Linode Forum
Linode Community Forums
 FAQFAQ    SearchSearch    MembersMembers      Register Register 
 LoginLogin [ Anonymous ] 
Post new topic  Reply to topic
Author Message
 Post subject: strange load average
PostPosted: Thu May 03, 2007 10:51 pm 
Offline
Newbie

Joined: Thu May 03, 2007 2:26 pm
Posts: 4
All:

I have my linode running fedora core, and I have a strange, high, load average: (~0.5, see bottom of post.)

Code:
[unix]$ ps aux
USER       PID %CPU %MEM    VSZ   RSS TTY      STAT START   TIME COMMAND
root         1  0.0  0.2   2028   644 ?        Ss   22:10   0:00 init [3] 
root         2  0.0  0.0      0     0 ?        SN   22:10   0:00 [ksoftirqd/0]
root         3  0.0  0.0      0     0 ?        S<   22:10   0:00 [events/0]
root         4  0.0  0.0      0     0 ?        S<   22:10   0:00 [khelper]
root         5  0.0  0.0      0     0 ?        S<   22:10   0:00 [kthread]
root        49  0.0  0.0      0     0 ?        S<   22:10   0:00 [kblockd/0]
root        61  0.0  0.0      0     0 ?        S    22:10   0:00 [pdflush]
root        62  0.0  0.0      0     0 ?        S    22:10   0:00 [pdflush]
root        63  0.0  0.0      0     0 ?        S<   22:10   0:00 [kswapd0]
root        64  0.0  0.0      0     0 ?        S<   22:10   0:00 [aio/0]
root        67  0.0  0.0      0     0 ?        S<   22:10   0:00 [jfsIO]
root        68  0.0  0.0      0     0 ?        S<   22:10   0:00 [jfsCommit]
root        69  0.0  0.0      0     0 ?        S<   22:10   0:00 [jfsSync]
root        70  0.0  0.0      0     0 ?        S<   22:10   0:00 [xfslogd/0]
root        71  0.0  0.0      0     0 ?        S<   22:10   0:00 [xfsdatad/0]
root       616  0.0  0.0      0     0 ?        S<   22:10   0:00 [kcryptd/0]
root       617  0.0  0.0      0     0 ?        S<   22:10   0:00 [ksnapd]
root       713  0.0  0.0      0     0 ?        S<   22:10   0:00 [kjournald]
root       768  0.0  0.2   2120   564 ?        S<s  22:10   0:00 /sbin/udevd -d
root      2295  0.0  0.2   2276   540 ?        Ss   22:10   0:00 /sbin/dhclient -1 -q -lf /var/
root      2380  0.0  0.2   1796   704 ?        Ss   22:10   0:00 syslogd -m 0
root      2383  0.0  0.1   1636   392 ?        Ss   22:10   0:00 klogd -x
root      2443  0.0  0.4  10640  1228 ?        Ssl  22:10   0:00 pcscd
root      2477  0.0  0.3   5176   944 ?        Ss   22:11   0:00 /usr/sbin/sshd
root      2496  0.0  0.6   8520  1640 ?        Ss   22:11   0:00 sendmail: accepting connection
smmsp     2504  0.0  0.5   7568  1456 ?        Ss   22:11   0:00 sendmail: Queue runner@01:00:0
root      2523  0.0  0.4   5220  1096 ?        Ss   22:11   0:00 crond
root      2542  0.0  0.1   2204   428 ?        Ss   22:11   0:00 /usr/sbin/atd
root      2548  0.0  0.1   1620   424 tty0     Ss+  22:11   0:00 /sbin/mingetty tty0
root      2629  0.0  0.9   8024  2380 ?        Ss   22:20   0:00 sshd: npk [priv]
npk       2631  0.0  0.7   8148  1876 ?        S    22:20   0:00 sshd: npk@pts/0 
npk       2632  0.0  0.5   4620  1468 pts/0    Ss   22:20   0:00 -bash
npk       2682  0.0  0.3   4216   936 pts/0    R+   22:41   0:00 ps aux
[unix]$ uptime
 22:49:33 up 38 min,  1 user,  load average: 0.40, 0.41, 0.36

Can someone explain why this is the case?

n


Top
   
 Post subject:
PostPosted: Fri May 04, 2007 5:31 am 
Offline
Senior Member
User avatar

Joined: Sat Mar 24, 2007 6:09 pm
Posts: 59
Location: South Africa
Hi,

I have exactly the same problem on my Linode. It's been that way ever since I changed to the 2.6.20-linode28 kernel.

Load average hovers around 0.4 all the time for me.

My vmstats show 100% idle times:

Code:
procs -----------memory---------- ---swap-- -----io---- -system-- ----cpu----
 r  b   swpd   free   buff  cache   si   so    bi    bo   in   cs us sy id wa
 0  0      0   6964  83548 125664    0    0     1    11   61   15  0  0 100  0
 0  0      0   6964  83548 125664    0    0     0     0  110   17  0  0 100  0
 0  0      0   6964  83548 125664    0    0     0     0  105   13  0  0 100  0
 0  0      0   6964  83548 125664    0    0     0     0  105   13  0  0 100  0
 0  0      0   7012  83548 125664    0    0     0     0  105   17  0  0 100  0


I also set up a log to see if there was a trend, but the graph is pretty much flat, as you can see:

Code:
  0.7 ++-+--+--+--+--+-+--+--+--+--+--+--+--+--+--+--+--+-+--+--+--+--+--+-++
      +     +     +    +     +     +     + "load-20070429" using 1:2 ****** +
      |                                                                     |
  0.6 ++                                                                   ++
      |                                                                     |
      |                                                                     |
      |                                                                     |
  0.5 ++                                                                   +*
      |                                                                     *
      |                                                                     *
  0.4 ++                                                                   +*
      |*                                         *  **                  *  *|
      |***** **  ** **          *****   ** ****** **  ***   **   ********* *|
  0.3 +*    * **** *  **********    **** ***             ***  ****        **+
      *                                                                    *|
      *                                                                     |
      *                                                                     |
  0.2 ++                                                                   ++
      |                                                                     |
      +     +     +    +     +     +     +     +     +    +     +     +     +
  0.1 ++-+--+--+--+--+-+--+--+--+--+--+--+--+--+--+--+--+-+--+--+--+--+--+-++
    00:00 02:00 04:0006:00 08:00 10:00 12:00 14:00 16:0018:00 20:00 22:00 00:00


The load is wrecking havoc with my monitoring - I was actually considering opening a ticket, but then I saw your post.

--deckert


Top
   
 Post subject:
PostPosted: Fri May 04, 2007 9:46 am 
Offline
Linode Staff
User avatar

Joined: Tue Apr 15, 2003 6:24 pm
Posts: 3090
Website: http://www.linode.com/
Location: Galloway, NJ
Jeff knows about this and is looking into it.

-Chris


Top
   
 Post subject:
PostPosted: Fri May 04, 2007 10:46 am 
Offline
Senior Member
User avatar

Joined: Sat Mar 24, 2007 6:09 pm
Posts: 59
Location: South Africa
caker wrote:
Jeff knows about this and is looking into it.

-Chris


Thanks caker. I'd be happy to assist in testing (i.e. be a guineapig).

Also, the load does not affect the actual performance of my Linode. I've done a couple of staggered tests between the 2.4-latest and 2.6 latest kernels and here are the results:

Code:
OS                  : Linux 2.4.29-linode39-1um
C compiler          : gcc version 3.3.4
libc                : ld-2.3.2.so
MEMORY INDEX        : 13.791
INTEGER INDEX       : 9.333
FLOATING-POINT INDEX: 23.904


and

Code:
OS                  : Linux 2.6.20-linode28
C compiler          : gcc version 3.3.4
libc                : ld-2.3.2.so
MEMORY INDEX        : 16.524
INTEGER INDEX       : 11.235
FLOATING-POINT INDEX: 28.948


So the 2.6 kernels are a little faster, even with the additional load indicated.

--deckert


Top
   
 Post subject:
PostPosted: Sat May 05, 2007 7:11 pm 
Offline
Newbie

Joined: Thu May 03, 2007 2:26 pm
Posts: 4
So if I can summarize:

it seems as if there is an unaccounted for load on machines, but this load has no affect on performance or CPU use percentage. For some reason, I find this disconcerting :)

take care
n


Top
   
 Post subject:
PostPosted: Sun May 06, 2007 7:52 am 
Offline
Senior Member
User avatar

Joined: Fri Oct 24, 2003 3:51 pm
Posts: 965
Location: Netherlands
npk1977 wrote:
it seems as if there is an unaccounted for load on machines

The load is being incorrectly calculated. Something similar happened previously - the kernel reported 1+'actual load value'.

_________________
/ Peter


Top
   
 Post subject:
PostPosted: Sun May 06, 2007 8:53 am 
Offline
Linode Staff
User avatar

Joined: Tue Apr 15, 2003 6:24 pm
Posts: 3090
Website: http://www.linode.com/
Location: Galloway, NJ
Jeff found the problem and has provided a fix for it. I'll be building a new kernel in the next few days with the correction.

EDIT: http://lkml.org/lkml/2007/5/4/369

-Chris


Last edited by caker on Sun May 06, 2007 10:57 am, edited 1 time in total.

Top
   
 Post subject:
PostPosted: Sun May 06, 2007 10:43 am 
Offline
Senior Member
User avatar

Joined: Fri Oct 24, 2003 3:51 pm
Posts: 965
Location: Netherlands
That link points to an Ingo Molnar initiated 'KVM paravirtualization for Linux' thread om lkml.org - or did I miss something?

_________________
/ Peter


Top
   
 Post subject:
PostPosted: Sun May 06, 2007 10:57 am 
Offline
Linode Staff
User avatar

Joined: Tue Apr 15, 2003 6:24 pm
Posts: 3090
Website: http://www.linode.com/
Location: Galloway, NJ
pclissold wrote:
That link points to an Ingo Molnar initiated 'KVM paravirtualization for Linux' thread om lkml.org - or did I miss something?

Whoops. Fixed.

-Chris


Top
   
 Post subject:
PostPosted: Sun May 06, 2007 4:29 pm 
Offline
Senior Member
User avatar

Joined: Sat Mar 24, 2007 6:09 pm
Posts: 59
Location: South Africa
caker wrote:
Jeff found the problem and has provided a fix for it. I'll be building a new kernel in the next few days with the correction.

Nicely done, caker! Thanks for pushing this through to Jeff for us.

--deckert


Top
   
Display posts from previous:  Sort by  
Post new topic  Reply to topic


Who is online

Users browsing this forum: No registered users and 1 guest


You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum

Search for:
Jump to:  
RSS

Powered by phpBB® Forum Software © phpBB Group