| 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
| ||
|
Date: Fri, 14 Oct 2016 10:28:26 +0800
From: kernel test robot <xiaolong.ye@...el.com>
To: Al Viro <viro@...iv.linux.org.uk>
Cc: LKML <linux-kernel@...r.kernel.org>,
Linus Torvalds <torvalds@...ux-foundation.org>, lkp@...org
Subject: [lkp] [switch generic_file_splice_read() to use of ] 82c156f853:
netperf.Throughput_Mbps -4.3% regression
FYI, we noticed a -4.3% regression of netperf.Throughput_Mbps due to commit:
commit 82c156f853840645604acd7c2cebcb75ed1b6652 ("switch generic_file_splice_read() to use of ->read_iter()")
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git master
in testcase: netperf
on test machine: 16 threads Intel(R) Xeon(R) CPU D-1541 @ 2.10GHz with 8G memory
with following parameters:
ip: ipv4
runtime: 300s
nr_threads: 200%
cluster: cs-localhost
test: TCP_SENDFILE
cpufreq_governor: performance
Netperf is a benchmark that can be use to measure various aspect of networking performance.
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.
Details are as below:
-------------------------------------------------------------------------------------------------->
To reproduce:
git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git
cd lkp-tests
bin/lkp install job.yaml # job file is attached in this email
bin/lkp run job.yaml
=========================================================================================
cluster/compiler/cpufreq_governor/ip/kconfig/nr_threads/rootfs/runtime/tbox_group/test/testcase:
cs-localhost/gcc-6/performance/ipv4/x86_64-rhel-7.2/200%/debian-x86_64-2016-08-31.cgz/300s/lkp-bdw-de1/TCP_SENDFILE/netperf
commit:
241699cd72 ("new iov_iter flavour: pipe-backed")
82c156f853 ("switch generic_file_splice_read() to use of ->read_iter()")
241699cd72a8489c 82c156f853840645604acd7c2c
---------------- --------------------------
%stddev %change %stddev
\ | \
11696 ± 0% -4.3% 11194 ± 0% netperf.Throughput_Mbps
32745 ± 13% +110.1% 68800 ± 40% netperf.time.involuntary_context_switches
919.25 ± 0% +4.4% 959.50 ± 0% netperf.time.percent_of_cpu_this_job_got
2708 ± 0% +4.6% 2831 ± 0% netperf.time.system_time
3331360 ± 0% -4.8% 3169954 ± 0% netperf.time.voluntary_context_switches
22484 ± 2% +11.3% 25033 ± 6% meminfo.Active(file)
314919 ± 16% +132.9% 733525 ± 44% softirqs.RCU
32891 ± 0% -3.3% 31793 ± 1% vmstat.system.cs
5620 ± 2% +11.3% 6258 ± 6% proc-vmstat.nr_active_file
5620 ± 2% +11.3% 6258 ± 6% proc-vmstat.nr_zone_active_file
5389 ± 94% +199.8% 16156 ± 53% sched_debug.cfs_rq:/.spread0.max
7.82 ± 9% +37.9% 10.78 ± 7% sched_debug.cfs_rq:/.util_avg.stddev
584356 ± 11% -16.3% 489033 ± 4% sched_debug.cpu.nr_switches.max
105882 ± 12% -19.3% 85494 ± 9% sched_debug.cpu.nr_switches.stddev
1.504e+12 ± 0% +5.2% 1.582e+12 ± 0% perf-stat.branch-instructions
0.23 ± 0% -27.1% 0.17 ± 0% perf-stat.branch-miss-rate%
3.429e+09 ± 0% -23.3% 2.629e+09 ± 0% perf-stat.branch-misses
2.01e+11 ± 0% -5.3% 1.903e+11 ± 0% perf-stat.cache-misses
2.01e+11 ± 0% -5.3% 1.903e+11 ± 0% perf-stat.cache-references
9958921 ± 0% -3.3% 9628936 ± 1% perf-stat.context-switches
3.121e+12 ± 0% +1.5% 3.167e+12 ± 0% perf-stat.dTLB-loads
0.01 ± 13% -11.7% 0.01 ± 0% perf-stat.dTLB-store-miss-rate%
1.828e+08 ± 13% -11.0% 1.627e+08 ± 0% perf-stat.dTLB-store-misses
2.36e+08 ± 2% -49.0% 1.204e+08 ± 5% perf-stat.iTLB-load-misses
1.093e+08 ± 12% -33.6% 72525628 ± 28% perf-stat.iTLB-loads
8.491e+12 ± 0% +3.5% 8.79e+12 ± 0% perf-stat.instructions
36006 ± 2% +103.4% 73247 ± 6% perf-stat.instructions-per-iTLB-miss
0.76 ± 0% +3.3% 0.78 ± 0% perf-stat.ipc
5.73 ± 0% -100.0% 0.00 ± -1% perf-profile.calltrace.cycles-pp.__generic_file_splice_read.generic_file_splice_read.do_splice_to.splice_direct_to_actor.do_splice_direct
0.00 ± -1% +Inf% 0.97 ± 3% perf-profile.calltrace.cycles-pp.__radix_tree_lookup.radix_tree_lookup_slot.find_get_entry.pagecache_get_page.generic_file_read_iter
0.00 ± -1% +Inf% 2.81 ± 1% perf-profile.calltrace.cycles-pp.copy_page_to_iter.generic_file_read_iter.generic_file_splice_read.do_splice_to.splice_direct_to_actor
8.45 ± 0% +58.1% 13.36 ± 0% perf-profile.calltrace.cycles-pp.do_splice_to.splice_direct_to_actor.do_splice_direct.do_sendfile.sys_sendfile64
0.00 ± -1% +Inf% 2.86 ± 1% perf-profile.calltrace.cycles-pp.find_get_entry.pagecache_get_page.generic_file_read_iter.generic_file_splice_read.do_splice_to
2.89 ± 2% -100.0% 0.00 ± -1% perf-profile.calltrace.cycles-pp.find_get_pages_contig.__generic_file_splice_read.generic_file_splice_read.do_splice_to.splice_direct_to_actor
0.00 ± -1% +Inf% 10.29 ± 0% perf-profile.calltrace.cycles-pp.generic_file_read_iter.generic_file_splice_read.do_splice_to.splice_direct_to_actor.do_splice_direct
6.65 ± 1% +75.5% 11.68 ± 0% perf-profile.calltrace.cycles-pp.generic_file_splice_read.do_splice_to.splice_direct_to_actor.do_splice_direct.do_sendfile
0.00 ± -1% +Inf% 3.47 ± 1% perf-profile.calltrace.cycles-pp.pagecache_get_page.generic_file_read_iter.generic_file_splice_read.do_splice_to.splice_direct_to_actor
0.00 ± -1% +Inf% 1.15 ± 3% perf-profile.calltrace.cycles-pp.radix_tree_lookup_slot.find_get_entry.pagecache_get_page.generic_file_read_iter.generic_file_splice_read
2.88 ± 1% +16.9% 3.37 ± 2% perf-profile.children.cycles-pp.___might_sleep
5.77 ± 0% -100.0% 0.00 ± -1% perf-profile.children.cycles-pp.__generic_file_splice_read
0.00 ± -1% +Inf% 1.07 ± 3% perf-profile.children.cycles-pp.__radix_tree_lookup
0.98 ± 2% +28.6% 1.26 ± 2% perf-profile.children.cycles-pp.atime_needs_update
8.49 ± 0% +57.9% 13.40 ± 0% perf-profile.children.cycles-pp.do_splice_to
0.00 ± -1% +Inf% 3.00 ± 1% perf-profile.children.cycles-pp.find_get_entry
2.92 ± 2% -100.0% 0.00 ± -1% perf-profile.children.cycles-pp.find_get_pages_contig
0.00 ± -1% +Inf% 10.30 ± 0% perf-profile.children.cycles-pp.generic_file_read_iter
6.67 ± 1% +75.9% 11.74 ± 0% perf-profile.children.cycles-pp.generic_file_splice_read
0.00 ± -1% +Inf% 3.55 ± 1% perf-profile.children.cycles-pp.pagecache_get_page
0.00 ± -1% +Inf% 1.28 ± 3% perf-profile.children.cycles-pp.radix_tree_lookup_slot
0.98 ± 3% +38.1% 1.36 ± 2% perf-profile.children.cycles-pp.touch_atime
2.88 ± 1% +16.9% 3.37 ± 2% perf-profile.self.cycles-pp.___might_sleep
1.94 ± 1% -100.0% 0.00 ± -1% perf-profile.self.cycles-pp.__generic_file_splice_read
0.00 ± -1% +Inf% 1.07 ± 3% perf-profile.self.cycles-pp.__radix_tree_lookup
0.53 ± 3% +425.7% 2.76 ± 1% perf-profile.self.cycles-pp.copy_page_to_iter
0.00 ± -1% +Inf% 1.75 ± 2% perf-profile.self.cycles-pp.find_get_entry
2.13 ± 2% -100.0% 0.00 ± -1% perf-profile.self.cycles-pp.find_get_pages_contig
0.00 ± -1% +Inf% 2.26 ± 0% perf-profile.self.cycles-pp.generic_file_read_iter
perf-stat.branch-instructions
1.6e+12 O+OO---OO----O-O----OO-O-OO-O-OO-O-OO-O-OO-O-OO-O-OO-OO-O-OO-O-OO-O
* *.*.**.*.**.*.* **.*.** **.*.**.*.**.*.**.*.**.**.*.**.* |
1.4e+12 ++ : : : : : |
1.2e+12 ++ : : : : : |
| : : : : : |
1e+12 ++ : : : : : |
|: : : : : : |
8e+11 ++ : : : : : |
|:: :: : : |
6e+11 ++: :: : : |
4e+11 ++: :: : : |
| : : : |
2e+11 ++: : : |
| : : : |
0 ++*--O----O-O----OO---------*-------------------------------------+
perf-stat.ipc
0.8 O+O-O--O-O----O-O----O-O-OO-O-O-OO-O-O-OO-O-O-OO-O-O-OO-O-O-OO-O-O-OO-O
* **.*.*.**.*.*.* *.*.**.* **.*.*.**.*.*.**.*.*.**.*.*.**.*.* |
0.7 ++ : : : : : |
0.6 ++ : : : : : |
| : : : : : |
0.5 ++ : : : : : |
|: : : : : : |
0.4 ++ : : : : : |
|: : :: : : |
0.3 ++ : :: : : |
0.2 ++ : :: : : |
| : : : |
0.1 ++: : : |
| : : : |
0 ++*--O-----OO-----OO----------*---------------------------------------+
netperf.Throughput_Mbps
12000 *+**-*-*-**-*-**-*-**-*-*-**-*-**-*-**-*-*-**-*----*-**-*-*-**-*----+
O OO O O OO O O O OO O OO O OO O O OO O OO O OO O O OO O OO O
10000 ++ |
| |
| |
8000 ++ |
| |
6000 ++ |
| |
4000 ++ |
| |
| |
2000 ++ |
| |
0 ++---O----O-O----O-O------------------------------------------------+
[*] bisect-good sample
[O] bisect-bad sample
Thanks,
Xiaolong
View attachment "config-4.8.0-rc8-00009-g82c156f" of type "text/plain" (152576 bytes)
View attachment "job-script" of type "text/plain" (6922 bytes)
View attachment "job.yaml" of type "text/plain" (4429 bytes)
View attachment "reproduce" of type "text/plain" (1913 bytes)
Powered by blists - more mailing lists