Performance Test: Difference between revisions

From Yocto Project
Jump to navigationJump to search
No edit summary
 
(67 intermediate revisions by 4 users not shown)
Line 1: Line 1:
== Build Time Perfomance  ==
== Build time tracking ==
Script used for running the builds: (dylan/master branch): scripts/contrib/build-perf-test.sh


Two identical test systems are used for the results below, one with Ubuntu 12.04 (uname -nr: ubuntu12 3.8.0-31-generic) and one with Fedora 19 (uname -nr: fedora19 3.11.3-201.fc19.x86_64) with all updates available installed.
Script used for running the builds:  


All system/distro settings are distro's defaults, that includes:
*Before morty: poky/scripts/contrib/build-perf-test.sh
*After morty: poky/scripts/oe-build-perf-test
 
Two identical test systems are used for the results, with all updates available installed. Extra packages installed (besides what's by the default in the distro) are the ones in the Quick Start guide.
 
Configuration of the GDC Setup 2.1 - Current master
* Ubuntu 15.10 (Wily Werewolf)" -->  4.2.0-16-generic
* Fedora release 23 (Twenty Three) --> 4.7.10-100.fc23.x86_64
* HW configuration: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz, 16GB RAM,  1 x 600 GB SDD, 1 x 2 TB HDD
 
All system/distro settings are '''distro's defaults''', that includes:


- FS mount options: ext4 rw,relatime,data=ordered  
- FS mount options: ext4 rw,relatime,data=ordered  


- IO scheduler: cfq and CPU governer: ondemand
- IO scheduler: cfq and CPU governer: ondemand
HW config is: SandyBridge i7-2600 CPU @ 3.40GHz HT-enabled (4 cores/8 threads),  8GB RAM,  1 x 500 GB HDD


local.conf it's the default one (the script doesn't touch it except for changing DL_DIR if necessary).
local.conf it's the default one (the script doesn't touch it except for changing DL_DIR if necessary).
Line 20: Line 26:
MACHINE = "qemux86"</nowiki>
MACHINE = "qemux86"</nowiki>


In the tables below, unless otherwise noted, sizes are in kilobytes.
FAQ:
 
*Q: Where is 1.5_M2? It's there but it's called: 1.5_M1.final-412-geaa5df3 The M2 build wasn't released hence no git tag
'''Note:''' This page holds a re-run of milestone/RCs builds for the 1.5 cycle + 1.4.1/1.4.2 and for upcoming builds for 1.6. [https://wiki.yoctoproject.org/wiki/Performance_Test_Weekly_1.5 This page] has the old weekly results ran during the 1.5 cycle. The results differ because the test sytems used there are a bit different than those here (so don't cross compare results).
*Q: What's with the different number of RCs? See [[Yocto_Project_Release_Process#Milestone_Releases]]
*Q: Why are there more results for some commits? The script is ran from a cron job multiple times a day, sometimes master changes daily sometimes it doesn't, hence more results for one commit (ie weekends)


*Q: Where is M2 ? It's there but it's called: 1.5_M1.final-412-geaa5df3 The M2 build wasn't released hence no git tag
*Q: What's with the different number of RCs? See [[Yocto_Project_Release_Process#Milestone_Releases]]


== 1.4.1 & 1.4.2 Build Time results ==
== Daily Test Results ==
Build performance test suite is run multiple times per day. Latest test reports for master branch can found here:
* [https://wiki.yoctoproject.org/charts/build_perf/latest/ypperf-ubuntu16_master_qemux86.html Ubuntu 16.04]
* [https://wiki.yoctoproject.org/charts/build_perf/latest/ypperf-ubuntu16-xeon_master_qemux86.html Ubuntu 16.04 (Intel® Xeon® HW)]
* [https://wiki.yoctoproject.org/charts/build_perf/latest/ypperf-centos7_master_qemux86.html CentOS 7]
* [https://wiki.yoctoproject.org/charts/build_perf/latest/ypperf-opensuse422_master_qemux86.html OpenSUSE Leap 42.2] (retired)
* [https://wiki.yoctoproject.org/charts/build_perf/latest/ypperf-fedora25_master_qemux86.html Fedora 25] (retired)
* [https://wiki.yoctoproject.org/charts/build_perf/latest/ypperf01_master_qemux86.html Fedora 23] (retired)
* [https://wiki.yoctoproject.org/charts/build_perf/latest/ypperf02_master_qemux86.html Ubuntu 15.10] (retired)


<tab class=wikitable sep=comma head=top>
== Milestone Test results ==
hostname,branch:commit,git describe,bitbake core-image-sato,bitbake virtual/kernel,bitbake core-image-sato (rm_work),bitbake core-image-sato -c rootfs,bitbake -p (rm -rf cache/ tmp/cache/), bitbake -p (rm -rf tmp/cache/),bitbake -p,size of tmp dir, size of tmp dir (rm_work)
Guadalajara Setup from 2.1 M4 to actual master
ubuntu12,dylan:73f103bf9b2cdf985464dc53bf4f1cfd71d4531f,yocto-1.4.1,1:16:41,11:32.41,1:06:51,5:14.78,0:26.75,0:14.81,0:01.96,28213628,4743912
ubuntu12,dylan:73f103bf9b2cdf985464dc53bf4f1cfd71d4531f,yocto-1.4.1,1:14:31,11:34.66,1:06:41,5:12.70,0:26.54,0:14.74,0:01.92,28213772,4743844
ubuntu12,dylan:73f103bf9b2cdf985464dc53bf4f1cfd71d4531f,yocto-1.4.1,1:12:39,11:35.99,1:06:59,5:16.48,0:26.77,0:14.71,0:01.96,28217808,4743800
ubuntu12,dylan:d734ab491a30078d43dee5440c03acce2d251425,yocto-1.4.2,1:12:58,12:56.22,1:07:45,4:54.36,0:26.78,0:14.73,0:01.95,25349116,4767324
ubuntu12,dylan:d734ab491a30078d43dee5440c03acce2d251425,yocto-1.4.2,1:13:33,12:44.85,1:08:10,5:01.71,0:26.87,0:14.80,0:01.99,25349708,4767348
ubuntu12,dylan:d734ab491a30078d43dee5440c03acce2d251425,yocto-1.4.2,1:13:00,12:59.19,1:08:13,5:07.04,0:26.83,0:14.73,0:01.97,25363408,4767380
</tab>


* [https://wiki.yoctoproject.org/charts/perf_milestone_GDC/performance_test.html GDC Charts]


<tab class=wikitable sep=comma head=top>
== Old Test results ==
hostname,branch:commit,git describe,bitbake core-image-sato,bitbake virtual/kernel,bitbake core-image-sato (rm_work),bitbake core-image-sato -c rootfs,bitbake -p (rm -rf cache/ tmp/cache/), bitbake -p (rm -rf tmp/cache/),bitbake -p,size of tmp dir, size of tmp dir (rm_work)
</tab>


Milestone test results from the retired Romania Setup (Yocto 1.6 – 2.1) can be found from here:


== 1.5 Milestones results ==
* [https://wiki.yoctoproject.org/charts/perf_milestone/performance_test.html RO Charts]


<tab class=wikitable sep=comma head=top>
Raw test data from the retired Romania test setup has been moved to
hostname,branch:commit,git describe,bitbake core-image-sato,bitbake virtual/kernel,bitbake core-image-sato (rm_work),bitbake core-image-sato -c rootfs,bitbake -p (rm -rf cache/ tmp/cache/), bitbake -p (rm -rf tmp/cache/),bitbake -p,size of tmp dir, size of tmp dir (rm_work)
* [[Performance_Test_Old_Results]]
* [[Performance_Test_Weekly_1.5]] has the old weekly results ran during the 1.5 cycle.


</tab>
Configuration for the Romania Setup 1.6 - 2.1:


<tab class=wikitable sep=comma head=top>
* Ubuntu 12.04 (uname -nr: ubuntu12 3.8.0-31-generic) and
hostname,branch:commit,git describe,bitbake core-image-sato,bitbake virtual/kernel,bitbake core-image-sato (rm_work),bitbake core-image-sato -c rootfs,bitbake -p (rm -rf cache/ tmp/cache/), bitbake -p (rm -rf tmp/cache/),bitbake -p,size of tmp dir, size of tmp dir (rm_work)
* Fedora 19 (uname -nr: fedora19 3.11.3-201.fc19.x86_64)
thunderbird,master:a62aed41f2d8f874f7ae24d0e5be5dbc66ea2199,1.5_M1.rc1,1:06:19,16:02.83,1:15:05,4:54.64,0:31.35,0:18.24,0:02.19,25G,4.7G
* HW configuration: SandyBridge i7-2600 CPU @ 3.40GHz (4 cores/8 threads), 8GB RAM, 1 x 500 GB HDD
thunderbird,master:a62aed41f2d8f874f7ae24d0e5be5dbc66ea2199,1.5_M1.rc1,1:13:43,12:12.01,1:06:04,4:58.59,0:31.27,0:18.62,0:02.20,25G,4.7G
thunderbird,master:a62aed41f2d8f874f7ae24d0e5be5dbc66ea2199,1.5_M1.rc1,1:06:36,11:50.66,1:18:42,4:56.03,0:31.22,0:16.85,0:02.19,25G,4.7G
thunderbird,master:a62aed41f2d8f874f7ae24d0e5be5dbc66ea2199,1.5_M1.rc1,1:06:21,11:23.33,1:06:18,4:56.64,0:31.32,0:16.87,0:02.23,25G,4.7G
thunderbird,master:eaa5df34af42b6a37f6506847d0f3ef6ba0d298a,1.5_M2.rc1,1:08:59,12:55.64,1:10:29,4:52.32,0:32.29,0:17.37,0:02.13,25G,4.8G
thunderbird,master:eaa5df34af42b6a37f6506847d0f3ef6ba0d298a,1.5_M2.rc1,1:10:30,13:09.84,1:10:33,4:50.67,0:32.03,0:17.19,0:02.17,25G,4.8G
thunderbird,master:eaa5df34af42b6a37f6506847d0f3ef6ba0d298a,1.5_M2.rc1,1:09:36,12:43.86,1:10:17,4:52.71,0:32.11,0:17.31,0:02.16,25G,4.8G
thunderbird,master:9de0ad47462c13ac4a2d73e12e92be6c1b4e0415,1.5_M3.rc1,1:07:38,12:05.60,1:09:12,4:52.04,0:32.59,0:17.57,0:02.13,25G,4.8G
thunderbird,master:9de0ad47462c13ac4a2d73e12e92be6c1b4e0415,1.5_M3.rc1,1:07:46,11:36.30,1:09:33,4:52.40,0:32.68,0:17.47,0:02.11,25G,4.8G
thunderbird,master:9de0ad47462c13ac4a2d73e12e92be6c1b4e0415,1.5_M3.rc1,1:07:37,11:38.58,1:09:58,4:54.80,0:32.55,0:17.59,0:02.15,25G,4.8G
thunderbird,master:5745e45b18e5099e94b4d5a73bc97dc6d4cdc91f,1.5_M4.rc2,1:08:15,12:09.53,1:09:28,5:06.14,0:32.93,0:17.82,0:02.31,26640040,5070688
thunderbird,master:5745e45b18e5099e94b4d5a73bc97dc6d4cdc91f,1.5_M4.rc2,1:08:11,12:12.62,1:11:07,6:37.02,0:33.24,0:18.03,0:02.54,26639316,5070880
thunderbird,master:5745e45b18e5099e94b4d5a73bc97dc6d4cdc91f,1.5_M4.rc2,1:08:31,11:55.12,1:09:48,5:07.88,0:32.83,0:17.77,0:02.31,26640472,5070964
thunderbird,master:ed3ef0823fde89371a473d20c0127c0bd16d062b,1.5_M4.rc3,1:09:10,12:35.20,1:12:22,5:13.46,0:34.00,0:17.22,0:01.62,26191068,5007872
thunderbird,master:ed3ef0823fde89371a473d20c0127c0bd16d062b,1.5_M4.rc3,1:09:06,12:11.86,1:10:14,5:10.86,0:32.38,0:17.22,0:01.64,26191508,5007760
thunderbird,master:566ca1e4769b4ec7e3f6c6a98bb817db2221cf82,1.5_M5.rc1,1:09:06,12:19.34,1:09:50,5:01.06,0:32.06,0:16.88,0:01.67,26188240,5006064
thunderbird,master:566ca1e4769b4ec7e3f6c6a98bb817db2221cf82,1.5_M5.rc1,1:08:51,12:18.70,1:09:59,5:03.20,0:31.87,0:16.82,0:01.59,26187888,5006224
thunderbird,master:566ca1e4769b4ec7e3f6c6a98bb817db2221cf82,1.5_M5.rc1,1:08:50,12:21.37,1:10:36,4:58.62,0:32.37,0:16.91,0:01.62,26186304,5006164
thunderbird,master:853bc53cd58a621918f0e5ce662dba263d1befb4,1.5_M5.rc4,1:07:52,12:12.11,1:08:51,4:53.53,0:29.19,0:14.19,0:01.56,26272324,5029132
thunderbird,master:853bc53cd58a621918f0e5ce662dba263d1befb4,1.5_M5.rc4,1:08:03,12:06.52,1:08:59,4:53.33,0:29.17,0:14.14,0:01.57,26272832,5029180
thunderbird,master:853bc53cd58a621918f0e5ce662dba263d1befb4,1.5_M5.rc4,1:08:12,12:37.96,1:09:07,4:53.13,0:29.12,0:14.27,0:01.57,26273212,5029152
</tab>

Latest revision as of 14:17, 28 January 2019

Build time tracking

Script used for running the builds:

  • Before morty: poky/scripts/contrib/build-perf-test.sh
  • After morty: poky/scripts/oe-build-perf-test

Two identical test systems are used for the results, with all updates available installed. Extra packages installed (besides what's by the default in the distro) are the ones in the Quick Start guide.

Configuration of the GDC Setup 2.1 - Current master

  • Ubuntu 15.10 (Wily Werewolf)" --> 4.2.0-16-generic
  • Fedora release 23 (Twenty Three) --> 4.7.10-100.fc23.x86_64
  • HW configuration: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz, 16GB RAM, 1 x 600 GB SDD, 1 x 2 TB HDD

All system/distro settings are distro's defaults, that includes:

- FS mount options: ext4 rw,relatime,data=ordered

- IO scheduler: cfq and CPU governer: ondemand

local.conf it's the default one (the script doesn't touch it except for changing DL_DIR if necessary).

It however exports these in the enviroment: 

BB_NUMBER_THREADS = "8"
PARALLEL_MAKE = "-j 8"
MACHINE = "qemux86"

FAQ:

  • Q: Where is 1.5_M2? It's there but it's called: 1.5_M1.final-412-geaa5df3 The M2 build wasn't released hence no git tag
  • Q: What's with the different number of RCs? See Yocto_Project_Release_Process#Milestone_Releases
  • Q: Why are there more results for some commits? The script is ran from a cron job multiple times a day, sometimes master changes daily sometimes it doesn't, hence more results for one commit (ie weekends)


Daily Test Results

Build performance test suite is run multiple times per day. Latest test reports for master branch can found here:

Milestone Test results

Guadalajara Setup from 2.1 M4 to actual master

Old Test results

Milestone test results from the retired Romania Setup (Yocto 1.6 – 2.1) can be found from here:

Raw test data from the retired Romania test setup has been moved to

Configuration for the Romania Setup 1.6 - 2.1:

  • Ubuntu 12.04 (uname -nr: ubuntu12 3.8.0-31-generic) and
  • Fedora 19 (uname -nr: fedora19 3.11.3-201.fc19.x86_64)
  • HW configuration: SandyBridge i7-2600 CPU @ 3.40GHz (4 cores/8 threads), 8GB RAM, 1 x 500 GB HDD
Retrieved from "https://wiki.yoctoproject.org/wiki/index.php?title=Performance_Test&oldid=46678"