Re: [LKP] [rcu] kernel BUG at include/linux/pagemap.h:149!
by Frederic Weisbecker
On Fri, Sep 11, 2015 at 10:19:47AM +0800, Boqun Feng wrote:
> Subject: [PATCH 01/27] rcu: Don't disable preemption for Tiny and Tree RCU
> readers
>
> Because preempt_disable() maps to barrier() for non-debug builds,
> it forces the compiler to spill and reload registers. Because Tree
> RCU and Tiny RCU now only appear in CONFIG_PREEMPT=n builds, these
> barrier() instances generate needless extra code for each instance of
> rcu_read_lock() and rcu_read_unlock(). This extra code slows down Tree
> RCU and bloats Tiny RCU.
>
> This commit therefore removes the preempt_disable() and preempt_enable()
> from the non-preemptible implementations of __rcu_read_lock() and
> __rcu_read_unlock(), respectively.
>
> For debug purposes, preempt_disable() and preempt_enable() are still
> kept if CONFIG_PREEMPT_COUNT=y, which makes the detection of sleeping
> inside atomic sections still work in non-preemptible kernels.
>
> Signed-off-by: Boqun Feng <boqun.feng(a)gmail.com>
> Signed-off-by: Paul E. McKenney <paulmck(a)linux.vnet.ibm.com>
> ---
> include/linux/rcupdate.h | 6 ++++--
> include/linux/rcutiny.h | 1 +
> kernel/rcu/tree.c | 9 +++++++++
> 3 files changed, 14 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
> index d63bb77..6c3cece 100644
> --- a/include/linux/rcupdate.h
> +++ b/include/linux/rcupdate.h
> @@ -297,12 +297,14 @@ void synchronize_rcu(void);
>
> static inline void __rcu_read_lock(void)
> {
> - preempt_disable();
> + if (IS_ENABLED(CONFIG_PREEMPT_COUNT))
> + preempt_disable();
preempt_disable() is a no-op when !CONFIG_PREEMPT_COUNT, right?
Or rather it's a barrier(), which is anyway implied by rcu_read_lock().
So perhaps we can get rid of the IS_ENABLED() check?
1 year, 3 months
- 4
- 4
Test monitoring on custom github repo
by Thomas Garnier
Hi,
I am working on KASLR (PIE for x86_64). I previously used Kees (CCed)
branches for lkp bot testing but someone told be I could ask you to add a
custom github path to monitor all branches on it.
I pushed my changes to: https://github.com/thgarnie/linux (kasrl_pie_v2
right now)
Can you add it? Anything I need to do?
Thanks,
--
Thomas
1 year, 8 months
- 3
- 4
[lkp-robot] [mm/cma] 2b0f904a5a: fio.read_bw_MBps -16.1% regression
by kernel test robot
Greeting,
FYI, we noticed a -16.1% regression of fio.read_bw_MBps due to commit:
commit: 2b0f904a5a8781498417d67226fd12c5e56053ae ("mm/cma: manage the memory of the CMA area by using the ZONE_MOVABLE")
https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git master
in testcase: fio-basic
on test machine: 56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory
with following parameters:
disk: 2pmem
fs: ext4
runtime: 200s
nr_task: 50%
time_based: tb
rw: randread
bs: 2M
ioengine: mmap
test_size: 200G
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
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/nr_task/rootfs/runtime/rw/tbox_group/test_size/testcase/time_based:
2M/gcc-7/performance/2pmem/ext4/mmap/x86_64-rhel-7.2/50%/debian-x86_64-2016-08-31.cgz/200s/randread/lkp-hsw-ep6/200G/fio-basic/tb
commit:
f6572f9cd2 ("mm/page_alloc: don't reserve ZONE_HIGHMEM for ZONE_MOVABLE request")
2b0f904a5a ("mm/cma: manage the memory of the CMA area by using the ZONE_MOVABLE")
f6572f9cd248df2c 2b0f904a5a8781498417d67226
---------------- --------------------------
%stddev %change %stddev
\ | \
11451 -16.1% 9605 fio.read_bw_MBps
0.29 ± 5% +0.1 0.40 ± 3% fio.latency_1000us%
19.35 ± 5% -4.7 14.69 ± 3% fio.latency_10ms%
7.92 ± 3% +12.2 20.15 fio.latency_20ms%
0.05 ± 11% +0.0 0.09 ± 8% fio.latency_2ms%
70.22 -8.9 61.36 fio.latency_4ms%
0.29 ± 13% +0.0 0.33 ± 3% fio.latency_500us%
0.45 ± 29% +1.0 1.45 ± 4% fio.latency_50ms%
1.37 +0.1 1.44 fio.latency_750us%
9792 +31.7% 12896 fio.read_clat_90%_us
10560 +33.0% 14048 fio.read_clat_95%_us
15376 ± 10% +46.9% 22592 fio.read_clat_99%_us
4885 +19.2% 5825 fio.read_clat_mean_us
5725 -16.1% 4802 fio.read_iops
4.598e+09 -16.4% 3.845e+09 fio.time.file_system_inputs
453153 -8.4% 415215 fio.time.involuntary_context_switches
5.748e+08 -16.4% 4.806e+08 fio.time.major_page_faults
1822257 +23.7% 2254706 fio.time.maximum_resident_set_size
5089 +1.6% 5172 fio.time.system_time
514.50 -16.3% 430.48 fio.time.user_time
24569 ± 2% +9.6% 26917 ± 2% fio.time.voluntary_context_switches
54443725 -14.9% 46353339 interrupts.CAL:Function_call_interrupts
0.00 ± 79% -0.0 0.00 ± 17% mpstat.cpu.iowait%
4.45 -0.7 3.71 mpstat.cpu.usr%
1467516 +21.3% 1779543 ± 3% meminfo.Active
1276031 +23.7% 1578443 ± 4% meminfo.Active(file)
25789 ± 3% -76.7% 6013 ± 4% meminfo.CmaFree
1.296e+08 -12.6% 1.133e+08 turbostat.IRQ
41.89 -3.4% 40.47 turbostat.RAMWatt
17444 ± 2% -13.5% 15092 ± 3% turbostat.SMI
10896428 -16.4% 9111830 vmstat.io.bi
6010 -6.2% 5637 vmstat.system.cs
317438 -12.1% 278980 vmstat.system.in
1072892 ± 3% +21.5% 1303487 numa-meminfo.node0.Active
978318 +21.6% 1189809 ± 2% numa-meminfo.node0.Active(file)
222968 -25.2% 166818 numa-meminfo.node0.PageTables
47374 ± 2% +10.6% 52402 ± 7% numa-meminfo.node0.SUnreclaim
165213 +31.9% 217870 numa-meminfo.node1.PageTables
222405 +10.4% 245633 ± 2% numa-meminfo.node1.SReclaimable
102992 ± 46% -80.8% 19812 ± 38% numa-meminfo.node1.Shmem
2.475e+08 ± 2% -24.0% 1.881e+08 numa-numastat.node0.local_node
39371795 ± 14% +167.1% 1.052e+08 ± 2% numa-numastat.node0.numa_foreign
2.475e+08 ± 2% -24.0% 1.881e+08 numa-numastat.node0.numa_hit
31890417 ± 17% +40.2% 44705135 ± 8% numa-numastat.node0.numa_miss
31899482 ± 17% +40.2% 44713255 ± 8% numa-numastat.node0.other_node
2.566e+08 ± 2% -44.2% 1.433e+08 numa-numastat.node1.local_node
31890417 ± 17% +40.2% 44705135 ± 8% numa-numastat.node1.numa_foreign
2.566e+08 ± 2% -44.2% 1.433e+08 numa-numastat.node1.numa_hit
39371795 ± 14% +167.1% 1.052e+08 ± 2% numa-numastat.node1.numa_miss
39373660 ± 14% +167.1% 1.052e+08 ± 2% numa-numastat.node1.other_node
6047 ± 39% -66.5% 2028 ± 63% sched_debug.cfs_rq:/.exec_clock.min
461.37 ± 8% +64.9% 760.74 ± 20% sched_debug.cfs_rq:/.load_avg.avg
1105 ± 13% +1389.3% 16467 ± 56% sched_debug.cfs_rq:/.load_avg.max
408.99 ± 3% +495.0% 2433 ± 49% sched_debug.cfs_rq:/.load_avg.stddev
28746 ± 12% -18.7% 23366 ± 14% sched_debug.cfs_rq:/.min_vruntime.min
752426 ± 3% -12.7% 656636 ± 4% sched_debug.cpu.avg_idle.avg
144956 ± 61% -85.4% 21174 ± 26% sched_debug.cpu.avg_idle.min
245684 ± 11% +44.6% 355257 ± 2% sched_debug.cpu.avg_idle.stddev
236035 ± 15% +51.8% 358264 ± 16% sched_debug.cpu.nr_switches.max
42039 ± 22% +34.7% 56616 ± 8% sched_debug.cpu.nr_switches.stddev
3204 ± 24% -48.1% 1663 ± 30% sched_debug.cpu.sched_count.min
2132 ± 25% +38.7% 2957 ± 11% sched_debug.cpu.sched_count.stddev
90.67 ± 32% -71.8% 25.58 ± 26% sched_debug.cpu.sched_goidle.min
6467 ± 15% +22.3% 7912 ± 15% sched_debug.cpu.ttwu_count.max
1513 ± 27% -55.7% 670.92 ± 22% sched_debug.cpu.ttwu_count.min
1025 ± 20% +68.4% 1727 ± 9% sched_debug.cpu.ttwu_count.stddev
1057 ± 16% -62.9% 391.85 ± 31% sched_debug.cpu.ttwu_local.min
244876 +21.6% 297770 ± 2% numa-vmstat.node0.nr_active_file
88.00 ± 5% +19.3% 105.00 ± 5% numa-vmstat.node0.nr_isolated_file
55778 -25.1% 41765 numa-vmstat.node0.nr_page_table_pages
11843 ± 2% +10.6% 13100 ± 7% numa-vmstat.node0.nr_slab_unreclaimable
159.25 ± 42% -74.9% 40.00 ± 52% numa-vmstat.node0.nr_vmscan_immediate_reclaim
244862 +21.6% 297739 ± 2% numa-vmstat.node0.nr_zone_active_file
19364320 ± 19% +187.2% 55617595 ± 2% numa-vmstat.node0.numa_foreign
268155 ± 3% +49.6% 401089 ± 4% numa-vmstat.node0.workingset_activate
1.229e+08 -19.0% 99590617 numa-vmstat.node0.workingset_refault
6345 ± 3% -76.5% 1489 ± 3% numa-vmstat.node1.nr_free_cma
41335 +32.0% 54552 numa-vmstat.node1.nr_page_table_pages
25770 ± 46% -80.8% 4956 ± 38% numa-vmstat.node1.nr_shmem
55684 +10.4% 61475 ± 2% numa-vmstat.node1.nr_slab_reclaimable
1.618e+08 ± 8% -47.6% 84846798 ± 17% numa-vmstat.node1.numa_hit
1.617e+08 ± 8% -47.6% 84676284 ± 17% numa-vmstat.node1.numa_local
19365342 ± 19% +187.2% 55620100 ± 2% numa-vmstat.node1.numa_miss
19534837 ± 19% +185.6% 55790654 ± 2% numa-vmstat.node1.numa_other
1.296e+08 -21.0% 1.024e+08 numa-vmstat.node1.workingset_refault
1.832e+12 -7.5% 1.694e+12 perf-stat.branch-instructions
0.25 -0.0 0.23 perf-stat.branch-miss-rate%
4.666e+09 -16.0% 3.918e+09 perf-stat.branch-misses
39.88 +1.1 40.98 perf-stat.cache-miss-rate%
2.812e+10 -11.6% 2.485e+10 perf-stat.cache-misses
7.051e+10 -14.0% 6.064e+10 perf-stat.cache-references
1260521 -6.1% 1183071 perf-stat.context-switches
1.87 +9.6% 2.05 perf-stat.cpi
6707 ± 2% -5.2% 6359 perf-stat.cpu-migrations
1.04 ± 11% -0.3 0.77 ± 4% perf-stat.dTLB-load-miss-rate%
2.365e+10 ± 7% -25.9% 1.751e+10 ± 9% perf-stat.dTLB-load-misses
1.05e+12 ± 4% -9.5% 9.497e+11 ± 2% perf-stat.dTLB-stores
28.16 +2.2 30.35 ± 2% perf-stat.iTLB-load-miss-rate%
2.56e+08 -10.4% 2.295e+08 perf-stat.iTLB-loads
8.974e+12 -9.2% 8.151e+12 perf-stat.instructions
89411 -8.8% 81529 perf-stat.instructions-per-iTLB-miss
0.54 -8.8% 0.49 perf-stat.ipc
5.748e+08 -16.4% 4.806e+08 perf-stat.major-faults
52.82 +5.8 58.61 ± 2% perf-stat.node-load-miss-rate%
7.206e+09 ± 2% -18.6% 5.867e+09 ± 3% perf-stat.node-loads
17.96 ± 8% +15.7 33.69 ± 2% perf-stat.node-store-miss-rate%
2.055e+09 ± 8% +65.1% 3.393e+09 ± 4% perf-stat.node-store-misses
9.391e+09 ± 2% -28.9% 6.675e+09 perf-stat.node-stores
5.753e+08 -16.4% 4.811e+08 perf-stat.page-faults
305865 -16.3% 256108 proc-vmstat.allocstall_movable
1923 ± 14% -72.1% 537.00 ± 12% proc-vmstat.allocstall_normal
0.00 +Inf% 1577 ± 67% proc-vmstat.compact_isolated
1005 ± 4% -65.8% 344.00 ± 7% proc-vmstat.kswapd_low_wmark_hit_quickly
320062 +23.2% 394374 ± 4% proc-vmstat.nr_active_file
6411 ± 2% -76.4% 1511 ± 4% proc-vmstat.nr_free_cma
277.00 ± 12% -51.4% 134.75 ± 52% proc-vmstat.nr_vmscan_immediate_reclaim
320049 +23.2% 394353 ± 4% proc-vmstat.nr_zone_active_file
71262212 ± 15% +110.3% 1.499e+08 ± 3% proc-vmstat.numa_foreign
5.042e+08 ± 2% -34.3% 3.314e+08 proc-vmstat.numa_hit
5.041e+08 ± 2% -34.3% 3.314e+08 proc-vmstat.numa_local
71262212 ± 15% +110.3% 1.499e+08 ± 3% proc-vmstat.numa_miss
71273176 ± 15% +110.3% 1.499e+08 ± 3% proc-vmstat.numa_other
1007 ± 4% -65.6% 346.25 ± 7% proc-vmstat.pageoutrun
23070268 -16.0% 19386190 proc-vmstat.pgalloc_dma32
5.525e+08 -16.7% 4.603e+08 proc-vmstat.pgalloc_normal
5.753e+08 -16.4% 4.812e+08 proc-vmstat.pgfault
5.751e+08 -16.3% 4.813e+08 proc-vmstat.pgfree
5.748e+08 -16.4% 4.806e+08 proc-vmstat.pgmajfault
2.299e+09 -16.4% 1.923e+09 proc-vmstat.pgpgin
8.396e+08 -17.8% 6.901e+08 proc-vmstat.pgscan_direct
3.018e+08 ± 2% -13.0% 2.627e+08 proc-vmstat.pgscan_kswapd
4.1e+08 -15.1% 3.48e+08 proc-vmstat.pgsteal_direct
1.542e+08 ± 3% -20.9% 1.22e+08 ± 3% proc-vmstat.pgsteal_kswapd
23514 ± 4% -23.1% 18076 ± 16% proc-vmstat.slabs_scanned
343040 ± 2% +40.3% 481253 ± 2% proc-vmstat.workingset_activate
2.525e+08 -20.1% 2.018e+08 proc-vmstat.workingset_refault
13.64 ± 3% -1.7 11.96 ± 2% perf-profile.calltrace.cycles-pp.ext4_mpage_readpages.filemap_fault.ext4_filemap_fault.__do_fault.__handle_mm_fault
11.67 ± 3% -1.4 10.29 ± 2% perf-profile.calltrace.cycles-pp.submit_bio.ext4_mpage_readpages.filemap_fault.ext4_filemap_fault.__do_fault
11.64 ± 3% -1.4 10.25 ± 2% perf-profile.calltrace.cycles-pp.generic_make_request.submit_bio.ext4_mpage_readpages.filemap_fault.ext4_filemap_fault
11.10 ± 3% -1.3 9.82 ± 2% perf-profile.calltrace.cycles-pp.pmem_make_request.generic_make_request.submit_bio.ext4_mpage_readpages.filemap_fault
9.21 ± 3% -1.2 8.04 ± 3% perf-profile.calltrace.cycles-pp.pmem_do_bvec.pmem_make_request.generic_make_request.submit_bio.ext4_mpage_readpages
27.33 ± 4% -1.0 26.35 ± 5% perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_secondary.secondary_startup_64
27.33 ± 4% -1.0 26.35 ± 5% perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64
27.33 ± 4% -1.0 26.35 ± 5% perf-profile.calltrace.cycles-pp.cpuidle_enter_state.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64
27.33 ± 4% -1.0 26.35 ± 5% perf-profile.calltrace.cycles-pp.start_secondary.secondary_startup_64
26.79 ± 4% -0.8 25.98 ± 5% perf-profile.calltrace.cycles-pp.intel_idle.cpuidle_enter_state.do_idle.cpu_startup_entry.start_secondary
27.98 ± 3% -0.8 27.22 ± 4% perf-profile.calltrace.cycles-pp.secondary_startup_64
5.36 ± 12% -0.6 4.76 ± 7% perf-profile.calltrace.cycles-pp.kswapd.kthread.ret_from_fork
5.36 ± 12% -0.6 4.76 ± 7% perf-profile.calltrace.cycles-pp.shrink_node.kswapd.kthread.ret_from_fork
5.30 ± 12% -0.6 4.71 ± 7% perf-profile.calltrace.cycles-pp.shrink_inactive_list.shrink_node_memcg.shrink_node.kswapd.kthread
5.35 ± 12% -0.6 4.76 ± 7% perf-profile.calltrace.cycles-pp.shrink_node_memcg.shrink_node.kswapd.kthread.ret_from_fork
5.43 ± 12% -0.5 4.88 ± 7% perf-profile.calltrace.cycles-pp.ret_from_fork
5.43 ± 12% -0.5 4.88 ± 7% perf-profile.calltrace.cycles-pp.kthread.ret_from_fork
11.04 ± 2% -0.2 10.82 ± 2% perf-profile.calltrace.cycles-pp.shrink_page_list.shrink_inactive_list.shrink_node_memcg.shrink_node.do_try_to_free_pages
62.44 ± 2% +1.9 64.38 perf-profile.calltrace.cycles-pp.page_fault
62.38 ± 2% +2.0 64.33 perf-profile.calltrace.cycles-pp.__do_page_fault.do_page_fault.page_fault
62.38 ± 2% +2.0 64.34 perf-profile.calltrace.cycles-pp.do_page_fault.page_fault
61.52 ± 2% +2.1 63.58 perf-profile.calltrace.cycles-pp.handle_mm_fault.__do_page_fault.do_page_fault.page_fault
61.34 ± 2% +2.1 63.44 perf-profile.calltrace.cycles-pp.__handle_mm_fault.handle_mm_fault.__do_page_fault.do_page_fault.page_fault
30.18 ± 3% +2.3 32.45 ± 2% perf-profile.calltrace.cycles-pp.shrink_inactive_list.shrink_node_memcg.shrink_node.do_try_to_free_pages.try_to_free_pages
7.98 ± 3% +2.3 10.33 ± 2% perf-profile.calltrace.cycles-pp.add_to_page_cache_lru.filemap_fault.ext4_filemap_fault.__do_fault.__handle_mm_fault
30.48 ± 3% +2.4 32.83 ± 2% perf-profile.calltrace.cycles-pp.try_to_free_pages.__alloc_pages_slowpath.__alloc_pages_nodemask.filemap_fault.ext4_filemap_fault
30.46 ± 3% +2.4 32.81 ± 2% perf-profile.calltrace.cycles-pp.do_try_to_free_pages.try_to_free_pages.__alloc_pages_slowpath.__alloc_pages_nodemask.filemap_fault
30.46 ± 3% +2.4 32.81 ± 2% perf-profile.calltrace.cycles-pp.shrink_node.do_try_to_free_pages.try_to_free_pages.__alloc_pages_slowpath.__alloc_pages_nodemask
30.37 ± 3% +2.4 32.75 ± 2% perf-profile.calltrace.cycles-pp.shrink_node_memcg.shrink_node.do_try_to_free_pages.try_to_free_pages.__alloc_pages_slowpath
5.58 ± 4% +2.5 8.08 ± 2% perf-profile.calltrace.cycles-pp.__lru_cache_add.add_to_page_cache_lru.filemap_fault.ext4_filemap_fault.__do_fault
32.88 ± 3% +2.5 35.38 ± 2% perf-profile.calltrace.cycles-pp.__alloc_pages_nodemask.filemap_fault.ext4_filemap_fault.__do_fault.__handle_mm_fault
5.51 ± 4% +2.5 8.02 ± 2% perf-profile.calltrace.cycles-pp.pagevec_lru_move_fn.__lru_cache_add.add_to_page_cache_lru.filemap_fault.ext4_filemap_fault
4.24 ± 4% +2.5 6.76 ± 2% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.pagevec_lru_move_fn.__lru_cache_add.add_to_page_cache_lru.filemap_fault
4.18 ± 4% +2.5 6.70 ± 2% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irqsave.pagevec_lru_move_fn.__lru_cache_add.add_to_page_cache_lru
18.64 ± 3% +2.5 21.16 ± 2% perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock_irq.shrink_inactive_list.shrink_node_memcg.shrink_node
31.65 ± 3% +2.7 34.31 ± 2% perf-profile.calltrace.cycles-pp.__alloc_pages_slowpath.__alloc_pages_nodemask.filemap_fault.ext4_filemap_fault.__do_fault
17.21 ± 3% +2.7 19.93 ± 2% perf-profile.calltrace.cycles-pp._raw_spin_lock_irq.shrink_inactive_list.shrink_node_memcg.shrink_node.do_try_to_free_pages
56.37 ± 2% +2.8 59.21 perf-profile.calltrace.cycles-pp.__do_fault.__handle_mm_fault.handle_mm_fault.__do_page_fault.do_page_fault
56.36 ± 2% +2.8 59.20 perf-profile.calltrace.cycles-pp.ext4_filemap_fault.__do_fault.__handle_mm_fault.handle_mm_fault.__do_page_fault
56.10 ± 2% +2.9 58.97 perf-profile.calltrace.cycles-pp.filemap_fault.ext4_filemap_fault.__do_fault.__handle_mm_fault.handle_mm_fault
13.66 ± 3% -1.7 11.98 ± 2% perf-profile.children.cycles-pp.ext4_mpage_readpages
11.69 ± 3% -1.4 10.30 ± 2% perf-profile.children.cycles-pp.submit_bio
11.64 ± 3% -1.4 10.26 ± 2% perf-profile.children.cycles-pp.generic_make_request
11.12 ± 3% -1.3 9.84 ± 2% perf-profile.children.cycles-pp.pmem_make_request
9.27 ± 3% -1.1 8.12 ± 3% perf-profile.children.cycles-pp.pmem_do_bvec
27.33 ± 4% -1.0 26.35 ± 5% perf-profile.children.cycles-pp.start_secondary
27.98 ± 3% -0.8 27.22 ± 4% perf-profile.children.cycles-pp.secondary_startup_64
27.98 ± 3% -0.8 27.22 ± 4% perf-profile.children.cycles-pp.cpu_startup_entry
27.98 ± 3% -0.8 27.22 ± 4% perf-profile.children.cycles-pp.do_idle
27.97 ± 3% -0.8 27.22 ± 4% perf-profile.children.cycles-pp.cpuidle_enter_state
5.36 ± 12% -0.6 4.76 ± 7% perf-profile.children.cycles-pp.kswapd
27.42 ± 4% -0.6 26.84 ± 5% perf-profile.children.cycles-pp.intel_idle
5.43 ± 12% -0.5 4.88 ± 7% perf-profile.children.cycles-pp.kthread
5.43 ± 12% -0.5 4.88 ± 7% perf-profile.children.cycles-pp.ret_from_fork
14.25 -0.4 13.80 ± 2% perf-profile.children.cycles-pp.shrink_page_list
35.60 +1.7 37.31 ± 2% perf-profile.children.cycles-pp.shrink_inactive_list
35.89 +1.8 37.67 ± 2% perf-profile.children.cycles-pp.shrink_node
35.80 +1.8 37.60 ± 2% perf-profile.children.cycles-pp.shrink_node_memcg
62.46 ± 2% +2.0 64.41 perf-profile.children.cycles-pp.page_fault
62.43 ± 2% +2.0 64.39 perf-profile.children.cycles-pp.__do_page_fault
62.41 ± 2% +2.0 64.39 perf-profile.children.cycles-pp.do_page_fault
61.55 ± 2% +2.1 63.63 perf-profile.children.cycles-pp.handle_mm_fault
61.37 ± 2% +2.1 63.49 perf-profile.children.cycles-pp.__handle_mm_fault
8.00 ± 3% +2.3 10.35 ± 2% perf-profile.children.cycles-pp.add_to_page_cache_lru
30.55 ± 3% +2.4 32.92 ± 2% perf-profile.children.cycles-pp.try_to_free_pages
30.53 ± 3% +2.4 32.91 ± 2% perf-profile.children.cycles-pp.do_try_to_free_pages
5.59 ± 4% +2.5 8.09 ± 2% perf-profile.children.cycles-pp.__lru_cache_add
5.61 ± 4% +2.5 8.12 ± 2% perf-profile.children.cycles-pp.pagevec_lru_move_fn
32.97 ± 3% +2.5 35.50 ± 2% perf-profile.children.cycles-pp.__alloc_pages_nodemask
5.26 ± 4% +2.6 7.89 perf-profile.children.cycles-pp._raw_spin_lock_irqsave
19.05 ± 3% +2.7 21.72 ± 3% perf-profile.children.cycles-pp._raw_spin_lock_irq
31.72 ± 3% +2.7 34.41 ± 2% perf-profile.children.cycles-pp.__alloc_pages_slowpath
56.29 ± 2% +2.8 59.07 perf-profile.children.cycles-pp.filemap_fault
56.38 ± 2% +2.8 59.23 perf-profile.children.cycles-pp.__do_fault
56.37 ± 2% +2.8 59.21 perf-profile.children.cycles-pp.ext4_filemap_fault
24.54 +5.3 29.82 ± 2% perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath
9.20 ± 3% -1.2 8.04 ± 3% perf-profile.self.cycles-pp.pmem_do_bvec
27.42 ± 4% -0.6 26.84 ± 5% perf-profile.self.cycles-pp.intel_idle
24.54 +5.3 29.82 ± 2% perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath
fio.read_bw_MBps
11600 +-+-----------------------------------------------------------------+
11400 +-+. .+..+.+.+.+ .+.. .+. .+ + .+. .+.+.+. .+.+.+.+..+.+.+.+.|
| + + .+.+ + + + +. + |
11200 +-+ + |
11000 +-+ |
10800 +-+ |
10600 +-+ |
| |
10400 +-+ |
10200 +-+ |
10000 +-+ |
9800 +-+ |
O O O O O O O O O O |
9600 +-O O O O O O O O O |
9400 +-+-----------------------------------------------------------------+
fio.read_iops
5800 +-+------------------------------------------------------------------+
5700 +-+. .+..+.+.+.+ .+. .+. .+. + .+. .+.+.+.. .+.+.+.+.+..+.+.+.|
| + + .+..+ + + + + + |
5600 +-+ + |
5500 +-+ |
5400 +-+ |
5300 +-+ |
| |
5200 +-+ |
5100 +-+ |
5000 +-+ |
4900 +-+ |
O O O O O O O O O O |
4800 +-O O O O O O O O O |
4700 +-+------------------------------------------------------------------+
fio.read_clat_mean_us
6000 +-+------------------------------------------------------------------+
| |
5800 +-O O O O O O O O O O O O O O O |
O O O O |
| |
5600 +-+ |
| |
5400 +-+ |
| |
5200 +-+ |
| |
| +. |
5000 +-+ + +..+. .+. .+. .+. .+. |
| +.+.+..+.+.+.+ +.+.+ +..+ + +.+.+. +.+.+.+.+..+.+.+.|
4800 +-+------------------------------------------------------------------+
[*] 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.
Thanks,
Xiaolong
2 years, 4 months
- 4
- 12
[test_parman_move] watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [swapper:1]
by Fengguang Wu
Hello,
FYI this happens in mainline kernel 4.15.0-rc1.
It at least dates back to v4.12 .
It occurs in 2 out of 2 boots.
[ 95.347718] test passed
[ 95.359028] test_printf: all 260 tests passed
[ 96.656859] test_bitmap: test 13: input is '0-2047:128/256' OK, Time: 3332
[ 96.770961] test_bitmap: all 460506 tests passed
[ 96.783469] test_uuid: all 18 tests passed
[ 124.230111] watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [swapper:1]
[ 124.230111] CPU: 0 PID: 1 Comm: swapper Not tainted 4.15.0-rc1 #360
[ 124.230111] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014
[ 124.230111] task: d3430000 task.stack: d342c000
[ 124.230111] EIP: test_parman_move+0xe/0xb0:
test_parman_move at lib/test_parman.c:119
[ 124.230111] EFLAGS: 00200212 CPU: 0
[ 124.230111] EAX: d0c00000 EBX: 00000004 ECX: 00000930 EDX: 0000090c
[ 124.230111] ESI: d0740324 EDI: d359f680 EBP: d342dec4 ESP: d342debc
[ 124.230111] DS: 007b ES: 007b FS: 0000 GS: 0000 SS: 0068
[ 124.230111] CR0: 80050033 CR2: 00000000 CR3: 02b2b000 CR4: 000006b0
[ 124.230111] Call Trace:
[ 124.230111] parman_lsort_item_add+0x9d/0x190:
__list_del_entry at include/linux/list.h:117
(inlined by) list_move_tail at include/linux/list.h:182
(inlined by) parman_prio_shift_down at lib/parman.c:144
(inlined by) parman_lsort_item_add at lib/parman.c:200
[ 124.230111] parman_item_add+0x9/0x10:
parman_item_add at lib/parman.c:356
[ 124.230111] test_parman_init+0x358/0x3b5:
test_parman_run at lib/test_parman.c:284
(inlined by) test_parman_lsort at lib/test_parman.c:369
(inlined by) test_parman_init at lib/test_parman.c:383
[ 124.230111] ? test_uuid_init+0x1a9/0x1a9:
test_parman_init at lib/test_parman.c:382
[ 124.230111] do_one_initcall+0x7c/0x10e:
do_one_initcall at init/main.c:826
[ 124.230111] ? kernel_init_freeable+0xc3/0x15b:
do_initcall_level at init/main.c:891
(inlined by) do_initcalls at init/main.c:900
(inlined by) do_basic_setup at init/main.c:918
(inlined by) kernel_init_freeable at init/main.c:1066
[ 124.230111] kernel_init_freeable+0xe3/0x15b:
do_initcall_level at init/main.c:892
(inlined by) do_initcalls at init/main.c:900
(inlined by) do_basic_setup at init/main.c:918
(inlined by) kernel_init_freeable at init/main.c:1066
[ 124.230111] ? rest_init+0xc0/0xc0:
kernel_init at init/main.c:990
[ 124.230111] kernel_init+0xb/0xf0:
kernel_init at init/main.c:995
[ 124.230111] ? schedule_tail_wrapper+0x9/0xc:
schedule_tail_wrapper at arch/x86/entry/entry_32.S:267
[ 124.230111] ret_from_fork+0x19/0x24:
ret_from_fork at arch/x86/entry/entry_32.S:299
[ 124.230111] Code: e8 48 5f c2 00 5d 85 c0 0f 94 c0 0f b6 c0 c3 90 90 90 90 90 90 90 90 90 90 90 90 90 90 55 89 e5 57 53 8b 5d 08 8b 40 04 c1 e3 02 <8d> 3c 90 89 fa 8d 04 88 89 d9 e8 a3 be c2 00 83 fb 08 89 da 73
[ 124.230111] Kernel panic - not syncing: softlockup: hung tasks
[ 124.230111] CPU: 0 PID: 1 Comm: swapper Tainted: G L 4.15.0-rc1 #360
[ 124.230111] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014
[ 124.230111] Call Trace:
[ 124.230111] dump_stack+0x16/0x19:
dump_stack at lib/dump_stack.c:64
[ 124.230111] panic+0x86/0x1bd:
panic at kernel/panic.c:194
[ 124.230111] watchdog_timer_fn+0x1e7/0x1f0:
watchdog_timer_fn at kernel/watchdog.c:443
[ 124.230111] ? watchdog+0x20/0x20:
watchdog_timer_fn at kernel/watchdog.c:340
[ 124.230111] hrtimer_run_queues+0xf3/0x1d0:
__run_hrtimer at kernel/time/hrtimer.c:1211
(inlined by) __hrtimer_run_queues at kernel/time/hrtimer.c:1275
(inlined by) hrtimer_run_queues at kernel/time/hrtimer.c:1414
[ 124.230111] run_local_timers+0x8/0x40:
run_local_timers at kernel/time/timer.c:1700
[ 124.230111] update_process_times+0x22/0x50:
update_process_times at kernel/time/timer.c:1630
[ 124.230111] tick_nohz_handler+0x66/0x100:
tick_nohz_handler at kernel/time/tick-sched.c:1068
[ 124.230111] smp_apic_timer_interrupt+0x40/0x80:
exiting_irq at arch/x86/include/asm/apic.h:540
(inlined by) smp_apic_timer_interrupt at arch/x86/kernel/apic/apic.c:1052
[ 124.230111] ? irq_exit+0x2f/0xb0:
tick_irq_exit at kernel/softirq.c:385
(inlined by) irq_exit at kernel/softirq.c:407
[ 124.230111] apic_timer_interrupt+0x35/0x3c:
apic_timer_interrupt at arch/x86/include/asm/entry_arch.h:36
[ 124.230111] EIP: test_parman_move+0xe/0xb0:
test_parman_move at lib/test_parman.c:119
[ 124.230111] EFLAGS: 00200212 CPU: 0
[ 124.230111] EAX: d0c00000 EBX: 00000004 ECX: 00000930 EDX: 0000090c
[ 124.230111] ESI: d0740324 EDI: d359f680 EBP: d342dec4 ESP: d342debc
[ 124.230111] DS: 007b ES: 007b FS: 0000 GS: 0000 SS: 0068
[ 124.230111] parman_lsort_item_add+0x9d/0x190:
__list_del_entry at include/linux/list.h:117
(inlined by) list_move_tail at include/linux/list.h:182
(inlined by) parman_prio_shift_down at lib/parman.c:144
(inlined by) parman_lsort_item_add at lib/parman.c:200
[ 124.230111] parman_item_add+0x9/0x10:
parman_item_add at lib/parman.c:356
[ 124.230111] test_parman_init+0x358/0x3b5:
test_parman_run at lib/test_parman.c:284
(inlined by) test_parman_lsort at lib/test_parman.c:369
(inlined by) test_parman_init at lib/test_parman.c:383
[ 124.230111] ? test_uuid_init+0x1a9/0x1a9:
test_parman_init at lib/test_parman.c:382
[ 124.230111] do_one_initcall+0x7c/0x10e:
do_one_initcall at init/main.c:826
[ 124.230111] ? kernel_init_freeable+0xc3/0x15b:
do_initcall_level at init/main.c:891
(inlined by) do_initcalls at init/main.c:900
(inlined by) do_basic_setup at init/main.c:918
(inlined by) kernel_init_freeable at init/main.c:1066
[ 124.230111] kernel_init_freeable+0xe3/0x15b:
do_initcall_level at init/main.c:892
(inlined by) do_initcalls at init/main.c:900
(inlined by) do_basic_setup at init/main.c:918
(inlined by) kernel_init_freeable at init/main.c:1066
[ 124.230111] ? rest_init+0xc0/0xc0:
kernel_init at init/main.c:990
[ 124.230111] kernel_init+0xb/0xf0:
kernel_init at init/main.c:995
[ 124.230111] ? schedule_tail_wrapper+0x9/0xc:
schedule_tail_wrapper at arch/x86/entry/entry_32.S:267
[ 124.230111] ret_from_fork+0x19/0x24:
ret_from_fork at arch/x86/entry/entry_32.S:299
[ 124.230111] Kernel Offset: disabled
Attached the full dmesg, kconfig and reproduce scripts.
Thanks,
Fengguang
2 years, 5 months
- 1
- 1
[mm] b1f0502d04: INFO:trying_to_register_non-static_key
by kernel test robot
FYI, we noticed the following commit (built with gcc-7):
commit: b1f0502d04537ef55b0c296823affe332b100eb5 ("mm: VMA sequence count")
url: https://github.com/0day-ci/linux/commits/Laurent-Dufour/Speculative-page-...
in testcase: trinity
with following parameters:
runtime: 300s
test-description: Trinity is a linux system call fuzz tester.
test-url: http://codemonkey.org.uk/projects/trinity/
on test machine: qemu-system-x86_64 -enable-kvm -cpu SandyBridge -m 512M
caused below changes (please refer to attached dmesg/kmsg for entire log/backtrace):
+----------------------------------------+------------+------------+
| | 6a4ce82339 | b1f0502d04 |
+----------------------------------------+------------+------------+
| boot_successes | 8 | 4 |
| boot_failures | 0 | 4 |
| INFO:trying_to_register_non-static_key | 0 | 4 |
+----------------------------------------+------------+------------+
[ 22.212940] INFO: trying to register non-static key.
[ 22.213687] the code is fine but needs lockdep annotation.
[ 22.214459] turning off the locking correctness validator.
[ 22.227459] CPU: 0 PID: 547 Comm: trinity-main Not tainted 4.16.0-rc4-next-20180309-00007-gb1f0502 #239
[ 22.228904] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014
[ 22.230043] Call Trace:
[ 22.230409] dump_stack+0x5d/0x79
[ 22.231025] register_lock_class+0x226/0x45e
[ 22.231827] ? kvm_clock_read+0x21/0x30
[ 22.232544] ? kvm_sched_clock_read+0x5/0xd
[ 22.233330] __lock_acquire+0xa2/0x774
[ 22.234152] lock_acquire+0x4b/0x66
[ 22.234805] ? unmap_vmas+0x30/0x3d
[ 22.245680] unmap_page_range+0x56/0x48c
[ 22.248127] ? unmap_vmas+0x30/0x3d
[ 22.248741] ? lru_deactivate_file_fn+0x2c6/0x2c6
[ 22.249537] ? pagevec_lru_move_fn+0x9a/0xa9
[ 22.250244] unmap_vmas+0x30/0x3d
[ 22.250791] unmap_region+0xad/0x105
[ 22.251419] mmap_region+0x3cc/0x455
[ 22.252011] do_mmap+0x394/0x3e9
[ 22.261224] vm_mmap_pgoff+0x9c/0xe5
[ 22.261798] SyS_mmap_pgoff+0x19a/0x1d4
[ 22.262475] ? task_work_run+0x5e/0x9c
[ 22.263163] do_syscall_64+0x6d/0x103
[ 22.263814] entry_SYSCALL_64_after_hwframe+0x3d/0xa2
[ 22.264697] RIP: 0033:0x4573da
[ 22.267248] RSP: 002b:00007fffa22f1398 EFLAGS: 00000246 ORIG_RAX: 0000000000000009
[ 22.274720] RAX: ffffffffffffffda RBX: 0000000000000001 RCX: 00000000004573da
[ 22.276083] RDX: 0000000000000001 RSI: 0000000000001000 RDI: 0000000000000000
[ 22.277343] RBP: 000000000000001c R08: 000000000000001c R09: 0000000000000000
[ 22.278686] R10: 0000000000000002 R11: 0000000000000246 R12: 0000000000000000
[ 22.279930] R13: 0000000000001000 R14: 0000000000000002 R15: 0000000000000000
[ 22.391866] trinity-main uses obsolete (PF_INET,SOCK_PACKET)
[ 327.566956] sysrq: SysRq : Emergency Sync
[ 327.567849] Emergency Sync complete
[ 327.569975] sysrq: SysRq : Resetting
Elapsed time: 330
#!/bin/bash
# To reproduce,
# 1) save job-script and this script (both are attached in 0day report email)
# 2) run this script with your compiled kernel and optional env $INSTALL_MOD_PATH
kernel=$1
initrds=(
/osimage/yocto/yocto-minimal-x86_64-2016-04-22.cgz
/lkp/lkp/lkp-x86_64.cgz
/osimage/pkg/debian-x86_64-2016-08-31.cgz/trinity-static-x86_64-x86_64-6ddabfd2_2017-11-10.cgz
)
HTTP_PREFIX=https://github.com/0day-ci/lkp-qemu/raw/master
wget --timestamping "${initrds[@]/#/$HTTP_PREFIX}"
{
cat "${initrds[@]//*\//}"
[[ $INSTALL_MOD_PATH ]] && (
cd "$INSTALL_MOD_PATH"
find lib | cpio -o -H newc --quiet | gzip
)
echo job-script | cpio -o -H newc --quiet | gzip
} > initrd.img
qemu-img create -f qcow2 disk-vm-kbuild-yocto-x86_64-62-0 256G
kvm=(
qemu-system-x86_64
-enable-kvm
-cpu SandyBridge
-kernel $kernel
-initrd initrd.img
-m 512
-smp 1
-device e1000,netdev=net0
-netdev user,id=net0
-boot order=nc
-no-reboot
-watchdog i6300esb
-watchdog-action debug
-rtc base=localtime
-drive file=disk-vm-kbuild-yocto-x86_64-62-0,media=disk,if=virtio
-serial stdio
-display none
-monitor null
)
append=(
ip=::::vm-kbuild-yocto-x86_64-62::dhcp
root=/dev/ram0
user=lkp
job=/job-script
ARCH=x86_64
kconfig=x86_64-acpi-redef
branch=linux-devel/devel-catchup-201803161558
commit=b1f0502d04537ef55b0c296823affe332b100eb5
BOOT_IMAGE=/pkg/linux/x86_64-acpi-redef/gcc-7/b1f0502d04537ef55b0c296823affe332b100eb5/vmlinuz-4.16.0-rc4-next-20180309-00007-gb1f0502
max_uptime=1500
RESULT_ROOT=/result/trinity/300s/vm-kbuild-yocto-x86_64/yocto-minimal-x86_64-2016-04-22.cgz/x86_64-acpi-redef/gcc-7/b1f0502d04537ef55b0c296823affe332b100eb5/0
To reproduce:
git clone https://github.com/intel/lkp-tests.git
cd lkp-tests
bin/lkp qemu -k <bzImage> job-script # job-script is attached in this email
Thanks,
lkp
2 years, 5 months
- 3
- 9
[lkp-robot] [mm, numa] 9164ea32f3: stress-ng.numa.ops_per_sec -98.4% regression
by kernel test robot
Greeting,
We noticed a -98.4% regression of stress-ng.numa.ops_per_sec due to commit:
commit: 9164ea32f3057fd78f1ec8651f8fbc8ebc22f11b ("mm, numa: rework do_pages_move")
https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git master
in testcase: stress-ng
on test machine: 88 threads Intel(R) Xeon(R) CPU E5-2699 v4 @ 2.20GHz with 128G memory
with following parameters:
nr_threads: 100%
testtime: 60s
class: cpu
cpufreq_governor: performance
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
=========================================================================================
tbox_group/testcase/rootfs/kconfig/compiler/nr_threads/testtime/class/cpufreq_governor:
lkp-bdw-ep6/stress-ng/debian-x86_64-2016-08-31.cgz/x86_64-rhel-7.2/gcc-7/100%/60s/cpu/performance
commit:
a342b6bb547a31d83bf518d019c3b79f18cb4fcb
9164ea32f3057fd78f1ec8651f8fbc8ebc22f11b
a342b6bb547a31d8 9164ea32f3057fd78f1ec8651f
---------------- --------------------------
%stddev %change %stddev
\ | \
352.00 -50.0% 176.00 stress-ng.numa.ops
184.45 ± 3% -98.4% 2.88 stress-ng.numa.ops_per_sec
1388 +4.2% 1447 stress-ng.time.elapsed_time
1388 +4.2% 1447 stress-ng.time.elapsed_time.max
2.018e+08 +3.4% 2.086e+08 stress-ng.time.minor_page_faults
13855 +38.1% 19135 stress-ng.time.system_time
80826 ± 6% +257.6% 289070 numa-numastat.node0.other_node
97187 ± 5% +221.6% 312523 numa-numastat.node1.other_node
47961 ± 4% -16.6% 40014 slabinfo.kmalloc-32.active_objs
49364 ± 4% -15.2% 41862 slabinfo.kmalloc-32.num_objs
426.75 ± 7% -18.9% 346.25 ± 10% slabinfo.uid_cache.active_objs
517.00 ± 5% -18.8% 420.00 ± 7% slabinfo.uid_cache.num_objs
1388 +4.2% 1447 time.elapsed_time
1388 +4.2% 1447 time.elapsed_time.max
2.018e+08 +3.4% 2.086e+08 time.minor_page_faults
13855 +38.1% 19135 time.system_time
97993 ± 23% +51.6% 148559 ± 12% numa-meminfo.node0.Active
97993 ± 23% +51.6% 148558 ± 12% numa-meminfo.node0.Active(anon)
876.25 +20.7% 1057 ± 15% numa-meminfo.node0.Mlocked
50291 ± 27% +65.6% 83304 ± 7% numa-meminfo.node0.Shmem
67890 ± 28% -38.1% 42057 ± 15% numa-meminfo.node1.Shmem
24515 ± 23% +51.7% 37183 ± 12% numa-vmstat.node0.nr_active_anon
12.50 ± 20% +7180.0% 910.00 ± 4% numa-vmstat.node0.nr_isolated_anon
12606 ± 27% +65.4% 20849 ± 7% numa-vmstat.node0.nr_shmem
24515 ± 23% +51.7% 37184 ± 12% numa-vmstat.node0.nr_zone_active_anon
36187 ± 10% +196.0% 107098 ± 2% numa-vmstat.node0.numa_other
8.75 ± 54% +9928.6% 877.50 ± 3% numa-vmstat.node1.nr_isolated_anon
17014 ± 28% -38.1% 10527 ± 15% numa-vmstat.node1.nr_shmem
205708 +39.5% 286961 numa-vmstat.node1.numa_other
0.06 ± 8% -10.6% 0.06 ± 2% sched_debug.cfs_rq:/.nr_running.stddev
103.10 ± 13% +28.3% 132.28 ± 16% sched_debug.cpu.cpu_load[3].max
821150 ± 12% +36.3% 1119548 ± 11% sched_debug.cpu.nr_switches.max
121109 ± 2% +18.9% 143997 ± 9% sched_debug.cpu.nr_switches.stddev
394588 ± 13% +37.3% 541730 ± 11% sched_debug.cpu.ttwu_count.max
60367 ± 2% +18.7% 71679 ± 9% sched_debug.cpu.ttwu_count.stddev
339921 ± 15% +43.4% 487333 ± 12% sched_debug.cpu.ttwu_local.max
59641 ± 2% +18.9% 70937 ± 9% sched_debug.cpu.ttwu_local.stddev
16.50 ± 61% +10810.6% 1800 proc-vmstat.nr_isolated_anon
178024 +237.9% 601602 proc-vmstat.numa_other
61749688 +62.9% 1.006e+08 ± 21% proc-vmstat.pgalloc_movable
4.614e+08 +96.8% 9.079e+08 ± 2% proc-vmstat.pgalloc_normal
5.231e+08 +92.8% 1.008e+09 proc-vmstat.pgfree
251013 +339.4% 1102868 proc-vmstat.pgmigrate_success
25175 +3787.0% 978576 proc-vmstat.thp_deferred_split_page
3064 ± 7% -50.4% 1519 ± 22% proc-vmstat.unevictable_pgs_cleared
stress-ng.numa.ops
400 +-+-------------------------------------------------------------------+
| |
350 +-+.+..+.+.+.+.+..+.+.+.+.+.+..+.+.+.+.+..+.+.+.+ +.+.+.+.+.+..+.+.|
300 +-+ : : |
| : : |
250 +-+ : : |
| : : |
200 +-+ : : |
O O O O O O O O O O O O O O O O O O O : : |
150 +-+ : : |
100 +-+ : : |
| :: |
50 +-+ :: |
| : |
0 +-+-------------------------------------------------------------------+
stress-ng.numa.ops_per_sec
800 +-+-------------------------------------------------------------------+
| : : |
700 +-+ :: : |
600 +-+ : : :: |
| : : : : |
500 +-+ : : : : |
| : : : : |
400 +-+ : : : : |
| : : : : |
300 +-+ : : : : |
200 +-+ .+.+.+.. .+.+ +..+. .+.+.+ +.+ : .+. .+. |
| +.+..+.+ +.+ + + + : +.+ + +..+.+.|
100 +-+ + : + |
| :+ |
0 O-O-O--O-O-O-O-O--O-O-O-O-O-O--O-O-O-O-O------------------------------+
[*] 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.
Thanks,
Xiaolong
2 years, 5 months
- 3
- 3
7a9dc63e94 ("fs/dcache: disable preemption on i_dir_seq's .."): watchdog: BUG: soft lockup - CPU#0 stuck for 23s! [swapper:1]
by kernel test robot
Greetings,
0day kernel testing robot got the below dmesg and the first bad commit is
https://git.kernel.org/pub/scm/linux/kernel/git/clrkwllms/rt-linux.git rt-4.16-rc7
commit 7a9dc63e945d04d4d6c81c9f2dbf10fd87a22953
Author: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de>
AuthorDate: Fri Oct 20 11:29:53 2017 +0200
Commit: Clark Williams <williams(a)redhat.com>
CommitDate: Thu Mar 29 09:51:09 2018 -0500
fs/dcache: disable preemption on i_dir_seq's write side
i_dir_seq is an opencoded seqcounter. Based on the code it looks like we
could have two writers in parallel despite the fact that the d_lock is
held. The problem is that during the write process on RT the preemption
is still enabled and if this process is interrupted by a reader with RT
priority then we lock up.
To avoid that lock up I am disabling the preemption during the update.
The rename of i_dir_seq is here to ensure to catch new write sides in
future.
Cc: stable-rt(a)vger.kernel.org
Reported-by: Oleg.Karfich(a)wago.com
Signed-off-by: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de>
f5f8ed9ae4 fs/dcache: bringt back explicit INIT_HLIST_BL_HEAD init
7a9dc63e94 fs/dcache: disable preemption on i_dir_seq's write side
8d3edce808 Add localversion for -RT release
+------------------------------------------------------------------+------------+------------+------------+
| | f5f8ed9ae4 | 7a9dc63e94 | 8d3edce808 |
+------------------------------------------------------------------+------------+------------+------------+
| boot_successes | 31 | 0 | 0 |
| boot_failures | 2 | 15 | 19 |
| invoked_oom-killer:gfp_mask=0x | 1 | | |
| Mem-Info | 2 | | |
| Out_of_memory:Kill_process | 1 | | |
| Kernel_panic-not_syncing:Out_of_memory_and_no_killable_processes | 1 | | |
| BUG:soft_lockup-CPU##stuck_for#s | 0 | 15 | 19 |
| RIP:__d_lookup_rcu | 0 | 2 | 1 |
| Kernel_panic-not_syncing:softlockup:hung_tasks | 0 | 15 | 19 |
| RIP:d_alloc_parallel | 0 | 8 | 11 |
| RIP:lock_release | 0 | 2 | 2 |
| RIP:lock_is_held_type | 0 | 1 | |
| RIP:__sanitizer_cov_trace_pc | 0 | 2 | 1 |
| RIP:lock_acquire | 0 | 0 | 3 |
| RIP:debug_lockdep_rcu_enabled | 0 | 0 | 1 |
+------------------------------------------------------------------+------------+------------+------------+
[ 0.934010] pci 0000:00:00.0: Limiting direct PCI/PCI transfers
[ 0.935079] pci 0000:00:01.0: PIIX3: Enabling Passive Release
[ 0.936138] pci 0000:00:01.0: Activating ISA DMA hang workarounds
[ 0.937361] pci 0000:00:02.0: Video device with shadowed ROM at [mem 0x000c0000-0x000dffff]
[ 0.938977] PCI: CLS 0 bytes, default 64
[ 28.030041] watchdog: BUG: soft lockup - CPU#0 stuck for 23s! [swapper:1]
[ 28.033225] Modules linked in:
[ 28.033347] irq event stamp: 25232694
[ 28.033347] hardirqs last enabled at (25232693): [<000000007046e00e>] d_alloc_parallel+0x159/0xbd0
[ 28.033347] hardirqs last disabled at (25232694): [<00000000f019cb31>] interrupt_entry+0xb2/0xc0
[ 28.033347] softirqs last enabled at (25228688): [<00000000442b20e9>] __do_softirq+0x404/0x4ad
[ 28.033347] softirqs last disabled at (25228673): [<00000000930021e3>] irq_exit+0x64/0xf0
[ 28.033347] CPU: 0 PID: 1 Comm: swapper Not tainted 4.16.0-rc7-00219-g7a9dc63 #2
[ 28.033347] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014
[ 28.033347] RIP: 0010:d_alloc_parallel+0x15e/0xbd0
[ 28.033347] RSP: 0000:ffffc9000000b8d8 EFLAGS: 00000202 ORIG_RAX: ffffffffffffff12
[ 28.033347] RAX: ffff880000184000 RBX: 0000000000000202 RCX: 0000000000000007
[ 28.033347] RDX: 0000000000000007 RSI: ffff880000184758 RDI: 0000000000000202
[ 28.033347] RBP: ffffc9000000b998 R08: ffff880000184758 R09: 0000000000000000
[ 28.033347] R10: 0000000000000000 R11: 0000000000000000 R12: ffff88000002ca28
[ 28.033347] R13: 0000000000000000 R14: ffffffff838b40a8 R15: 00000000b9ce049d
[ 28.033347] FS: 0000000000000000(0000) GS:ffffffff82642000(0000) knlGS:0000000000000000
[ 28.033347] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 28.033347] CR2: 0000000000000000 CR3: 000000000261c001 CR4: 00000000000606b0
[ 28.033347] Call Trace:
[ 28.033347] ? find_held_lock+0x3c/0xb0
[ 28.033347] lookup_slow+0x130/0x310
[ 28.033347] walk_component+0x188/0x450
[ 28.033347] path_lookupat+0x286/0x370
[ 28.033347] ? pvclock_clocksource_read+0xa4/0x130
[ 28.033347] filename_lookup+0x128/0x280
[ 28.033347] ? ftrace_likely_update+0x52/0x60
[ 28.033347] ? strncpy_from_user+0x1e6/0x200
[ 28.033347] ? ftrace_likely_update+0x52/0x60
[ 28.033347] user_path_at_empty+0x45/0x50
[ 28.033347] ? user_path_at_empty+0x45/0x50
[ 28.033347] ? initrd_load+0x53/0x53
[ 28.033347] vfs_statx+0x92/0x100
[ 28.033347] ? do_early_param+0x6e/0xc5
[ 28.033347] ? initrd_load+0x53/0x53
[ 28.033347] clean_path+0x3f/0x99
[ 28.033347] ? parse_header+0x50/0xee
[ 28.033347] ? read_into+0x90/0x99
[ 28.033347] do_name+0x9c/0x307
[ 28.033347] write_buffer+0x37/0x4f
[ 28.033347] unpack_to_rootfs+0x10a/0x35c
[ 28.033347] ? unpack_to_rootfs+0x35c/0x35c
[ 28.033347] ? do_early_param+0xc5/0xc5
[ 28.033347] populate_rootfs+0x22/0xe9
[ 28.033347] do_one_initcall+0xa1/0x1d0
[ 28.033347] ? do_early_param+0xc5/0xc5
[ 28.033347] kernel_init_freeable+0x14a/0x201
[ 28.033347] ? rest_init+0x150/0x150
[ 28.033347] kernel_init+0x18/0x160
[ 28.033347] ? schedule_tail+0xf/0x60
[ 28.033347] ? rest_init+0x150/0x150
[ 28.033347] ret_from_fork+0x24/0x30
[ 28.033347] Code: c7 02 58 5a 75 16 e8 f2 1c ed ff 48 89 df 57 9d 0f 1f 44 00 00 e8 03 92 e5 ff eb 14 e8 dc 1c ed ff e8 f7 90 e5 ff 48 89 df 57 9d <0f> 1f 44 00 00 e8 c8 1c ed ff 48 c7 c0 e0 5f 84 82 31 c9 31 d2
[ 28.033347] Kernel panic - not syncing: softlockup: hung tasks
[ 28.033347] CPU: 0 PID: 1 Comm: swapper Tainted: G L 4.16.0-rc7-00219-g7a9dc63 #2
[ 28.033347] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014
[ 28.033347] Call Trace:
[ 28.033347] <IRQ>
[ 28.033347] dump_stack+0x1e/0x2d
[ 28.033347] panic+0xf5/0x2a5
[ 28.033347] ? watchdog_timer_fn+0x216/0x280
[ 28.033347] watchdog_timer_fn+0x222/0x280
[ 28.033347] __hrtimer_run_queues+0x315/0x620
[ 28.033347] ? softlockup_update_smpboot_threads+0xc0/0xc0
[ 28.033347] hrtimer_run_queues+0xa3/0xf0
[ 28.033347] run_local_timers+0x13/0x50
[ 28.033347] update_process_times+0x31/0x70
[ 28.033347] tick_nohz_handler+0xe0/0x150
[ 28.033347] smp_apic_timer_interrupt+0x136/0x260
[ 28.033347] apic_timer_interrupt+0xf/0x20
[ 28.033347] </IRQ>
[ 28.033347] RIP: 0010:d_alloc_parallel+0x15e/0xbd0
[ 28.033347] RSP: 0000:ffffc9000000b8d8 EFLAGS: 00000202 ORIG_RAX: ffffffffffffff12
[ 28.033347] RAX: ffff880000184000 RBX: 0000000000000202 RCX: 0000000000000007
[ 28.033347] RDX: 0000000000000007 RSI: ffff880000184758 RDI: 0000000000000202
[ 28.033347] RBP: ffffc9000000b998 R08: ffff880000184758 R09: 0000000000000000
[ 28.033347] R10: 0000000000000000 R11: 0000000000000000 R12: ffff88000002ca28
[ 28.033347] R13: 0000000000000000 R14: ffffffff838b40a8 R15: 00000000b9ce049d
[ 28.033347] ? find_held_lock+0x3c/0xb0
[ 28.033347] lookup_slow+0x130/0x310
[ 28.033347] walk_component+0x188/0x450
[ 28.033347] path_lookupat+0x286/0x370
[ 28.033347] ? pvclock_clocksource_read+0xa4/0x130
[ 28.033347] filename_lookup+0x128/0x280
[ 28.033347] ? ftrace_likely_update+0x52/0x60
[ 28.033347] ? strncpy_from_user+0x1e6/0x200
[ 28.033347] ? ftrace_likely_update+0x52/0x60
[ 28.033347] user_path_at_empty+0x45/0x50
[ 28.033347] ? user_path_at_empty+0x45/0x50
[ 28.033347] ? initrd_load+0x53/0x53
[ 28.033347] vfs_statx+0x92/0x100
[ 28.033347] ? do_early_param+0x6e/0xc5
[ 28.033347] ? initrd_load+0x53/0x53
[ 28.033347] clean_path+0x3f/0x99
[ 28.033347] ? parse_header+0x50/0xee
[ 28.033347] ? read_into+0x90/0x99
[ 28.033347] do_name+0x9c/0x307
[ 28.033347] write_buffer+0x37/0x4f
[ 28.033347] unpack_to_rootfs+0x10a/0x35c
[ 28.033347] ? unpack_to_rootfs+0x35c/0x35c
[ 28.033347] ? do_early_param+0xc5/0xc5
[ 28.033347] populate_rootfs+0x22/0xe9
[ 28.033347] do_one_initcall+0xa1/0x1d0
[ 28.033347] ? do_early_param+0xc5/0xc5
[ 28.033347] kernel_init_freeable+0x14a/0x201
[ 28.033347] ? rest_init+0x150/0x150
[ 28.033347] kernel_init+0x18/0x160
[ 28.033347] ? schedule_tail+0xf/0x60
[ 28.033347] ? rest_init+0x150/0x150
[ 28.033347] ret_from_fork+0x24/0x30
# HH:MM RESULT GOOD BAD GOOD_BUT_DIRTY DIRTY_NOT_BAD
git bisect start 2817f626b5dcaeccf9528b52d1aad8b95a1fe413 3eb2ce825ea1ad89d20f7a3b5780df850e4be274 --
git bisect bad 8d0092beccac1b24c089774f3ce20a92dffa8ffb # 02:35 B 0 1 19 4 Merge 'linux-review/Pablo-Neira-Ayuso/netfilter-nf_tables-rename-to-nft_set_lookup_global/20180329-150045' into devel-spot-201803300009
git bisect bad d68156c331b327275d0003f1abb6542ec43a6740 # 02:56 B 0 6 20 0 Merge 'ipmi/for-next' into devel-spot-201803300009
git bisect bad 0d65b47b780299b9e236742832b74cf3aa9a886e # 03:31 B 0 2 16 0 Merge 'linux-review/Mike-Looijmans/of_net-Implement-of_get_nvmem_mac_address-helper/20180329-215309' into devel-spot-201803300009
git bisect bad 5b74cbabf2bb56e3d3fe1781bd1410b6b8b27917 # 03:51 B 0 1 15 0 Merge 'mkl-can-next/j1939' into devel-spot-201803300009
git bisect good 87979f6a2630e0aaa9138d0df1d980590928d893 # 04:22 G 11 0 1 1 Merge 'linux-review/Bryan-O-Donoghue/rtc-snvs-Fix-usage-of-snvs_rtc_enable/20180329-235004' into devel-spot-201803300009
git bisect bad 209ddef2f01793fc343a501920ce97e5ed9f7c38 # 04:38 B 0 1 15 0 Merge 'net/master' into devel-spot-201803300009
git bisect bad 8ef70efbba301eb4b1f815eddeddacaff321a711 # 05:01 B 0 1 17 2 Merge 'clrkwllms-linux/rt-4.16-rc7' into devel-spot-201803300009
git bisect good 29ac151e0ba6d7846052d0646cea3e49af46d2db # 05:44 G 11 0 2 2 work-simple: Simple work queue implemenation
git bisect good 7a933c683b166a55258d3e67eec97bdb3cfff720 # 06:04 G 11 0 2 2 RCU: we need to skip that warning but only on sleeping locks
git bisect bad ce160e2411aa1269d35cb5da61b7798c0b36f280 # 06:15 B 0 3 21 4 rt: Introduce cpu_chill()
git bisect good 6dea0835f2d0d280fe696ff0b3b04b5cdd61855d # 06:43 G 11 0 4 6 fs: jbd2: pull your plug when waiting for space
git bisect bad 356ae1441d30dd81f4c0d985b45ce08644d0a160 # 07:06 B 0 11 25 0 x86: UV: raw_spinlock conversion
git bisect bad 757e0469dc4f31e0113b40800694a189ce371c20 # 07:06 B 0 13 27 0 x86: Convert mce timer to hrtimer
git bisect good f5f8ed9ae4072bb2d9d4fd397ae797ce6aac62dd # 07:29 G 11 0 1 1 fs/dcache: bringt back explicit INIT_HLIST_BL_HEAD init
git bisect bad 7a9dc63e945d04d4d6c81c9f2dbf10fd87a22953 # 07:29 B 0 15 29 0 fs/dcache: disable preemption on i_dir_seq's write side
# first bad commit: [7a9dc63e945d04d4d6c81c9f2dbf10fd87a22953] fs/dcache: disable preemption on i_dir_seq's write side
git bisect good f5f8ed9ae4072bb2d9d4fd397ae797ce6aac62dd # 07:37 G 30 0 5 6 fs/dcache: bringt back explicit INIT_HLIST_BL_HEAD init
# extra tests with debug options
git bisect bad 7a9dc63e945d04d4d6c81c9f2dbf10fd87a22953 # 08:01 B 0 2 16 0 fs/dcache: disable preemption on i_dir_seq's write side
# extra tests on HEAD of linux-devel/devel-spot-201803300009
git bisect bad 2817f626b5dcaeccf9528b52d1aad8b95a1fe413 # 08:06 B 0 51 74 6 0day head guard for 'devel-spot-201803300009'
# extra tests on tree/branch clrkwllms-linux/rt-4.16-rc7
git bisect bad 8d3edce808c8b961686681fac5a7016f4ca44d4f # 08:26 B 0 4 24 6 Add localversion for -RT release
# extra tests with first bad commit reverted
git bisect good 3ec5b3913e4703ec6a876cc5f0572fbb8bd22506 # 08:58 G 11 0 2 2 Revert "fs/dcache: disable preemption on i_dir_seq's write side"
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/lkp Intel Corporation
2 years, 5 months
- 2
- 1
[lkp-robot] [x86/mm/dump_pagetables] 75298aa179: unixbench.score -54.6% regression
by kernel test robot
Greeting,
FYI, we noticed a -54.6% regression of unixbench.score due to commit:
commit: 75298aa179d56cd64f54e58a19fffc8ab922b4c0 ("x86/mm/dump_pagetables: Add page table directory to the debugfs VFS hierarchy")
https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master
in testcase: unixbench
on test machine: 8 threads Intel(R) Core(TM) i7 CPU 870 @ 2.93GHz with 6G memory
with following parameters:
runtime: 300s
nr_task: 1
test: fsbuffer
test-description: UnixBench is the original BYTE UNIX benchmark suite aims to test performance of Unix-like system.
test-url: https://github.com/kdlucas/byte-unixbench
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
=========================================================================================
compiler/kconfig/nr_task/rootfs/runtime/tbox_group/test/testcase:
gcc-7/x86_64-rhel-7.2/1/debian-x86_64-2016-08-31.cgz/300s/nhm-white/fsbuffer/unixbench
commit:
385ce0ea4c ("x86/mm/pti: Add Kconfig")
75298aa179 ("x86/mm/dump_pagetables: Add page table directory to the debugfs VFS hierarchy")
385ce0ea4c078517 75298aa179d56cd64f54e58a19
---------------- --------------------------
%stddev %change %stddev
\ | \
2504 -54.6% 1136 unixbench.score
314.00 -13.8% 270.69 unixbench.time.system_time
25.94 +166.9% 69.24 unixbench.time.user_time
814029 ± 13% +46.3% 1190792 ± 23% cpuidle.C1E.time
8.52 -1.2 7.35 mpstat.cpu.sys%
0.83 +1.2 2.02 mpstat.cpu.usr%
3078 ± 2% +282.6% 11778 ± 84% softirqs.NET_RX
72639 +21.2% 88056 ± 8% softirqs.RCU
52985 +13.6% 60186 ± 6% softirqs.SCHED
4444 ± 11% +21.3% 5390 sched_debug.cfs_rq:/.min_vruntime.min
27287 ± 6% +28.1% 34967 ± 13% sched_debug.cpu.nr_switches.min
22060 ± 9% +32.3% 29177 ± 12% sched_debug.cpu.sched_count.min
7952 ± 12% +43.9% 11442 ± 11% sched_debug.cpu.sched_goidle.min
3.66e+11 -50.3% 1.821e+11 perf-stat.branch-instructions
0.53 +0.2 0.71 ± 2% perf-stat.branch-miss-rate%
1.953e+09 -33.9% 1.291e+09 ± 2% perf-stat.branch-misses
2.626e+09 -4.5% 2.507e+09 perf-stat.cache-references
0.89 ± 4% +104.0% 1.82 perf-stat.cpi
0.05 ± 63% +3.0 3.09 perf-stat.dTLB-load-miss-rate%
3.793e+08 ± 63% +3604.6% 1.405e+10 ± 2% perf-stat.dTLB-load-misses
7.065e+11 -37.6% 4.41e+11 perf-stat.dTLB-loads
0.10 ± 45% +9.6 9.67 perf-stat.dTLB-store-miss-rate%
3.49e+08 ± 44% +5206.8% 1.852e+10 perf-stat.dTLB-store-misses
3.534e+11 -51.1% 1.73e+11 perf-stat.dTLB-stores
0.00 +0.5 0.49 perf-stat.iTLB-load-miss-rate%
79490221 +5594.1% 4.526e+09 perf-stat.iTLB-load-misses
1.871e+12 -50.5% 9.256e+11 perf-stat.iTLB-loads
1.632e+12 ± 10% -48.6% 8.383e+11 ± 8% perf-stat.instructions
20535 ± 11% -99.1% 185.23 ± 9% perf-stat.instructions-per-iTLB-miss
1.12 ± 4% -51.1% 0.55 perf-stat.ipc
531615 +1.7% 540572 perf-stat.minor-faults
531616 +1.7% 540572 perf-stat.page-faults
39.40 ± 5% -18.4 20.96 ± 59% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_fastpath
20.52 ± 2% -10.8 9.69 ± 58% perf-profile.calltrace.cycles-pp.vfs_write.sys_write.entry_SYSCALL_64_fastpath
16.68 -10.1 6.56 ± 58% perf-profile.calltrace.cycles-pp.__vfs_write.vfs_write.sys_write.entry_SYSCALL_64_fastpath
21.17 ± 2% -10.0 11.17 ± 58% perf-profile.calltrace.cycles-pp.sys_write.entry_SYSCALL_64_fastpath
16.09 ± 11% -8.3 7.81 ± 59% perf-profile.calltrace.cycles-pp.vfs_read.sys_read.entry_SYSCALL_64_fastpath
16.97 ± 10% -7.8 9.12 ± 60% perf-profile.calltrace.cycles-pp.sys_read.entry_SYSCALL_64_fastpath
11.71 ± 11% -7.1 4.58 ± 58% perf-profile.calltrace.cycles-pp.__vfs_read.vfs_read.sys_read.entry_SYSCALL_64_fastpath
10.93 ± 11% -6.6 4.35 ± 58% perf-profile.calltrace.cycles-pp.generic_file_read_iter.__vfs_read.vfs_read.sys_read.entry_SYSCALL_64_fastpath
15.92 -6.2 9.69 ± 22% perf-profile.calltrace.cycles-pp.generic_file_write_iter.__vfs_write.vfs_write.sys_write.entry_SYSCALL_64_fastpath
13.90 -5.5 8.44 ± 21% perf-profile.calltrace.cycles-pp.__generic_file_write_iter.generic_file_write_iter.__vfs_write.vfs_write.sys_write
10.58 -4.0 6.62 ± 22% perf-profile.calltrace.cycles-pp.generic_perform_write.__generic_file_write_iter.generic_file_write_iter.__vfs_write.vfs_write
4.46 ± 12% -2.4 2.02 ± 58% perf-profile.calltrace.cycles-pp.copy_page_to_iter.generic_file_read_iter.__vfs_read.vfs_read.sys_read
3.96 ± 3% -1.6 2.34 ± 27% perf-profile.calltrace.cycles-pp.simple_write_begin.generic_perform_write.__generic_file_write_iter.generic_file_write_iter.__vfs_write
3.61 ± 3% -1.4 2.22 ± 30% perf-profile.calltrace.cycles-pp.grab_cache_page_write_begin.simple_write_begin.generic_perform_write.__generic_file_write_iter.generic_file_write_iter
3.21 ± 4% -1.4 1.83 ± 35% perf-profile.calltrace.cycles-pp.pagecache_get_page.grab_cache_page_write_begin.simple_write_begin.generic_perform_write.__generic_file_write_iter
2.28 ± 10% -1.3 0.99 ± 61% perf-profile.calltrace.cycles-pp.pagecache_get_page.generic_file_read_iter.__vfs_read.vfs_read.sys_read
2.40 ± 10% -1.2 1.25 ± 58% perf-profile.calltrace.cycles-pp.copyout.copy_page_to_iter.generic_file_read_iter.__vfs_read.vfs_read
2.05 ± 10% -1.1 0.91 ± 61% perf-profile.calltrace.cycles-pp.find_get_entry.pagecache_get_page.generic_file_read_iter.__vfs_read.vfs_read
2.16 ± 11% -1.0 1.16 ± 57% perf-profile.calltrace.cycles-pp.copy_user_generic_string.copyout.copy_page_to_iter.generic_file_read_iter.__vfs_read
1.88 ± 4% -0.9 1.01 ± 19% perf-profile.calltrace.cycles-pp.simple_write_end.generic_perform_write.__generic_file_write_iter.generic_file_write_iter.__vfs_write
1.28 ± 13% -0.9 0.41 ± 58% perf-profile.calltrace.cycles-pp.touch_atime.generic_file_read_iter.__vfs_read.vfs_read.sys_read
1.25 ± 14% -0.9 0.40 ±102% perf-profile.calltrace.cycles-pp.file_update_time.__generic_file_write_iter.generic_file_write_iter.__vfs_write.vfs_write
1.11 ± 5% -0.8 0.35 ±100% perf-profile.calltrace.cycles-pp.dentry_needs_remove_privs.file_remove_privs.__generic_file_write_iter.generic_file_write_iter.__vfs_write
2.28 ± 2% -0.7 1.57 ± 17% perf-profile.calltrace.cycles-pp.iov_iter_copy_from_user_atomic.generic_perform_write.__generic_file_write_iter.generic_file_write_iter.__vfs_write
1.44 ± 5% -0.6 0.84 ± 15% perf-profile.calltrace.cycles-pp.file_remove_privs.__generic_file_write_iter.generic_file_write_iter.__vfs_write.vfs_write
1.55 ± 6% -0.4 1.15 ± 9% perf-profile.calltrace.cycles-pp.copyin.iov_iter_copy_from_user_atomic.generic_perform_write.__generic_file_write_iter.generic_file_write_iter
1.43 ± 6% -0.3 1.09 ± 8% perf-profile.calltrace.cycles-pp.copy_user_generic_string.copyin.iov_iter_copy_from_user_atomic.generic_perform_write.__generic_file_write_iter
0.28 ±100% +0.8 1.06 ± 28% perf-profile.calltrace.cycles-pp.__inode_security_revalidate.selinux_file_permission.security_file_permission.vfs_write.sys_write
0.95 ± 9% +1.6 2.57 ± 16% perf-profile.calltrace.cycles-pp.selinux_file_permission.security_file_permission.vfs_write.sys_write.entry_SYSCALL_64_fastpath
0.00 +8.2 8.23 ±160% perf-profile.calltrace.cycles-pp.write
53.03 ± 4% +10.5 63.52 ± 5% perf-profile.calltrace.cycles-pp.secondary_startup_64
44.85 ± 14% +12.2 57.03 ± 5% perf-profile.calltrace.cycles-pp.cpuidle_enter_state.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64
45.59 ± 13% +12.4 57.96 ± 5% perf-profile.calltrace.cycles-pp.cpu_startup_entry.start_secondary.secondary_startup_64
45.59 ± 13% +12.4 57.96 ± 5% perf-profile.calltrace.cycles-pp.do_idle.cpu_startup_entry.start_secondary.secondary_startup_64
45.59 ± 13% +12.4 57.96 ± 5% perf-profile.calltrace.cycles-pp.start_secondary.secondary_startup_64
36.13 ± 13% +13.3 49.42 ± 9% perf-profile.calltrace.cycles-pp.intel_idle.cpuidle_enter_state.do_idle.cpu_startup_entry.start_secondary
40.08 ± 5% -12.3 27.81 ± 12% perf-profile.children.cycles-pp.entry_SYSCALL_64_fastpath
16.55 ± 10% -8.1 8.45 ± 54% perf-profile.children.cycles-pp.vfs_read
unixbench.score
2600 +--------------------------------------------------------------------+
| .+.+.+.+.+ + +.+.+.+.+.+.+.+.+.+.+.|
2400 |.+.+.+.+.+.+ + +.+.+.++.+.+.+ |
2200 |-+ +. + |
| + |
2000 |-+ |
| |
1800 |-+ |
| |
1600 |-+ |
1400 |-+ |
| |
1200 |-+ |
| O O O O O O O O O O O O O |
1000 +--------------------------------------------------------------------+
[*] 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.
Thanks,
Xiaolong
2 years, 6 months
- 3
- 2
[lkp-robot] [sched/fair] d59ad49131: unixbench.score +19.4% improvement
by kernel test robot
Greeting,
We noticed a +19.4% improvement of unixbench.score due to commit:
commit: d59ad49131bbfd57293d00a007383cc98aff2710 ("sched/fair: Remove check in idle_balance against migration_cost")
url: https://github.com/0day-ci/linux/commits/Rohit-Jain/sched-fair-Remove-che...
in testcase: unixbench
on test machine: 8 threads Intel(R) Core(TM) i7 CPU 870 @ 2.93GHz with 6G memory
with following parameters:
runtime: 300s
nr_task: 100%
test: spawn
test-description: UnixBench is the original BYTE UNIX benchmark suite aims to test performance of Unix-like system.
test-url: https://github.com/kdlucas/byte-unixbench
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
=========================================================================================
tbox_group/testcase/rootfs/kconfig/compiler/runtime/nr_task/test:
nhm-white/unixbench/debian-x86_64-2016-08-31.cgz/x86_64-rhel-7.2/gcc-7/300s/100%/spawn
commit:
v4.16-rc4
d59ad49131bbfd57293d00a007383cc98aff2710
v4.16-rc4 d59ad49131bbfd57293d00a007
---------------- --------------------------
%stddev %change %stddev
\ | \
3202 +19.4% 3824 unixbench.score
4062446 ± 4% -12.2% 3565055 ± 3% unixbench.time.involuntary_context_switches
2.809e+08 +18.9% 3.34e+08 unixbench.time.minor_page_faults
611.56 +12.3% 686.50 unixbench.time.percent_of_cpu_this_job_got
862.38 +14.4% 986.68 unixbench.time.system_time
1170 +10.3% 1290 unixbench.time.user_time
23973299 +15.5% 27696636 unixbench.time.voluntary_context_switches
13386322 +19.2% 15962986 unixbench.workload
24295 +46.7% 35646 ± 10% interrupts.CAL:Function_call_interrupts
93923 ± 7% -25.3% 70144 ± 10% meminfo.DirectMap4k
42426 ± 3% +13.0% 47960 meminfo.Shmem
21.95 ± 5% -9.7 12.28 mpstat.cpu.idle%
71.10 +9.3 80.37 mpstat.cpu.sys%
2430631 +13.5% 2758915 softirqs.RCU
921699 +26.9% 1169816 softirqs.SCHED
355.45 -100.0% 0.00 uptime.boot
780.22 ± 6% -100.0% 0.00 uptime.idle
4.00 +9800.0% 396.00 vmstat.memory.buff
138810 -11.7% 122590 vmstat.system.cs
2.163e+08 -76.8% 50241754 cpuidle.C1.time
8231502 -68.3% 2607969 ± 2% cpuidle.C1.usage
67306881 -88.4% 7799355 ± 2% cpuidle.C1E.time
2343272 -86.1% 325846 ± 2% cpuidle.C1E.usage
277490 ± 9% -37.1% 174635 ± 2% cpuidle.C3.usage
4062446 ± 4% -12.2% 3565055 ± 3% time.involuntary_context_switches
2.809e+08 +18.9% 3.34e+08 time.minor_page_faults
611.56 +12.3% 686.50 time.percent_of_cpu_this_job_got
862.38 +14.4% 986.68 time.system_time
1170 +10.3% 1290 time.user_time
23973299 +15.5% 27696636 time.voluntary_context_switches
124.00 ± 19% -100.0% 0.00 slabinfo.btrfs_path.active_objs
124.00 ± 19% -100.0% 0.00 slabinfo.btrfs_path.num_objs
249.33 ± 10% -33.5% 165.75 ± 10% slabinfo.buffer_head.active_objs
249.33 ± 10% -33.5% 165.75 ± 10% slabinfo.buffer_head.num_objs
10443 ± 5% +19.4% 12471 ± 6% slabinfo.kmalloc-32.active_objs
10825 ± 5% +18.0% 12773 ± 7% slabinfo.kmalloc-32.num_objs
3987 +35.8% 5413 slabinfo.kmalloc-64.active_objs
3987 +35.8% 5413 slabinfo.kmalloc-64.num_objs
36.89 ± 7% +171.1% 100.00 proc-vmstat.nr_active_file
10606 ± 3% +13.1% 11991 proc-vmstat.nr_shmem
unixbench.score
4000 O-+-O-O--------------------------------------------------------------+
| O O O O O O O O O O O O O O O O O O O O |
3500 +-+ |
3000 +-+.+.+..+.+.+.+.+.+..+.+.+ +.+..+.+.+.+.+.+.+ +.+.+.+.+..+.+.+.|
| : : : : |
2500 +-+ : : : : |
| : : : : |
2000 +-+ : : : : |
| : : : : |
1500 +-+ : : : : |
1000 +-+ : : : : |
| : : : : |
500 +-+ : :: |
| : : |
0 +-+------------------------------------------------------------------+
unixbench.workload
1.8e+07 +-+---------------------------------------------------------------+
O O O O |
1.6e+07 +-O O O O O O O O O O O O O O O O O O O |
1.4e+07 +-+ .+.+. .+.+.|
|.+.+.+.+.+.+.+..+.+.+.+.+ +.+.+.+.+.+ + +.+.+.+.+.+ |
1.2e+07 +-+ : : : : |
1e+07 +-+ : : : : |
| : : : : |
8e+06 +-+ : : : : |
6e+06 +-+ : : : : |
| : : : : |
4e+06 +-+ : : : : |
2e+06 +-+ : :: |
| : : |
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.
Thanks,
Xiaolong
2 years, 6 months
- 1
- 0
[lkp-robot] [mm/cma] 4405c5fd84: vm-scalability.throughput +26.5% improvement
by kernel test robot
Greeting,
FYI, we noticed a +26.5% improvement of vm-scalability.throughput due to commit:
commit: 4405c5fd8434809972dd2996c4dbfe5124b01d55 ("mm/cma: manage the memory of the CMA area by using the ZONE_MOVABLE")
https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git master
in testcase: vm-scalability
on test machine: 72 threads Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz with 128G memory
with following parameters:
runtime: 300
thp_enabled: never
thp_defrag: always
nr_task: 8
nr_pmem: 4
priority: 1
test: swap-w-seq-mt
cpufreq_governor: performance
test-description: The motivation behind this suite is to exercise functions and regions of the mm/ of the Linux kernel which are of interest to us.
test-url: https://git.kernel.org/cgit/linux/kernel/git/wfg/vm-scalability.git/
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
=========================================================================================
compiler/cpufreq_governor/kconfig/nr_pmem/nr_task/priority/rootfs/runtime/tbox_group/test/testcase/thp_defrag/thp_enabled:
gcc-7/performance/x86_64-rhel-7.2/4/8/1/debian-x86_64-2016-08-31.cgz/300/lkp-hsw-ep2/swap-w-seq-mt/vm-scalability/always/never
commit:
41fd9c44d9 ("mm/page_alloc: don't reserve ZONE_HIGHMEM for ZONE_MOVABLE request")
4405c5fd84 ("mm/cma: manage the memory of the CMA area by using the ZONE_MOVABLE")
41fd9c44d94101ec 4405c5fd8434809972dd2996c4
---------------- --------------------------
%stddev %change %stddev
\ | \
3278698 +26.5% 4148766 ± 2% vm-scalability.throughput
0.76 ± 2% -7.9% 0.70 ± 2% vm-scalability.free_time
414083 +28.8% 533402 ± 2% vm-scalability.median
37.39 -11.2% 33.19 vm-scalability.time.elapsed_time
37.39 -11.2% 33.19 vm-scalability.time.elapsed_time.max
646.75 -10.1% 581.25 vm-scalability.time.percent_of_cpu_this_job_got
182.59 -24.6% 137.76 ± 2% vm-scalability.time.system_time
59.42 -6.8% 55.40 vm-scalability.time.user_time
8942 ± 9% +105.6% 18384 ± 6% vm-scalability.time.voluntary_context_switches
2089321 ± 5% -26.6% 1532791 ± 3% cpuidle.C1.time
62485028 -32.1% 42426989 ± 4% interrupts.CAL:Function_call_interrupts
9.87 -2.0 7.89 mpstat.cpu.sys%
859.75 ± 14% +54.6% 1329 ± 34% slabinfo.dmaengine-unmap-16.active_objs
859.75 ± 14% +54.6% 1329 ± 34% slabinfo.dmaengine-unmap-16.num_objs
2691121 ± 9% -31.9% 1832052 ± 8% softirqs.RCU
565376 -10.6% 505518 ± 2% softirqs.TIMER
1798289 ± 20% +219.4% 5744223 ± 6% numa-numastat.node0.numa_foreign
11379510 ± 6% -30.9% 7864229 ± 5% numa-numastat.node1.local_node
11380678 ± 6% -30.9% 7867707 ± 5% numa-numastat.node1.numa_hit
1798289 ± 20% +219.4% 5744223 ± 6% numa-numastat.node1.numa_miss
1799458 ± 20% +219.4% 5747704 ± 6% numa-numastat.node1.other_node
7.148e+08 ± 4% -35.5% 4.607e+08 ± 6% perf-node.node-load-misses
2.806e+08 ± 2% -25.9% 2.079e+08 ± 7% perf-node.node-loads
27.75 ± 5% +9.9% 30.50 ± 3% perf-node.node-local-load-ratio
2.166e+08 ± 3% -27.1% 1.579e+08 ± 8% perf-node.node-store-misses
2.734e+08 ± 9% -43.9% 1.534e+08 ± 10% perf-node.node-stores
447.75 ± 2% -10.8% 399.25 ± 2% turbostat.Avg_MHz
15.16 ± 2% -1.8 13.36 turbostat.Busy%
0.07 ± 5% -0.0 0.06 ± 7% turbostat.C1%
1.875e+08 -33.8% 1.242e+08 ± 4% turbostat.IRQ
152.01 -2.7% 147.85 turbostat.PkgWatt
14.18 -2.3% 13.85 turbostat.RAMWatt
586.75 ± 7% +13.5% 666.25 ± 3% vmstat.memory.buff
5757201 ± 3% +22.8% 7068800 ± 4% vmstat.memory.free
27365780 -39.1% 16652327 ± 2% vmstat.memory.swpd
9.00 -22.2% 7.00 vmstat.procs.r
829.00 ± 13% -38.6% 509.00 ± 5% vmstat.swap.si
1658990 -26.7% 1215747 vmstat.swap.so
1636758 -23.0% 1260916 vmstat.system.in
47862 ± 6% -65.1% 16689 ± 6% meminfo.CmaFree
83417008 -9.9% 75152314 meminfo.Committed_AS
1850235 -19.2% 1494102 ± 4% meminfo.Inactive
1849617 -19.3% 1493422 ± 4% meminfo.Inactive(anon)
5362375 ± 3% +22.4% 6564299 meminfo.MemAvailable
5534597 ± 2% +22.3% 6766142 meminfo.MemFree
103923 -21.3% 81789 meminfo.PageTables
73933617 +13.6% 83992710 meminfo.SwapFree
11799653 -8.0% 10850808 ± 3% numa-meminfo.node0.AnonPages
937028 -19.4% 755072 ± 6% numa-meminfo.node0.Inactive
936810 -19.4% 754801 ± 6% numa-meminfo.node0.Inactive(anon)
2741438 ± 8% +35.6% 3716602 ± 9% numa-meminfo.node0.MemFree
59023 -51.4% 28701 ± 9% numa-meminfo.node0.PageTables
921828 ± 2% -20.4% 733395 ± 5% numa-meminfo.node1.Inactive
921425 ± 2% -20.5% 732971 ± 5% numa-meminfo.node1.Inactive(anon)
45693 +17.0% 53445 ± 5% numa-meminfo.node1.PageTables
8923 ± 4% +66.6% 14863 ± 25% sched_debug.cfs_rq:/.min_vruntime.avg
16889 ± 10% +36.7% 23084 ± 14% sched_debug.cfs_rq:/.min_vruntime.max
2110 ± 9% +22.4% 2584 ± 11% sched_debug.cfs_rq:/.min_vruntime.stddev
2287 ± 30% +205.4% 6985 ± 10% sched_debug.cfs_rq:/.spread0.avg
10329 ± 13% +47.8% 15262 ± 5% sched_debug.cfs_rq:/.spread0.max
2119 ± 8% +21.2% 2569 ± 10% sched_debug.cfs_rq:/.spread0.stddev
1223 ± 17% +25.1% 1531 ± 21% sched_debug.cfs_rq:/.util_avg.max
3392 ± 36% +534.3% 21519 ± 58% sched_debug.cpu.avg_idle.min
2929484 ± 2% -8.5% 2679073 ± 3% numa-vmstat.node0.nr_anon_pages
705776 ± 9% +36.5% 963258 ± 6% numa-vmstat.node0.nr_free_pages
232015 -20.0% 185568 ± 7% numa-vmstat.node0.nr_inactive_anon
11856 ± 6% +23.8% 14680 ± 9% numa-vmstat.node0.nr_indirectly_reclaimable
14587 -51.7% 7041 ± 7% numa-vmstat.node0.nr_page_table_pages
3831258 ± 3% -25.8% 2842415 ± 11% numa-vmstat.node0.nr_vmscan_write
3831285 ± 3% -25.8% 2842319 ± 11% numa-vmstat.node0.nr_written
232105 -20.0% 185668 ± 7% numa-vmstat.node0.nr_zone_inactive_anon
942274 ± 14% +268.2% 3469716 ± 7% numa-vmstat.node0.numa_foreign
11986 ± 5% -64.6% 4238 ± 8% numa-vmstat.node1.nr_free_cma
228092 ± 2% -21.5% 179096 ± 6% numa-vmstat.node1.nr_inactive_anon
11051 ± 6% -25.6% 8224 ± 17% numa-vmstat.node1.nr_indirectly_reclaimable
2930 ± 9% -11.1% 2604 ± 10% numa-vmstat.node1.nr_mapped
11307 ± 2% +17.1% 13236 ± 6% numa-vmstat.node1.nr_page_table_pages
4507408 ± 3% -19.7% 3619831 ± 10% numa-vmstat.node1.nr_vmscan_write
4507421 ± 3% -19.7% 3619853 ± 10% numa-vmstat.node1.nr_written
228157 ± 2% -21.5% 179161 ± 6% numa-vmstat.node1.nr_zone_inactive_anon
7544972 ± 3% -36.3% 4806885 ± 9% numa-vmstat.node1.numa_hit
7381155 ± 3% -37.1% 4641005 ± 9% numa-vmstat.node1.numa_local
943340 ± 14% +268.0% 3471701 ± 7% numa-vmstat.node1.numa_miss
1107163 ± 12% +228.6% 3637587 ± 7% numa-vmstat.node1.numa_other
0.77 ± 2% -0.2 0.58 ± 4% perf-stat.branch-miss-rate%
1.461e+09 -23.3% 1.121e+09 ± 6% perf-stat.branch-misses
25.39 -1.6 23.82 ± 2% perf-stat.cache-miss-rate%
1.492e+09 ± 2% -26.0% 1.104e+09 ± 7% perf-stat.cache-misses
5.877e+09 -21.2% 4.634e+09 ± 6% perf-stat.cache-references
1.63 -10.3% 1.47 perf-stat.cpi
1.223e+12 ± 2% -12.0% 1.075e+12 ± 7% perf-stat.cpu-cycles
1.01 ± 2% -0.2 0.85 ± 6% perf-stat.dTLB-load-miss-rate%
1.873e+09 ± 10% -24.1% 1.423e+09 ± 6% perf-stat.dTLB-load-misses
1.038e+11 ± 2% -13.8% 8.95e+10 ± 7% perf-stat.dTLB-stores
5.226e+08 ± 5% -21.4% 4.108e+08 perf-stat.iTLB-load-misses
90580077 ± 5% -13.8% 78079215 ± 4% perf-stat.iTLB-loads
1434 ± 5% +24.6% 1787 ± 8% perf-stat.instructions-per-iTLB-miss
0.61 +11.5% 0.68 perf-stat.ipc
5290 ± 3% -17.7% 4356 ± 5% perf-stat.major-faults
71.12 -2.3 68.81 perf-stat.node-load-miss-rate%
7.031e+08 ± 4% -33.4% 4.681e+08 ± 6% perf-stat.node-load-misses
2.853e+08 ± 3% -25.6% 2.122e+08 ± 7% perf-stat.node-loads
45.16 ± 6% +4.0 49.16 ± 3% perf-stat.node-store-miss-rate%
2.153e+08 ± 3% -29.0% 1.529e+08 perf-stat.node-store-misses
2.634e+08 ± 11% -39.9% 1.584e+08 ± 6% perf-stat.node-stores
119681 ± 3% -27.8% 86457 ± 5% proc-vmstat.allocstall_movable
40547 ± 14% -53.6% 18814 ± 31% proc-vmstat.allocstall_normal
629.25 ± 93% -99.7% 2.00 ± 61% proc-vmstat.compact_stall
18.75 ± 31% +212.0% 58.50 ± 89% proc-vmstat.kswapd_high_wmark_hit_quickly
129618 ± 3% +26.4% 163840 ± 3% proc-vmstat.nr_dirty_background_threshold
259555 ± 3% +26.4% 328082 ± 3% proc-vmstat.nr_dirty_threshold
11625 ± 5% -64.0% 4188 ± 8% proc-vmstat.nr_free_cma
1344481 ± 3% +26.2% 1696756 ± 3% proc-vmstat.nr_free_pages
465487 -19.8% 373471 ± 3% proc-vmstat.nr_inactive_anon
189.25 ± 5% -24.7% 142.50 ± 9% proc-vmstat.nr_isolated_anon
26266 -22.0% 20495 proc-vmstat.nr_page_table_pages
8458281 ± 2% -23.7% 6456268 ± 4% proc-vmstat.nr_vmscan_write
16689767 -34.4% 10944327 ± 5% proc-vmstat.nr_written
465637 -19.8% 373643 ± 3% proc-vmstat.nr_zone_inactive_anon
4610783 ± 2% +72.2% 7938811 proc-vmstat.numa_foreign
20568554 -17.2% 17030926 proc-vmstat.numa_hit
20554622 -17.2% 17017000 proc-vmstat.numa_local
4610783 ± 2% +72.2% 7938811 proc-vmstat.numa_miss
4624715 ± 2% +72.0% 7952737 proc-vmstat.numa_other
11566637 ± 2% -14.0% 9944302 ± 5% proc-vmstat.numa_pte_updates
1439116 ± 2% -24.9% 1080676 ± 11% proc-vmstat.pgalloc_dma32
17284194 -33.1% 11570103 ± 5% proc-vmstat.pgdeactivate
9.00 ± 19% +15077.8% 1366 ± 77% proc-vmstat.pgmigrate_success
17280106 -32.9% 11600628 ± 5% proc-vmstat.pgrefill
12136735 ± 12% -38.3% 7491459 ± 14% proc-vmstat.pgscan_direct
6262493 -30.7% 4340098 ± 5% proc-vmstat.pgscan_kswapd
10431149 ± 2% -36.6% 6608259 ± 5% proc-vmstat.pgsteal_direct
6260464 -30.7% 4337402 ± 5% proc-vmstat.pgsteal_kswapd
6045 ± 17% -47.4% 3179 ± 23% proc-vmstat.pswpin
16693811 -34.4% 10948374 ± 5% proc-vmstat.pswpout
33044 ± 6% -20.3% 26344 ± 4% proc-vmstat.slabs_scanned
vm-scalability.throughput
4.4e+06 +-+---------------------------------------------------------------+
| O |
4.2e+06 +-O O O O O O O O O O O |
O O O O |
| |
4e+06 +-+ O |
| O O |
3.8e+06 +-+ |
| |
3.6e+06 +-+ |
| |
| .+ |
3.4e+06 +-+ .+ + .+.+.+.. .+.+.+. |
| + .+.+.+.+.+..+.+ +.+.+.+. .+. .+ + +.+. .+.|
3.2e+06 +-+---------------------------------------------------------------+
[*] 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.
Thanks,
Xiaolong
2 years, 6 months
- 1
- 0