You are not logged in.
- Topics: Active | Unanswered
#1 2012-05-10 16:21:22
- greg5
- Member
- From: Columbus OH
- Registered: 2011-09-28
- Posts: 19
Troubleshooting a high load average on idle.
uptime:
12:12:18 up 1:10, 1 user, load average: 1.38, 1.10, 1.07That seems unusually high to me, I seem to think it is normally around .05 or something near there on idle.
Possibly some useful info:
top:
1364 greg 20 0 646m 130m 39m S 7.3 3.3 15:39.15 chrome
810 root 19 -1 145m 51m 28m S 4.6 1.3 7:38.17 X
1616 greg 20 0 504m 65m 25m S 1.0 1.7 2:48.65 chrome
833 greg 20 0 123m 2356 1744 S 0.7 0.1 0:33.43 synergys
1536 greg 20 0 952m 132m 20m S 0.7 3.3 0:42.03 chrome
844 greg 20 0 20496 2008 1188 S 0.3 0.0 0:04.98 tmux
2731 root 20 0 0 0 0 S 0.3 0.0 0:01.65 kworker/1:0
3688 greg 20 0 11464 1352 940 R 0.3 0.0 0:00.19 top
1 root 20 0 4188 664 564 S 0.0 0.0 0:00.36 init
2 root 20 0 0 0 0 S 0.0 0.0 0:00.00 kthreadd
3 root 20 0 0 0 0 S 0.0 0.0 0:02.84 ksoftirqd/0
6 root rt 0 0 0 0 S 0.0 0.0 0:00.00 migration/0
7 root rt 0 0 0 0 S 0.0 0.0 0:00.03 watchdog/0
8 root rt 0 0 0 0 S 0.0 0.0 0:00.00 migration/1
10 root 20 0 0 0 0 S 0.0 0.0 0:00.86 ksoftirqd/1
12 root rt 0 0 0 0 S 0.0 0.0 0:00.03 watchdog/1
13 root rt 0 0 0 0 S 0.0 0.0 0:00.00 migration/2
15 root 20 0 0 0 0 S 0.0 0.0 0:00.92 ksoftirqd/2
16 root rt 0 0 0 0 S 0.0 0.0 0:00.03 watchdog/2
17 root 0 -20 0 0 0 S 0.0 0.0 0:00.00 cpuset
18 root 0 -20 0 0 0 S 0.0 0.0 0:00.00 khelper
19 root 20 0 0 0 0 S 0.0 0.0 0:00.00 kdevtmpfs
20 root 0 -20 0 0 0 S 0.0 0.0 0:00.00 netns
21 root 20 0 0 0 0 S 0.0 0.0 0:00.02 sync_supers
22 root 20 0 0 0 0 S 0.0 0.0 0:00.00 bdi-default free -m:
total used free shared buffers cached
Mem: 3957 1798 2158 0 50 420
-/+ buffers/cache: 1327 2629
Swap: 3813 0 3813iostat:
Linux 3.3.5-1-ARCH (red5) 05/10/12 _x86_64_ (3 CPU)
avg-cpu: %user %nice %system %iowait %steal %idle
8.71 0.35 1.85 0.03 0.00 89.06
Device: tps kB_read/s kB_wrtn/s kB_read kB_wrtn
sdb 0.25 1.03 0.00 7808 24
sda 7.25 57.41 52.53 433555 396645Last edited by greg5 (2012-05-10 17:10:27)
Offline
#2 2012-05-10 18:18:40
- vehk
- Member
- Registered: 2012-03-18
- Posts: 7
Re: Troubleshooting a high load average on idle.
I have also been getting high load averages recently.
Since I upgraded the kernel yesterday (3.3.5-1), I tried downgrading to 3.3.4-2 which fixed the issue for me.
Even when showing a high load when idling, my system does not seem to be less responsive.
Could this be an error in the load average calculation?
Last edited by vehk (2012-05-10 18:21:08)
Offline
#3 2012-05-10 21:28:14
- Kaso_Da_Zmok
- Member
- Registered: 2007-11-01
- Posts: 19
Re: Troubleshooting a high load average on idle.
i have also noticed this since kernel 3.3.4 and 3.3.5 on three different systems the load average on idle is 0.6 - 0.8 for no apparent reason. downgrading to 3.3.3 fixes. wth
top - 22:31:08 up 3:37, 5 users, load average: 0.72, 0.95, 1.28
Tasks: 153 total, 1 running, 152 sleeping, 0 stopped, 0 zombie
%Cpu0 : 0.3 us, 0.3 sy, 0.0 ni, 99.3 id, 0.0 wa, 0.0 hi, 0.0 si, 0.0 st
%Cpu1 : 0.3 us, 0.0 sy, 0.0 ni, 99.7 id, 0.0 wa, 0.0 hi, 0.0 si, 0.0 st
%Cpu2 : 7.3 us, 2.2 sy, 0.0 ni, 90.1 id, 0.3 wa, 0.0 hi, 0.0 si, 0.0 st
%Cpu3 : 0.7 us, 0.0 sy, 0.0 ni, 99.3 id, 0.0 wa, 0.0 hi, 0.0 si, 0.0 st
%Cpu4 : 0.3 us, 1.0 sy, 0.0 ni, 98.7 id, 0.0 wa, 0.0 hi, 0.0 si, 0.0 st
%Cpu5 : 0.3 us, 0.3 sy, 0.0 ni, 99.3 id, 0.0 wa, 0.0 hi, 0.0 si, 0.0 st
Kb Mem: 8169368 total, 7342008 used, 827360 free, 432208 buffers
Kb Swap: 2097148 total, 7360 used, 2089788 free, 6014616 cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
3194 root 20 0 219m 64m 7336 S 6.3 0.8 24:37.89 Xorg
9941 risko 20 0 1328m 365m 36m S 0.7 4.6 20:25.78 firefox
21281 risko 20 0 72472 7504 2892 S 0.7 0.1 0:00.39 xterm
3146 root 20 0 139m 1980 1320 S 0.3 0.0 0:02.41 automount
3404 transmis 20 0 162m 3244 2172 S 0.3 0.0 0:03.51 transmission-da
8953 root 20 0 0 0 0 S 0.3 0.0 0:03.26 kworker/1:0
21109 root 20 0 0 0 0 S 0.3 0.0 0:00.86 kworker/2:0
21181 risko 20 0 72472 7480 2864 S 0.3 0.1 0:00.72 xterm
21205 risko 20 0 21516 1676 1136 S 0.3 0.0 0:01.18 top
21288 risko 20 0 21660 1892 1140 R 0.3 0.0 0:00.70 top Last edited by Kaso_Da_Zmok (2012-05-10 21:31:33)
Offline
#4 2012-05-10 23:07:45
- ahammel
- Member
- Registered: 2012-05-01
- Posts: 23
Re: Troubleshooting a high load average on idle.
Highly unscientific test ahoy! I've got htop up and running on two different machines: one with my Arch install running the 3.3.5 kernel, and the other with a Fedora build running 3.3.4. Both have Firefox 12.0 up in one workspace and a konsole running htop through tmux in the other. The Fedora build (3.3.4) is showing load averages around 0, while the Arch box (3.3.5) reports a one-minute load average of between 0.5 and 0.6 if I don't touch anything. The reported cpu usage is similar on both machines (~1%/0/0/0). Disclaimer: the hardware is not remotely similar. Also the Arch build is running dwm while the Fedora is running xmonad, but xmonad uses more cpu than dwm, so I doubt that's the problem.
I would guess that the way load averages are calculated has changed for the 3.3.5 kernel. Couldn't say how. I can't find anything that looks like it might be to blame in the 3.3.5 change log, but kernel development is a bit above my pay grade.
Have you taken a look with htop or powertop to see if any processes are taking up a lot of CPU time?
Laptop: Arch+i3 Personal file sever: Slackware Work PC: Fedora+wmii
Work file sever: FreeBSD Work application server: Scientific Linux
I'm an addict.
Offline
#5 2012-05-11 10:15:53
- vehk
- Member
- Registered: 2012-03-18
- Posts: 7
Re: Troubleshooting a high load average on idle.
Have you taken a look with htop or powertop to see if any processes are taking up a lot of CPU time?
Here's a snapshot of top after 10 minutes of idling. I don't see anything suspicious.
top - 11:52:16 up 32 min, 0 users, load average: 0.88, 0.93, 0.93
Tasks: 103 total, 1 running, 102 sleeping, 0 stopped, 0 zombie
%Cpu(s): 7.0 us, 3.0 sy, 0.0 ni, 89.7 id, 0.3 wa, 0.0 hi, 0.0 si, 0.0 st
Kb Mem: 2067836 total, 1019336 used, 1048500 free, 31696 buffers
Kb Swap: 2355196 total, 0 used, 2355196 free, 590200 cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
859 root 20 0 67840 48m 16m S 8.3 2.4 3:00.83 X
1877 vehk 20 0 19768 10m 4924 S 2.0 0.5 0:42.34 awesome
1920 vehk 20 0 5628 2372 1236 S 0.7 0.1 0:11.49 htop
1884 vehk 20 0 147m 29m 22m S 0.3 1.5 0:02.61 keepassx
1 root 20 0 2128 648 576 S 0.0 0.0 0:00.55 init
2 root 20 0 0 0 0 S 0.0 0.0 0:00.00 kthreadd
3 root 20 0 0 0 0 S 0.0 0.0 0:01.30 ksoftirqd/0
6 root rt 0 0 0 0 S 0.0 0.0 0:00.00 migration/0
7 root rt 0 0 0 0 S 0.0 0.0 0:00.00 watchdog/0I couldn't find anything relevant in the kernel changelog either.
Offline
#6 2012-05-11 11:31:57
- TheJJ
- Member
- Registered: 2011-09-29
- Posts: 11
- Website
Re: Troubleshooting a high load average on idle.
I've got the same problem and didnt find any solution yet. also my core temperature is now 55° C instead of 35-40° in idle.
my load:
13:24:43 up 23:16, 0 users, load average: 0.49, 0.70, 0.77Linux jjpad 3.3.5-1-ARCH #1 SMP PREEMPT Mon May 7 19:57:51 CEST 2012 x86_64 Intel(R) Core(TM) i5-2520M CPU @ 2.50GHz GenuineIntel GNU/Linuxtop:
top - 13:25:40 up 23:17, 0 users, load average: 0.44, 0.64, 0.74
Tasks: 153 total, 1 running, 152 sleeping, 0 stopped, 0 zombie
%Cpu(s): 1.0 us, 0.4 sy, 0.2 ni, 98.4 id, 0.0 wa, 0.0 hi, 0.0 si, 0.0 st
Kb Mem: 8062796 total, 2705376 used, 5357420 free, 171912 buffers
Kb Swap: 0 total, 0 used, 0 free, 1320892 cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
1700 root 20 0 176m 24m 6984 S 3.0 0.3 13:45.02 X
7776 jj 20 0 526m 42m 24m S 1.7 0.5 0:45.35 chromium
7973 jj 20 0 98656 11m 4296 S 1.0 0.1 0:02.07 urxvt
2253 jj 20 0 15400 1768 1124 R 0.7 0.0 0:00.05 top
1034 root 20 0 6264 404 296 S 0.3 0.0 0:02.01 ifplugd
6367 jj 25 5 907m 95m 20m S 0.3 1.2 0:10.60 chromium
1 root 20 0 4188 720 612 S 0.0 0.0 0:02.04 init
2 root 20 0 0 0 0 S 0.0 0.0 0:00.01 kthreadd
3 root 20 0 0 0 0 S 0.0 0.0 0:05.43 ksoftirqd/0
6 root rt 0 0 0 0 S 0.0 0.0 0:00.00 migration/0
21 root 0 -20 0 0 0 S 0.0 0.0 0:00.00 cpuset
22 root 0 -20 0 0 0 S 0.0 0.0 0:00.00 khelper
23 root 20 0 0 0 0 S 0.0 0.0 0:00.00 kdevtmpfs
24 root 0 -20 0 0 0 S 0.0 0.0 0:00.00 netns
25 root 20 0 0 0 0 S 0.0 0.0 0:00.10 sync_supers
26 root 20 0 0 0 0 S 0.0 0.0 0:00.00 bdi-default
27 root 0 -20 0 0 0 S 0.0 0.0 0:00.00 kblockd
28 root 20 0 0 0 0 S 0.0 0.0 0:00.02 khungtaskd
29 root 20 0 0 0 0 S 0.0 0.0 0:00.00 kswapd0
30 root 25 5 0 0 0 S 0.0 0.0 0:00.00 ksmd
31 root 39 19 0 0 0 S 0.0 0.0 0:03.27 khugepaged
32 root 20 0 0 0 0 S 0.0 0.0 0:00.00 fsnotify_mark
33 root 0 -20 0 0 0 S 0.0 0.0 0:00.00 crypto
35 root 0 -20 0 0 0 S 0.0 0.0 0:00.00 kthrotld
61 root 0 -20 0 0 0 S 0.0 0.0 0:00.00 ata_sff
62 root 20 0 0 0 0 S 0.0 0.0 0:00.00 scsi_eh_0
63 root 20 0 0 0 0 S 0.0 0.0 0:00.00 scsi_eh_1
64 root 20 0 0 0 0 S 0.0 0.0 0:00.00 scsi_eh_2
67 root 20 0 0 0 0 S 0.0 0.0 0:00.00 scsi_eh_3
68 root 20 0 0 0 0 S 0.0 0.0 0:00.00 scsi_eh_4
69 root 20 0 0 0 0 S 0.0 0.0 0:00.00 scsi_eh_5
84 root 20 0 0 0 0 S 0.0 0.0 0:00.05 khubd
85 root 0 -20 0 0 0 S 0.0 0.0 0:00.00 cfg80211
87 root 0 -20 0 0 0 S 0.0 0.0 0:00.00 iwlwifi
98 root 20 0 0 0 0 S 0.0 0.0 0:01.36 jbd2/sda5-8
99 root 0 -20 0 0 0 S 0.0 0.0 0:00.00 ext4-dio-unwrit
257 root 0 -20 0 0 0 S 0.0 0.0 0:00.00 ktpacpid
270 root 0 -20 0 0 0 S 0.0 0.0 0:00.00 kpsmoused
etcetc.the wattage of the system is now at 14-20 W in idle, it was down to 7 before.
my powertop reports nothing special,
about 50-100 wakeups/s
Anyone any ideas what to do except downgrading?
Offline
#7 2012-05-11 14:50:15
- Mr.Elendig
- #archlinux@freenode channel op
- From: The intertubes
- Registered: 2004-11-07
- Posts: 4,094
Re: Troubleshooting a high load average on idle.
check iotop and xrestop too
Evil #archlinux@libera.chat channel op and general support dude.
. files on github, Screenshots, Random pics and the rest
Offline
#8 2012-05-11 15:47:04
- ahammel
- Member
- Registered: 2012-05-01
- Posts: 23
Re: Troubleshooting a high load average on idle.
@ TheJJ and Vekh:
X seems to be eating a lot more resources on your systems than mine. Is that a typical load for X in your desktop environments? I get about 3 wakeups/second from X in dwm.
Powertop also tells me I'm getting a fair number of rescheduling interrupts from the kernel (20–50/second). If either of you are seeing something similar, it might be an ACPI/APIC problem. The Ubuntu docs have a troubleshooting guide for this here.
Laptop: Arch+i3 Personal file sever: Slackware Work PC: Fedora+wmii
Work file sever: FreeBSD Work application server: Scientific Linux
I'm an addict.
Offline
#9 2012-05-11 15:56:19
- TheJJ
- Member
- Registered: 2011-09-29
- Posts: 11
- Website
Re: Troubleshooting a high load average on idle.
a friend of mine also has the same issues on a sony laptop (don't know which exacktly)
i'm using i3 and a thinkpad x220t, and i dont't think i changed anything when this power regression occured, except updating arch packages.
~ $ sar
Linux 3.3.5-1-ARCH 05/11/2012 _x86_64_ (4 CPU)
03:01:02 PM CPU %user %nice %system %iowait %steal %idle
03:11:02 PM all 0.35 0.00 0.20 0.00 0.00 99.45
03:21:02 PM all 1.53 0.00 0.60 0.00 0.00 97.87
03:31:02 PM all 1.50 0.00 0.66 0.00 0.00 97.84
03:41:02 PM all 1.16 0.00 0.66 0.00 0.00 98.18
04:06:07 PM all 2.48 0.00 1.96 0.02 0.00 95.55
05:01:01 PM all 1.64 0.00 0.49 0.01 0.00 97.87
05:11:01 PM all 1.96 0.00 0.55 0.02 0.00 97.47
05:21:01 PM all 4.12 0.00 1.15 0.01 0.00 94.73
05:31:01 PM all 0.86 0.00 0.30 0.00 0.00 98.84
05:41:01 PM all 0.98 0.00 0.38 0.01 0.00 98.64
05:51:01 PM all 0.81 0.00 0.35 0.00 0.00 98.84
Average: all 1.60 0.00 0.61 0.01 0.00 97.78really annoying, my battery run time is 1/4 of what is was before...
Last edited by TheJJ (2012-05-11 16:46:15)
Offline
#10 2012-05-11 16:46:37
- vehk
- Member
- Registered: 2012-03-18
- Posts: 7
Re: Troubleshooting a high load average on idle.
X seems to be eating a lot more resources on your systems than mine. Is that a typical load for X in your desktop environments?
I already looked into this because it did seem a bit high. Turns out there was a bug in my awesome configuration that lead to high CPU usage. X is now down to ~2% CPU and 2-3 wakeups.
I still get relatively high load averages though, so I will look into ACPI/APIC.
Edit:
With both the new and old kernel I get 50-80 rescheduling interrupts per second. The guide talks about "many hundreds or possibly thousands" of interrupts, so
I can't image this being an issue with acpi/apic. Also, I can't find any 'misbehaving' application whatsoever. Considering that top/iostat etc. don't show anything
odd, what else is there to check?
Last edited by vehk (2012-05-11 21:33:15)
Offline
#11 2012-05-11 21:55:38
- Fr3ak0ut
- Member
- Registered: 2012-01-20
- Posts: 1
Re: Troubleshooting a high load average on idle.
Hi,
I have the same problem and i am using i3 on a Sony SB. My average core temperature increased a bit and my system wattage is now about 15 W in idle (before it was about 8 W). My average load in idle is much more than before, too. The only thing i did today was updating my packages.
My current load:
23:51:25 up 2:29, 0 users, load average: 0.53, 0.71, 0.90Linux andre-laptop 3.3.5-1-ARCH #1 SMP PREEMPT Mon May 7 19:57:51 CEST 2012 x86_64 Intel(R) Core(TM) i7-2620M CPU @ 2.70GHz GenuineIntel GNU/LinuxOffline
#12 2012-05-12 05:08:30
- brebs
- Member
- Registered: 2007-04-03
- Posts: 3,742
Re: Troubleshooting a high load average on idle.
The 3.3.4-3.3.5 patch has several wireless patches - are you using wireless?
Offline
#13 2012-05-12 09:41:32
- vehk
- Member
- Registered: 2012-03-18
- Posts: 7
Re: Troubleshooting a high load average on idle.
No, I don't use wireless. My workstation has a wired connection to a router.
After examining lsmod I found that the bluetooth module and its dependencies are loaded although I don't need them.
The old kernel does not load these modules. Disabling them did not resolve the issue, however. Could it be a misbehaving module?
Here is my ls{mod,pci,usb} and uname.
I just booted with the fallback initramfs (autodetect off). The bluetooth module was not loaded, but the issue remains.
Last edited by vehk (2012-05-12 09:54:22)
Offline
#14 2012-05-12 14:59:11
- TheJJ
- Member
- Registered: 2011-09-29
- Posts: 11
- Website
Re: Troubleshooting a high load average on idle.
i created a bug in the tracker:
Offline
#15 2012-05-14 12:08:12
- bernarcher
- Forum Fellow
- From: Germany
- Registered: 2009-02-17
- Posts: 2,281
Re: Troubleshooting a high load average on idle.
Moved to Kernel & Hardware.
To know or not to know ...
... the questions remain forever.
Offline
#16 2012-05-14 14:36:57
- Kilzool
- Member
- From: Ireland
- Registered: 2010-08-04
- Posts: 232
Re: Troubleshooting a high load average on idle.
I also have noticed almost double and even triple average loads since kernel update (compared to the kernel prior).
Offline
#17 2012-05-14 14:40:09
- Army
- Member
- Registered: 2007-12-07
- Posts: 1,784
Re: Troubleshooting a high load average on idle.
I don't have this issue. Maybe it's because I use the ck-kernel?
Offline
#18 2012-05-14 22:09:28
- alexcriss
- Member
- Registered: 2010-05-24
- Posts: 121
Re: Troubleshooting a high load average on idle.
I think I am seeing this also on 3.4-rc7, while 3.3.4 seems to be fine.
My machine is a Lenovo T420s, SNB CPU and GPU, if it might help. I'll gladly provide other details if someody might have a clue on what's going on
Offline
#19 2012-05-15 15:08:01
- Butcher
- Member
- Registered: 2009-02-04
- Posts: 158
Re: Troubleshooting a high load average on idle.
3.3.5-1-ARCH and happens here as well. I've never had over 1.0 of load average when using the computer, but it's happening now.
17:07:46 up 16:05, 2 users, load average: 1,67, 1,49, 1,54
Last edited by Butcher (2012-05-15 15:08:17)
Offline
#20 2012-05-17 10:16:22
- krum
- Member
- From: Grenoble - FR
- Registered: 2008-04-10
- Posts: 32
Re: Troubleshooting a high load average on idle.
Same issue, last kernel 3.3.6 and a full intel box.
top - 12:14:38 up 1:46, 2 users, load average: 0,66, 0,38, 0,47
Tasks: 116 total, 2 running, 114 sleeping, 0 stopped, 0 zombie
%Cpu0 : 0,7 us, 2,0 sy, 0,0 ni, 97,3 id, 0,0 wa, 0,0 hi, 0,0 si, 0,0 st
%Cpu1 : 0,7 us, 0,7 sy, 0,0 ni, 98,7 id, 0,0 wa, 0,0 hi, 0,0 si, 0,0 st
%Cpu2 : 1,0 us, 0,0 sy, 0,0 ni, 99,0 id, 0,0 wa, 0,0 hi, 0,0 si, 0,0 st
%Cpu3 : 0,3 us, 0,3 sy, 0,0 ni, 99,3 id, 0,0 wa, 0,0 hi, 0,0 si, 0,0 st
Kb Mem: 3949640 total, 2036824 used, 1912816 free, 84968 buffers
Kb Swap: 0 total, 0 used, 0 free, 1093948 cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
890 root 20 0 147m 18m 5328 S 2,3 0,5 4:01.07 Xorg
1109 david 20 0 1345m 116m 34m S 1,3 3,0 2:48.28 gnome-shell
1218 david 20 0 478m 20m 11m S 1,0 0,5 0:00.63 gnome-terminal
1268 david 20 0 1088m 54m 23m S 0,3 1,4 0:01.97 rhythmbox
3865 root 20 0 13696 1676 1072 R 0,3 0,0 0:00.02 top
1 root 20 0 4188 680 584 S 0,0 0,0 0:00.43 init
2 root 20 0 0 0 0 S 0,0 0,0 0:00.00 kthreadd
3 root 20 0 0 0 0 S 0,0 0,0 0:00.16 ksoftirqd/0
6 root rt 0 0 0 0 S 0,0 0,0 0:00.00 migration/0Offline
#21 2012-05-17 19:26:29
- archwade
- Member
- Registered: 2010-01-26
- Posts: 14
Re: Troubleshooting a high load average on idle.
Which video drivers are you using?
Openchrome upstream changed the default acceleration method from XAA to EXA in openchrome-0.2.906. I was having huge problems with UI framerate / sluggishness after upgrading. If this applies, see the section on AccelMethod in wiki:OpenChrome Troubleshooting.
Last edited by archwade (2012-05-17 19:27:11)
Offline
#22 2012-05-17 19:57:48
- alexcriss
- Member
- Registered: 2010-05-24
- Posts: 121
Re: Troubleshooting a high load average on idle.
xf86-video-intel with SNB hardware here
Offline
#23 2012-05-17 20:04:04
- archwade
- Member
- Registered: 2010-01-26
- Posts: 14
Re: Troubleshooting a high load average on idle.
It may be good to check /var/log/Xorg.0.log anyway, since that's what led me to find my issue. I was seeing a ton of errors from X complaining about the EXA module in OpenChrome, so it could be a place to start.
If anyone else has a working and non-working versions available, it could also be worth diffing the Xorg.0.log files to see if anything jumps out there.
Offline
#24 2012-05-18 15:12:03
- rLy
- Member
- From: Hungary
- Registered: 2011-06-01
- Posts: 7
Re: Troubleshooting a high load average on idle.
Hi, I noticed the high load a few days ago. That time it was around 1 but today more than 2
top - 17:03:18 up 10:50, 2 users, load average: 2,19, 2,35, 2,50
Tasks: 140 total, 1 running, 138 sleeping, 0 stopped, 1 zombie
%Cpu(s): 14,3 us, 3,9 sy, 1,2 ni, 76,4 id, 4,0 wa, 0,0 hi, 0,2 si, 0,0 st
Kb Mem: 4053156 total, 3574632 used, 478524 free, 65960 buffers
Kb Swap: 4192960 total, 181656 used, 4011304 free, 1775288 cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
1348 rly 20 0 27332 15m 776 S 6,5 0,4 7:44.29 wineserver
1472 rly 20 0 2833m 246m 20m S 6,5 6,2 12:18.64 steam.exe
1 root 20 0 30428 1892 1356 S 0,0 0,0 0:00.40 systemd
2 root 20 0 0 0 0 S 0,0 0,0 0:00.00 kthreadd
3 root 20 0 0 0 0 S 0,0 0,0 0:07.71 ksoftirqd/0
6 root rt 0 0 0 0 S 0,0 0,0 0:00.00 migration/0
7 root rt 0 0 0 0 S 0,0 0,0 0:00.06 watchdog/0
8 root rt 0 0 0 0 S 0,0 0,0 0:00.00 migration/1
10 root 20 0 0 0 0 S 0,0 0,0 0:08.57 ksoftirqd/1
12 root rt 0 0 0 0 S 0,0 0,0 0:00.05 watchdog/1
13 root 0 -20 0 0 0 S 0,0 0,0 0:00.00 cpuset
14 root 0 -20 0 0 0 S 0,0 0,0 0:00.00 khelper
15 root 20 0 0 0 0 S 0,0 0,0 0:00.00 kdevtmpfs
16 root 0 -20 0 0 0 S 0,0 0,0 0:00.00 netns
17 root 20 0 0 0 0 S 0,0 0,0 0:00.05 sync_supers
18 root 20 0 0 0 0 S 0,0 0,0 0:00.00 bdi-default
19 root 0 -20 0 0 0 S 0,0 0,0 0:00.00 kblockd
21 root 20 0 0 0 0 S 0,0 0,0 0:00.01 khungtaskd
22 root 20 0 0 0 0 S 0,0 0,0 0:10.64 kswapd0
23 root 25 5 0 0 0 S 0,0 0,0 0:00.00 ksmd
24 root 39 19 0 0 0 S 0,0 0,0 0:12.59 khugepaged
25 root 20 0 0 0 0 S 0,0 0,0 0:00.00 fsnotify_markYesterday updates:
[2012-05-17 18:33] starting full system upgrade
[2012-05-17 18:44] upgraded nvidia-utils (295.49-1 -> 295.53-1)
[2012-05-17 18:44] upgraded 0ad-data (a9-1 -> a10-1)
[2012-05-17 18:44] upgraded 0ad (a9-1 -> a10-1)
[2012-05-17 18:44] upgraded libcups (1.5.2-2 -> 1.5.3-1)
[2012-05-17 18:45] upgraded cups (1.5.2-2 -> 1.5.3-1)
[2012-05-17 18:45] upgraded glib2 (2.32.2-2 -> 2.32.3-1)
[2012-05-17 18:45] upgraded lib32-nvidia-utils (295.49-1 -> 295.53-1)
[2012-05-17 18:45] upgraded libnl (3.2.7-1 -> 3.2.9-1)
[2012-05-17 18:45] upgraded nvidia (295.49-1 -> 295.53-1)
[2012-05-17 18:45] upgraded opencl-nvidia (295.49-1 -> 295.53-1)
[2012-05-17 18:45] upgraded soprano (2.7.5-1 -> 2.7.6-1)
[2012-05-17 18:45] upgraded unrar (4.2.1-1 -> 4.2.2-1)
[2012-05-17 18:45] upgraded xorg-xinput (1.5.99.901-1 -> 1.6.0-1)Offline
#25 2012-05-21 13:17:24
- alexcriss
- Member
- Registered: 2010-05-24
- Posts: 121
Re: Troubleshooting a high load average on idle.
Same report on Fedora:
https://bugzilla.redhat.com/show_bug.cgi?id=822877
Offline