2010-10-24 06:50:54 |
Juliano Ravasi |
bug |
|
|
added bug |
2010-10-29 21:01:52 |
Juliano Ravasi |
description |
Since upgrading to Maverick, I'm frequently observing instances of the timer interrupts suddenly stopping being processed (or even produced?) for a few minutes. The system becomes sluggish as a whole, all CPU cores go high on Sys% usage. This continues for 3-5 minutes, then suddenly goes back to normal, just like how it started.
It is certainly related to the timer interrupt: If I continuously 'cat /proc/interrupts' (or just run it under 'watch') during the time the system is affected, interrupt 0 (IR-IO-APIC-edge timer) stays frozen until the problem goes away. No messages appear on dmesg or in /var/log/kern.log.
The problem always starts at random, with no particular cause, but it seems more frequent when making heavy use of both sound and graphics at the same time. It is very common to happen when I start playing some game on Wine. It seems to also vanish at random after 3-5 minutes have passed, but zapping the X server seems to a way to restore the normal behaviour (it happened twice until now, I need more tests to confirm).
I don't know what more I can say about this issue, but feel free to ask; I'm willing to provide as much information as possible to have this fixed.
ProblemType: Bug
DistroRelease: Ubuntu 10.10
Package: linux-image-2.6.35-22-generic 2.6.35-22.35
Regression: Yes
Reproducible: No
ProcVersionSignature: Ubuntu 2.6.35-22.35-generic 2.6.35.4
Uname: Linux 2.6.35-22-generic x86_64
NonfreeKernelModules: nvidia
AlsaVersion: Advanced Linux Sound Architecture Driver Version 1.0.23.
Architecture: amd64
AudioDevicesInUse:
USER PID ACCESS COMMAND
/dev/snd/controlC0: juliano 2781 F.... kmix
CRDA: Error: [Errno 2] No such file or directory
Card0.Amixer.info:
Card hw:0 'Intel'/'HDA Intel at 0xf0000000 irq 22'
Mixer name : 'Realtek ALC889'
Components : 'HDA:10ec0889,80860022,00100004'
Controls : 42
Simple ctrls : 24
Date: Sun Oct 24 04:25:13 2010
Frequency: I don't know.
HibernationDevice: RESUME=UUID=4f433bf6-748e-432d-b93f-de4d0e693b91
InstallationMedia: Kubuntu 10.10 "Maverick Meerkat" - Release amd64 (20101008)
ProcCmdLine: BOOT_IMAGE=/boot/vmlinuz-2.6.35-22-generic root=/dev/mapper/Nagisa1-Root ro rootdelay=5
ProcEnviron:
LANGUAGE=
PATH=(custom, user)
LANG=en_US.UTF-8
SHELL=/bin/zsh
RelatedPackageVersions: linux-firmware 1.38
RfKill:
SourcePackage: linux
UserAsoundrc:
#pcm.!default plug:hw:0
#ctl.!default hw:0
dmi.bios.date: 08/30/2010
dmi.bios.vendor: Intel Corp.
dmi.bios.version: SOX5810J.86A.5456.2010.0830.0013
dmi.board.asset.tag: Base Board Asset Tag
dmi.board.name: DX58SO
dmi.board.vendor: Intel Corporation
dmi.board.version: AAE29331-703
dmi.chassis.type: 2
dmi.modalias: dmi:bvnIntelCorp.:bvrSOX5810J.86A.5456.2010.0830.0013:bd08/30/2010:svn:pn:pvr:rvnIntelCorporation:rnDX58SO:rvrAAE29331-703:cvn:ct2:cvr: |
Since upgrading to Maverick, I'm frequently observing instances of the timer interrupts suddenly stopping being processed (or even produced?) for a few minutes. The system becomes sluggish as a whole, all CPU cores go high on Sys% usage. This continues for 3-5 minutes, then suddenly goes back to normal, just like how it started.
It is certainly related to the timer interrupt: If I continuously 'cat /proc/interrupts' (or just run it under 'watch') during the time the system is affected, interrupt 0 (IR-IO-APIC-edge timer) stays frozen until the problem goes away. No messages appear on dmesg or in /var/log/kern.log.
The problem always starts at random, with no particular cause, but it seems more frequent when making heavy use of both sound and graphics at the same time. It is very common to happen when I start playing some game on Wine. It seems to also vanish at random after 3-5 minutes have passed, but zapping the X server seems to a way to restore the normal behaviour (it happened twice until now, I need more tests to confirm).
The system is:
Processor: Intel Core i7 930 (2.8 GHz, 4 cores × 2 threads)
Mainboard: Intel DX58SO Extreme
Memory: 6 GiB
Storage: 3 × 1 TB Samsung HardDisks on a RAID 5 array, LVM on top.
I don't know what more I can say about this issue, but feel free to ask; I'm willing to provide as much information as possible to have this fixed.
ProblemType: Bug
DistroRelease: Ubuntu 10.10
Package: linux-image-2.6.35-22-generic 2.6.35-22.35
Regression: Yes
Reproducible: No
ProcVersionSignature: Ubuntu 2.6.35-22.35-generic 2.6.35.4
Uname: Linux 2.6.35-22-generic x86_64
NonfreeKernelModules: nvidia
AlsaVersion: Advanced Linux Sound Architecture Driver Version 1.0.23.
Architecture: amd64
AudioDevicesInUse:
USER PID ACCESS COMMAND
/dev/snd/controlC0: juliano 2781 F.... kmix
CRDA: Error: [Errno 2] No such file or directory
Card0.Amixer.info:
Card hw:0 'Intel'/'HDA Intel at 0xf0000000 irq 22'
Mixer name : 'Realtek ALC889'
Components : 'HDA:10ec0889,80860022,00100004'
Controls : 42
Simple ctrls : 24
Date: Sun Oct 24 04:25:13 2010
Frequency: I don't know.
HibernationDevice: RESUME=UUID=4f433bf6-748e-432d-b93f-de4d0e693b91
InstallationMedia: Kubuntu 10.10 "Maverick Meerkat" - Release amd64 (20101008)
ProcCmdLine: BOOT_IMAGE=/boot/vmlinuz-2.6.35-22-generic root=/dev/mapper/Nagisa1-Root ro rootdelay=5
ProcEnviron:
LANGUAGE=
PATH=(custom, user)
LANG=en_US.UTF-8
SHELL=/bin/zsh
RelatedPackageVersions: linux-firmware 1.38
RfKill:
SourcePackage: linux
UserAsoundrc:
#pcm.!default plug:hw:0
#ctl.!default hw:0
dmi.bios.date: 08/30/2010
dmi.bios.vendor: Intel Corp.
dmi.bios.version: SOX5810J.86A.5456.2010.0830.0013
dmi.board.asset.tag: Base Board Asset Tag
dmi.board.name: DX58SO
dmi.board.vendor: Intel Corporation
dmi.board.version: AAE29331-703
dmi.chassis.type: 2
dmi.modalias: dmi:bvnIntelCorp.:bvrSOX5810J.86A.5456.2010.0830.0013:bd08/30/2010:svn:pn:pvr:rvnIntelCorporation:rnDX58SO:rvrAAE29331-703:cvn:ct2:cvr:
|
|
2010-10-29 21:18:24 |
Juliano Ravasi |
description |
Since upgrading to Maverick, I'm frequently observing instances of the timer interrupts suddenly stopping being processed (or even produced?) for a few minutes. The system becomes sluggish as a whole, all CPU cores go high on Sys% usage. This continues for 3-5 minutes, then suddenly goes back to normal, just like how it started.
It is certainly related to the timer interrupt: If I continuously 'cat /proc/interrupts' (or just run it under 'watch') during the time the system is affected, interrupt 0 (IR-IO-APIC-edge timer) stays frozen until the problem goes away. No messages appear on dmesg or in /var/log/kern.log.
The problem always starts at random, with no particular cause, but it seems more frequent when making heavy use of both sound and graphics at the same time. It is very common to happen when I start playing some game on Wine. It seems to also vanish at random after 3-5 minutes have passed, but zapping the X server seems to a way to restore the normal behaviour (it happened twice until now, I need more tests to confirm).
The system is:
Processor: Intel Core i7 930 (2.8 GHz, 4 cores × 2 threads)
Mainboard: Intel DX58SO Extreme
Memory: 6 GiB
Storage: 3 × 1 TB Samsung HardDisks on a RAID 5 array, LVM on top.
I don't know what more I can say about this issue, but feel free to ask; I'm willing to provide as much information as possible to have this fixed.
ProblemType: Bug
DistroRelease: Ubuntu 10.10
Package: linux-image-2.6.35-22-generic 2.6.35-22.35
Regression: Yes
Reproducible: No
ProcVersionSignature: Ubuntu 2.6.35-22.35-generic 2.6.35.4
Uname: Linux 2.6.35-22-generic x86_64
NonfreeKernelModules: nvidia
AlsaVersion: Advanced Linux Sound Architecture Driver Version 1.0.23.
Architecture: amd64
AudioDevicesInUse:
USER PID ACCESS COMMAND
/dev/snd/controlC0: juliano 2781 F.... kmix
CRDA: Error: [Errno 2] No such file or directory
Card0.Amixer.info:
Card hw:0 'Intel'/'HDA Intel at 0xf0000000 irq 22'
Mixer name : 'Realtek ALC889'
Components : 'HDA:10ec0889,80860022,00100004'
Controls : 42
Simple ctrls : 24
Date: Sun Oct 24 04:25:13 2010
Frequency: I don't know.
HibernationDevice: RESUME=UUID=4f433bf6-748e-432d-b93f-de4d0e693b91
InstallationMedia: Kubuntu 10.10 "Maverick Meerkat" - Release amd64 (20101008)
ProcCmdLine: BOOT_IMAGE=/boot/vmlinuz-2.6.35-22-generic root=/dev/mapper/Nagisa1-Root ro rootdelay=5
ProcEnviron:
LANGUAGE=
PATH=(custom, user)
LANG=en_US.UTF-8
SHELL=/bin/zsh
RelatedPackageVersions: linux-firmware 1.38
RfKill:
SourcePackage: linux
UserAsoundrc:
#pcm.!default plug:hw:0
#ctl.!default hw:0
dmi.bios.date: 08/30/2010
dmi.bios.vendor: Intel Corp.
dmi.bios.version: SOX5810J.86A.5456.2010.0830.0013
dmi.board.asset.tag: Base Board Asset Tag
dmi.board.name: DX58SO
dmi.board.vendor: Intel Corporation
dmi.board.version: AAE29331-703
dmi.chassis.type: 2
dmi.modalias: dmi:bvnIntelCorp.:bvrSOX5810J.86A.5456.2010.0830.0013:bd08/30/2010:svn:pn:pvr:rvnIntelCorporation:rnDX58SO:rvrAAE29331-703:cvn:ct2:cvr:
|
Since upgrading to Maverick, I'm frequently observing instances of the timer interrupts suddenly stopping being processed (or even produced?) for a few minutes. The system becomes sluggish as a whole, all CPU cores go high on Sys% usage. This continues for 3-5 minutes, then suddenly goes back to normal, just like how it started.
It is certainly related to the timer interrupt: If I continuously 'cat /proc/interrupts' (or just run it under 'watch') during the time the system is affected, interrupt 0 (IR-IO-APIC-edge timer) stays frozen until the problem goes away. No messages appear on dmesg or in /var/log/kern.log.
The problem always starts at random, with no particular cause, but it seems more frequent when making heavy use of both sound and graphics at the same time. It is very common to happen when I start playing some game on Wine. It seems to also vanish at random after 3-5 minutes have passed, but zapping the X server seems to a way to restore the normal behaviour (it happened twice until now, I need more tests to confirm).
The system is:
Processor: Intel Core i7 930 (2.8 GHz, 4 cores × 2 threads)
Mainboard: Intel DX58SO Extreme
Memory: 6 GiB
Storage: 3 × 1 TB Samsung HardDisks on a RAID 5 array, LVM on top.
Video: nVidia GTX 460 (with proprietary drivers)
I don't know what more I can say about this issue, but feel free to ask; I'm willing to provide as much information as possible to have this fixed.
ProblemType: Bug
DistroRelease: Ubuntu 10.10
Package: linux-image-2.6.35-22-generic 2.6.35-22.35
Regression: Yes
Reproducible: No
ProcVersionSignature: Ubuntu 2.6.35-22.35-generic 2.6.35.4
Uname: Linux 2.6.35-22-generic x86_64
NonfreeKernelModules: nvidia
AlsaVersion: Advanced Linux Sound Architecture Driver Version 1.0.23.
Architecture: amd64
AudioDevicesInUse:
USER PID ACCESS COMMAND
/dev/snd/controlC0: juliano 2781 F.... kmix
CRDA: Error: [Errno 2] No such file or directory
Card0.Amixer.info:
Card hw:0 'Intel'/'HDA Intel at 0xf0000000 irq 22'
Mixer name : 'Realtek ALC889'
Components : 'HDA:10ec0889,80860022,00100004'
Controls : 42
Simple ctrls : 24
Date: Sun Oct 24 04:25:13 2010
Frequency: I don't know.
HibernationDevice: RESUME=UUID=4f433bf6-748e-432d-b93f-de4d0e693b91
InstallationMedia: Kubuntu 10.10 "Maverick Meerkat" - Release amd64 (20101008)
ProcCmdLine: BOOT_IMAGE=/boot/vmlinuz-2.6.35-22-generic root=/dev/mapper/Nagisa1-Root ro rootdelay=5
ProcEnviron:
LANGUAGE=
PATH=(custom, user)
LANG=en_US.UTF-8
SHELL=/bin/zsh
RelatedPackageVersions: linux-firmware 1.38
RfKill:
SourcePackage: linux
UserAsoundrc:
#pcm.!default plug:hw:0
#ctl.!default hw:0
dmi.bios.date: 08/30/2010
dmi.bios.vendor: Intel Corp.
dmi.bios.version: SOX5810J.86A.5456.2010.0830.0013
dmi.board.asset.tag: Base Board Asset Tag
dmi.board.name: DX58SO
dmi.board.vendor: Intel Corporation
dmi.board.version: AAE29331-703
dmi.chassis.type: 2
dmi.modalias: dmi:bvnIntelCorp.:bvrSOX5810J.86A.5456.2010.0830.0013:bd08/30/2010:svn:pn:pvr:rvnIntelCorporation:rnDX58SO:rvrAAE29331-703:cvn:ct2:cvr:
|
|
2010-10-29 21:28:41 |
Adam Ziegler |
bug |
|
|
added subscriber Adam Ziegler |
2010-11-11 03:24:23 |
dcecchin |
bug |
|
|
added subscriber Kalidarn |
2010-11-11 18:53:05 |
Juliano Ravasi |
summary |
Timer interrupt freezes, system becomes sluggish |
Intel Core i7, nVidia proprietary - Timer interrupt freezes, system becomes sluggish |
|
2010-11-17 00:18:48 |
dyna |
bug |
|
|
added subscriber dyna |
2010-11-17 17:23:59 |
dyna |
bug watch added |
|
http://bugzilla.kernel.org/show_bug.cgi?id=8300 |
|
2010-11-19 09:34:56 |
Bruno |
bug |
|
|
added subscriber Bruno |
2010-12-13 14:07:37 |
Toni Shocker |
bug |
|
|
added subscriber Toni Shocker |
2010-12-13 15:52:24 |
Juliano Ravasi |
summary |
Intel Core i7, nVidia proprietary - Timer interrupt freezes, system becomes sluggish |
Intel Core i7 - Timer interrupt freezes, high CPU usage, system becomes sluggish |
|
2011-01-23 07:32:11 |
Darryl Schultz |
bug |
|
|
added subscriber Darryl Schultz |
2011-04-07 00:49:27 |
Brad Figg |
linux (Ubuntu): status |
New |
Confirmed |
|
2011-05-24 14:41:07 |
Jeremy Foshee |
tags |
amd64 apport-bug kernel-fs maverick needs-upstream-testing regression-potential |
amd64 apport-bug kernel-fs maverick needs-upstream-testing |
|
2012-06-10 11:10:41 |
penalvch |
linux (Ubuntu): status |
Confirmed |
Incomplete |
|