| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20171226051838.GD3172@yexl-desktop>
Date: Tue, 26 Dec 2017 13:18:38 +0800
From: kernel test robot <xiaolong.ye@...el.com>
To: Jan Kara <jack@...e.cz>
Cc: Stephen Rothwell <sfr@...b.auug.org.au>,
"Darrick J. Wong" <darrick.wong@...cle.com>,
Dave Chinner <david@...morbit.com>,
Linus Torvalds <torvalds@...ux-foundation.org>,
Andrew Morton <akpm@...ux-foundation.org>,
LKML <linux-kernel@...r.kernel.org>, lkp@...org
Subject: [lkp-robot] [mm] 18333aa4c7: vm-scalability.throughput -16.9%
regression
Greeting,
FYI, we noticed a -16.9% regression of vm-scalability.throughput due to commit:
commit: 18333aa4c7c9779667b94832669f51e1a0da35bd ("mm: readahead: increase maximum readahead window")
https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git master
in testcase: vm-scalability
on test machine: 4 threads Intel(R) Core(TM) i5-2300 CPU @ 2.80GHz with 4G memory
with following parameters:
runtime: 300s
test: lru-file-readtwice
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/rootfs/runtime/tbox_group/test/testcase:
gcc-7/performance/x86_64-rhel-7.2/debian-x86_64-2016-08-31.cgz/300s/lkp-sb02/lru-file-readtwice/vm-scalability
commit:
54ddf8e573 ("mm: update comment describing tlb_gather_mmu")
18333aa4c7 ("mm: readahead: increase maximum readahead window")
54ddf8e5737ba210 18333aa4c7c9779667b9483266
---------------- --------------------------
%stddev %change %stddev
\ | \
725892 -16.9% 603249 vm-scalability.median
5795950 -16.9% 4815925 vm-scalability.throughput
301.75 +3.2% 311.50 vm-scalability.time.percent_of_cpu_this_job_got
880.34 +3.8% 913.50 vm-scalability.time.system_time
32.57 -13.4% 28.21 vm-scalability.time.user_time
1.739e+09 -16.9% 1.445e+09 vm-scalability.workload
22.09 +2.5% 22.63 ± 2% boot-time.boot
3.48 -0.4 3.11 ± 2% mpstat.cpu.usr%
404820 ± 5% -9.3% 366990 ± 5% softirqs.RCU
42.56 -5.3% 40.31 turbostat.CorWatt
46.85 -4.1% 44.93 turbostat.PkgWatt
107785 ± 23% -76.1% 25753 ± 38% proc-vmstat.allocstall_movable
1057 ± 25% -43.8% 594.50 ± 29% proc-vmstat.allocstall_normal
401891 ± 19% +91.0% 767485 ± 30% proc-vmstat.compact_free_scanned
4116 ± 20% +100.0% 8233 ± 9% proc-vmstat.kswapd_low_wmark_hit_quickly
4.253e+08 -19.7% 3.414e+08 ± 2% proc-vmstat.numa_hit
4.253e+08 -19.7% 3.414e+08 ± 2% proc-vmstat.numa_local
4123 ± 20% +99.9% 8242 ± 9% proc-vmstat.pageoutrun
3.663e+08 -20.1% 2.926e+08 ± 2% proc-vmstat.pgalloc_dma32
58824553 ± 5% -17.3% 48621818 ± 4% proc-vmstat.pgalloc_normal
4.252e+08 -19.7% 3.415e+08 ± 2% proc-vmstat.pgfree
8457976 ± 22% -72.7% 2306350 ± 28% proc-vmstat.pgscan_direct
4.159e+08 -18.7% 3.381e+08 ± 2% proc-vmstat.pgscan_kswapd
8457862 ± 22% -72.7% 2306346 ± 28% proc-vmstat.pgsteal_direct
4.159e+08 -18.7% 3.381e+08 ± 2% proc-vmstat.pgsteal_kswapd
5762375 ± 8% -11.9% 5076561 ± 8% proc-vmstat.slabs_scanned
2096577 ± 7% -13.2% 1819917 ± 6% proc-vmstat.workingset_nodereclaim
72513535 ± 14% -31.4% 49736071 ± 9% proc-vmstat.workingset_refault
5.59e+11 -19.6% 4.493e+11 perf-stat.branch-instructions
0.21 -0.0 0.20 ± 2% perf-stat.branch-miss-rate%
1.179e+09 -23.3% 9.047e+08 ± 2% perf-stat.branch-misses
49.64 +5.6 55.23 perf-stat.cache-miss-rate%
2.733e+10 -5.6% 2.58e+10 perf-stat.cache-misses
5.507e+10 -15.2% 4.67e+10 perf-stat.cache-references
1.16 +24.9% 1.45 perf-stat.cpi
22880 ± 2% +9.2% 24993 perf-stat.cpu-migrations
4.34e+09 ± 21% -32.1% 2.947e+09 ± 8% perf-stat.dTLB-load-misses
8.91e+11 -19.3% 7.191e+11 perf-stat.dTLB-loads
0.14 ± 2% -0.0 0.13 ± 2% perf-stat.dTLB-store-miss-rate%
9.476e+08 ± 2% -26.1% 7.002e+08 ± 2% perf-stat.dTLB-store-misses
6.684e+11 -18.9% 5.421e+11 perf-stat.dTLB-stores
92.35 -6.0 86.40 ± 2% perf-stat.iTLB-load-miss-rate%
3.378e+08 ± 5% -31.9% 2.301e+08 ± 5% perf-stat.iTLB-load-misses
2.942e+12 -19.9% 2.358e+12 perf-stat.instructions
8735 ± 5% +17.6% 10274 ± 4% perf-stat.instructions-per-iTLB-miss
0.86 -19.9% 0.69 perf-stat.ipc
1692 -3.5% 1632 perf-stat.path-length
370695 ± 5% +12.7% 417657 ± 3% sched_debug.cfs_rq:/.min_vruntime.min
461.00 ± 2% -15.7% 388.80 ± 8% sched_debug.cfs_rq:/.runnable_load_avg.avg
1046 ± 2% -23.1% 804.92 ± 8% sched_debug.cfs_rq:/.runnable_load_avg.max
344.27 ± 5% -25.5% 256.55 ± 7% sched_debug.cfs_rq:/.runnable_load_avg.stddev
621159 ± 7% +26.2% 784010 ± 6% sched_debug.cpu.avg_idle.avg
831350 ± 3% +14.6% 953127 sched_debug.cpu.avg_idle.max
433080 ± 15% +30.1% 563288 ± 17% sched_debug.cpu.avg_idle.min
456.34 -13.8% 393.43 ± 8% sched_debug.cpu.cpu_load[0].avg
1039 ± 3% -21.2% 818.92 ± 8% sched_debug.cpu.cpu_load[0].max
344.95 ± 4% -23.7% 263.17 ± 7% sched_debug.cpu.cpu_load[0].stddev
454.29 ± 2% -13.7% 392.06 ± 8% sched_debug.cpu.cpu_load[1].avg
1031 ± 3% -21.7% 807.17 ± 10% sched_debug.cpu.cpu_load[1].max
338.94 ± 4% -25.0% 254.22 ± 12% sched_debug.cpu.cpu_load[1].stddev
455.58 ± 2% -12.7% 397.84 ± 6% sched_debug.cpu.cpu_load[2].avg
1022 ± 3% -23.2% 786.12 ± 13% sched_debug.cpu.cpu_load[2].max
331.60 ± 5% -27.9% 238.98 ± 17% sched_debug.cpu.cpu_load[2].stddev
454.64 -11.2% 403.58 ± 5% sched_debug.cpu.cpu_load[3].avg
1014 ± 2% -19.8% 813.75 ± 11% sched_debug.cpu.cpu_load[3].max
326.47 ± 3% -24.2% 247.38 ± 16% sched_debug.cpu.cpu_load[3].stddev
451.42 -10.2% 405.29 ± 4% sched_debug.cpu.cpu_load[4].avg
993.83 -16.1% 833.88 ± 9% sched_debug.cpu.cpu_load[4].max
316.34 ± 2% -19.7% 254.02 ± 13% sched_debug.cpu.cpu_load[4].stddev
1667 ± 41% -44.4% 926.56 ± 33% sched_debug.cpu.nr_load_updates.stddev
155309 ± 9% -24.0% 117967 ± 8% sched_debug.cpu.nr_switches.min
141416 ± 9% -25.9% 104800 ± 10% sched_debug.cpu.sched_count.min
65991 ± 9% -28.0% 47537 ± 11% sched_debug.cpu.ttwu_count.min
57074 ± 11% -28.9% 40580 ± 12% sched_debug.cpu.ttwu_local.min
50.12 -11.6 38.55 ± 2% perf-profile.calltrace.cycles.ondemand_readahead.generic_file_read_iter.xfs_file_buffered_aio_read.xfs_file_read_iter.__vfs_read
50.11 -11.6 38.53 ± 2% perf-profile.calltrace.cycles.__do_page_cache_readahead.ondemand_readahead.generic_file_read_iter.xfs_file_buffered_aio_read.xfs_file_read_iter
40.98 -9.5 31.47 ± 2% perf-profile.calltrace.cycles.mpage_readpages.__do_page_cache_readahead.ondemand_readahead.generic_file_read_iter.xfs_file_buffered_aio_read
27.27 -7.0 20.26 ± 3% perf-profile.calltrace.cycles.do_mpage_readpage.mpage_readpages.__do_page_cache_readahead.ondemand_readahead.generic_file_read_iter
22.53 -3.1 19.48 ± 2% perf-profile.calltrace.cycles.shrink_inactive_list.shrink_node_memcg.shrink_node.kswapd.kthread
23.37 -2.8 20.57 perf-profile.calltrace.cycles.ret_from_fork
23.37 -2.8 20.57 perf-profile.calltrace.cycles.kthread.ret_from_fork
22.61 -2.8 19.81 perf-profile.calltrace.cycles.shrink_node_memcg.shrink_node.kswapd.kthread.ret_from_fork
23.04 -2.8 20.27 perf-profile.calltrace.cycles.shrink_node.kswapd.kthread.ret_from_fork
23.06 -2.8 20.31 perf-profile.calltrace.cycles.kswapd.kthread.ret_from_fork
13.23 -2.4 10.78 ± 2% perf-profile.calltrace.cycles.add_to_page_cache_lru.mpage_readpages.__do_page_cache_readahead.ondemand_readahead.generic_file_read_iter
16.43 -2.4 14.05 ± 2% perf-profile.calltrace.cycles.shrink_page_list.shrink_inactive_list.shrink_node_memcg.shrink_node.kswapd
6.48 -1.5 5.00 perf-profile.calltrace.cycles.__alloc_pages_nodemask.__do_page_cache_readahead.ondemand_readahead.generic_file_read_iter.xfs_file_buffered_aio_read
6.67 -1.3 5.36 ± 2% perf-profile.calltrace.cycles.__remove_mapping.shrink_page_list.shrink_inactive_list.shrink_node_memcg.shrink_node
6.13 -1.3 4.84 ± 2% perf-profile.calltrace.cycles.__lru_cache_add.add_to_page_cache_lru.mpage_readpages.__do_page_cache_readahead.ondemand_readahead
5.79 -1.2 4.56 ± 3% perf-profile.calltrace.cycles.pagevec_lru_move_fn.__lru_cache_add.add_to_page_cache_lru.mpage_readpages.__do_page_cache_readahead
6.03 -0.8 5.19 ± 5% perf-profile.calltrace.cycles.__add_to_page_cache_locked.add_to_page_cache_lru.mpage_readpages.__do_page_cache_readahead.ondemand_readahead
5.64 -0.6 5.00 ± 2% perf-profile.calltrace.cycles.isolate_lru_pages.shrink_inactive_list.shrink_node_memcg.shrink_node.kswapd
6.00 -0.5 5.52 ± 2% perf-profile.calltrace.cycles.free_unref_page_list.shrink_page_list.shrink_inactive_list.shrink_node_memcg.shrink_node
5.48 -0.4 5.05 ± 2% perf-profile.calltrace.cycles.free_unref_page_commit.free_unref_page_list.shrink_page_list.shrink_inactive_list.shrink_node_memcg
5.06 -0.4 4.70 ± 2% perf-profile.calltrace.cycles.free_pcppages_bulk.free_unref_page_commit.free_unref_page_list.shrink_page_list.shrink_inactive_list
3.22 +1.9 5.16 ± 4% perf-profile.calltrace.cycles.pagecache_get_page.generic_file_read_iter.xfs_file_buffered_aio_read.xfs_file_read_iter.__vfs_read
3.08 +2.0 5.06 ± 4% perf-profile.calltrace.cycles.find_get_entry.pagecache_get_page.generic_file_read_iter.xfs_file_buffered_aio_read.xfs_file_read_iter
74.06 +3.1 77.17 perf-profile.calltrace.cycles.entry_SYSCALL_64_fastpath
71.19 +3.5 74.66 perf-profile.calltrace.cycles.sys_read.entry_SYSCALL_64_fastpath
70.80 +3.5 74.34 perf-profile.calltrace.cycles.vfs_read.sys_read.entry_SYSCALL_64_fastpath
68.78 +3.9 72.68 perf-profile.calltrace.cycles.__vfs_read.vfs_read.sys_read.entry_SYSCALL_64_fastpath
68.23 +4.0 72.26 perf-profile.calltrace.cycles.xfs_file_read_iter.__vfs_read.vfs_read.sys_read.entry_SYSCALL_64_fastpath
67.73 +4.1 71.86 perf-profile.calltrace.cycles.xfs_file_buffered_aio_read.xfs_file_read_iter.__vfs_read.vfs_read.sys_read
66.12 +4.4 70.52 perf-profile.calltrace.cycles.generic_file_read_iter.xfs_file_buffered_aio_read.xfs_file_read_iter.__vfs_read.vfs_read
10.07 +14.4 24.48 perf-profile.calltrace.cycles.copy_page_to_iter.generic_file_read_iter.xfs_file_buffered_aio_read.xfs_file_read_iter.__vfs_read
9.05 +14.6 23.65 perf-profile.calltrace.cycles.copyout.copy_page_to_iter.generic_file_read_iter.xfs_file_buffered_aio_read.xfs_file_read_iter
9.00 +14.6 23.61 perf-profile.calltrace.cycles.copy_user_generic_string.copyout.copy_page_to_iter.generic_file_read_iter.xfs_file_buffered_aio_read
50.12 -11.6 38.55 ± 2% perf-profile.children.cycles.ondemand_readahead
50.11 -11.6 38.53 ± 2% perf-profile.children.cycles.__do_page_cache_readahead
40.98 -9.5 31.47 ± 2% perf-profile.children.cycles.mpage_readpages
27.27 -7.0 20.26 ± 3% perf-profile.children.cycles.do_mpage_readpage
22.67 -3.2 19.48 ± 2% perf-profile.children.cycles.shrink_inactive_list
22.75 -2.9 19.82 perf-profile.children.cycles.shrink_node_memcg
23.19 -2.9 20.29 perf-profile.children.cycles.shrink_node
23.37 -2.8 20.57 perf-profile.children.cycles.kthread
23.37 -2.8 20.57 perf-profile.children.cycles.ret_from_fork
23.06 -2.8 20.31 perf-profile.children.cycles.kswapd
16.53 -2.5 14.05 ± 2% perf-profile.children.cycles.shrink_page_list
13.23 -2.4 10.78 ± 2% perf-profile.children.cycles.add_to_page_cache_lru
6.55 -1.5 5.03 perf-profile.children.cycles.__alloc_pages_nodemask
6.74 -1.4 5.36 ± 2% perf-profile.children.cycles.__remove_mapping
6.14 -1.3 4.85 ± 3% perf-profile.children.cycles.__lru_cache_add
5.79 -1.1 4.67 ± 5% perf-profile.children.cycles.pagevec_lru_move_fn
5.42 -1.0 4.40 ± 2% perf-profile.children.cycles.__radix_tree_lookup
5.39 -0.9 4.51 perf-profile.children.cycles.get_page_from_freelist
6.03 -0.8 5.19 ± 5% perf-profile.children.cycles.__add_to_page_cache_locked
5.66 -0.5 5.14 ± 3% perf-profile.children.cycles.isolate_lru_pages
6.09 -0.5 5.58 perf-profile.children.cycles.free_unref_page_list
5.48 -0.4 5.05 ± 2% perf-profile.children.cycles.free_unref_page_commit
6.86 -0.4 6.46 ± 3% perf-profile.children.cycles.__list_del_entry_valid
5.09 -0.4 4.71 ± 2% perf-profile.children.cycles.free_pcppages_bulk
3.22 +2.0 5.17 ± 4% perf-profile.children.cycles.pagecache_get_page
3.08 +2.0 5.06 ± 4% perf-profile.children.cycles.find_get_entry
74.32 +3.1 77.43 perf-profile.children.cycles.entry_SYSCALL_64_fastpath
71.25 +3.5 74.72 perf-profile.children.cycles.sys_read
70.87 +3.5 74.41 perf-profile.children.cycles.vfs_read
68.84 +3.9 72.73 perf-profile.children.cycles.__vfs_read
68.23 +4.0 72.26 perf-profile.children.cycles.xfs_file_read_iter
67.73 +4.1 71.86 perf-profile.children.cycles.xfs_file_buffered_aio_read
66.12 +4.4 70.53 perf-profile.children.cycles.generic_file_read_iter
10.07 +14.4 24.48 perf-profile.children.cycles.copy_page_to_iter
9.05 +14.6 23.65 perf-profile.children.cycles.copyout
9.02 +14.6 23.63 perf-profile.children.cycles.copy_user_generic_string
23.66 -6.1 17.57 ± 4% perf-profile.self.cycles.do_mpage_readpage
5.36 -1.0 4.35 ± 2% perf-profile.self.cycles.__radix_tree_lookup
6.86 -0.4 6.46 ± 3% perf-profile.self.cycles.__list_del_entry_valid
8.88 +14.4 23.26 ± 2% perf-profile.self.cycles.copy_user_generic_string
vm-scalability.throughput
6e+06 +-+---------------------------------------------------------------+
| |
5.8e+06 +-+.+..+.+.+.+.+..+.+.+.+.+..+.+.+.+.+..+.+.+.+.+..+.+.+.+.+..+.+.|
| |
5.6e+06 +-+ |
| |
5.4e+06 +-+ |
| |
5.2e+06 +-+ |
| |
5e+06 +-+ O O O |
O O O |
4.8e+06 +-+ O O O O O O O O O |
| O O O O |
4.6e+06 +-+---------------------------------------------------------------+
vm-scalability.median
740000 +-+----------------------------------------------------------------+
|.+.+..+.+.+.+..+.+.+.+..+.+.+. .+.+.+.+.+..+.+.+.+.. .+.+.+..+.+.|
720000 +-+ +. + |
700000 +-+ |
| |
680000 +-+ |
| |
660000 +-+ |
| |
640000 +-+ O |
620000 O-+ O |
| O |
600000 +-O O O O O O O O O O |
| O O O O |
580000 +-+------O---------------------------------------------------------+
vm-scalability.workload
1.75e+09 +-+--------------------------------------------------------------+
| + + +. + + +.+ + |
1.7e+09 +-+ |
| |
1.65e+09 +-+ |
| |
1.6e+09 +-+ |
| |
1.55e+09 +-+ |
| |
1.5e+09 +-+ O O O |
O O |
1.45e+09 +-O O O O |
| O O O O O O O O O O |
1.4e+09 +-+--------------------------------------------------------------+
perf-stat.instructions
3e+12 +-+---------------------------------------------------------------+
|.+.+.. .+.+.+. .+. .+.. .+. .+.+.. .+.+.+.+..+.+.|
2.9e+12 +-+ + +. +.+.+.+..+.+.+.+ + + + |
| |
2.8e+12 +-+ |
| |
2.7e+12 +-+ |
| |
2.6e+12 +-+ |
| |
2.5e+12 +-+ |
| |
2.4e+12 +-+ O |
O O O O O O O O O O O O O O O O O O |
2.3e+12 +-+---------------------------------------------------------------+
perf-stat.cache-references
5.6e+10 +-+---------------------------------------------------------------+
5.5e+10 +-+.+.. .+.+. .+. .+. .+.+.. .+.+.+.+.. .+.|
| + +.+..+ + +..+.+.+.+.+..+.+.+ + + |
5.4e+10 +-+ |
5.3e+10 +-+ |
| |
5.2e+10 +-+ |
5.1e+10 +-+ |
5e+10 +-+ |
| |
4.9e+10 +-+ |
4.8e+10 +-+ |
| |
4.7e+10 O-+ O O O O O O O O O O O O O O O |
4.6e+10 +-O--------O-------------------O----------------------------------+
perf-stat.cache-misses
2.8e+10 +-+--------------------------------------------------------------+
| + |
2.75e+10 +-+.+.. .+.+.+. .+. +.+. + + .+.. .|
| + +.+. +.+. .+. .+.+. .+. .. + + +.+.+ |
2.7e+10 +-+ + +..+ + + |
| |
2.65e+10 +-+ |
| O O |
2.6e+10 +-+ O O O O O O |
| O O O O |
2.55e+10 +-+ O |
| O O |
2.5e+10 O-+ O |
| O O |
2.45e+10 +-+--------------------------------------------------------------+
perf-stat.branch-instructions
5.8e+11 +-+---------------------------------------------------------------+
| |
5.6e+11 +-+.+..+.+.+.+.+..+.+. .+.. .+. .+.+..+.+.+.+.+..+.+.|
| +.+.+..+.+.+.+ + + |
5.4e+11 +-+ |
| |
5.2e+11 +-+ |
| |
5e+11 +-+ |
| |
4.8e+11 +-+ |
| |
4.6e+11 +-+ |
O O O O O O O O O O O O O O O O O O O |
4.4e+11 +-+---------------------------------------------------------------+
perf-stat.branch-misses
1.25e+09 +-+--------------------------------------------------------------+
| + +. |
1.2e+09 +-+ + + : .+.+. + +.+..+.+.+.|
1.15e+09 +-+.+.. + + + : .+. .+. + |
| + +.+.+.+ +.+.+.+.+..+.+.+ + |
1.1e+09 +-+ |
1.05e+09 +-+ |
| |
1e+09 +-+ |
9.5e+08 +-+ |
| O O O O |
9e+08 +-+ O O O O O O O O O |
8.5e+08 O-+ O O O |
| O O |
8e+08 +-+--------------------------------------------------------------+
perf-stat.dTLB-loads
9e+11 +-+---------------------------------------------------------------+
8.8e+11 +-+.+..+ +.+.+..+.+.+.+.+..+.+.+.+.+..+.+.+ +.+.+ +..+.+ |
| |
8.6e+11 +-+ |
8.4e+11 +-+ |
| |
8.2e+11 +-+ |
8e+11 +-+ |
7.8e+11 +-+ |
| |
7.6e+11 +-+ |
7.4e+11 +-+ |
O O O O O O O O O O O O O O |
7.2e+11 +-+ O O O O O |
7e+11 +-+---------------------------------------------------------------+
perf-stat.dTLB-stores
6.8e+11 +-+---------------------------------------------------------------+
|.+.+..+.+.+.+.+..+.+.+.+.+..+.+.+.+.+..+.+.+.+.+..+.+.+.+.+..+.+.|
6.6e+11 +-+ |
6.4e+11 +-+ |
| |
6.2e+11 +-+ |
| |
6e+11 +-+ |
| |
5.8e+11 +-+ |
5.6e+11 +-+ |
| |
5.4e+11 O-O O O O O O O O O O O O O O O O O O |
| |
5.2e+11 +-+---------------------------------------------------------------+
perf-stat.dTLB-store-misses
1e+09 +-+---------------------------------------------------------------+
| .+.. +. .+.. + + .+ + + :: +.+ |
9.5e+08 +-+ + +.+ .+.+.+. .+ + + .. + + + : : .. +|
9e+08 +-+ + + +. + + +.+..+. : +.+ |
| + |
8.5e+08 +-+ |
| |
8e+08 +-+ |
| |
7.5e+08 +-+ |
7e+08 +-+ O O O |
| O O O O O O O O O |
6.5e+08 O-O O O O O O |
| |
6e+08 +-+---------------------------------------------------------------+
perf-stat.cache-miss-rate_
57 +-+--------------------------------------------------------------------+
| |
56 +-+ O O O O O O O |
55 +-+ O O O O |
| O O O O |
54 O-+ |
| O O O |
53 +-+ |
| |
52 +-+ |
51 +-+ |
| |
50 +-+..+. .+.. .+.. .+.+..+. .+.. .+. .+. |
| + + + +.+..+.+..+.+ + +..+.+.+. +..+.+.+..+.|
49 +-+--------------------------------------------------------------------+
perf-stat.ipc
0.88 +-+------------------------------------------------------------------+
0.86 +-+..+. .+..+. .+.. .+. .+. .+..+. .+..+.+.+. .+.|
| + +.+ +.+.+..+.+.+..+.+ +. + + +. |
0.84 +-+ |
0.82 +-+ |
| |
0.8 +-+ |
0.78 +-+ |
0.76 +-+ |
| |
0.74 +-+ |
0.72 +-+ |
| |
0.7 O-O O O O O O O O O O O O O O O O O |
0.68 +-+-----------------------------O------------------------------------+
perf-stat.cpi
1.5 +-+------------------------------------------------------------------+
| |
1.45 O-O O O O O O O O O O O O O O O O O O |
1.4 +-+ |
| |
1.35 +-+ |
| |
1.3 +-+ |
| |
1.25 +-+ |
1.2 +-+ |
| .+.+. .+.+.+..+. .+.. .+. |
1.15 +-+..+.+.+..+.+.+.+. +. +.+ + +..+.+.+..+.+.+.+..+.|
| |
1.1 +-+------------------------------------------------------------------+
vm-scalability.time.system_time
920 +-+-------------------------------------------------------------------+
915 +-+ O O |
O O O O O O O O O O O O O O O O O |
910 +-+ |
905 +-+ |
| |
900 +-+ |
895 +-+ |
890 +-+ |
| |
885 +-+ |
880 +-+ .+.+ .+. .+.. .+.+. .+. .+.|
|.+..+.+.+. + .+. .+..+.+.+. + +.+.+. +..+ +. |
875 +-+ +..+.+.+. + |
870 +-+-------------------------------------------------------------------+
vm-scalability.time.percent_of_cpu_this_job_got
314 +-+-------------------------------------------------------------------+
| O O O O |
312 O-O O O O O O O O O O O O |
| O O |
310 +-+ |
| |
308 +-+ |
| |
306 +-+ |
| |
304 +-+ |
| +.+ +.+ |
302 +-+ .. + .+. .+..+.+.+..+. .+.. .+. .. + .+. .+.|
|.+..+.+.+ +..+.+.+. + + + + +..+ +. |
300 +-+-------------------------------------------------------------------+
[*] 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
View attachment "config-4.15.0-rc3-00141-g18333aa" of type "text/plain" (163758 bytes)
View attachment "job-script" of type "text/plain" (7149 bytes)
View attachment "job.yaml" of type "text/plain" (4795 bytes)
View attachment "reproduce" of type "text/plain" (1105 bytes)
Powered by blists - more mailing lists