High CPU system usage

Denis Beauchemin Denis.Beauchemin at USHERBROOKE.CA
Tue Aug 23 21:18:30 IST 2005


    [ The following text is in the "ISO-8859-1" character set. ]
    [ Your display is set for the "US-ASCII" character set.  ]
    [ Some characters may be displayed incorrectly. ]

Ugo Bellavance wrote:

>Hi everyone,
>
>	During a period of high load, a server shows a lot of system CPU time
>in use.  We got a big backlog during this period.  Here is an excerpt of
>the sar report for this period.  Any ideas welcome... this is kernel 2.4
>from Whitebox linux 3.  Please ask if you need more details.
>
>09:20:00 AM       all     77.69      0.00     15.58      1.03      5.70
>09:20:00 AM         0     77.48      0.00     15.87      0.99      5.66
>09:20:00 AM         1     77.90      0.00     15.29      1.07      5.74
>09:30:00 AM       all     74.27      0.00     14.41      1.02     10.30
>09:30:00 AM         0     74.38      0.00     14.81      1.01      9.81
>09:30:00 AM         1     74.17      0.00     14.00      1.04     10.79
>09:40:01 AM       all     74.15      0.00     13.85      0.98     11.01
>09:40:01 AM         0     73.84      0.00     13.93      1.02     11.21
>09:40:01 AM         1     74.46      0.00     13.78      0.95     10.81
>09:50:01 AM       all     77.80      0.00     14.66      1.12      6.41
>09:50:01 AM         0     77.83      0.00     14.81      1.06      6.29
>09:50:01 AM         1     77.77      0.00     14.51      1.18      6.53
>10:00:00 AM       all     79.11      0.00     17.06      0.94      2.89
>10:00:00 AM         0     78.97      0.00     17.14      1.02      2.88
>10:00:00 AM         1     79.25      0.00     16.98      0.86      2.91
>10:10:01 AM       all     80.71      0.00     15.30      0.54      3.45
>10:10:01 AM         0     80.60      0.00     15.34      0.56      3.50
>10:10:01 AM         1     80.82      0.00     15.26      0.53      3.40
>10:20:01 AM       all     72.02      0.00     12.79      1.01     14.18
>10:20:01 AM         0     72.06      0.00     12.81      0.97     14.15
>10:20:01 AM         1     71.99      0.00     12.76      1.04     14.22
>10:30:01 AM       all     69.96      0.00     12.66      1.17     16.21
>10:30:01 AM         0     69.86      0.00     12.60      1.16     16.38
>10:30:01 AM         1     70.05      0.00     12.73      1.18     16.04
>10:40:00 AM       all     77.87      0.00     15.42      0.58      6.13
>10:40:00 AM         0     77.90      0.00     15.45      0.58      6.07
>10:40:00 AM         1     77.85      0.00     15.38      0.59      6.18
>10:49:59 AM       all     65.56      0.00     17.65      3.93     12.87
>10:49:59 AM         0     64.74      0.00     17.76      3.89     13.61
>10:49:59 AM         1     66.37      0.00     17.54      3.96     12.13
>11:00:01 AM       all     64.52      0.00     22.36      6.82      6.30
>11:00:01 AM         0     64.78      0.00     22.18      6.75      6.28
>11:00:01 AM         1     64.26      0.00     22.55      6.89      6.31
>11:10:01 AM       all     64.00      0.00     21.29      6.63      8.08
>11:10:01 AM         0     63.83      0.00     21.29      6.66      8.23
>11:10:01 AM         1     64.17      0.00     21.30      6.60      7.93
>11:20:00 AM       all     69.71      0.00     21.51      3.57      5.21
>11:20:00 AM         0     69.45      0.00     21.55      3.62      5.39
>11:20:00 AM         1     69.98      0.00     21.47      3.52      5.03
>
>Average:          all     50.51      0.00     10.56      2.32     36.61
>Average:            0     50.38      0.00     10.62      2.33     36.68
>Average:            1     50.64      0.00     10.50      2.31     36.55
>
>Regards,
>  
>
Ugo,

I'm guessing your output refers to:
Time          CPU     %user     %nice   %system   %iowait     %idle

Those numbers are not uncommon here and the server copes well with 
incoming traffic...

Is your server swapping?  It doesn't seem to be I/O depraved either 
(mine show worst iowait but I only have a single disk).

What processes are displayed by top when this happens?

Denis

-- 
   _
  °v°   Denis Beauchemin, analyste
 /(_)\  Université de Sherbrooke, S.T.I.
  ^ ^   T: 819.821.8000x2252 F: 819.821.8045



------------------------ MailScanner list ------------------------
To unsubscribe, email jiscmail at jiscmail.ac.uk with the words:
'leave mailscanner' in the body of the email.
Before posting, read the Wiki (http://wiki.mailscanner.info/) and
the archives (http://www.jiscmail.ac.uk/lists/mailscanner.html).

Support MailScanner development - buy the book off the website!

    [ Part 2, "S/MIME Cryptographic Signature"  ]
    [ Application/X-PKCS7-SIGNATURE  4.4KB. ]
    [ Unable to print this part. ]




More information about the MailScanner mailing list