| 2012-10-30 13:16:01 |
Removed by request |
bug |
|
|
added bug |
| 2012-10-30 13:16:01 |
Removed by request |
attachment added |
|
threads.py https://bugs.launchpad.net/bugs/1073148/+attachment/3418558/+files/threads.py |
|
| 2012-10-30 13:30:08 |
Brad Figg |
linux (Ubuntu): status |
New |
Incomplete |
|
| 2012-10-30 13:32:19 |
Joseph Salisbury |
linux (Ubuntu): importance |
Undecided |
Medium |
|
| 2012-10-30 14:22:10 |
Joseph Salisbury |
tags |
|
raring |
|
| 2012-10-30 14:22:37 |
Joseph Salisbury |
tags |
raring |
needs-upstream-testing raring |
|
| 2012-10-30 14:36:52 |
Removed by request |
tags |
needs-upstream-testing raring |
apport-collected needs-upstream-testing raring |
|
| 2012-10-30 14:36:53 |
Removed by request |
description |
I'm using Ubuntu 13.04 dev and have noticed a high cpu overhead if a process is using multiple threads and computing them on different threads. To measure this I have written a little script in Python which I will attach.
The script will create 2 threads which are using only a little time of a cpu core. On my AMD Phenom II X6 1045T the Linux kernel will assign the 2 threads on 2 cores which will use a total cpu time of 40% from a maximum of 600%. But if I'm using "taskset -ap 0x00000001 pid_of_script" the 2 threads will be assigned to 1 core and the total cpu usage will be only 25% from 600%.
I'm wondering why there is a cpu overhead of 60% if the Linux kernel is using 2 cores instead of 1 core. |
I'm using Ubuntu 13.04 dev and have noticed a high cpu overhead if a process is using multiple threads and computing them on different threads. To measure this I have written a little script in Python which I will attach.
The script will create 2 threads which are using only a little time of a cpu core. On my AMD Phenom II X6 1045T the Linux kernel will assign the 2 threads on 2 cores which will use a total cpu time of 40% from a maximum of 600%. But if I'm using "taskset -ap 0x00000001 pid_of_script" the 2 threads will be assigned to 1 core and the total cpu usage will be only 25% from 600%.
I'm wondering why there is a cpu overhead of 60% if the Linux kernel is using 2 cores instead of 1 core.
---
AlsaVersion: Advanced Linux Sound Architecture Driver Version 1.0.25.
AplayDevices:
**** List of PLAYBACK Hardware Devices ****
card 0: SB [HDA ATI SB], device 0: ALC662 rev1 Analog [ALC662 rev1 Analog]
Subdevices: 0/1
Subdevice #0: subdevice #0
ApportVersion: 2.6.1-0ubuntu6
Architecture: amd64
AudioDevicesInUse:
USER PID ACCESS COMMAND
/dev/snd/controlC0: sworddragon 2374 F.... plugin-containe
/dev/snd/pcmC0D0p: sworddragon 2374 F...m plugin-containe
/dev/snd/timer: sworddragon 2374 f.... plugin-containe
CRDA: Error: [Errno 2] No such file or directory
Card0.Amixer.info:
Card hw:0 'SB'/'HDA ATI SB at 0xf9ff4000 irq 16'
Mixer name : 'Realtek ALC662 rev1'
Components : 'HDA:10ec0662,18497662,00100101'
Controls : 33
Simple ctrls : 18
CurrentDmesg:
Error: command ['sh', '-c', 'dmesg | comm -13 --nocheck-order /var/log/dmesg -'] failed with exit code 1: comm: /var/log/dmesg: No such file or directory
dmesg: write failed: Broken pipe
DistroRelease: Ubuntu 13.04
EcryptfsInUse: Yes
IwConfig: Error: [Errno 2] No such file or directory
Lsusb: Error: [Errno 2] No such file or directory
MachineType: To Be Filled By O.E.M. To Be Filled By O.E.M.
MarkForUpload: True
NonfreeKernelModules: nvidia
Package: linux (not installed)
ProcEnviron:
TERM=xterm
PATH=(custom, no user)
LANG=de_DE.UTF-8
SHELL=/bin/bash
ProcFB: 0 VESA VGA
ProcKernelCmdLine: BOOT_IMAGE=/boot/vmlinuz-3.5.0-17-generic root=UUID=f1ce7323-74dc-46f7-95f7-887cc54403e7 ro
ProcVersionSignature: Ubuntu 3.5.0-17.28-generic 3.5.5
RfKill: Error: [Errno 2] No such file or directory
Tags: raring
Uname: Linux 3.5.0-17-generic x86_64
UpgradeStatus: No upgrade log present (probably fresh install)
UserGroups: adm cdrom dialout lpadmin plugdev sambashare sudo
dmi.bios.date: 05/21/2012
dmi.bios.vendor: American Megatrends Inc.
dmi.bios.version: P1.20
dmi.board.asset.tag: BC5FF4739C55
dmi.board.name: 960GM/U3S3 FX
dmi.board.vendor: ASRock
dmi.chassis.asset.tag: To Be Filled By O.E.M.
dmi.chassis.type: 3
dmi.chassis.vendor: To Be Filled By O.E.M.
dmi.chassis.version: To Be Filled By O.E.M.
dmi.modalias: dmi:bvnAmericanMegatrendsInc.:bvrP1.20:bd05/21/2012:svnToBeFilledByO.E.M.:pnToBeFilledByO.E.M.:pvrToBeFilledByO.E.M.:rvnASRock:rn960GM/U3S3FX:rvr:cvnToBeFilledByO.E.M.:ct3:cvrToBeFilledByO.E.M.:
dmi.product.name: To Be Filled By O.E.M.
dmi.product.version: To Be Filled By O.E.M.
dmi.sys.vendor: To Be Filled By O.E.M. |
|
| 2012-10-30 14:36:54 |
Removed by request |
attachment added |
|
AlsaDevices.txt https://bugs.launchpad.net/bugs/1073148/+attachment/3418648/+files/AlsaDevices.txt |
|
| 2012-10-30 14:36:56 |
Removed by request |
attachment added |
|
ArecordDevices.txt https://bugs.launchpad.net/bugs/1073148/+attachment/3418649/+files/ArecordDevices.txt |
|
| 2012-10-30 14:36:58 |
Removed by request |
attachment added |
|
Card0.Amixer.values.txt https://bugs.launchpad.net/bugs/1073148/+attachment/3418650/+files/Card0.Amixer.values.txt |
|
| 2012-10-30 14:36:59 |
Removed by request |
attachment added |
|
Card0.Codecs.codec.0.txt https://bugs.launchpad.net/bugs/1073148/+attachment/3418651/+files/Card0.Codecs.codec.0.txt |
|
| 2012-10-30 14:37:00 |
Removed by request |
attachment added |
|
Lspci.txt https://bugs.launchpad.net/bugs/1073148/+attachment/3418652/+files/Lspci.txt |
|
| 2012-10-30 14:37:03 |
Removed by request |
attachment added |
|
PciMultimedia.txt https://bugs.launchpad.net/bugs/1073148/+attachment/3418653/+files/PciMultimedia.txt |
|
| 2012-10-30 14:37:04 |
Removed by request |
attachment added |
|
ProcCpuinfo.txt https://bugs.launchpad.net/bugs/1073148/+attachment/3418654/+files/ProcCpuinfo.txt |
|
| 2012-10-30 14:37:06 |
Removed by request |
attachment added |
|
ProcInterrupts.txt https://bugs.launchpad.net/bugs/1073148/+attachment/3418655/+files/ProcInterrupts.txt |
|
| 2012-10-30 14:37:07 |
Removed by request |
attachment added |
|
ProcModules.txt https://bugs.launchpad.net/bugs/1073148/+attachment/3418656/+files/ProcModules.txt |
|
| 2012-10-30 14:37:10 |
Removed by request |
attachment added |
|
UdevDb.txt https://bugs.launchpad.net/bugs/1073148/+attachment/3418657/+files/UdevDb.txt |
|
| 2012-10-30 14:37:11 |
Removed by request |
attachment added |
|
UdevLog.txt https://bugs.launchpad.net/bugs/1073148/+attachment/3418658/+files/UdevLog.txt |
|
| 2012-10-30 14:37:14 |
Removed by request |
attachment added |
|
WifiSyslog.txt https://bugs.launchpad.net/bugs/1073148/+attachment/3418659/+files/WifiSyslog.txt |
|
| 2012-10-30 14:39:12 |
Removed by request |
tags |
apport-collected needs-upstream-testing raring |
apport-collected kernel-unable-to-test-upstream raring |
|
| 2012-10-30 14:39:25 |
Removed by request |
linux (Ubuntu): status |
Incomplete |
Confirmed |
|
| 2012-11-14 14:53:00 |
Removed by request |
tags |
apport-collected kernel-unable-to-test-upstream raring |
apport-collected raring |
|
| 2012-11-14 19:19:03 |
Joseph Salisbury |
linux (Ubuntu): status |
Confirmed |
Triaged |
|
| 2012-11-15 07:53:30 |
Removed by request |
tags |
apport-collected raring |
apport-collected kernel-unable-to-test-upstream raring |
|
| 2012-11-16 22:29:08 |
Joseph Salisbury |
linux (Ubuntu): status |
Triaged |
Won't Fix |
|
| 2012-11-19 15:08:58 |
Joseph Salisbury |
linux (Ubuntu): status |
Won't Fix |
Triaged |
|
| 2012-12-13 11:06:02 |
Removed by request |
bug watch added |
|
http://bugzilla.kernel.org/show_bug.cgi?id=51691 |
|
| 2012-12-18 21:27:41 |
Removed by request |
description |
I'm using Ubuntu 13.04 dev and have noticed a high cpu overhead if a process is using multiple threads and computing them on different threads. To measure this I have written a little script in Python which I will attach.
The script will create 2 threads which are using only a little time of a cpu core. On my AMD Phenom II X6 1045T the Linux kernel will assign the 2 threads on 2 cores which will use a total cpu time of 40% from a maximum of 600%. But if I'm using "taskset -ap 0x00000001 pid_of_script" the 2 threads will be assigned to 1 core and the total cpu usage will be only 25% from 600%.
I'm wondering why there is a cpu overhead of 60% if the Linux kernel is using 2 cores instead of 1 core.
---
AlsaVersion: Advanced Linux Sound Architecture Driver Version 1.0.25.
AplayDevices:
**** List of PLAYBACK Hardware Devices ****
card 0: SB [HDA ATI SB], device 0: ALC662 rev1 Analog [ALC662 rev1 Analog]
Subdevices: 0/1
Subdevice #0: subdevice #0
ApportVersion: 2.6.1-0ubuntu6
Architecture: amd64
AudioDevicesInUse:
USER PID ACCESS COMMAND
/dev/snd/controlC0: sworddragon 2374 F.... plugin-containe
/dev/snd/pcmC0D0p: sworddragon 2374 F...m plugin-containe
/dev/snd/timer: sworddragon 2374 f.... plugin-containe
CRDA: Error: [Errno 2] No such file or directory
Card0.Amixer.info:
Card hw:0 'SB'/'HDA ATI SB at 0xf9ff4000 irq 16'
Mixer name : 'Realtek ALC662 rev1'
Components : 'HDA:10ec0662,18497662,00100101'
Controls : 33
Simple ctrls : 18
CurrentDmesg:
Error: command ['sh', '-c', 'dmesg | comm -13 --nocheck-order /var/log/dmesg -'] failed with exit code 1: comm: /var/log/dmesg: No such file or directory
dmesg: write failed: Broken pipe
DistroRelease: Ubuntu 13.04
EcryptfsInUse: Yes
IwConfig: Error: [Errno 2] No such file or directory
Lsusb: Error: [Errno 2] No such file or directory
MachineType: To Be Filled By O.E.M. To Be Filled By O.E.M.
MarkForUpload: True
NonfreeKernelModules: nvidia
Package: linux (not installed)
ProcEnviron:
TERM=xterm
PATH=(custom, no user)
LANG=de_DE.UTF-8
SHELL=/bin/bash
ProcFB: 0 VESA VGA
ProcKernelCmdLine: BOOT_IMAGE=/boot/vmlinuz-3.5.0-17-generic root=UUID=f1ce7323-74dc-46f7-95f7-887cc54403e7 ro
ProcVersionSignature: Ubuntu 3.5.0-17.28-generic 3.5.5
RfKill: Error: [Errno 2] No such file or directory
Tags: raring
Uname: Linux 3.5.0-17-generic x86_64
UpgradeStatus: No upgrade log present (probably fresh install)
UserGroups: adm cdrom dialout lpadmin plugdev sambashare sudo
dmi.bios.date: 05/21/2012
dmi.bios.vendor: American Megatrends Inc.
dmi.bios.version: P1.20
dmi.board.asset.tag: BC5FF4739C55
dmi.board.name: 960GM/U3S3 FX
dmi.board.vendor: ASRock
dmi.chassis.asset.tag: To Be Filled By O.E.M.
dmi.chassis.type: 3
dmi.chassis.vendor: To Be Filled By O.E.M.
dmi.chassis.version: To Be Filled By O.E.M.
dmi.modalias: dmi:bvnAmericanMegatrendsInc.:bvrP1.20:bd05/21/2012:svnToBeFilledByO.E.M.:pnToBeFilledByO.E.M.:pvrToBeFilledByO.E.M.:rvnASRock:rn960GM/U3S3FX:rvr:cvnToBeFilledByO.E.M.:ct3:cvrToBeFilledByO.E.M.:
dmi.product.name: To Be Filled By O.E.M.
dmi.product.version: To Be Filled By O.E.M.
dmi.sys.vendor: To Be Filled By O.E.M. |
I'm using Ubuntu 13.04 dev and have noticed a high cpu overhead if a process is using multiple threads and computing them on different cores. To measure this I have written a little script in Python which I will attach.
The script will create 2 threads which are using only a little time of a cpu core. On my AMD Phenom II X6 1045T the Linux kernel will assign the 2 threads on 2 cores which will use a total cpu time of 40% from a maximum of 600%. But if I'm using "taskset -ap 0x00000001 pid_of_script" the 2 threads will be assigned to 1 core and the total cpu usage will be only 25% from 600%.
I'm wondering why there is a cpu overhead of 60% if the Linux kernel is using 2 cores instead of 1 core.
---
AlsaVersion: Advanced Linux Sound Architecture Driver Version 1.0.25.
AplayDevices:
**** List of PLAYBACK Hardware Devices ****
card 0: SB [HDA ATI SB], device 0: ALC662 rev1 Analog [ALC662 rev1 Analog]
Subdevices: 0/1
Subdevice #0: subdevice #0
ApportVersion: 2.6.1-0ubuntu6
Architecture: amd64
AudioDevicesInUse:
USER PID ACCESS COMMAND
/dev/snd/controlC0: sworddragon 2374 F.... plugin-containe
/dev/snd/pcmC0D0p: sworddragon 2374 F...m plugin-containe
/dev/snd/timer: sworddragon 2374 f.... plugin-containe
CRDA: Error: [Errno 2] No such file or directory
Card0.Amixer.info:
Card hw:0 'SB'/'HDA ATI SB at 0xf9ff4000 irq 16'
Mixer name : 'Realtek ALC662 rev1'
Components : 'HDA:10ec0662,18497662,00100101'
Controls : 33
Simple ctrls : 18
CurrentDmesg:
Error: command ['sh', '-c', 'dmesg | comm -13 --nocheck-order /var/log/dmesg -'] failed with exit code 1: comm: /var/log/dmesg: No such file or directory
dmesg: write failed: Broken pipe
DistroRelease: Ubuntu 13.04
EcryptfsInUse: Yes
IwConfig: Error: [Errno 2] No such file or directory
Lsusb: Error: [Errno 2] No such file or directory
MachineType: To Be Filled By O.E.M. To Be Filled By O.E.M.
MarkForUpload: True
NonfreeKernelModules: nvidia
Package: linux (not installed)
ProcEnviron:
TERM=xterm
PATH=(custom, no user)
LANG=de_DE.UTF-8
SHELL=/bin/bash
ProcFB: 0 VESA VGA
ProcKernelCmdLine: BOOT_IMAGE=/boot/vmlinuz-3.5.0-17-generic root=UUID=f1ce7323-74dc-46f7-95f7-887cc54403e7 ro
ProcVersionSignature: Ubuntu 3.5.0-17.28-generic 3.5.5
RfKill: Error: [Errno 2] No such file or directory
Tags: raring
Uname: Linux 3.5.0-17-generic x86_64
UpgradeStatus: No upgrade log present (probably fresh install)
UserGroups: adm cdrom dialout lpadmin plugdev sambashare sudo
dmi.bios.date: 05/21/2012
dmi.bios.vendor: American Megatrends Inc.
dmi.bios.version: P1.20
dmi.board.asset.tag: BC5FF4739C55
dmi.board.name: 960GM/U3S3 FX
dmi.board.vendor: ASRock
dmi.chassis.asset.tag: To Be Filled By O.E.M.
dmi.chassis.type: 3
dmi.chassis.vendor: To Be Filled By O.E.M.
dmi.chassis.version: To Be Filled By O.E.M.
dmi.modalias: dmi:bvnAmericanMegatrendsInc.:bvrP1.20:bd05/21/2012:svnToBeFilledByO.E.M.:pnToBeFilledByO.E.M.:pvrToBeFilledByO.E.M.:rvnASRock:rn960GM/U3S3FX:rvr:cvnToBeFilledByO.E.M.:ct3:cvrToBeFilledByO.E.M.:
dmi.product.name: To Be Filled By O.E.M.
dmi.product.version: To Be Filled By O.E.M.
dmi.sys.vendor: To Be Filled By O.E.M. |
|
| 2013-11-19 10:52:07 |
penalvch |
tags |
apport-collected kernel-unable-to-test-upstream raring |
apport-collected bios-outdated-1.40 kernel-unable-to-test-upstream raring |
|
| 2013-11-19 10:52:22 |
penalvch |
linux (Ubuntu): status |
Triaged |
Incomplete |
|
| 2013-11-20 12:13:19 |
Removed by request |
linux (Ubuntu): status |
Incomplete |
New |
|
| 2013-11-20 12:13:44 |
Removed by request |
tags |
apport-collected bios-outdated-1.40 kernel-unable-to-test-upstream raring |
apport-collected kernel-unable-to-test-upstream raring |
|
| 2013-11-20 12:14:17 |
Removed by request |
attachment added |
|
Testcase https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1073148/+attachment/3913241/+files/threads.c |
|
| 2013-11-20 12:14:38 |
Removed by request |
attachment removed |
threads.py https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1073148/+attachment/3418558/+files/threads.py |
|
|
| 2013-11-20 12:27:33 |
penalvch |
tags |
apport-collected kernel-unable-to-test-upstream raring |
apport-collected kernel-unable-to-test-upstream latest-bios-1.40 raring |
|
| 2013-11-20 12:27:49 |
penalvch |
tags |
apport-collected kernel-unable-to-test-upstream latest-bios-1.40 raring |
apport-collected kernel-unable-to-test-upstream latest-bios-1.40 raring trusty |
|
| 2013-11-20 12:30:12 |
penalvch |
tags |
apport-collected kernel-unable-to-test-upstream latest-bios-1.40 raring trusty |
apport-collected kernel-unable-to-test-upstream latest-bios-1.40 needs-upstream-testing raring regression-potential trusty |
|
| 2013-11-20 12:30:18 |
Brad Figg |
linux (Ubuntu): status |
New |
Incomplete |
|
| 2013-11-20 12:32:58 |
penalvch |
bug task added |
|
linux |
|
| 2013-11-20 12:34:11 |
penalvch |
summary |
High cpu overhead on using multiple cores |
[960GM/U3S3 FX] Higher than expected cpu overhead on using multiple cores |
|
| 2013-11-20 12:38:17 |
penalvch |
linux (Ubuntu): status |
Incomplete |
Confirmed |
|
