High idle load on 64bit Ubuntu 12.04 with 3.2.0-24-generic kernel

[Rafał Ochmański]

Since the update to 3.2.0-24-generic kernel and despite >90% of idle CPU the load remains relatively high. On 3.2.0-17 it used to be barely above 0, now it rarely drops below 1. Powertop also reports high power usage by the CPU (~8W). The processor is 2.4GHz Intel i5-2430M and going back to 3.2.0-17-generic solves these problems.

$ top

top - 23:27:42 up 26 min, 3 users, load average: 1.66, 1.80, 1.46
Tasks: 216 total, 1 running, 214 sleeping, 0 stopped, 1 zombie
Cpu(s): 0.2%us, 0.3%sy, 0.0%ni, 99.5%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Mem: 8082692k total, 2235412k used, 5847280k free, 159640k buffers
Swap: 8294396k total, 0k used, 8294396k free, 984832k cached

  PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
 3764 rmo 20 0 1075m 260m 38m S 1 3.3 1:39.84 firefox
 4514 rmo 20 0 17452 1512 1072 R 1 0.0 0:00.12 top
 1772 root 20 0 236m 6628 5236 S 0 0.1 0:00.47 NetworkManager
 2013 root 20 0 154m 23m 8008 S 0 0.3 1:09.09 Xorg
 3294 rmo 20 0 1190m 74m 30m S 0 0.9 1:28.46 compiz
 3501 rmo 20 0 575m 20m 11m S 0 0.3 0:10.38 gnome-terminal
    1 root 20 0 24544 2516 1380 S 0 0.0 0:01.22 init
    2 root 20 0 0 0 0 S 0 0.0 0:00.00 kthreadd
    3 root 20 0 0 0 0 S 0 0.0 0:00.20 ksoftirqd/0
    6 root RT 0 0 0 0 S 0 0.0 0:00.00 migration/0
    8 root RT 0 0 0 0 S 0 0.0 0:00.00 migration/1
   10 root 20 0 0 0 0 S 0 0.0 0:00.18 ksoftirqd/1
   13 root RT 0 0 0 0 S 0 0.0 0:00.00 migration/2
   14 root 20 0 0 0 0 S 0 0.0 0:00.60 kworker/2:0
   15 root 20 0 0 0 0 S 0 0.0 0:00.09 ksoftirqd/2
   17 root RT 0 0 0 0 S 0 0.0 0:00.00 migration/3
   19 root 20 0 0 0 0 S 0 0.0 0:00.06 ksoftirqd/3
   21 root 0 -20 0 0 0 S 0 0.0 0:00.00 cpuset
   22 root 0 -20 0 0 0 S 0 0.0 0:00.00 khelper
   23 root 20 0 0 0 0 S 0 0.0 0:00.00 kdevtmpfs
   24 root 0 -20 0 0 0 S 0 0.0 0:00.00 netns
   26 root 20 0 0 0 0 S 0 0.0 0:00.00 sync_supers
   27 root 20 0 0 0 0 S 0 0.0 0:00.00 bdi-default
   28 root 0 -20 0 0 0 S 0 0.0 0:00.00 kintegrityd
   29 root 0 -20 0 0 0 S 0 0.0 0:00.00 kblockd
   30 root 0 -20 0 0 0 S 0 0.0 0:00.00 ata_sff
   31 root 20 0 0 0 0 S 0 0.0 0:00.01 khubd
   32 root 0 -20 0 0 0 S 0 0.0 0:00.00 md
   34 root 20 0 0 0 0 S 0 0.0 0:00.00 khungtaskd
   35 root 20 0 0 0 0 S 0 0.0 0:00.00 kswapd0
   36 root 25 5 0 0 0 S 0 0.0 0:00.00 ksmd
   37 root 39 19 0 0 0 S 0 0.0 0:00.00 khugepaged

$ uname -a
Linux flax 3.2.0-24-generic #37-Ubuntu SMP Wed Apr 25 08:43:22 UTC 2012 x86_64 x86_64 x86_64 GNU/Linux

I have compared CPU power usage (as reported by powertop) with the same programs running and it seems that on the newer kernel it's 2-2.5W higher whether idle, when running a browser or playing a movie.

What other information should I include?
---
AlsaVersion: Advanced Linux Sound Architecture Driver Version 1.0.24.
ApportVersion: 2.0.1-0ubuntu7
Architecture: amd64
ArecordDevices:
 **** List of CAPTURE Hardware Devices ****
 card 0: PCH [HDA Intel PCH], device 0: CONEXANT Analog [CONEXANT Analog]
   Subdevices: 1/1
   Subdevice #0: subdevice #0
AudioDevicesInUse:
 USER PID ACCESS COMMAND
 /dev/snd/controlC0: rmo 3195 F.... pulseaudio
Card0.Amixer.info:
 Card hw:0 'PCH'/'HDA Intel PCH at 0xf7f00000 irq 51'
   Mixer name : 'Intel CougarPoint HDMI'
   Components : 'HDA:14f1506e,10280510,00100002 HDA:80862805,80860101,00100000'
   Controls : 15
   Simple ctrls : 7
DistroRelease: Ubuntu 12.04
HibernationDevice: RESUME=UUID=3f6a429d-1aaa-4de1-b7c2-9e38a342e5f3
MachineType: Dell Inc. Vostro V131
Package: linux (not installed)
ProcFB: 0 inteldrmfb
ProcKernelCmdLine: BOOT_IMAGE=/vmlinuz-3.2.0-24-generic root=/dev/mapper/flax-root ro
ProcVersionSignature: Ubuntu 3.2.0-24.37-generic 3.2.14
RelatedPackageVersions:
 linux-restricted-modules-3.2.0-24-generic N/A
 linux-backports-modules-3.2.0-24-generic N/A
 linux-firmware 1.79
SourcePackage: linux
StagingDrivers: mei
Tags: precise staging precise staging
Uname: Linux 3.2.0-24-generic x86_64
UpgradeStatus: Upgraded to precise on 2012-03-04 (65 days ago)
UserGroups: adm admin cdrom dialout libvirtd lpadmin plugdev sambashare
dmi.bios.date: 10/24/2011
dmi.bios.vendor: Dell Inc.
dmi.bios.version: A03
dmi.board.name: 0X3GJK
dmi.board.vendor: Dell Inc.
dmi.board.version: A03
dmi.chassis.type: 8
dmi.chassis.vendor: Dell Inc.
dmi.chassis.version: Not Specified
dmi.modalias: dmi:bvnDellInc.:bvrA03:bd10/24/2011:svnDellInc.:pnVostroV131:pvrNotSpecified:rvnDellInc.:rn0X3GJK:rvrA03:cvnDellInc.:ct8:cvrNotSpecified:
dmi.product.name: Vostro V131
dmi.product.version: Not Specified
dmi.sys.vendor: Dell Inc.

[Ubuntu Foundations Team Bug Bot (crichton)]

Thank you for taking the time to report this bug and helping to make Ubuntu better. It seems that your bug report is not filed about a specific source package though, rather it is just filed against Ubuntu in general. It is important that bug reports be filed about source packages so that people interested in the package can find the bugs about it. You can find some hints about determining what package your bug might be about at https://wiki.ubuntu.com/Bugs/FindRightPackage. You might also ask for help in the #ubuntu-bugs irc channel on Freenode.

To change the source package that this bug is filed about visit https://bugs.launchpad.net/ubuntu/+bug/995284/+editstatus and add the package name in the text box next to the word Package.

[This is an automated message. I apologize if it reached you inappropriately; please just reply to this message indicating so.]

[Brad Figg (brad-figg)]

This bug is missing log files that will aid in diagnosing the problem. From a terminal window please run:

apport-collect 995284

and then change the status of the bug to 'Confirmed'.

If, due to the nature of the issue you have encountered, you are unable to run this command, please add a comment stating that fact and change the bug status to 'Confirmed'.

This change has been made by an automated script, maintained by the Ubuntu Kernel Team.

[arnuschky (abrutschy)]

I can confirm this - my system constantly shows a high load (> 1) when being idle. It seems to be disk access that is slow. I am running dm-crypt + LUKS + lvm2 + raid (hardware RAID 5 on a 3ware SATA controller with 5400umin disks). You can imagine that the system never was the fastest, but as it's only a storage server, I don't care so much. (raid/disks are fine)

Sometimes, the system even slows down to a load > 10. When this happens, boot takes ~10 minutes. This problem seems to occur randomly, or at least I had problems reproducing it each boot. I am running apport-collect 995284 now to confirm.

[arnuschky (abrutschy)]

Reverting back to 3.0.0-16 solved this problem, BTW.

[arnuschky (abrutschy)]

AlsaDevices:
 total 0
 crw-rw---T 1 root audio 116, 1 May 7 19:38 seq
 crw-rw---T 1 root audio 116, 33 May 7 19:38 timer
AplayDevices: Error: [Errno 2] No such file or directory
ApportVersion: 2.0.1-0ubuntu7
Architecture: amd64
ArecordDevices: Error: [Errno 2] No such file or directory
AudioDevicesInUse: Error: command ['fuser', '-v', '/dev/snd/seq', '/dev/snd/timer'] failed with exit code 1:
CRDA: Error: command ['iw', 'reg', 'get'] failed with exit code 1: nl80211 not found.
DistroRelease: Ubuntu 12.04
HibernationDevice: RESUME=UUID=c974b118-38c3-41af-bf67-a79f19e25916
InstallationMedia: Ubuntu-Server 11.04 "Natty Narwhal" - Release amd64 (20110426)
IwConfig:
 lo no wireless extensions.

 eth1 no wireless extensions.

 eth0 no wireless extensions.
MachineType: Dell Computer Corporation PowerEdge 2800
Package: linux (not installed)
PciMultimedia:

ProcFB: 0 radeondrmfb
ProcKernelCmdLine: BOOT_IMAGE=/vmlinuz-3.2.0-24-generic root=/dev/mapper/hostname-root ro all_generic_ide=1 quiet
ProcVersionSignature: Ubuntu 3.2.0-24.37-generic 3.2.14
RelatedPackageVersions:
 linux-restricted-modules-3.2.0-24-generic N/A
 linux-backports-modules-3.2.0-24-generic N/A
 linux-firmware 1.79
RfKill: Error: [Errno 2] No such file or directory
Tags: precise
Uname: Linux 3.2.0-24-generic x86_64
UpgradeStatus: Upgraded to precise on 2012-05-05 (4 days ago)
UserGroups:

WifiSyslog:

dmi.bios.date: 04/25/2008
dmi.bios.vendor: Dell Computer Corporation
dmi.bios.version: A07
dmi.board.name: 0T7916
dmi.board.vendor: Dell Computer Corporation
dmi.board.version: A02
dmi.chassis.type: 17
dmi.chassis.vendor: Dell Computer Corporation
dmi.modalias: dmi:bvnDellComputerCorporation:bvrA07:bd04/25/2008:svnDellComputerCorporation:pnPowerEdge2800:pvr:rvnDellComputerCorporation:rn0T7916:rvrA02:cvnDellComputerCorporation:ct17:cvr:
dmi.product.name: PowerEdge 2800
dmi.sys.vendor: Dell Computer Corporation

[arnuschky (abrutschy)]

apport information

[arnuschky (abrutschy)]

apport information

[arnuschky (abrutschy)]

apport information

[arnuschky (abrutschy)]

apport information

[arnuschky (abrutschy)]

apport information

[arnuschky (abrutschy)]

apport information

[arnuschky (abrutschy)]

apport information

[arnuschky (abrutschy)]

apport information

[arnuschky (abrutschy)]

apport information

[arnuschky (abrutschy)]

apport information

[arnuschky (abrutschy)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

apport information

[Rafał Ochmański (rmopl)]

I too have an ecrypted LVM set up.

[Stefano Dall'Agata (essedia1960)]

Aggiungo il mio, Compaq cq60 103el Ubuntu Precise a 32 bit.

stefano@stefano-laptop:~$ top

top - 12:53:12 up 11 min, 1 user, load average: 1.63, 1.65, 1.00
Tasks: 174 total, 1 running, 172 sleeping, 0 stopped, 1 zombie
Cpu(s): 10.3%us, 9.9%sy, 0.0%ni, 79.1%id, 0.7%wa, 0.0%hi, 0.0%si, 0.0%st
Mem: 3095536k total, 1306020k used, 1789516k free, 140544k buffers
Swap: 3148704k total, 0k used, 3148704k free, 550276k cached

  PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
 2477 stefano 20 0 395m 103m 33m S 14 3.4 1:27.99 compiz
 2891 stefano 20 0 477m 86m 41m S 7 2.9 0:32.85 rhythmbox
 1295 root 20 0 73524 54m 11m S 5 1.8 1:03.80 Xorg
 3001 stefano 20 0 572m 184m 40m S 5 6.1 2:00.08 firefox
 2622 stefano 20 0 147m 22m 11m S 3 0.7 0:16.38 unity-panel-ser
 3225 stefano 20 0 149m 15m 11m S 2 0.5 0:00.90 gnome-terminal
 2504 stefano 20 0 137m 11m 8712 S 2 0.4 0:08.98 indicator-multi
 2435 stefano 9 -11 162m 6268 4452 S 2 0.2 0:07.58 pulseaudio
   25 root 20 0 0 0 0 S 1 0.0 0:01.24 kworker/1:1
  354 root 20 0 0 0 0 S 1 0.0 0:01.38 kworker/0:2
 2381 stefano 20 0 7336 3276 628 S 1 0.1 0:06.57 dbus-daemon
 2654 stefano 20 0 45140 4360 3552 S 1 0.1 0:04.55 indicator-appli
 2635 stefano 20 0 42984 10m 8760 S 0 0.4 0:00.49 gtk-window-deco
 3285 stefano 20 0 2836 1176 880 R 0 0.0 0:00.11 top
    1 root 20 0 3648 2104 1352 S 0 0.1 0:00.74 init
    2 root 20 0 0 0 0 S 0 0.0 0:00.00 kthreadd
    3 root 20 0 0 0 0 S 0 0.0 0:00.40 ksoftirqd/0

[Philippe Serbruyns (phiser678)]

Hi
I can confirm this bug. It's keeping me busy for a while, so I investigated a lot of ubuntu kernels by recompiling them and try them out.
It seems it came already from a revision from Ubuntu 3.2.0-21.34-generic (backported from kernel v3.2.13)
to Ubuntu 3.2.0-22.35-generic (backported from kernel v3.2.14). So from 3.2.0-22.35 it was introduced.
I checked with git and there are 306 files changed, 131914 insertions(+), 129758 deletions(-), so alot has to be traced.
I see some changes in the following files, which could cause the high idle load (my wild guess):
 arch/x86/kernel/apic/io_apic.c | 40 +-
 arch/x86/kernel/entry_32.S | 17 +-
 arch/x86/kernel/tls.c | 4 +-
 arch/x86/kernel/tsc.c | 10 +
 arch/x86/kernel/vm86_32.c | 2 +
 arch/x86/net/bpf_jit_comp.c | 14 +-
and
 kernel/futex.c | 19 +-
 kernel/irq/chip.c | 3 +-
 kernel/irq/manage.c | 2 +-
 kernel/module.c | 3 +-
 kernel/power/hibernate.c | 7 +-
 kernel/sched.c | 55 +-
kernel/time/ntp.c | 2 +-

or
 mm/bootmem.c | 5 +-
 mm/memcontrol.c | 4 +
 mm/memory.c | 16 +-
 mm/mempolicy.c | 2 +-
 mm/mincore.c | 2 +-
 mm/pagewalk.c | 2 +-
 mm/slub.c | 3 +-
 mm/sparse.c | 30 +-
 mm/swapfile.c | 4 +-

I will check the linux kernels if they have it as well

[arnuschky (abrutschy)]

It seems to be related to disk access, and therefore systems with an encrypted root file system might be more affected than others. Stephano, are you also using dm-crypt on an lvm2?

Anyways, thanks for all the effort Phillipe - let us know if we can help with testing or providing more information!

[Jozef Losonsky (jozef-losonsky)]

Hi I just red this - it looks like issue we're facing - nice reading anyway http://www.smythies.com/~doug/network/load_average/index.html

[arnuschky (abrutschy)]

So somebody introduced a patch because the computed load averages were too low - and now they are way too high. Nice. :)

But this would mean that it's an error merely related to display/reporting, right? In my case, I am not 100% sure if the system is actually slower ("loaded"), but it sure feels like it.

I will try to reproduce the condition in which system boot took ~10 minutes and load consistently higher than 10.

[Philippe Serbruyns (phiser678)]

I can confirm that disabling "tickless system" in "Processor type and features" (CONFIG_NO_HZ is not set) solves the mistery load problem when recompiling the current Ubuntu kernel (3.2.0-24.38-generic). Thanks Jozef for pointing me this out, and it seems to keep a lot of people busy about this already for some time.

[Joseph Salisbury (jsalisbury)]

Would it be possible for you to test the latest upstream kernel? Refer to https://wiki.ubuntu.com/KernelMainlineBuilds . Please test the latest v3.4kernel[1] (Not a kernel in the daily directory). Once you've tested the upstream kernel, please remove the 'needs-upstream-testing' tag(Only that one tag, please leave the other tags). This can be done by clicking on the yellow pencil icon next to the tag located at the bottom of the bug description and deleting the 'needs-upstream-testing' text.

If this bug is fixed in the mainline kernel, please add the following tag 'kernel-fixed-upstream'.

If the mainline kernel does not fix this bug, please add the tag: 'kernel-bug-exists-upstream'.

If you are unable to test the mainline kernel, for example it will not boot, please add the tag: 'kernel-unable-to-test-upstream'.
Once testing of the upstream kernel is complete, please mark this bug as "Confirmed".

Thanks in advance.

http://kernel.ubuntu.com/~kernel-ppa/mainline/v3.4-rc7-precise/

[Joseph Salisbury (jsalisbury)]

This could be a dup of bug 985661

[Doug Smythies (dsmythies)]

It is not clear to me if this is a dup of bug 985661 or not. Some discussion goes beyond just reported load averages.
As for the reported load averages part someone above said: "So somebody introduced a patch because the computed load averages were too low - and now they are way too high."
Actually, the reported load averages, under many conditions were massively too low, actually 0.0. Now, apparently, under "idle" conditions on desktops reported load averages can be somewhat too high. Compounding the issue is that people are comparing to kernels without the patch, which would report load averages that are too low.
As someone noted above proper comparitvie results can be obatined by compiling the kernel with CONFIG_NO_HZ=no.
Two people above listed output from the "top" command which can also be used to estimate the real load average. For the first one (the OP) I got 0.17 and for the second one (post # 40) I got 0.53 (I realize it is rediculous to state them to two decimal places).
Over the entire operational space of all loads and all idle enter/exit frequencies and all number of processes, I still think the reported load averages are better than they were. It is not clear to me that there is a better solution within the current context of how load averages are calculated with tickless kernels.

[Doug Smythies (dsmythies)]

For example, the attached graph: Without the recent load averages calculation changes, every data point in the graph would be at a reported load average of 0.0.
The ilde enter/exit frequency for the graph was 180 hertz, so as to be divisible always by the number of processes, yet remain not near any known alias frequency or to go below 25 hertz, where things begin to change.

[Jonas Jelten (jonas-jelten)]

Also tracked at ArchLinux:

https://bugs.archlinux.org/task/29850

[arnuschky (abrutschy)]

My system definitely has a problem with load (and not only with a display/calculation of the load value that is wrong).

Every task I do on the system takes ages. For example, "apt-get upgrade" for linux-* 3.2.0-24.38 took ~35 minutes. In general, disk access seems to be very slow, and if there are multiple processes running (backup, mlocate.updatedb, or other simple but disk IO bound tasks) the system load is easily around 8-10.

Like Rafael, I am using an encrypted LVM setup. Maybe the calculation of the load values is not related after all?

Here's my top (someone was asking for it, no?)

top - 09:17:33 up 14 days, 13:40, 1 user, load average: 1.83, 1.93, 2.91
Tasks: 137 total, 1 running, 136 sleeping, 0 stopped, 0 zombie
Cpu(s): 1.8%us, 0.8%sy, 0.0%ni, 73.0%id, 24.3%wa, 0.0%hi, 0.0%si, 0.0%st
Mem: 2050676k total, 1814212k used, 236464k free, 318688k buffers
Swap: 1998844k total, 23252k used, 1975592k free, 1102336k cached

  PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
 6226 root 20 0 17328 1264 908 R 2 0.1 0:00.01 top
    1 root 20 0 24320 1516 680 S 0 0.1 0:01.86 init
    2 root 20 0 0 0 0 S 0 0.0 0:00.26 kthreadd
    3 root 20 0 0 0 0 S 0 0.0 5:37.66 ksoftirqd/0
    5 root 20 0 0 0 0 S 0 0.0 0:00.62 kworker/u:0
    6 root RT 0 0 0 0 S 0 0.0 0:00.00 migration/0
    7 root RT 0 0 0 0 S 0 0.0 0:04.43 watchdog/0
    8 root RT 0 0 0 0 S 0 0.0 0:00.00 migration/1
   10 root 20 0 0 0 0 S 0 0.0 1:46.03 ksoftirqd/1
   12 root RT 0 0 0 0 S 0 0.0 0:03.69 watchdog/1
   13 root 0 -20 0 0 0 S 0 0.0 0:00.00 cpuset
   14 root 0 -20 0 0 0 S 0 0.0 0:00.00 khelper
   15 root 20 0 0 0 0 S 0 0.0 0:00.02 kdevtmpfs
   16 root 0 -20 0 0 0 S 0 0.0 0:00.00 netns
   17 root 20 0 0 0 0 S 0 0.0 0:00.00 kworker/u:1
   18 root 20 0 0 0 0 S 0 0.0 0:04.53 sync_supers
   19 root 20 0 0 0 0 S 0 0.0 0:00.08 bdi-default
   20 root 0 -20 0 0 0 S 0 0.0 0:00.00 kintegrityd
   21 root 0 -20 0 0 0 S 0 0.0 0:00.00 kblockd
   22 root 0 -20 0 0 0 S 0 0.0 0:00.00 ata_sff
   23 root 20 0 0 0 0 S 0 0.0 0:00.00 khubd
   24 root 0 -20 0 0 0 S 0 0.0 0:00.00 md
   26 root 20 0 0 0 0 S 0 0.0 0:00.88 khungtaskd
   27 root 20 0 0 0 0 S 0 0.0 2:07.20 kswapd0
   28 root 25 5 0 0 0 S 0 0.0 0:00.00 ksmd
   29 root 39 19 0 0 0 S 0 0.0 0:00.00 khugepaged
   30 root 20 0 0 0 0 S 0 0.0 0:00.01 fsnotify_mark
   31 root 20 0 0 0 0 S 0 0.0 0:00.00 ecryptfs-kthrea
   32 root 0 -20 0 0 0 S 0 0.0 0:00.00 crypto
   40 root 0 -20 0 0 0 S 0 0.0 0:00.00 kthrotld
   41 root 20 0 0 0 ...

[shnifti (b-rous)]

Issue fixed using: Linux 3.2.0-26-generic

Thisk my whole püroductive environment is unuseable!!!

[shnifti (b-rous)]

Issue STILL NOT FIXED using Linux 3.2.0-26-generic.

This really sucks, my whole productive environment is unuseable!!!

[arnuschky (abrutschy)]

I can confirm this. System is unusable with 3.2.0-xx, I am using Oneiric's 3.0.0-16 for production.

[Tim Kuijsten (kuijsten)]

I'm not sure whether to comment here or on #985661 but the load on my netbook and pc is both often above 1 after upgrading to 12.04. It looks like it got a little better with recent kernel updates (to 0.6 - 1.0 on idle, still way too high ofcours), but the system still feels obviously less responsive than it used to be pre-12.04.

[penalvch (penalvch)]

Rafał Ochmański, this bug was reported a while ago and there hasn't been any activity in it recently. We were wondering if this is still an issue? If so, could you please test the latest upstream kernel available following https://wiki.ubuntu.com/KernelMainlineBuilds ? It will allow additional upstream developers to examine the issue. Please do not test the kernel in the daily folder, but the one all the way at the bottom. Once you've tested the upstream kernel, please comment on which kernel version specifically you tested and remove the tag:
needs-upstream-testing

This can be done by clicking on the yellow pencil icon next to the tag located at the bottom of the bug description and deleting the text:
needs-upstream-testing

If this bug is fixed in the mainline kernel, please add the following tags:
kernel-fixed-upstream
kernel-fixed-upstream-VERSION-NUMBER

where VERSION-NUMBER is the version number of the kernel you tested.

If the mainline kernel does not fix this bug, please add the following tags:
kernel-bug-exists-upstream
kernel-bug-exists-upstream-VERSION-NUMBER

where VERSION-NUMBER is the version number of the kernel you tested.

If you are unable to test the mainline kernel, please comment as to why specifically you were unable to test it and add the following tags:
kernel-unable-to-test-upstream
kernel-unable-to-test-upstream-VERSION-NUMBER

where VERSION-NUMBER is the version number of the kernel you tested.

Please let us know your results. Thank you for your understanding.

Helpful Bug Reporting Links:
https://help.ubuntu.com/community/ReportingBugs#Bug_Reporting_Etiquette
https://help.ubuntu.com/community/ReportingBugs#A3._Make_sure_the_bug_hasn.27t_already_been_reported
https://help.ubuntu.com/community/ReportingBugs#Adding_Apport_Debug_Information_to_an_Existing_Launchpad_Bug
https://help.ubuntu.com/community/ReportingBugs#Adding_Additional_Attachments_to_an_Existing_Launchpad_Bug

[Rafał Ochmański (rmopl)]

I haven't tested with the mainline kernel (yet, will do later) but it's still an issue with 3.2.0-27-generic. Right now CPU is ~395% idling (two cores with hyper-threading), disk reads and writes are next to zero but the load is 1.7.

It may be because of the heat or some change in configuration and therefore unrelated but performance of the system in general seems to have taken a dive since 3.2.0-17.

[Nicolas Krzywinski (nsk7even)]

Ok, guys I am unsure whether I am at correct place here - so please help me figure this out.

For me the increased cpu load since upgrade to 12.04 varies from bootup to bootup (I don't know why and what I do differently). I don't feel the system being slower though.

I identified the migration processes to eat up the cpu (see below). The cpu load ranges from nearly unvisible to approx. a quarter when looking at the system monitor panel applet (gnome classic mode). It may be that it decreases over time ... but all this stuff is only subjective observations as I don't know how to measure properly.

Please have a look at my ps aux output as this shows the relation of cpu time the migration processes use, compared to e. g. banshee I am using for this whole uptime mainly (besides opera): http://pastebin.com/7PXM4WZX

nsk@sesta09:~$ uptime
 23:22:50 up 2:13, 1 user, load average: 1.48, 1.39, 1.44

Within this booted session I did nothing actively than hearing music with banshee and browsing/emailing with opera, so everyone can see that the migration cpu time is way too high. But I can not tell if those are real cpu cycles or if this is a reporting problem.

nsk@sesta09:~$ uname -a
Linux sesta09 3.2.0-27-generic #43-Ubuntu SMP Fri Jul 6 14:25:57 UTC 2012 x86_64 x86_64 x86_64 GNU/Linux

Please ask me for more if something else will help!

[penalvch (penalvch)]

Nicolas Krzywinski, could you please file a new report by executing the following in a terminal:
ubuntu-bug linux

For more on this, please see the Ubuntu Bug Control and Ubuntu Bug Squad article:
https://wiki.ubuntu.com/Bugs/BestPractices#X.2BAC8-Reporting.Focus_on_One_Issue

and Ubuntu Community article:
https://help.ubuntu.com/community/ReportingBugs#Bug_Reporting_Etiquette

When opening up the new report, please feel free to subscribe me to it. Thank you for your understanding.

Helpful Bug Reporting Links:
https://help.ubuntu.com/community/ReportingBugs#A3._Make_sure_the_bug_hasn.27t_already_been_reported
https://help.ubuntu.com/community/ReportingBugs#Adding_Apport_Debug_Information_to_an_Existing_Launchpad_Bug
https://help.ubuntu.com/community/ReportingBugs#Adding_Additional_Attachments_to_an_Existing_Launchpad_Bug

[Doug Smythies (dsmythies)]

Issues with reported load averages have been fixed in the upstream kernel. So far, they have been backported to the as yet unreleased ubuntu kernel 3.2.0-29.45 or .46.
As for any real high loads, I do not know anything.
See also bug #1029431 (search for "load-ave") and https://launchpad.net/ubuntu/precise/+source/linux/3.2.0-29.46 (search for "load-ave")

[Rafael García (rgo)]

I updated to kernel 3.4.6 (from quantal repository) and seems to fix this issue, top shows me high idle and low load.

$ uname -a
Kernel Linux envy 3.4.6-030406-generic #201207191609 SMP Thu Jul 19 20:11:13 UTC 2012 x86_64 x86_64 x86_64 GNU/Linux

[Dama Lema (damalema)]

I have had this issue since upgrade to 12.04.
Installed and tried a few kernels:
3.4.0-030400_3.4.0-030400.201205210521Precise Pangolin) - High load
3.1.5-030105_3.1.5-030105.201112091259(Precise Pangolin) - High load
3.0.0-0300_3.0.0-0300.201107220917(Quantal Quetzal) - Seems to work fine.

[Launchpad Janitor (janitor)]

[Expired for linux (Ubuntu) because there has been no activity for 60 days.]

[Sesshomurai (darren-ontrenet)]

Hi,
  When will this be available to 12.04 64bit desktop users from apt update? Right now 12.04 desktop 64bit is totally unusable due to the high load and constant churning of my CPU fan. Can't do a thing with it....

[penalvch (penalvch)]

Sesshomurai, if you have a bug in Ubuntu, could you please file a new report by executing the following in a terminal:
ubuntu-bug linux

For more on this, please see the Ubuntu Kernel team article:
https://wiki.ubuntu.com/KernelTeam/KernelTeamBugPolicies#Filing_Kernel_Bug_reports

the Ubuntu Bug Control team and Ubuntu Bug Squad team article:
https://wiki.ubuntu.com/Bugs/BestPractices#X.2BAC8-Reporting.Focus_on_One_Issue

and Ubuntu Community article:
https://help.ubuntu.com/community/ReportingBugs#Bug_reporting_etiquette

When opening up the new report, please feel free to subscribe me to it.

Please note, not filing a new report may delay your problem being addressed as quickly as possible.

Thank you for your understanding.

[Derek Simkowiak (derek-x)]

Still there in ubuntu 14.04. We have an idle system with (basically) nothing going on, and it hovers at 1.0:

ubuntu@build-globallogic:~$ uptime
 11:09:18 up 6 days, 18:21, 1 user, load average: 1.00, 1.01, 1.05
ubuntu@build-globallogic:~$ uname -a
Linux build-globallogic 3.13.0-29-generic #53-Ubuntu SMP Wed Jun 4 21:00:20 UTC 2014 x86_64 x86_64 x86_64 GNU/Linux

[penalvch (penalvch)]

Derek Simkowiak, thank you for your comment. So your hardware and problem may be tracked, could you please file a new report with Ubuntu by executing the following in a terminal while booted into the default Ubuntu kernel (not a mainline one) via:
ubuntu-bug linux

For more on this, please read the official Ubuntu documentation:
Ubuntu Bug Control and Ubuntu Bug Squad: https://wiki.ubuntu.com/Bugs/BestPractices#X.2BAC8-Reporting.Focus_on_One_Issue
Ubuntu Kernel Team: https://wiki.ubuntu.com/KernelTeam/KernelTeamBugPolicies#Filing_Kernel_Bug_reports
Ubuntu Community: https://help.ubuntu.com/community/ReportingBugs#Bug_reporting_etiquette

When opening up the new report, please feel free to subscribe me to it.

Thank you for your understanding.

Helpful bug reporting tips:
https://wiki.ubuntu.com/ReportingBugs

[Launchpad Janitor (janitor)]

[Expired for linux (Ubuntu) because there has been no activity for 60 days.]