3 0.14 ±173% perf-profile.calltrace.cycles-pp.__vm_insert_mixed.dax_iomap_pte_fault.ext4_dax_huge_fault.do_wp_page.__handle_mm_fault -16.1 0.13 ±173% perf-profile.calltrace.cycles-pp.track_pfn_insert.__vm_insert_mixed.dax_iomap_pte_fault.ext4_dax_huge_fault.do_wp_page +0.6 0.58 perf-profile.calltrace.cycles-pp.__get_io_u +0.8 0.78 ± 14% perf-profile.calltrace.cycles-pp.__hrtimer_run_queues.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt +0.8 1.16 ± 24% perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry.start_kernel +0.8 1.17 ± 24% perf-profile.calltrace.cycles-pp.cpuidle_enter.do_idle.cpu_startup_entry.start_kernel.secondary_startup_64 +0.8 1.17 ± 24% perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_kernel.secondary_startup_64 +0.8 1.17 ± 24% perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_kernel.secondary_startup_64 +0.8 1.17 ± 24% perf-profile.calltrace.cycles-pp.start_kernel.secondary_startup_64 +0.9 0.85 ± 11% perf-profile.calltrace.cycles-pp.dax_iomap_pmd_fault.ext4_dax_huge_fault.__handle_mm_fault.handle_mm_fault.__do_page_fault +1.0 0.98 ± 10% perf-profile.calltrace.cycles-pp.hrtimer_interrupt.smp_apic_timer_interrupt.apic_timer_interrupt +1.0 1.05 ± 17% perf-profile.calltrace.cycles-pp.io_u_mark_submit +1.1 1.12 ± 9% perf-profile.calltrace.cycles-pp.smp_apic_timer_interrupt.apic_timer_interrupt +1.2 1.17 ± 9% perf-profile.calltrace.cycles-pp.apic_timer_interrupt +1.2 1.19 ± 2% perf-profile.calltrace.cycles-pp.utime_since_now +1.2 1.20 ± 6% perf-profile.calltrace.cycles-pp.add_clat_sample +1.2 1.21 ± 5% perf-profile.calltrace.cycles-pp.add_lat_sample +1.2 1.22 ± 7% perf-profile.calltrace.cycles-pp.ramp_time_over +1.5 1.51 ± 9% perf-profile.calltrace.cycles-pp.ext4_dax_huge_fault.__handle_mm_fault.handle_mm_fault.__do_page_fault.do_page_fault +3.6 3.64 ± 3% perf-profile.calltrace.cycles-pp.get_io_u +4.0 4.02 ± 3% perf-profile.calltrace.cycles-pp.io_queue_event +4.5 4.46 ± 4% perf-profile.calltrace.cycles-pp.td_io_queue +5.4 5.40 ± 4% perf-profile.calltrace.cycles-pp.fio_gettime +9.7 9.71 ± 4% perf-profile.calltrace.cycles-pp.io_u_sync_complete +25.9 56.78 ± 3% perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry.start_secondary +26.0 56.80 ± 3% perf-profile.calltrace.cycles-pp.cpuidle_enter.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64 +26.1 57.08 ± 2% perf-profile.calltrace.cycles-pp.intel_idle.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry +26.3 57.20 ± 3% perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64 +26.3 57.21 ± 3% perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_secondary.secondary_startup_64 +26.3 57.21 ± 3% perf-profile.calltrace.cycles-pp.start_secondary.secondary_startup_64 +27.1 58.38 ± 3% perf-profile.calltrace.cycles-pp.secondary_startup_64 -62.8 3.76 ± 14% perf-profile.children.cycles-pp.page_fault -62.7 3.69 ± 14% perf-profile.children.cycles-pp.__do_page_fault -62.7 3.74 ± 14% perf-profile.children.cycles-pp.do_page_fault -62.7 3.46 ± 15% perf-profile.children.cycles-pp.handle_mm_fault -62.7 3.35 ± 15% perf-profile.children.cycles-pp.__handle_mm_fault -62.7 3.20 ± 15% perf-profile.children.cycles-pp.ext4_dax_huge_fault -59.9 1.37 ± 25% perf-profile.children.cycles-pp.dax_iomap_pte_fault -57.5 0.86 ± 28% perf-profile.children.cycles-pp.__vm_insert_mixed -56.6 1.17 ± 22% perf-profile.children.cycles-pp.lookup_memtype -56.6 1.17 ± 22% perf-profile.children.cycles-pp.track_pfn_insert -56.0 0.40 ± 24% perf-profile.children.cycles-pp._raw_spin_lock -55.2 0.07 ± 11% perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath -45.8 0.89 ± 23% perf-profile.children.cycles-pp.__do_fault -18.3 0.82 ± 27% perf-profile.children.cycles-pp.do_wp_page -2.5 0.28 ± 13% perf-profile.children.cycles-pp.jbd2__journal_start -2.5 0.21 ± 11% perf-profile.children.cycles-pp.start_this_handle -1.9 0.35 ± 16% perf-profile.children.cycles-pp.ext4_iomap_begin -1.2 0.48 ± 24% perf-profile.children.cycles-pp._raw_read_lock -1.1 0.18 ± 14% perf-profile.children.cycles-pp.__ext4_journal_stop -1.0 0.17 ± 13% perf-profile.children.cycles-pp.jbd2_journal_stop -1.0 0.71 ± 21% perf-profile.children.cycles-pp.pat_pagerange_is_ram -1.0 0.69 ± 22% perf-profile.children.cycles-pp.find_next_iomem_res -1.0 0.71 ± 21% perf-profile.children.cycles-pp.walk_system_ram_range -1.0 0.08 ± 24% perf-profile.children.cycles-pp.jbd2_transaction_committed -0.7 0.10 ± 14% perf-profile.children.cycles-pp.__ext4_journal_start_sb -0.7 0.10 ± 17% perf-profile.children.cycles-pp.ext4_journal_check_start -0.5 0.03 ±100% perf-profile.children.cycles-pp.insert_pfn -0.1 0.13 ± 23% perf-profile.children.cycles-pp.sync_regs -0.1 0.11 ± 14% perf-profile.children.cycles-pp.rbt_memtype_lookup -0.1 0.05 ± 61% perf-profile.children.cycles-pp.dax_insert_entry -0.1 0.04 ± 57% perf-profile.children.cycles-pp._raw_spin_lock_irq -0.1 0.07 ± 22% perf-profile.children.cycles-pp.dax_unlock_entry -0.1 0.08 ± 27% perf-profile.children.cycles-pp.ext4_es_lookup_extent -0.0 0.07 ± 22% perf-profile.children.cycles-pp.dax_iomap_pfn -0.0 0.10 ± 8% perf-profile.children.cycles-pp.xas_store +0.0 0.10 ± 5% perf-profile.children.cycles-pp.___perf_sw_event +0.0 0.19 ± 6% perf-profile.children.cycles-pp.grab_mapping_entry +0.0 0.11 ± 7% perf-profile.children.cycles-pp.get_unlocked_entry +0.0 0.10 ± 8% perf-profile.children.cycles-pp.xas_find_conflict +0.1 0.06 ± 6% perf-profile.children.cycles-pp.ktime_get_update_offsets_now +0.1 0.05 ± 8% perf-profile.children.cycles-pp.lapic_next_deadline +0.1 0.05 ± 8% perf-profile.children.cycles-pp.hrtimer_active +0.1 0.06 ± 9% perf-profile.children.cycles-pp.td_set_runstate +0.1 0.06 ± 14% perf-profile.children.cycles-pp.swapgs_restore_regs_and_return_to_usermode +0.1 0.06 ± 11% perf-profile.children.cycles-pp.__run_perf_stat +0.1 0.06 ± 11% perf-profile.children.cycles-pp.process_interval +0.1 0.06 ± 11% perf-profile.children.cycles-pp.read_counters +0.1 0.07 ± 10% perf-profile.children.cycles-pp.vmacache_find +0.1 0.07 ± 17% perf-profile.children.cycles-pp.console_unlock +0.1 0.06 ± 17% perf-profile.children.cycles-pp.cmd_stat +0.1 0.07 ± 11% perf-profile.children.cycles-pp.find_vma +0.1 0.08 ± 10% perf-profile.children.cycles-pp.irq_work_run_list +0.1 0.07 ± 12% perf-profile.children.cycles-pp.queue_full +0.1 0.07 ± 16% perf-profile.children.cycles-pp.log_io_u +0.1 0.07 ± 12% perf-profile.children.cycles-pp.ext4_data_block_valid_rcu +0.1 0.07 ± 28% perf-profile.children.cycles-pp.io_serial_in +0.1 0.07 ± 10% perf-profile.children.cycles-pp.__ext4_get_inode_loc +0.1 0.15 ± 9% perf-profile.children.cycles-pp.ext4_mark_iloc_dirty +0.1 0.08 ± 27% perf-profile.children.cycles-pp.__x64_sys_poll +0.1 0.08 ± 27% perf-profile.children.cycles-pp.do_sys_poll +0.1 0.08 ± 14% perf-profile.children.cycles-pp.get_start_offset +0.1 0.08 perf-profile.children.cycles-pp.lock_file +0.1 0.08 ± 15% perf-profile.children.cycles-pp.vfs_read +0.1 0.08 ± 30% perf-profile.children.cycles-pp.rcu_core +0.1 0.08 ± 10% perf-profile.children.cycles-pp.ksys_read +0.1 0.09 ± 21% perf-profile.children.cycles-pp.perf_evlist__poll +0.1 0.09 ± 21% perf-profile.children.cycles-pp.poll +0.1 0.09 ± 4% perf-profile.children.cycles-pp.flow_threshold_exceeded +0.1 0.10 ± 14% perf-profile.children.cycles-pp.ext4_reserve_inode_write +0.1 0.10 ± 33% perf-profile.children.cycles-pp.update_curr +0.1 0.11 ± 21% perf-profile.children.cycles-pp.native_write_msr +0.1 0.43 ± 7% perf-profile.children.cycles-pp.ext4_dirty_inode +0.1 0.11 ± 7% perf-profile.children.cycles-pp.get_file +0.1 0.11 ± 19% perf-profile.children.cycles-pp._raw_spin_lock_irqsave +0.1 0.50 ± 8% perf-profile.children.cycles-pp.generic_update_time +0.1 0.14 ± 60% perf-profile.children.cycles-pp.tick_nohz_get_sleep_length +0.1 0.13 ± 6% perf-profile.children.cycles-pp.put_file_log +0.1 0.13 ± 40% perf-profile.children.cycles-pp.perf_mux_hrtimer_handler +0.1 0.13 ± 23% perf-profile.children.cycles-pp.update_load_avg +0.1 0.16 ± 37% perf-profile.children.cycles-pp.__generic_file_write_iter +0.1 0.16 ± 37% perf-profile.children.cycles-pp.generic_perform_write +0.1 0.19 ± 23% perf-profile.children.cycles-pp.dax_wake_entry +0.1 0.17 ± 37% perf-profile.children.cycles-pp.generic_file_write_iter +0.1 0.17 ± 38% perf-profile.children.cycles-pp.new_sync_write +0.1 0.17 ± 37% perf-profile.children.cycles-pp.__GI___libc_write +0.2 0.18 ± 36% perf-profile.children.cycles-pp.record__pushfn +0.2 0.18 ± 36% perf-profile.children.cycles-pp.writen +0.2 0.18 ± 34% perf-profile.children.cycles-pp.ksys_write +0.2 0.18 ± 34% perf-profile.children.cycles-pp.vfs_write +0.2 0.18 ± 36% perf-profile.children.cycles-pp.perf_mmap__push +0.2 0.27 ± 8% perf-profile.children.cycles-pp.ext4_mark_inode_dirty +0.2 0.19 ± 35% perf-profile.children.cycles-pp.record__mmap_read_evlist +0.2 0.21 ± 5% perf-profile.children.cycles-pp.unlock_file +0.2 0.17 ± 4% perf-profile.children.cycles-pp.utime_since +0.2 0.20 ± 26% perf-profile.children.cycles-pp.rcu_sched_clock_irq +0.2 0.20 ± 2% perf-profile.children.cycles-pp.in_ramp_time +0.2 0.27 ± 31% perf-profile.children.cycles-pp.cmd_record +0.2 0.28 ± 56% perf-profile.children.cycles-pp.menu_select +0.2 0.24 ± 4% perf-profile.children.cycles-pp.put_file +0.2 0.28 ± 57% perf-profile.children.cycles-pp.__softirqentry_text_start +0.3 0.33 ± 25% perf-profile.children.cycles-pp.__libc_start_main +0.3 0.33 ± 25% perf-profile.children.cycles-pp.main +0.3 0.33 ± 25% perf-profile.children.cycles-pp.run_builtin +0.3 0.30 perf-profile.children.cycles-pp.td_io_prep +0.3 0.31 ± 2% perf-profile.children.cycles-pp.ntime_since +0.3 0.36 ± 54% perf-profile.children.cycles-pp.irq_exit +0.3 0.40 ± 26% perf-profile.children.cycles-pp.task_tick_fair +0.4 0.35 ± 11% perf-profile.children.cycles-pp.io_u_mark_depth +0.4 0.38 ± 13% perf-profile.children.cycles-pp.vmf_insert_pfn_pmd +0.4 0.51 ± 19% perf-profile.children.cycles-pp.scheduler_tick +0.5 0.46 ± 8% perf-profile.children.cycles-pp.io_u_mark_complete +0.5 0.56 ± 16% perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe +0.5 0.56 ± 16% perf-profile.children.cycles-pp.do_syscall_64 +0.6 0.58 perf-profile.children.cycles-pp.__get_io_u +0.7 0.91 ± 10% perf-profile.children.cycles-pp.update_process_times +0.8 0.94 ± 9% perf-profile.children.cycles-pp.tick_sched_handle +0.8 1.17 ± 24% perf-profile.children.cycles-pp.start_kernel +0.8 1.01 ± 9% perf-profile.children.cycles-pp.tick_sched_timer +0.9 0.86 ± 10% perf-profile.children.cycles-pp.dax_iomap_pmd_fault +1.0 1.05 ± 16% perf-profile.children.cycles-pp.io_u_mark_submit +1.0 1.26 ± 3% perf-profile.children.cycles-pp.__hrtimer_run_queues +1.1 1.19 ± 2% perf-profile.children.cycles-pp.utime_since_now +1.1 1.21 ± 5% perf-profile.children.cycles-pp.add_lat_sample +1.1 1.20 ± 6% perf-profile.children.cycles-pp.add_clat_sample +1.2 1.66 ± 5% perf-profile.children.cycles-pp.hrtimer_interrupt +1.2 1.23 ± 7% perf-profile.children.cycles-pp.ramp_time_over +1.6 2.09 ± 14% perf-profile.children.cycles-pp.smp_apic_timer_interrupt +1.6 2.17 ± 14% perf-profile.children.cycles-pp.apic_timer_interrupt +3.5 3.78 ± 3% perf-profile.children.cycles-pp.get_io_u +4.9 5.06 ± 3% perf-profile.children.cycles-pp.td_io_queue +5.2 5.49 ± 4% perf-profile.children.cycles-pp.fio_gettime +5.5 5.45 ± 4% perf-profile.children.cycles-pp.io_queue_event +8.8 8.92 ± 4% perf-profile.children.cycles-pp.io_u_sync_complete +26.1 57.08 ± 2% perf-profile.children.cycles-pp.intel_idle +26.3 57.21 ± 3% perf-profile.children.cycles-pp.start_secondary +26.8 57.96 ± 3% perf-profile.children.cycles-pp.cpuidle_enter_state +26.8 57.97 ± 3% perf-profile.children.cycles-pp.cpuidle_enter +27.1 58.38 ± 3% perf-profile.children.cycles-pp.do_idle +27.1 58.38 ± 3% perf-profile.children.cycles-pp.secondary_startup_64 +27.1 58.38 ± 3% perf-profile.children.cycles-pp.cpu_startup_entry -54.9 0.07 ± 11% perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath -1.3 0.08 ± 11% perf-profile.self.cycles-pp.start_this_handle -1.2 0.48 ± 25% perf-profile.self.cycles-pp._raw_read_lock -1.1 0.10 ± 12% perf-profile.self.cycles-pp.jbd2_journal_stop -0.8 0.38 ± 16% perf-profile.self.cycles-pp.find_next_iomem_res -0.7 0.34 ± 26% perf-profile.self.cycles-pp._raw_spin_lock -0.6 0.08 ± 13% perf-profile.self.cycles-pp.ext4_journal_check_start -0.1 0.13 ± 23% perf-profile.self.cycles-pp.sync_regs -0.1 0.04 ± 58% perf-profile.self.cycles-pp.ext4_iomap_begin -0.1 0.11 ± 16% perf-profile.self.cycles-pp.rbt_memtype_lookup -0.1 0.04 ± 57% perf-profile.self.cycles-pp._raw_spin_lock_irq -0.0 0.04 ± 59% perf-profile.self.cycles-pp.handle_mm_fault +0.0 0.08 ± 5% perf-profile.self.cycles-pp.xas_find_conflict +0.1 0.05 ± 8% perf-profile.self.cycles-pp.hrtimer_interrupt +0.1 0.05 ± 8% perf-profile.self.cycles-pp.log_io_u +0.1 0.05 ± 8% perf-profile.self.cycles-pp.ktime_get_update_offsets_now +0.1 0.05 ± 8% perf-profile.self.cycles-pp.hrtimer_active +0.1 0.06 ± 9% perf-profile.self.cycles-pp.td_set_runstate +0.1 0.06 ± 11% perf-profile.self.cycles-pp.io_serial_in +0.1 0.07 ± 10% perf-profile.self.cycles-pp.vmacache_find +0.1 0.06 ± 6% perf-profile.self.cycles-pp.lock_file +0.1 0.07 ± 17% perf-profile.self.cycles-pp.ext4_data_block_valid_rcu +0.1 0.07 ± 12% perf-profile.self.cycles-pp.queue_full +0.1 0.08 ± 11% perf-profile.self.cycles-pp.ext4_mark_iloc_dirty +0.1 0.08 ± 14% perf-profile.self.cycles-pp.get_start_offset +0.1 0.08 ± 10% perf-profile.self.cycles-pp.get_file +0.1 0.09 ± 4% perf-profile.self.cycles-pp.flow_threshold_exceeded +0.1 0.09 ± 40% perf-profile.self.cycles-pp.menu_select +0.1 0.09 ± 15% perf-profile.self.cycles-pp._raw_spin_lock_irqsave +0.1 0.10 ± 18% perf-profile.self.cycles-pp.native_write_msr +0.1 0.10 ± 4% perf-profile.self.cycles-pp.put_file_log +0.1 0.18 ± 18% perf-profile.self.cycles-pp.dax_wake_entry +0.2 0.20 ± 6% perf-profile.self.cycles-pp.unlock_file +0.2 0.17 ± 4% perf-profile.self.cycles-pp.utime_since +0.2 0.19 ± 29% perf-profile.self.cycles-pp.rcu_sched_clock_irq +0.2 0.20 ± 3% perf-profile.self.cycles-pp.in_ramp_time +0.2 0.20 ± 10% perf-profile.self.cycles-pp.io_u_mark_depth +0.2 0.22 ± 5% perf-profile.self.cycles-pp.put_file +0.2 0.24 ± 2% perf-profile.self.cycles-pp.td_io_prep +0.3 0.31 ± 2% perf-profile.self.cycles-pp.ntime_since +0.4 0.45 ± 8% perf-profile.self.cycles-pp.io_u_mark_complete +0.6 0.57 ± 2% perf-profile.self.cycles-pp.__get_io_u +0.7 0.70 ± 15% perf-profile.self.cycles-pp.io_u_mark_submit +0.9 0.91 ± 8% perf-profile.self.cycles-pp.ramp_time_over +1.1 1.14 ± 2% perf-profile.self.cycles-pp.utime_since_now +1.1 1.20 ± 5% perf-profile.self.cycles-pp.add_lat_sample +1.1 1.18 ± 5% perf-profile.self.cycles-pp.add_clat_sample +3.4 3.70 ± 3% perf-profile.self.cycles-pp.get_io_u +4.8 4.92 ± 3% perf-profile.self.cycles-pp.td_io_queue +5.1 5.37 ± 4% perf-profile.self.cycles-pp.fio_gettime +5.4 5.40 ± 4% perf-profile.self.cycles-pp.io_queue_event +7.3 7.38 ± 4% perf-profile.self.cycles-pp.io_u_sync_complete +26.1 57.07 ± 2% perf-profile.self.cycles-pp.intel_idle

fio.read_bw_MBps

50000 +-+-----------------------------------------------------------------+ | O | 45000 +-+ O O O O | 40000 O-+ O O O O O O O O O O O | | O O O O O | 35000 +-+ O | 30000 +-+ | | | 25000 +-+ | 20000 +-+ | | | 15000 +-+ | 10000 +-+ | |..+..+..+. .+..+.. .+.+..+..+..+..+..+.+..+..+.. .+..+.+..+..| 5000 +-+-----------------------------------------------------------------+

fio.read_iops

1.2e+07 +-+O--------------------------------------------------------------+ 1.1e+07 +-+ O O O O | O O O O O O O O O O | 1e+07 +-+ O O O O O O | 9e+06 +-+ O O | 8e+06 +-+ | 7e+06 +-+ | | | 6e+06 +-+ | 5e+06 +-+ | 4e+06 +-+ | 3e+06 +-+ | | | 2e+06 +-++..+.+..+..+..+.+..+..+..+.+..+..+..+.+..+..+..+.+..+..+..+.+..| 1e+06 +-+---------------------------------------------------------------+

fio.read_clat_mean_us

8000 +-+------------------------------------------------------------------+ | .+.. .+..+.. | 7000 +-++..+..+..+.+..+. +..+..+..+..+ +..+..+..+..+..+.+..+..+..| | | 6000 +-+ | | | 5000 +-+ | | | 4000 +-+ | | | 3000 +-+ | | O | 2000 O-+ O O O O O O O O O O O O O O O O O | | O O O O | 1000 +-+------------------------------------------------------------------+

fio.read_clat_stddev

16000 +-+-----------------------------------------------------------------+ | + + + | 14000 +-+ : : : : : : | 12000 +-+ : : : : : :| | : : .+.. : : : :| 10000 +-++.. : +..+..+.. .+.. .+. +..+..+.+.. : +..+..+. : | | + +. +.+. + + | 8000 +-+ | | | 6000 +-+ | 4000 +-+ | | | 2000 O-+ O O O O O O O O O O O O | | O O O O O O O O O O | 0 +-+-----------------------------------------------------------------+

fio.read_clat_90__us

20000 +-+-----------------------------------------------------------------+ |..+..+..+.+..+..+..+..+..+.+..+..+..+..+..+.+..+..+..+..+..+.+..+..| 18000 +-+ | 16000 +-+ | | | 14000 +-+ | 12000 +-+ | | | 10000 +-+ | 8000 +-+ | | | 6000 +-+ | 4000 +-+ | O O O O O O O O O O O O | 2000 +-+O--O--O-O-------------------O-----------O-O-----O--O--O----O-----+

fio.read_clat_95__us

22000 +-+-----------------------------------------------------------------+ 20000 +-++..+.. .+..+.. .+..+..+.+..+.. .+..+.+.. | | +.+..+..+. +.+..+..+. +..+. +..| 18000 +-+ | 16000 +-+ | | | 14000 +-+ | 12000 +-+ | 10000 +-+ | | | 8000 +-+ | 6000 +-+ | | | 4000 O-+ O O O O O O O O O O O O O O O O O | 2000 +-+O--O------------------------O-----------O----------O-------------+

fio.read_clat_99__us

24000 +-+-----------------------------------------------------------------+ 22000 +-+ +.+..+..+..+. +.+..+..+..+. +..+. +..| | | 20000 +-+ | 18000 +-+ | 16000 +-+ | 14000 +-+ | | | 12000 +-+ | 10000 +-+ | 8000 +-+ | 6000 +-+ | O O O O O O O O O O O O O O O O O O O O O | 4000 +-+O O | 2000 +-+-----------------------------------------------------------------+

fio.write_bw_MBps

fio.write_iops

fio.write_clat_mean_us

22000 +-+-----------------------------------------------------------------+ 20000 +-++..+..+.+..+..+..+..+..+.+..+..+..+..+..+.+..+..+..+..+..+.+..+..| | | 18000 +-+ | 16000 +-+ | 14000 +-+ | 12000 +-+ | | | 10000 +-+ | 8000 +-+ | 6000 +-+ | 4000 +-+ | | | 2000 O-+O O O O O O O O O O O O O O O O O O O O O O | 0 +-+-----------------------------------------------------------------+

fio.write_clat_90__us

25000 +-+-----------------------------------------------------------------+ |..+..+..+.+..+..+..+..+..+.+..+..+..+..+..+.+..+..+..+..+..+.+..+..| | | 20000 +-+ | | | | | 15000 +-+ | | | 10000 +-+ | | | | | 5000 +-+ | | O O | O O O O O O O O O O O O O O O O O O O O O | 0 +-+-----------------------------------------------------------------+

fio.write_clat_95__us

30000 +-+-----------------------------------------------------------------+ | | 25000 +-++..+..+.+..+..+..+..+..+.+..+..+..+..+..+.+..+..+..+..+..+.+..+..| | | | | 20000 +-+ | | | 15000 +-+ | | | 10000 +-+ | | | | | 5000 +-+ O O | O O O O O O O O O O O O O O O O O O O O O | 0 +-+-----------------------------------------------------------------+

fio.write_clat_99__us

40000 +-+-----------------------------------------------------------------+ | +.. +.. | 35000 +-+ + .+.. .+.. .. ..| 30000 +-++..+..+ +..+. +..+.+..+..+. +..+.+..+..+ +..+.+..+ | | | 25000 +-+ | | | 20000 +-+ | | | 15000 +-+ | 10000 +-+ | | | 5000 O-+O O O O O O O O O O O O O O O O O O O O O O | | | 0 +-+-----------------------------------------------------------------+

fio.latency_2us_

70 +-+O-------------------------------------------------------------------+ | O O O O | 60 +-+ O O | O O O O O O O O | 50 +-+ O O O O O | | O | 40 +-+ O | | | 30 +-+ O | | | 20 +-+ | | | 10 +-+ | | | 0 +-+--------------------------------------------------------------------+

fio.latency_20us_

50 +-+--------------------------------------------------------------------+ 45 +-+ .+.. +..+..+..+ | |..+..+..+.. .+. .. + .+..+..+..+..+.. .+..+..+..+..| 40 +-+ +. +..+ +. +. | 35 +-+ | | | 30 +-+ | 25 +-+ | 20 +-+ | | | 15 +-+ | 10 +-+ | | | 5 +-+ | 0 O-+O--O--O--O--O--O--O--O--O--O--O--O-O--O--O--O--O--O--O--O--O--O-----+

fio.latency_50us_

35 +-+--------------------------------------------------------------------+ | | 30 +-+ +.. +..+ +.. | |.. .. : + .+..+..+.. .. +.. ..| 25 +-++..+..+ +.. : + + +..+..+ +..+..+ | | : +..+.. .. | 20 +-+ + + | | | 15 +-+ | | | 10 +-+ | | | 5 +-+ | | | 0 O-+O--O--O--O--O--O--O--O--O--O--O--O-O--O--O--O--O--O--O--O--O--O-----+

fio.workload

5e+09 +-+---------------------------------------------------------------+ | O O O O | 4.5e+09 +-+ O O O | 4e+09 O-+ O O O O O O O O O O O O O | | O | 3.5e+09 +-+ O | 3e+09 +-+ | | | 2.5e+09 +-+ | 2e+09 +-+ | | | 1.5e+09 +-+ | 1e+09 +-+ | |..+..+.+..+..+..+.+..+..+..+.+..+..+..+.+..+..+..+.+..+..+..+.+..| 5e+08 +-+---------------------------------------------------------------+

fio.time.user_time

10000 +-+-----------------------------------------------------------------+ 9000 O-+O O O O O O O O O O O O O O O O O O O O O O | | | 8000 +-+ | 7000 +-+ | | | 6000 +-+ | 5000 +-+ | 4000 +-+ | | | 3000 +-+ | 2000 +-+ | | | 1000 +-++..+..+.+..+..+..+..+..+.+..+..+..+..+..+.+..+..+..+..+..+.+..+..| 0 +-+-----------------------------------------------------------------+

fio.time.system_time

10000 +-+-----------------------------------------------------------------+ 9000 +-++..+..+.+..+..+.. .+..+.+..+..+..+.. .+.+..+..+..+..+..+.+..+..| | +. +. | 8000 +-+ | 7000 +-+ | | | 6000 +-+ | 5000 +-+ | 4000 +-+ | | | 3000 +-+ | 2000 +-+ | | | 1000 +-+ | 0 O-+O--O--O-O--O--O--O--O--O-O--O--O--O--O--O-O--O--O--O--O--O-O-----+

fio.time.percent_of_cpu_this_job_got

4600 +-+------------------------------------------------------------------+ O O O O O O O O O O O O O O O O O O O O O O O | 4550 +-+ | 4500 +-+ | | | 4450 +-+ | | | 4400 +-+ | | | 4350 +-+ | 4300 +-+ | | +.. | 4250 +-+ .. | |..+..+..+..+.+ +..+..+..+..+..+.+..+..+..+..+..+..+..+.+..+..+..| 4200 +-+------------------------------------------------------------------+

fio.time.elapsed_time

228 +-+-------------------------------------------------------------------+ | +. + +..+..+. +. +. +. +. | 226 +-+ + + | 224 +-+ + | | | 222 +-+ | 220 +-+ | | | 218 +-+ | 216 +-+ | | | 214 +-+ | 212 +-+ | | | 210 O-+O--O--O--O--O--O-O--O--O--O--O--O--O--O--O--O--O--O-O--O--O--O-----+

fio.time.elapsed_time.max

fio.time.minor_page_faults

5e+08 +-+---------------------------------------------------------------+ |..+..+.+..+..+. +..+..+..+ +..+..+.+..+..+..+.+..+..+..+.+..| 4.5e+08 +-+ | 4e+08 +-+ | | | 3.5e+08 +-+ | 3e+08 +-+ | | | 2.5e+08 +-+ | 2e+08 +-+ | | | 1.5e+08 +-+ | 1e+08 +-+ | O O O O O O O O O O O O O O O O O O O O O | 5e+07 +-+------------------------------O--O-----------------------------+

fio.time.voluntary_context_switches

24000 +-+-----------------------------------------------------------------+ |..+..+..+.+..+..+..+..+..+ +..+.. .+..+.+..+..+..+..+..+.+..+..| 23500 +-+ +. | | | | | 23000 +-+ | | | 22500 +-+ | | | 22000 +-+ | | | | O O | 21500 O-+ O O O O O O O O O O O O O O | | O O O O O | 21000 +-+-------------------------O---------------------------------------+

[*] bisect-good sample [O] bisect-bad sample

*************************************************************************************************** lkp-csl-2sp6: 96 threads Intel(R) Xeon(R) Gold 6252 CPU @ 2.10GHz with 256G memory ========================================================================================= bs/compiler/cpufreq_governor/disk/fs/ioengine/kconfig/mount_option/nr_task/rootfs/runtime/rw/tbox_group/test_size/testcase/time_based/ucode: 2M/gcc-7/performance/2pmem/ext4/mmap/x86_64-rhel-7.6/dax/50%/debian-x86_64-2019-05-14.cgz/200s/write/lkp-csl-2sp6/200G/fio-basic/tb/0x5000021

commit: v5.4-rc4 a70e8083a9 ("fs/dax: Fix pmd vs pte conflict detection")

v5.4-rc4 a70e8083a91b17a7c77012f7746 ---------------- --------------------------- fail:runs %reproduction fail:runs | | | 1:5 -12% 0:4 perf-profile.children.cycles-pp.error_entry %stddev %change %stddev \ | \ 22.58 ± 15% -21.6 0.94 ± 79% fio.latency_10ms% 77.40 ± 4% -77.4 0.01 ± 24% fio.latency_20ms% 0.01 ± 81% +60.9 60.94 ± 59% fio.latency_2ms% 0.01 ± 50% +36.8 36.85 ± 97% fio.latency_4ms% 227.24 -7.4% 210.34 fio.time.elapsed_time 227.24 -7.4% 210.34 fio.time.elapsed_time.max 4.65e+08 -90.4% 44651382 ± 6% fio.time.minor_page_faults 4235 +8.1% 4577 fio.time.percent_of_cpu_this_job_got 9021 -96.5% 314.08 ± 3% fio.time.system_time 603.69 ± 2% +1443.2% 9315 fio.time.user_time 25150 ± 2% -10.0% 22623 fio.time.voluntary_context_switches 907948 +363.7% 4210010 ± 15% fio.workload 9079 +363.7% 42099 ± 15% fio.write_bw_MBps 11180441 -81.1% 2109440 ± 16% fio.write_clat_90%_us 11285299 -80.4% 2211840 ± 16% fio.write_clat_95%_us 11652300 -65.4% 4026368 ± 7% fio.write_clat_99%_us 10493648 -81.5% 1937158 ± 16% fio.write_clat_mean_us 755702 ± 11% -43.3% 428848 ± 12% fio.write_clat_stddev 4539 +363.7% 21049 ± 15% fio.write_iops 23285 ± 5% -71.3% 6686 ± 15% cpuidle.POLL.usage 41.24 -39.4 1.83 ± 2% mpstat.cpu.all.sys% 2.76 ± 2% +44.1 46.82 mpstat.cpu.all.usr% 56.37 -8.1% 51.80 iostat.cpu.idle 40.89 -95.6% 1.82 ± 2% iostat.cpu.system 2.74 ± 2% +1590.9% 46.39 iostat.cpu.user 1179347 ± 15% -63.3% 433356 ± 29% numa-numastat.node0.local_node 1204191 ± 13% -62.7% 448980 ± 24% numa-numastat.node0.numa_hit 1384986 ± 12% -71.9% 388829 ± 28% numa-numastat.node1.local_node 1391284 ± 11% -70.9% 404502 ± 23% numa-numastat.node1.numa_hit 56.40 -8.2% 51.75 vmstat.cpu.id 2.00 +2200.0% 46.00 vmstat.cpu.us 2102090 -20.3% 1676188 vmstat.memory.cache 1602 -5.4% 1516 vmstat.system.cs 504545 -80.7% 97541 meminfo.KReclaimable 10737953 -14.9% 9139470 meminfo.Memused 1591563 -89.8% 162150 ± 5% meminfo.PageTables 504545 -80.7% 97541 meminfo.SReclaimable 685303 -59.1% 280065 meminfo.Slab 57985 -21.0% 45801 meminfo.max_used_kB 1244 +12.1% 1394 turbostat.Avg_MHz 44.66 +5.3 49.96 turbostat.Busy% 54.06 ± 2% -9.3% 49.05 turbostat.CPU%c1 54.80 +12.2% 61.50 turbostat.CoreTmp 56.40 ± 2% +9.5% 61.75 turbostat.PkgTmp 247.09 +17.2% 289.48 turbostat.PkgWatt 137.84 +36.8% 188.59 turbostat.RAMWatt 2176 ± 12% +19.1% 2592 ± 6% slabinfo.avc_xperms_data.active_objs 2176 ± 12% +19.1% 2592 ± 6% slabinfo.avc_xperms_data.num_objs 1818 ± 5% -35.8% 1167 ± 5% slabinfo.dquot.active_objs 1818 ± 5% -35.8% 1167 ± 5% slabinfo.dquot.num_objs 15953 ± 2% +8.3% 17277 ± 2% slabinfo.kmalloc-512.active_objs 16088 ± 2% +8.1% 17385 ± 3% slabinfo.kmalloc-512.num_objs 789.20 ± 5% +11.3% 878.00 ± 6% slabinfo.pool_workqueue.active_objs 768474 -92.6% 56580 slabinfo.radix_tree_node.active_objs 13726 -92.6% 1010 slabinfo.radix_tree_node.active_slabs 768688 -92.6% 56646 slabinfo.radix_tree_node.num_objs 13726 -92.6% 1010 slabinfo.radix_tree_node.num_slabs 310305 ± 18% -82.3% 54895 ± 6% numa-meminfo.node0.KReclaimable 17976285 ± 6% +9.4% 19667753 ± 7% numa-meminfo.node0.MemFree 843639 ± 4% -92.3% 64794 ± 44% numa-meminfo.node0.PageTables 310305 ± 18% -82.3% 54895 ± 6% numa-meminfo.node0.SReclaimable 408879 ± 14% -61.0% 159577 ± 2% numa-meminfo.node0.Slab 80122 ±172% +150.1% 200350 ± 93% numa-meminfo.node1.Inactive 79981 ±173% +150.3% 200180 ± 93% numa-meminfo.node1.Inactive(anon) 193866 ± 29% -78.0% 42668 ± 10% numa-meminfo.node1.KReclaimable 84665 ±166% +146.3% 208493 ± 91% numa-meminfo.node1.Mapped 749499 ± 4% -87.0% 97358 ± 22% numa-meminfo.node1.PageTables 193866 ± 29% -78.0% 42668 ± 10% numa-meminfo.node1.SReclaimable 276049 ± 21% -56.3% 120510 ± 3% numa-meminfo.node1.Slab 4495963 ± 6% +9.4% 4918393 ± 7% numa-vmstat.node0.nr_free_pages 210021 ± 4% -92.3% 16203 ± 44% numa-vmstat.node0.nr_page_table_pages 77599 ± 18% -82.3% 13719 ± 6% numa-vmstat.node0.nr_slab_reclaimable 1659023 ± 8% -33.9% 1096193 ± 18% numa-vmstat.node0.numa_hit 1633793 ± 8% -33.9% 1080213 ± 17% numa-vmstat.node0.numa_local 19906 ±173% +151.2% 50007 ± 93% numa-vmstat.node1.nr_inactive_anon 21108 ±166% +147.1% 52152 ± 91% numa-vmstat.node1.nr_mapped 186480 ± 4% -87.0% 24268 ± 22% numa-vmstat.node1.nr_page_table_pages 48450 ± 29% -78.0% 10661 ± 10% numa-vmstat.node1.nr_slab_reclaimable 19906 ±173% +151.2% 50006 ± 93% numa-vmstat.node1.nr_zone_inactive_anon 1299939 ± 11% -33.2% 868151 ± 24% numa-vmstat.node1.numa_hit 1137570 ± 11% -38.8% 696149 ± 28% numa-vmstat.node1.numa_local 162369 ± 7% +5.9% 172002 ± 8% numa-vmstat.node1.numa_other 777339 +6.2% 825713 proc-vmstat.nr_active_anon 5072 +2.7% 5208 proc-vmstat.nr_active_file 742845 +8.4% 805220 proc-vmstat.nr_anon_pages 1387 +8.0% 1497 proc-vmstat.nr_anon_transparent_hugepages 951491 +4.1% 990957 proc-vmstat.nr_dirty_background_threshold 1905310 +4.1% 1984338 proc-vmstat.nr_dirty_threshold 9596723 +4.1% 9991832 proc-vmstat.nr_free_pages 95152 +8.9% 103606 proc-vmstat.nr_inactive_anon 96870 +9.3% 105877 proc-vmstat.nr_mapped 396937 ± 2% -89.8% 40520 ± 5% proc-vmstat.nr_page_table_pages 125996 -80.6% 24386 proc-vmstat.nr_slab_reclaimable 777339 +6.2% 825713 proc-vmstat.nr_zone_active_anon 5072 +2.7% 5208 proc-vmstat.nr_zone_active_file 95152 +8.9% 103606 proc-vmstat.nr_zone_inactive_anon 2621128 -66.5% 879152 ± 2% proc-vmstat.numa_hit 2589980 -67.3% 847841 ± 2% proc-vmstat.numa_local 19962 ± 21% +16.8% 23324 ± 13% proc-vmstat.numa_pages_migrated 56091 ± 24% -35.2% 36320 ± 6% proc-vmstat.pgactivate 3543684 -52.0% 1702505 proc-vmstat.pgalloc_normal 4.656e+08 -90.3% 45213914 ± 6% proc-vmstat.pgfault 3468918 -52.4% 1650770 proc-vmstat.pgfree 19962 ± 21% +16.8% 23324 ± 13% proc-vmstat.pgmigrate_success 907948 -91.3% 78860 ± 5% proc-vmstat.thp_fault_fallback 58.57 ± 16% +514.0% 359.57 ± 37% sched_debug.cfs_rq:/.MIN_vruntime.avg 5269 ± 9% +435.2% 28206 ± 36% sched_debug.cfs_rq:/.MIN_vruntime.max 551.52 ± 11% +473.4% 3162 ± 37% sched_debug.cfs_rq:/.MIN_vruntime.stddev 129.89 ± 7% +162.5% 340.93 ± 13% sched_debug.cfs_rq:/.exec_clock.min 58.59 ± 16% +513.9% 359.64 ± 37% sched_debug.cfs_rq:/.max_vruntime.avg 5271 ± 9% +435.2% 28212 ± 36% sched_debug.cfs_rq:/.max_vruntime.max 551.73 ± 11% +473.3% 3163 ± 37% sched_debug.cfs_rq:/.max_vruntime.stddev 0.02 ± 13% +64.9% 0.03 ± 23% sched_debug.cfs_rq:/.nr_spread_over.avg 545.21 ± 3% -14.2% 467.53 ± 7% sched_debug.cfs_rq:/.util_est_enqueued.avg 602620 +37.4% 827802 sched_debug.cpu.avg_idle.avg 47781 ± 17% +140.5% 114924 ± 60% sched_debug.cpu.avg_idle.min 366457 -44.7% 202505 ± 4% sched_debug.cpu.avg_idle.stddev 2.94 ± 4% +825.6% 27.20 ± 18% sched_debug.cpu.clock.stddev 2.94 ± 4% +825.6% 27.20 ± 18% sched_debug.cpu.clock_task.stddev 0.00 ± 4% +293.4% 0.00 sched_debug.cpu.next_balance.stddev 16092 ± 17% -33.4% 10717 ± 14% sched_debug.cpu.sched_count.max 83.25 ± 8% +92.4% 160.19 ± 31% sched_debug.cpu.sched_count.min 711.37 ± 2% -9.8% 641.54 sched_debug.cpu.sched_goidle.avg 8020 ± 17% -33.9% 5302 ± 14% sched_debug.cpu.sched_goidle.max 22.80 ± 2% -72.3% 6.31 ± 13% sched_debug.cpu.sched_goidle.min 8084 ± 19% -38.5% 4968 ± 21% sched_debug.cpu.ttwu_count.max 50.55 ± 7% +105.0% 103.62 ± 43% sched_debug.cpu.ttwu_count.min 1295 ± 9% -33.3% 864.58 ± 15% sched_debug.cpu.ttwu_count.stddev 448.69 ± 2% -12.4% 392.94 sched_debug.cpu.ttwu_local.avg 30.35 ± 6% +57.7% 47.88 ± 36% sched_debug.cpu.ttwu_local.min 945.06 ± 20% -33.1% 632.26 ± 11% sched_debug.cpu.ttwu_local.stddev 5.20 ± 80% +1823.1% 100.00 ± 81% interrupts.CPU12.RES:Rescheduling_interrupts 2.20 ± 72% +3934.1% 88.75 ± 62% interrupts.CPU13.RES:Rescheduling_interrupts 95.60 ± 85% -67.8% 30.75 ± 44% interrupts.CPU13.TLB:TLB_shootdowns 0.80 ± 93% +31775.0% 255.00 ±143% interrupts.CPU15.RES:Rescheduling_interrupts 1.20 ± 81% +56733.3% 682.00 ±162% interrupts.CPU21.RES:Rescheduling_interrupts 2.00 ± 44% +3025.0% 62.50 ± 40% interrupts.CPU22.RES:Rescheduling_interrupts 4.40 ± 71% +15718.2% 696.00 ±135% interrupts.CPU23.RES:Rescheduling_interrupts 7.60 ±121% +2702.6% 213.00 ±148% interrupts.CPU27.RES:Rescheduling_interrupts 32.00 ±181% +476.6% 184.50 ± 57% interrupts.CPU3.RES:Rescheduling_interrupts 1.20 ± 97% +45858.3% 551.50 ±166% interrupts.CPU33.RES:Rescheduling_interrupts 15.40 ± 80% +679.2% 120.00 ± 84% interrupts.CPU5.RES:Rescheduling_interrupts 4.60 ±168% +2150.0% 103.50 ± 57% interrupts.CPU50.RES:Rescheduling_interrupts 7.60 ±104% +1232.2% 101.25 ± 55% interrupts.CPU51.RES:Rescheduling_interrupts 4.60 ±168% +10590.2% 491.75 ±136% interrupts.CPU53.RES:Rescheduling_interrupts 8.40 ±194% +2120.2% 186.50 ± 87% interrupts.CPU55.RES:Rescheduling_interrupts 7.60 ±193% +1011.8% 84.50 ± 24% interrupts.CPU58.RES:Rescheduling_interrupts 3.80 ±187% +3307.9% 129.50 ± 65% interrupts.CPU59.RES:Rescheduling_interrupts 2530 +15.3% 2918 ± 8% interrupts.CPU60.CAL:Function_call_interrupts 3.40 ±171% +6841.2% 236.00 ±110% interrupts.CPU60.RES:Rescheduling_interrupts 2.80 ±165% +5132.1% 146.50 ± 82% interrupts.CPU61.RES:Rescheduling_interrupts 5.60 ±200% +1859.8% 109.75 ± 38% interrupts.CPU63.RES:Rescheduling_interrupts 2.80 ±182% +2739.3% 79.50 ± 24% interrupts.CPU64.RES:Rescheduling_interrupts 2.80 ±182% +3301.8% 95.25 ± 47% interrupts.CPU66.RES:Rescheduling_interrupts 1.80 ±123% +8622.2% 157.00 ±105% interrupts.CPU69.RES:Rescheduling_interrupts 2540 ± 35% +63.1% 4143 ± 13% interrupts.CPU7.NMI:Non-maskable_interrupts 2540 ± 35% +63.1% 4143 ± 13% interrupts.CPU7.PMI:Performance_monitoring_interrupts 7.80 ±112% +3980.1% 318.25 ±127% interrupts.CPU7.RES:Rescheduling_interrupts 2918 ± 31% +40.2% 4092 ± 18% interrupts.CPU79.NMI:Non-maskable_interrupts 2918 ± 31% +40.2% 4092 ± 18% interrupts.CPU79.PMI:Performance_monitoring_interrupts 5.00 ±111% +1120.0% 61.00 ±111% interrupts.CPU8.RES:Rescheduling_interrupts 2499 ± 33% +58.8% 3968 ± 19% interrupts.CPU80.NMI:Non-maskable_interrupts 2499 ± 33% +58.8% 3968 ± 19% interrupts.CPU80.PMI:Performance_monitoring_interrupts 2930 ± 30% +56.6% 4590 ± 36% interrupts.CPU81.NMI:Non-maskable_interrupts 2930 ± 30% +56.6% 4590 ± 36% interrupts.CPU81.PMI:Performance_monitoring_interrupts 2864 ± 31% +40.6% 4026 ± 21% interrupts.CPU85.NMI:Non-maskable_interrupts 2864 ± 31% +40.6% 4026 ± 21% interrupts.CPU85.PMI:Performance_monitoring_interrupts 2880 ± 33% +42.5% 4106 ± 20% interrupts.CPU86.NMI:Non-maskable_interrupts 2880 ± 33% +42.5% 4106 ± 20% interrupts.CPU86.PMI:Performance_monitoring_interrupts 6.60 ±118% +2365.9% 162.75 ± 41% interrupts.CPU9.RES:Rescheduling_interrupts 2516 ± 34% +60.4% 4037 ± 21% interrupts.CPU90.NMI:Non-maskable_interrupts 2516 ± 34% +60.4% 4037 ± 21% interrupts.CPU90.PMI:Performance_monitoring_interrupts 19.60 ± 99% +185.7% 56.00 ± 64% interrupts.CPU90.RES:Rescheduling_interrupts 45.80 ± 57% +110.2% 96.25 ± 39% interrupts.CPU90.TLB:TLB_shootdowns 2480 ± 35% +63.8% 4062 ± 21% interrupts.CPU91.NMI:Non-maskable_interrupts 2480 ± 35% +63.8% 4062 ± 21% interrupts.CPU91.PMI:Performance_monitoring_interrupts 2745 ± 25% +46.3% 4016 ± 20% interrupts.CPU92.NMI:Non-maskable_interrupts 2745 ± 25% +46.3% 4016 ± 20% interrupts.CPU92.PMI:Performance_monitoring_interrupts 15.80 ± 62% +469.6% 90.00 ± 73% interrupts.CPU92.RES:Rescheduling_interrupts 2496 ± 34% +61.0% 4020 ± 20% interrupts.CPU93.NMI:Non-maskable_interrupts 2496 ± 34% +61.0% 4020 ± 20% interrupts.CPU93.PMI:Performance_monitoring_interrupts 14.60 ± 61% +679.1% 113.75 ± 94% interrupts.CPU93.RES:Rescheduling_interrupts 46.20 ± 52% +47.7% 68.25 ± 41% interrupts.CPU93.TLB:TLB_shootdowns 2512 ± 34% +61.5% 4056 ± 18% interrupts.CPU94.NMI:Non-maskable_interrupts 2512 ± 34% +61.5% 4056 ± 18% interrupts.CPU94.PMI:Performance_monitoring_interrupts 20.40 ± 67% +221.1% 65.50 ± 69% interrupts.CPU94.RES:Rescheduling_interrupts 506.40 ± 27% -36.5% 321.75 ± 12% interrupts.IWI:IRQ_work_interrupts 26.37 ± 5% +1527.5% 429.21 ± 5% perf-stat.i.MPKI 4.044e+09 ± 4% -86.6% 5.422e+08 ± 6% perf-stat.i.branch-instructions 0.36 ± 5% +0.4 0.71 ± 7% perf-stat.i.branch-miss-rate% 13139077 ± 2% -71.0% 3808633 ± 2% perf-stat.i.branch-misses 40.81 ± 5% +3.0 43.77 ± 3% perf-stat.i.cache-miss-rate% 2.185e+08 ± 6% +150.0% 5.462e+08 ± 10% perf-stat.i.cache-misses 5.04e+08 ± 4% +141.9% 1.219e+09 ± 13% perf-stat.i.cache-references 1545 -6.2% 1449 perf-stat.i.context-switches 6.27 ± 3% +638.0% 46.28 ± 8% perf-stat.i.cpi 1.19e+11 +9.2% 1.299e+11 perf-stat.i.cpu-cycles 890.35 ± 10% -42.9% 508.33 ± 11% perf-stat.i.cycles-between-cache-misses 2315604 ± 3% -85.8% 329151 ± 4% perf-stat.i.dTLB-load-misses 4.693e+09 ± 3% -84.4% 7.32e+08 ± 6% perf-stat.i.dTLB-loads 2.76 ± 3% -1.5 1.24 ± 3% perf-stat.i.dTLB-store-miss-rate% 56407157 ± 3% -87.3% 7140595 ± 6% perf-stat.i.dTLB-store-misses 1.824e+09 -68.8% 5.692e+08 ± 9% perf-stat.i.dTLB-stores 75.83 -20.8 55.02 ± 2% perf-stat.i.iTLB-load-miss-rate% 11955091 -73.7% 3145209 ± 7% perf-stat.i.iTLB-load-misses 3255737 -22.2% 2533427 ± 3% perf-stat.i.iTLB-loads 1.772e+10 ± 3% -83.7% 2.883e+09 ± 7% perf-stat.i.instructions 1717 ± 5% -44.3% 956.76 ± 3% perf-stat.i.instructions-per-iTLB-miss 0.22 ± 2% -81.5% 0.04 ± 7% perf-stat.i.ipc 2041764 -89.4% 216527 ± 6% perf-stat.i.minor-faults 46.19 ± 7% -41.3 4.92 ± 8% perf-stat.i.node-load-miss-rate% 12550181 ± 15% -83.5% 2075631 ± 23% perf-stat.i.node-load-misses 17032624 ± 3% +654.5% 1.285e+08 ± 27% perf-stat.i.node-loads 39521035 ± 10% +177.3% 1.096e+08 ± 35% perf-stat.i.node-store-misses 22609084 ± 19% +442.8% 1.227e+08 ± 41% perf-stat.i.node-stores 2041781 -89.4% 216529 ± 6% perf-stat.i.page-faults 28.49 ± 6% +1379.4% 421.53 ± 5% perf-stat.overall.MPKI 0.33 ± 2% +0.4 0.71 ± 7% perf-stat.overall.branch-miss-rate% 6.72 ± 3% +575.2% 45.40 ± 8% perf-stat.overall.cpi 547.41 ± 7% -56.1% 240.54 ± 10% perf-stat.overall.cycles-between-cache-misses 0.05 ± 2% -0.0 0.05 ± 4% perf-stat.overall.dTLB-load-miss-rate% 3.00 ± 3% -1.8 1.24 ± 2% perf-stat.overall.dTLB-store-miss-rate% 78.60 -23.3 55.31 ± 2% perf-stat.overall.iTLB-load-miss-rate% 1482 ± 4% -38.2% 916.91 ± 4% perf-stat.overall.instructions-per-iTLB-miss 0.15 ± 3% -85.1% 0.02 ± 7% perf-stat.overall.ipc 42.15 ± 8% -40.5 1.61 ± 11% perf-stat.overall.node-load-miss-rate% 4422813 ± 3% -96.7% 143888 ± 7% perf-stat.overall.path-length 4.027e+09 ± 4% -86.6% 5.393e+08 ± 6% perf-stat.ps.branch-instructions 13081765 ± 2% -71.0% 3788024 ± 2% perf-stat.ps.branch-misses 2.175e+08 ± 6% +150.1% 5.441e+08 ± 10% perf-stat.ps.cache-misses 5.018e+08 ± 4% +142.0% 1.214e+09 ± 13% perf-stat.ps.cache-references 1538 -6.2% 1442 perf-stat.ps.context-switches 1.185e+11 +9.2% 1.294e+11 perf-stat.ps.cpu-cycles 2305544 ± 3% -85.8% 327568 ± 4% perf-stat.ps.dTLB-load-misses 4.673e+09 ± 3% -84.4% 7.286e+08 ± 6% perf-stat.ps.dTLB-loads 56162654 ± 3% -87.3% 7112891 ± 6% perf-stat.ps.dTLB-store-misses 1.816e+09 -68.8% 5.663e+08 ± 9% perf-stat.ps.dTLB-stores 11903152 -73.7% 3131396 ± 7% perf-stat.ps.iTLB-load-misses 3241524 -22.2% 2522758 ± 2% perf-stat.ps.iTLB-loads 1.764e+10 ± 3% -83.7% 2.868e+09 ± 7% perf-stat.ps.instructions 2032916 -89.4% 215676 ± 6% perf-stat.ps.minor-faults 12495695 ± 15% -83.5% 2063340 ± 23% perf-stat.ps.node-load-misses 16958923 ± 3% +655.0% 1.28e+08 ± 27% perf-stat.ps.node-loads 39349478 ± 10% +177.4% 1.092e+08 ± 35% perf-stat.ps.node-store-misses 22511418 ± 19% +442.9% 1.222e+08 ± 41% perf-stat.ps.node-stores 2032932 -89.4% 215678 ± 6% perf-stat.ps.page-faults 4.015e+12 ± 3% -85.1% 5.985e+11 ± 7% perf-stat.total.instructions 7276 ± 14% +461.8% 40876 ± 6% softirqs.CPU0.RCU 7428 ± 27% +499.5% 44535 ± 9% softirqs.CPU1.RCU 90558 ± 18% -19.2% 73203 ± 3% softirqs.CPU1.TIMER 7372 ± 31% +494.3% 43809 ± 5% softirqs.CPU10.RCU 6380 ± 5% +597.8% 44523 ± 6% softirqs.CPU11.RCU 26925 ± 21% -63.9% 9707 ±101% softirqs.CPU11.SCHED 95764 ± 17% -22.9% 73876 ± 6% softirqs.CPU11.TIMER 6839 ± 21% +532.9% 43287 ± 6% softirqs.CPU12.RCU 6195 ± 4% +608.2% 43878 ± 7% softirqs.CPU13.RCU 6379 ± 7% +542.5% 40985 softirqs.CPU14.RCU 6234 ± 6% +601.4% 43724 ± 6% softirqs.CPU15.RCU 6744 ± 4% +594.0% 46802 ± 9% softirqs.CPU16.RCU 96371 ± 16% -25.5% 71817 ± 4% softirqs.CPU16.TIMER 6560 ± 3% +608.8% 46502 ± 10% softirqs.CPU17.RCU 6456 ± 2% +662.1% 49208 ± 3% softirqs.CPU18.RCU 21824 ± 40% -80.9% 4168 ± 10% softirqs.CPU18.SCHED 7235 ± 23% +550.6% 47074 ± 10% softirqs.CPU19.RCU 7523 ± 27% +487.8% 44225 ± 9% softirqs.CPU2.RCU 7973 ± 26% +486.7% 46778 ± 10% softirqs.CPU20.RCU 6831 ± 4% +615.9% 48903 ± 6% softirqs.CPU21.RCU 24201 ± 37% -57.4% 10314 ± 95% softirqs.CPU21.SCHED 6985 ± 8% +525.8% 43713 ± 10% softirqs.CPU22.RCU 6729 ± 9% +509.6% 41024 ± 5% softirqs.CPU23.RCU 7647 ± 7% +561.8% 50609 ± 7% softirqs.CPU24.RCU 6613 ± 8% +607.1% 46768 ± 7% softirqs.CPU25.RCU 6228 ± 5% +607.8% 44084 ± 10% softirqs.CPU26.RCU 6370 ± 4% +590.8% 44004 ± 9% softirqs.CPU27.RCU 5960 ± 5% +668.2% 45791 ± 12% softirqs.CPU28.RCU 6476 ± 8% +589.5% 44652 ± 7% softirqs.CPU29.RCU 8136 ± 21% +464.6% 45941 ± 9% softirqs.CPU3.RCU 6270 ± 10% +634.2% 46042 ± 7% softirqs.CPU30.RCU 6267 ± 5% +605.2% 44200 ± 10% softirqs.CPU31.RCU 5940 ± 2% +656.6% 44941 ± 6% softirqs.CPU32.RCU 6015 ± 2% +640.3% 44535 ± 11% softirqs.CPU33.RCU 5833 ± 3% +620.7% 42042 ± 11% softirqs.CPU34.RCU 7405 ± 32% +512.2% 45332 ± 6% softirqs.CPU35.RCU 5908 ± 5% +663.2% 45091 ± 6% softirqs.CPU36.RCU 6216 ± 2% +650.7% 46666 ± 7% softirqs.CPU37.RCU 5960 +637.4% 43954 ± 4% softirqs.CPU38.RCU 5806 ± 5% +670.3% 44725 ± 4% softirqs.CPU39.RCU 6711 ± 8% +561.7% 44406 ± 9% softirqs.CPU4.RCU 5746 ± 4% +677.9% 44698 ± 6% softirqs.CPU40.RCU 5945 ± 3% +658.4% 45090 ± 4% softirqs.CPU41.RCU 5935 ± 2% +680.0% 46293 ± 5% softirqs.CPU42.RCU 5880 +676.0% 45628 ± 5% softirqs.CPU43.RCU 5908 +669.4% 45463 ± 5% softirqs.CPU44.RCU 5996 ± 2% +656.0% 45334 ± 5% softirqs.CPU45.RCU 6450 ± 7% +598.1% 45026 ± 5% softirqs.CPU46.RCU 5566 ± 12% +603.2% 39142 ± 9% softirqs.CPU47.RCU 6942 ± 12% +574.0% 46795 ± 4% softirqs.CPU48.RCU 6225 ± 4% +602.6% 43742 ± 11% softirqs.CPU49.RCU 6666 ± 21% +565.3% 44356 ± 3% softirqs.CPU5.RCU 25268 ± 38% -60.3% 10034 ±105% softirqs.CPU5.SCHED 6271 ± 8% +596.6% 43690 ± 10% softirqs.CPU50.RCU 5995 ± 7% +631.4% 43848 ± 10% softirqs.CPU51.RCU 7059 ± 31% +494.0% 41931 ± 18% softirqs.CPU52.RCU 6309 ± 6% +541.8% 40493 ± 14% softirqs.CPU53.RCU 6369 ± 3% +577.4% 43144 ± 10% softirqs.CPU54.RCU 6443 ± 13% +544.3% 41520 ± 9% softirqs.CPU55.RCU 6359 ± 14% +559.3% 41923 ± 12% softirqs.CPU56.RCU 6309 ± 5% +601.7% 44273 ± 9% softirqs.CPU57.RCU 6342 ± 11% +585.7% 43490 ± 11% softirqs.CPU58.RCU 6249 ± 6% +547.2% 40445 ± 13% softirqs.CPU59.RCU 6260 ± 10% +609.4% 44414 ± 7% softirqs.CPU6.RCU 6397 ± 15% +582.1% 43638 ± 14% softirqs.CPU60.RCU 6411 ± 9% +613.7% 45759 ± 6% softirqs.CPU61.RCU 6225 ± 7% +602.2% 43716 ± 3% softirqs.CPU62.RCU 6169 ± 7% +592.9% 42749 ± 11% softirqs.CPU63.RCU 6528 ± 7% +605.1% 46029 ± 9% softirqs.CPU64.RCU 6488 ± 12% +601.3% 45497 ± 10% softirqs.CPU65.RCU 6408 ± 7% +506.0% 38834 ± 6% softirqs.CPU66.RCU 6431 ± 5% +601.7% 45124 ± 10% softirqs.CPU67.RCU 6289 ± 7% +627.6% 45763 ± 9% softirqs.CPU68.RCU 6651 ± 9% +530.1% 41916 ± 10% softirqs.CPU69.RCU 6370 ± 13% +593.1% 44148 ± 5% softirqs.CPU7.RCU 27083 ± 16% -52.0% 13004 ± 75% softirqs.CPU7.SCHED 106068 ± 14% -31.0% 73147 ± 4% softirqs.CPU7.TIMER 6287 ± 7% +667.9% 48279 ± 8% softirqs.CPU70.RCU 7080 ± 15% +610.7% 50320 ± 6% softirqs.CPU71.RCU 6229 ± 13% +584.6% 42645 ± 5% softirqs.CPU72.RCU 5633 ± 6% +697.9% 44944 ± 10% softirqs.CPU73.RCU 5720 ± 8% +681.2% 44689 ± 11% softirqs.CPU74.RCU 5614 ± 7% +704.3% 45154 ± 8% softirqs.CPU75.RCU 5672 ± 4% +696.8% 45199 ± 9% softirqs.CPU76.RCU 5717 ± 6% +620.1% 41171 ± 12% softirqs.CPU77.RCU 5741 ± 5% +631.2% 41981 ± 9% softirqs.CPU78.RCU 5634 ± 6% +712.8% 45795 ± 9% softirqs.CPU79.RCU 6579 ± 7% +547.3% 42586 ± 9% softirqs.CPU8.RCU 5515 ± 5% +688.6% 43491 ± 7% softirqs.CPU80.RCU 29701 ± 5% -47.5% 15599 ± 75% softirqs.CPU80.SCHED 6523 ± 25% +548.7% 42319 ± 6% softirqs.CPU81.RCU 5764 ± 3% +653.2% 43416 ± 11% softirqs.CPU82.RCU 5590 ± 4% +695.1% 44452 ± 8% softirqs.CPU83.RCU 5667 ± 5% +715.9% 46238 ± 14% softirqs.CPU84.RCU 5880 ± 9% +647.1% 43931 ± 8% softirqs.CPU85.RCU 5775 ± 3% +640.7% 42780 ± 11% softirqs.CPU86.RCU 6126 ± 10% +573.2% 41245 ± 11% softirqs.CPU87.RCU 5728 ± 3% +652.8% 43124 ± 7% softirqs.CPU88.RCU 5617 ± 2% +683.2% 43993 ± 9% softirqs.CPU89.RCU 6054 ± 7% +561.2% 40033 ± 3% softirqs.CPU9.RCU 29041 ± 5% -13.7% 25050 ± 13% softirqs.CPU9.SCHED 5813 ± 5% +667.4% 44609 ± 8% softirqs.CPU90.RCU 6071 ± 12% +620.2% 43727 ± 9% softirqs.CPU91.RCU 6124 ± 5% +615.8% 43837 ± 9% softirqs.CPU92.RCU 5891 ± 8% +626.8% 42815 ± 9% softirqs.CPU93.RCU 6384 ± 26% +594.5% 44342 ± 7% softirqs.CPU94.RCU 5795 ± 9% +666.8% 44438 ± 8% softirqs.CPU95.RCU 606775 ± 3% +600.3% 4249152 softirqs.RCU 1736128 ± 3% -11.4% 1538649 softirqs.SCHED 64.54 ± 7% -63.2 1.32 ± 19% perf-profile.calltrace.cycles-pp.__do_fault.__handle_mm_fault.handle_mm_fault.__do_page_fault.do_page_fault 64.51 ± 7% -63.2 1.30 ± 19% perf-profile.calltrace.cycles-pp.ext4_dax_huge_fault.__do_fault.__handle_mm_fault.handle_mm_fault.__do_page_fault 64.68 ± 7% -60.8 3.91 ± 19% perf-profile.calltrace.cycles-pp.__handle_mm_fault.handle_mm_fault.__do_page_fault.do_page_fault.page_fault 64.79 ± 7% -60.7 4.05 ± 19% perf-profile.calltrace.cycles-pp.handle_mm_fault.__do_page_fault.do_page_fault.page_fault 65.11 ± 7% -60.6 4.46 ± 18% perf-profile.calltrace.cycles-pp.page_fault 65.02 ± 7% -60.6 4.37 ± 18% perf-profile.calltrace.cycles-pp.__do_page_fault.do_page_fault.page_fault 65.07 ± 7% -60.6 4.44 ± 18% perf-profile.calltrace.cycles-pp.do_page_fault.page_fault 54.60 ± 10% -53.7 0.93 ± 18% perf-profile.calltrace.cycles-pp.dax_iomap_pte_fault.ext4_dax_huge_fault.__do_fault.__handle_mm_fault.handle_mm_fault 49.90 ± 12% -49.7 0.18 ±173% perf-profile.calltrace.cycles-pp.__vm_insert_mixed.dax_iomap_pte_fault.ext4_dax_huge_fault.__do_fault.__handle_mm_fault 49.36 ± 12% -49.2 0.17 ±173% perf-profile.calltrace.cycles-pp.track_pfn_insert.__vm_insert_mixed.dax_iomap_pte_fault.ext4_dax_huge_fault.__do_fault 49.36 ± 12% -49.2 0.17 ±173% perf-profile.calltrace.cycles-pp.lookup_memtype.track_pfn_insert.__vm_insert_mixed.dax_iomap_pte_fault.ext4_dax_huge_fault 47.65 ± 12% -47.7 0.00 perf-profile.calltrace.cycles-pp._raw_spin_lock.lookup_memtype.track_pfn_insert.__vm_insert_mixed.dax_iomap_pte_fault 47.09 ± 12% -47.1 0.00 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock.lookup_memtype.track_pfn_insert.__vm_insert_mixed 6.22 ± 21% -6.2 0.00 perf-profile.calltrace.cycles-pp.jbd2__journal_start.ext4_dax_huge_fault.__do_fault.__handle_mm_fault.handle_mm_fault 6.11 ± 21% -6.1 0.00 perf-profile.calltrace.cycles-pp.start_this_handle.jbd2__journal_start.ext4_dax_huge_fault.__do_fault.__handle_mm_fault 0.70 ± 24% +0.6 1.31 ± 35% perf-profile.calltrace.cycles-pp.cpuidle_enter.do_idle.cpu_startup_entry.start_kernel.secondary_startup_64 0.70 ± 24% +0.6 1.31 ± 35% perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry.start_kernel 0.70 ± 24% +0.6 1.33 ± 36% perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_kernel.secondary_startup_64 0.70 ± 24% +0.6 1.33 ± 36% perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_kernel.secondary_startup_64 0.70 ± 24% +0.6 1.33 ± 36% perf-profile.calltrace.cycles-pp.start_kernel.secondary_startup_64 0.00 +0.9 0.91 ± 28% perf-profile.calltrace.cycles-pp.__mark_inode_dirty.generic_update_time.file_update_time.ext4_dax_huge_fault.__handle_mm_fault 0.00 +0.9 0.91 ± 27% perf-profile.calltrace.cycles-pp.generic_update_time.file_update_time.ext4_dax_huge_fault.__handle_mm_fault.handle_mm_fault 0.00 +0.9 0.95 ± 27% perf-profile.calltrace.cycles-pp.file_update_time.ext4_dax_huge_fault.__handle_mm_fault.handle_mm_fault.__do_page_fault 0.00 +1.2 1.17 ± 19% perf-profile.calltrace.cycles-pp.dax_iomap_pmd_fault.ext4_dax_huge_fault.__handle_mm_fault.handle_mm_fault.__do_page_fault 0.00 +2.4 2.39 ± 24% perf-profile.calltrace.cycles-pp.ext4_dax_huge_fault.__handle_mm_fault.handle_mm_fault.__do_page_fault.do_page_fault 0.10 ±200% +21.7 21.78 ± 13% perf-profile.calltrace.cycles-pp.get_io_u 33.25 ± 15% +34.9 68.17 ± 4% perf-profile.calltrace.cycles-pp.intel_idle.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry 32.74 ± 15% +35.6 68.39 ± 4% perf-profile.calltrace.cycles-pp.cpuidle_enter_state.cpuidle_enter.do_idle.cpu_startup_entry.start_secondary 32.75 ± 15% +35.7 68.42 ± 4% perf-profile.calltrace.cycles-pp.cpuidle_enter.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64 32.84 ± 15% +36.4 69.27 ± 4% perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64 32.84 ± 15% +36.4 69.27 ± 4% perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_secondary.secondary_startup_64 32.84 ± 15% +36.4 69.27 ± 4% perf-profile.calltrace.cycles-pp.start_secondary.secondary_startup_64 33.54 ± 15% +37.1 70.60 ± 4% perf-profile.calltrace.cycles-pp.secondary_startup_64 64.54 ± 7% -63.2 1.33 ± 19% perf-profile.children.cycles-pp.__do_fault 64.54 ± 7% -60.8 3.70 ± 19% perf-profile.children.cycles-pp.ext4_dax_huge_fault 64.68 ± 7% -60.7 3.95 ± 19% perf-profile.children.cycles-pp.__handle_mm_fault 64.80 ± 7% -60.7 4.09 ± 19% perf-profile.children.cycles-pp.handle_mm_fault 65.02 ± 7% -60.6 4.42 ± 18% perf-profile.children.cycles-pp.__do_page_fault 65.13 ± 7% -60.6 4.53 ± 18% perf-profile.children.cycles-pp.page_fault 65.08 ± 7% -60.6 4.50 ± 18% perf-profile.children.cycles-pp.do_page_fault 54.61 ± 10% -53.7 0.93 ± 18% perf-profile.children.cycles-pp.dax_iomap_pte_fault 49.90 ± 12% -49.4 0.52 ± 21% perf-profile.children.cycles-pp.__vm_insert_mixed 49.36 ± 12% -48.4 0.93 ± 19% perf-profile.children.cycles-pp.lookup_memtype 49.36 ± 12% -48.4 0.94 ± 19% perf-profile.children.cycles-pp.track_pfn_insert 48.14 ± 12% -47.9 0.25 ± 20% perf-profile.children.cycles-pp._raw_spin_lock 47.11 ± 12% -47.1 0.05 ± 59% perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath 6.40 ± 20% -6.0 0.37 ± 39% perf-profile.children.cycles-pp.start_this_handle 6.52 ± 19% -6.0 0.49 ± 35% perf-profile.children.cycles-pp.jbd2__journal_start 4.07 ± 21% -3.7 0.40 ± 21% perf-profile.children.cycles-pp.ext4_iomap_begin 3.11 ± 17% -2.8 0.30 ± 29% perf-profile.children.cycles-pp.__ext4_journal_stop 2.94 ± 17% -2.7 0.28 ± 30% perf-profile.children.cycles-pp.jbd2_journal_stop 2.65 ± 16% -2.2 0.47 ± 30% perf-profile.children.cycles-pp._raw_read_lock 1.90 ± 23% -1.9 0.03 ±100% perf-profile.children.cycles-pp.jbd2_transaction_committed 1.78 ± 20% -1.6 0.17 ± 19% perf-profile.children.cycles-pp.__ext4_journal_start_sb 1.75 ± 20% -1.6 0.15 ± 19% perf-profile.children.cycles-pp.ext4_journal_check_start 1.52 ± 19% -1.5 0.04 ±100% perf-profile.children.cycles-pp.add_transaction_credits 1.51 ± 8% -0.9 0.61 ± 21% perf-profile.children.cycles-pp.find_next_iomem_res 1.53 ± 8% -0.9 0.64 ± 21% perf-profile.children.cycles-pp.pat_pagerange_is_ram 1.53 ± 8% -0.9 0.63 ± 21% perf-profile.children.cycles-pp.walk_system_ram_range 0.14 ± 7% -0.1 0.06 ± 59% perf-profile.children.cycles-pp.dax_insert_entry 0.11 ± 6% -0.1 0.04 ± 58% perf-profile.children.cycles-pp.dax_unlock_entry 0.09 ± 9% -0.1 0.03 ±100% perf-profile.children.cycles-pp._raw_spin_lock_irq 0.15 ± 13% -0.1 0.10 ± 15% perf-profile.children.cycles-pp.rbt_memtype_lookup 0.07 ± 5% -0.0 0.03 ±100% perf-profile.children.cycles-pp.___might_sleep 0.09 ± 11% +0.0 0.12 ± 13% perf-profile.children.cycles-pp.ext4_es_lookup_extent 0.07 ± 10% +0.0 0.12 ± 21% perf-profile.children.cycles-pp.kmem_cache_alloc 0.02 ±123% +0.0 0.07 ± 19% perf-profile.children.cycles-pp.__sb_start_write 0.02 ±122% +0.1 0.07 ± 5% perf-profile.children.cycles-pp.serial8250_console_putchar 0.02 ±122% +0.1 0.07 ± 5% perf-profile.children.cycles-pp.wait_for_xmitr 0.02 ±122% +0.1 0.08 ± 11% perf-profile.children.cycles-pp.serial8250_console_write 0.02 ±122% +0.1 0.08 ± 11% perf-profile.children.cycles-pp.uart_console_write 0.02 ±123% +0.1 0.08 ± 10% perf-profile.children.cycles-pp.irq_work_run_list 0.02 ±123% +0.1 0.08 ± 10% perf-profile.children.cycles-pp.console_unlock 0.00 +0.1 0.06 ± 14% perf-profile.children.cycles-pp.read 0.00 +0.1 0.06 ± 14% perf-profile.children.cycles-pp.__libc_fork 0.00 +0.1 0.06 ± 11% perf-profile.children.cycles-pp.search_binary_handler 0.00 +0.1 0.06 ± 11% perf-profile.children.cycles-pp.load_elf_binary 0.01 ±200% +0.1 0.07 ± 31% perf-profile.children.cycles-pp.io_serial_in 0.00 +0.1 0.07 ± 17% perf-profile.children.cycles-pp.exit_mmap 0.00 +0.1 0.07 ± 19% perf-profile.children.cycles-pp.ext4_inode_csum_set 0.00 +0.1 0.07 ± 12% perf-profile.children.cycles-pp.mmput 0.16 ± 21% +0.1 0.22 ± 14% perf-profile.children.cycles-pp.ext4_map_blocks 0.00 +0.1 0.07 ± 5% perf-profile.children.cycles-pp.irq_work_interrupt 0.00 +0.1 0.07 ± 5% perf-profile.children.cycles-pp.smp_irq_work_interrupt 0.00 +0.1 0.07 ± 5% perf-profile.children.cycles-pp.irq_work_run 0.00 +0.1 0.07 ± 5% perf-profile.children.cycles-pp.printk 0.00 +0.1 0.07 ± 5% perf-profile.children.cycles-pp.vprintk_emit 0.00 +0.1 0.07 ± 14% perf-profile.children.cycles-pp.__schedule 0.00 +0.1 0.08 ± 19% perf-profile.children.cycles-pp.__wake_up_common_lock 0.02 ±200% +0.1 0.10 ± 24% perf-profile.children.cycles-pp.ext4_data_block_valid 0.00 +0.1 0.09 ± 19% perf-profile.children.cycles-pp.native_write_msr 0.00 +0.1 0.09 ± 21% perf-profile.children.cycles-pp.kthread 0.00 +0.1 0.09 ± 12% perf-profile.children.cycles-pp.__do_execve_file 0.00 +0.1 0.09 ± 12% perf-profile.children.cycles-pp.execve 0.00 +0.1 0.09 ± 24% perf-profile.children.cycles-pp.ret_from_fork 0.10 ± 7% +0.1 0.19 ± 15% perf-profile.children.cycles-pp.__perf_sw_event 0.00 +0.1 0.09 ± 13% perf-profile.children.cycles-pp.__x64_sys_execve 0.00 +0.1 0.09 ± 28% perf-profile.children.cycles-pp.vmacache_find 0.00 +0.1 0.09 ± 37% perf-profile.children.cycles-pp.__run_perf_stat 0.00 +0.1 0.09 ± 37% perf-profile.children.cycles-pp.cmd_stat 0.00 +0.1 0.09 ± 37% perf-profile.children.cycles-pp.process_interval 0.00 +0.1 0.09 ± 37% perf-profile.children.cycles-pp.read_counters 0.00 +0.1 0.10 ± 27% perf-profile.children.cycles-pp.ext4_data_block_valid_rcu 0.00 +0.1 0.10 ± 24% perf-profile.children.cycles-pp.find_vma 0.00 +0.1 0.10 ± 11% perf-profile.children.cycles-pp.perf_mux_hrtimer_handler 0.00 +0.1 0.10 ± 29% perf-profile.children.cycles-pp.get_next_timer_interrupt 0.07 ± 9% +0.1 0.18 ± 15% perf-profile.children.cycles-pp.___perf_sw_event 0.00 +0.1 0.11 ± 33% perf-profile.children.cycles-pp.do_wait 0.05 +0.1 0.18 ± 23% perf-profile.children.cycles-pp.dax_wake_entry 0.00 +0.1 0.13 ± 31% perf-profile.children.cycles-pp.__do_sys_wait4 0.00 +0.1 0.13 ± 31% perf-profile.children.cycles-pp.kernel_wait4 0.00 +0.1 0.13 ± 31% perf-profile.children.cycles-pp.__waitpid 0.00 +0.1 0.14 ± 28% perf-profile.children.cycles-pp.vfs_read 0.42 ± 9% +0.1 0.56 ± 6% perf-profile.children.cycles-pp.native_irq_return_iret 0.00 +0.1 0.14 ± 36% perf-profile.children.cycles-pp.update_load_avg 0.00 +0.1 0.14 ± 29% perf-profile.children.cycles-pp.ksys_read 0.11 ± 10% +0.1 0.25 ± 23% perf-profile.children.cycles-pp.ext4_mark_iloc_dirty 0.00 +0.1 0.14 ± 23% perf-profile.children.cycles-pp.__ext4_get_inode_loc 0.00 +0.1 0.15 ± 30% perf-profile.children.cycles-pp._raw_spin_lock_irqsave 0.14 ± 9% +0.2 0.29 ± 16% perf-profile.children.cycles-pp.grab_mapping_entry 0.05 ± 7% +0.2 0.21 ± 17% perf-profile.children.cycles-pp.get_unlocked_entry 0.05 ± 52% +0.2 0.22 ± 49% perf-profile.children.cycles-pp.writen 0.05 ± 52% +0.2 0.22 ± 49% perf-profile.children.cycles-pp.__GI___libc_write 0.05 ± 52% +0.2 0.22 ± 47% perf-profile.children.cycles-pp.record__pushfn 0.05 ± 55% +0.2 0.23 ± 47% perf-profile.children.cycles-pp.perf_mmap__push 0.02 ±122% +0.2 0.20 ± 47% perf-profile.children.cycles-pp.__generic_file_write_iter 0.02 ±123% +0.2 0.20 ± 47% perf-profile.children.cycles-pp.generic_perform_write 0.05 ± 52% +0.2 0.23 ± 42% perf-profile.children.cycles-pp.vfs_write 0.02 ±122% +0.2 0.21 ± 48% perf-profile.children.cycles-pp.generic_file_write_iter 0.04 ± 83% +0.2 0.22 ± 44% perf-profile.children.cycles-pp.new_sync_write 0.05 ± 55% +0.2 0.24 ± 48% perf-profile.children.cycles-pp.record__mmap_read_evlist 0.05 ± 52% +0.2 0.23 ± 43% perf-profile.children.cycles-pp.ksys_write 0.00 +0.2 0.20 ± 22% perf-profile.children.cycles-pp.ext4_reserve_inode_write 0.00 +0.2 0.20 ± 20% perf-profile.children.cycles-pp.xas_find_conflict 0.01 ±200% +0.2 0.23 ± 36% perf-profile.children.cycles-pp.tick_nohz_next_event 0.08 ± 18% +0.2 0.31 ± 48% perf-profile.children.cycles-pp.cmd_record 0.01 ±200% +0.3 0.28 ± 35% perf-profile.children.cycles-pp.tick_nohz_get_sleep_length 0.09 ± 16% +0.3 0.40 ± 31% perf-profile.children.cycles-pp.__libc_start_main 0.09 ± 16% +0.3 0.40 ± 31% perf-profile.children.cycles-pp.main 0.09 ± 16% +0.3 0.40 ± 31% perf-profile.children.cycles-pp.run_builtin 0.61 ± 10% +0.3 0.94 ± 26% perf-profile.children.cycles-pp.__mark_inode_dirty 0.45 ± 9% +0.3 0.78 ± 27% perf-profile.children.cycles-pp.ext4_dirty_inode 0.13 ± 11% +0.3 0.47 ± 23% perf-profile.children.cycles-pp.ext4_mark_inode_dirty 0.08 ± 23% +0.3 0.42 ± 38% perf-profile.children.cycles-pp.task_tick_fair 0.63 ± 10% +0.4 0.98 ± 26% perf-profile.children.cycles-pp.file_update_time 0.57 ± 10% +0.4 0.93 ± 27% perf-profile.children.cycles-pp.generic_update_time 0.00 +0.5 0.46 ± 20% perf-profile.children.cycles-pp.vmf_insert_pfn_pmd 0.10 ± 27% +0.5 0.57 ± 40% perf-profile.children.cycles-pp.scheduler_tick 0.06 ± 54% +0.5 0.58 ± 34% perf-profile.children.cycles-pp.menu_select 0.70 ± 24% +0.6 1.33 ± 36% perf-profile.children.cycles-pp.start_kernel 0.19 ± 36% +0.7 0.94 ± 42% perf-profile.children.cycles-pp.update_process_times 0.11 ± 11% +0.8 0.91 ± 15% perf-profile.children.cycles-pp.do_syscall_64 0.19 ± 36% +0.8 0.99 ± 42% perf-profile.children.cycles-pp.tick_sched_handle 0.11 ± 11% +0.8 0.91 ± 15% perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe 0.22 ± 32% +0.8 1.05 ± 42% perf-profile.children.cycles-pp.tick_sched_timer 0.26 ± 29% +1.0 1.25 ± 38% perf-profile.children.cycles-pp.__hrtimer_run_queues 0.00 +1.2 1.17 ± 19% perf-profile.children.cycles-pp.dax_iomap_pmd_fault 0.42 ± 23% +1.4 1.80 ± 40% perf-profile.children.cycles-pp.hrtimer_interrupt 0.52 ± 26% +2.1 2.58 ± 41% perf-profile.children.cycles-pp.smp_apic_timer_interrupt 0.56 ± 25% +2.1 2.69 ± 40% perf-profile.children.cycles-pp.apic_timer_interrupt 0.46 ± 8% +21.4 21.84 ± 13% perf-profile.children.cycles-pp.get_io_u 33.24 ± 15% +34.9 68.17 ± 4% perf-profile.children.cycles-pp.intel_idle 33.45 ± 15% +36.3 69.73 ± 4% perf-profile.children.cycles-pp.cpuidle_enter_state 33.45 ± 15% +36.3 69.74 ± 4% perf-profile.children.cycles-pp.cpuidle_enter 32.84 ± 15% +36.4 69.27 ± 4% perf-profile.children.cycles-pp.start_secondary 33.54 ± 15% +37.1 70.60 ± 4% perf-profile.children.cycles-pp.secondary_startup_64 33.54 ± 15% +37.1 70.60 ± 4% perf-profile.children.cycles-pp.cpu_startup_entry 33.55 ± 15% +37.1 70.60 ± 4% perf-profile.children.cycles-pp.do_idle 46.84 ± 12% -46.8 0.05 ± 59% perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath 3.44 ± 21% -3.3 0.13 ± 47% perf-profile.self.cycles-pp.start_this_handle 2.89 ± 17% -2.7 0.17 ± 39% perf-profile.self.cycles-pp.jbd2_journal_stop 2.63 ± 16% -2.2 0.46 ± 31% perf-profile.self.cycles-pp._raw_read_lock 1.70 ± 20% -1.6 0.14 ± 22% perf-profile.self.cycles-pp.ext4_journal_check_start 1.52 ± 20% -1.5 0.04 ±100% perf-profile.self.cycles-pp.add_transaction_credits 1.02 ± 6% -0.8 0.22 ± 23% perf-profile.self.cycles-pp._raw_spin_lock 1.06 ± 9% -0.7 0.39 ± 18% perf-profile.self.cycles-pp.find_next_iomem_res 0.08 ± 17% -0.1 0.03 ±100% perf-profile.self.cycles-pp.ext4_iomap_begin 0.15 ± 11% -0.1 0.10 ± 15% perf-profile.self.cycles-pp.rbt_memtype_lookup 0.06 ± 7% -0.0 0.03 ±100% perf-profile.self.cycles-pp.___might_sleep 0.00 +0.1 0.06 ± 11% perf-profile.self.cycles-pp.ext4_es_lookup_extent 0.00 +0.1 0.09 ± 19% perf-profile.self.cycles-pp.native_write_msr 0.04 ± 50% +0.1 0.13 ± 29% perf-profile.self.cycles-pp.ext4_mark_iloc_dirty 0.06 ± 8% +0.1 0.14 ± 18% perf-profile.self.cycles-pp.___perf_sw_event 0.00 +0.1 0.09 ± 24% perf-profile.self.cycles-pp.ext4_data_block_valid_rcu 0.00 +0.1 0.09 ± 28% perf-profile.self.cycles-pp.vmacache_find 0.00 +0.1 0.10 ± 22% perf-profile.self.cycles-pp.kmem_cache_alloc 0.00 +0.1 0.12 ± 27% perf-profile.self.cycles-pp._raw_spin_lock_irqsave 0.05 +0.1 0.18 ± 23% perf-profile.self.cycles-pp.dax_wake_entry 0.42 ± 9% +0.1 0.56 ± 6% perf-profile.self.cycles-pp.native_irq_return_iret 0.00 +0.2 0.16 ± 18% perf-profile.self.cycles-pp.xas_find_conflict 0.00 +0.2 0.18 ± 29% perf-profile.self.cycles-pp.menu_select 0.45 ± 9% +21.1 21.52 ± 14% perf-profile.self.cycles-pp.get_io_u 33.24 ± 15% +34.9 68.17 ± 4% perf-profile.self.cycles-pp.intel_idle

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, Rong Chen

1900

days inactive

1906

days old

linux-stable-mirror@lists.linaro.org

2 comments

participants

tags (0)

participants (3)

Dan Williams
Johannes Thumshirn
kernel test robot