1 |
On Fri, Dec 18, 2009 at 2:38 PM, Florian Philipp |
2 |
<lists@f_philipp.fastmail.net> wrote: |
3 |
> Hi list! |
4 |
> |
5 |
> My virtual server seems to have a problem and I don't know how to find it. |
6 |
> |
7 |
> Today, while trying to create a new postgresql database I noticed that |
8 |
> certain system operations seem to take ages. Normal work on the shell |
9 |
> works just fine but for example accessing the postgresql server through |
10 |
> psql, restarting tomcat, postgresql or zope all show the very same behavior: |
11 |
> Execution freezes, the load average climbs to 1-1.9 and after a few |
12 |
> minutes (maybe longer) the task finishes correctly. During all this |
13 |
> time, top reports that the CPUs are 100% idle. |
14 |
> |
15 |
> Other services, for example rsyncd or openvpn, work normally. I also |
16 |
> tried restarting the VM. Shutdown took maybe 10 or 15 minutes. Booting |
17 |
> was much faster with only a few minutes until all services were up and |
18 |
> running. However, it didn't solve the problem. |
19 |
> |
20 |
> So, my question is: How can I find out what is causing this? Can I |
21 |
> somehow trace it? Find out why a process waits? |
22 |
> |
23 |
> Keep in mind that this is a virtual server. I have no control over the |
24 |
> kernel. Oh, and before you ask: The only recent update was rkhunter from |
25 |
> 1.2.9-r1 to 1.3.4-r2. I also enabled the chkrootkit weekly cronjob. |
26 |
> |
27 |
> Thanks in advance! |
28 |
> Florian Philipp |
29 |
|
30 |
Well... it'll cause a MASS of output to sift through .. but strace is |
31 |
likely the most powerful tool for the job of simply seeing what a |
32 |
process is calling and when (notably, what call is left waiting to |
33 |
return as the whole process blocks). I'd also take a look at iotop, |
34 |
though the fact that top shows the cpu as idle rather than sitting in |
35 |
iowait makes me doubt that iotop would tell you too much. |
36 |
|
37 |
-- |
38 |
Poison [BLX] |
39 |
Joshua M. Murphy |