Re: cpu usage
Mario Remy Almeida <[email protected]>
| Newsgroups | gmane.mail.qmail.ldap |
|---|---|
| Organization | ISA |
| Message-ID | <1221137511.6544.38.camel@mario> |
Hi Russ,
There is no problem if kernel allows qmail-smtpd for 100% cpu usage but
the load average should not go high. which means there are more request
waiting for the processor.
Please help me with this issue
Below is the output of top and vmstat.
Output of *** TOP ***
12:15:53 up 37 days, 5:10, 4 users, load average: 32.13, 31.24,
30.32
156 processes: 123 sleeping, 33 running, 0 zombie, 0 stopped
CPU states: cpu user nice system irq softirq iowait idle
total 98.5% 1.1% 0.2% 0.0% 0.0% 0.0% 0.0%
cpu00 98.6% 0.7% 0.5% 0.0% 0.0% 0.0% 0.0%
cpu01 98.4% 1.5% 0.0% 0.0% 0.0% 0.0% 0.0%
Mem: 244072k av, 234236k used, 9836k free, 0k shrd, 34580k
buff
74336k actv, 10812k in_d, 1744k in_c
Swap: 1052248k av, 30248k used, 1022000k free 42360k
cached
PID USER PRI NI SIZE RSS SHARE STAT %CPU %MEM TIME CPU
COMMAND
26509 root 25 0 180 180 104 R 3.9 0.0 54:16 1
qmail-smtpd
27131 root 25 0 180 180 104 R 3.9 0.0 35:45 0
qmail-smtpd
27939 root 25 0 180 180 104 R 3.9 0.0 26:53 1
qmail-smtpd
28198 root 25 0 180 176 104 R 3.9 0.0 24:13 0
qmail-smtpd
28307 root 25 0 180 180 104 R 3.9 0.0 23:43 0
qmail-smtpd
29099 root 25 0 188 188 112 R 3.9 0.0 16:32 1
qmail-smtpd
29460 root 25 0 268 268 192 R 3.9 0.1 14:32 1
qmail-smtpd
29540 root 25 0 264 264 192 R 3.9 0.1 13:47 0
qmail-smtpd
30162 root 25 0 268 268 192 R 3.9 0.1 9:36 1
qmail-smtpd
32114 root 25 0 448 448 372 R 3.9 0.1 2:05 1
qmail-smtpd
28777 root 25 0 188 188 112 R 3.7 0.0 19:00 1
qmail-smtpd
30403 root 25 0 268 268 192 R 3.6 0.1 8:43 1
qmail-smtpd
30390 root 25 0 268 268 192 R 3.1 0.1 8:35 0
qmail-smtpd
26009 root 25 0 180 180 104 R 2.9 0.0 91:38 1
qmail-smtpd
26236 root 25 0 176 176 104 R 2.9 0.0 70:51 0
qmail-smtpd
26434 root 25 0 176 176 104 R 2.9 0.0 57:30 0
qmail-smtpd
26629 root 25 0 180 180 104 R 2.9 0.0 47:31 0
qmail-smtpd
26902 root 25 0 180 180 104 R 2.9 0.0 41:03 1
qmail-smtpd
26957 root 25 0 184 180 104 R 2.9 0.0 41:45 1
qmail-smtpd
27411 root 25 0 180 180 104 R 2.9 0.0 33:25 1
qmail-smtpd
28855 root 25 0 188 188 112 R 2.9 0.0 18:45 0
qmail-smtpd
29879 root 25 0 264 264 192 R 2.9 0.1 12:10 1
qmail-smtpd
25937 root 25 0 180 180 104 R 2.9 0.0 92:05 1
qmail-smtpd
30694 root 25 0 444 444 372 R 2.9 0.1 7:38 1
qmail-smtpd
31109 root 25 0 448 448 372 R 2.9 0.1 4:58 0
qmail-smtpd
31251 root 25 0 444 444 372 R 2.9 0.1 4:22 1
qmail-smtpd
31439 root 25 0 448 448 372 R 2.9 0.1 3:43 0
qmail-smtpd
32657 root 25 0 448 448 372 R 2.9 0.1 0:18 0
qmail-smtpd
32661 root 25 0 448 448 372 R 2.9 0.1 0:19 0
qmail-smtpd
28052 root 39 15 176 176 104 R N 0.5 0.0 6:35 0
qmail-smtpd
27108 root 39 19 176 176 104 R N 0.2 0.0 15:57 0
qmail-smtpd
27794 root 39 19 180 180 104 R N 0.2 0.0 7:16 0
qmail-smtpd
Output of vmstat for every 2sec
procs memory swap io system
cpu
r b swpd free buff cache si so bi bo in cs us sy
id wa
34 0 29152 82484 3380 18852 0 0 0 56 136 52 100
0 0 0
34 0 29152 82052 3404 19128 0 0 146 104 152 110 100
0 0 0
34 0 29152 82052 3412 19132 0 0 0 74 136 52 100
0 0 0
35 0 29152 82052 3460 19152 0 0 10 92 121 82 100
0 0 0
33 0 29152 82068 3500 19140 0 0 12 84 114 62 100
0 0 0
33 0 29152 82068 3500 19140 0 0 0 0 130 36 100
0 0 0
33 0 29152 82068 3508 19140 0 0 0 66 137 61 100
0 0 0
33 0 29152 82068 3508 19140 0 0 0 0 132 40 100
0 0 0
33 0 29152 82068 3508 19140 0 0 0 0 105 34 100
0 0 0
33 0 29152 82068 3516 19140 0 0 0 6 109 36 100
0 0 0
33 0 29152 82068 3516 19140 0 0 0 0 137 38 100
0 0 0
33 0 29152 82068 3524 19140 0 0 0 6 106 35 100
0 0 0
33 0 29152 82068 3524 19140 0 0 0 0 133 38 100
0 0 0
33 0 29152 82068 3532 19140 0 0 0 6 109 37 100
0 0 0
33 0 29152 82068 3532 19140 0 0 0 0 105 32 100
0 0 0
35 0 29152 82060 3532 19140 0 0 0 0 137 49 100
0 0 0
33 0 29152 82068 3548 19136 0 0 4 112 142 56 100
0 0 0
33 0 29152 82068 3548 19136 0 0 0 0 128 38 100
0 0 0
33 0 29152 82068 3556 19136 0 0 0 84 149 62 100
0 0 0
34 0 29152 82068 3556 19136 0 0 0 0 107 35 100
0 0 0
33 0 29152 82068 3556 19136 0 0 0 0 130 38 100
0 0 0
33 0 29152 82068 3564 19136 0 0 0 58 119 35 100
0 0 0
33 0 29152 82068 3564 19136 0 0 0 0 127 38 100
0 0 0
33 0 29152 82068 3572 19136 0 0 0 6 106 38 100
0 0 0
33 0 29152 82068 3572 19136 0 0 0 0 108 32 100
0 0 0
33 0 29152 82068 3572 19136 0 0 0 0 134 37 100
0 0 0
33 0 29152 82068 3580 19136 0 0 0 6 108 37 100
0 0 0
33 0 29152 82068 3580 19136 0 0 0 0 132 39 100
0 0 0
33 0 29152 82068 3588 19136 0 0 0 6 108 36 100
0 0 0
33 0 29152 82068 3588 19136 0 0 0 0 105 34 100
0 0 0
33 0 29152 82068 3588 19136 0 0 0 0 131 37 100
0 0 0
33 0 29152 82068 3596 19136 0 0 0 24 108 35 100
0 0 0
33 0 29152 82068 3596 19136 0 0 0 0 134 39 100
0 0 0
33 0 29152 82068 3604 19136 0 0 0 32 118 66 100
0 0 0
33 0 29152 82068 3604 19136 0 0 0 0 131 54 100
0 0 0
Regards,
Mario
On Thu, 2008-09-11 at 07:47 -0400, Russell Simpkins wrote:
> > Hi Russ,
> >
> > As i told you that i have enabled the log level to 16 but no luck i
> > din't get any such messages releated to errors of cpu usage.
> >
> >
> > Regards,
> > Mario
>
> Do you see anything abnormal when you look at the output of
>
> top
>
> or with
>
> vmstat 2
>
> ? Just because a process is using 100% of the cpu, does not in and of
> itself always mean there is a problem. If there are no other process
> running, then the kernel can allow the mail server to use 100%. You should
> look at top to see how busy the server is vs how idle. If the box is 98%
> busy and 2% idle and/or you see a lot of blocked threads with vmstat, then
> you should continue looking.
>
> If you find that your server is too busy, you could try adjusting down
> some of your checks to see if that helps. Make sure that you don't have
> log files growing out of control. You can try a restart of qmail. You
> should verified that your ldap server is optimized.
>
> Hope that helps.
>
> Russ
>