On Sat, Apr 05, 2008 at 12:00:44PM +0800, Pete Kay wrote: > Hi, > > Here is my w,free, top results when my linux server's network become too > slow again ( it just happened). > > w output: > 19:41:19 up 1 day, 20:07, 6 users, load average: 1.46, 1.85, 1.86 > USER TTY FROM LOGIN@ IDLE JCPU PCPU WHAT > anne :0 - Thu23 ?xdm? 26:59 0.87s > x-session-manag > root pts/2 :0.0 Thu23 19:28 56.31s 56.29s asterisk > -vvvvv > root pts/3 :0.0 Fri20 10:18 0.42s 0.42s bash > root pts/4 :0.0 Fri21 0.00s 0.80s 0.00s w > root pts/5 :0.0 Fri01 24:43 0.00s 0.00s bash > root pts/6 :0.0 Fri01 20:02 0.04s 0.04s bash nothing overly exciting here
>
> free output:
> total used free shared buffers cached
> Mem: 1028492 1009284 19208 0 4700 649756
> -/+ buffers/cache: 354828 673664
> Swap: 2650684 123532 2527152
>
this looks okay as well, about 30% is being used as cache
> top output:
> top - 19:41:37 up 1 day, 20:08, 6 users, load average: 1.33, 1.80, 1.84
> Tasks: 140 total, 3 running, 134 sleeping, 3 stopped, 0 zombie
> Cpu(s): 32.2%us, 29.0%sy, 0.0%ni, 37.1%id, 1.7%wa, 0.0%hi, 0.0%si,
> 0.0%st
> Mem: 1028492k total, 1011888k used, 16604k free, 4724k buffers
> Swap: 2650684k total, 123532k used, 2527152k free, 652132k cached
>
> PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
> 4292 root 25 0 15808 1004 856 R 98 0.1 1441:12 notify.php
do you normally see this running high when you have the network problem
?
> 6623 anne 15 0 337m 145m 26m S 24 14.5 169:28.67 firefox-bin
> 5574 anne 15 0 67260 17m 11m S 0 1.8 0:08.40 nautilus
> 5550 root 15 0 2228 1168 856 R 0 0.1 0:00.07 top
> 1 root 15 0 1944 504 476 S 0 0.0 0:01.27 init
> 2 root RT 0 0 0 0 S 0 0.0 0:00.01 migration/0
> 3 root 34 19 0 0 0 S 0 0.0 0:00.00 ksoftirqd/0
> 4 root RT 0 0 0 0 S 0 0.0 0:00.00 migration/1
> 5 root 34 19 0 0 0 S 0 0.0 0:00.00 ksoftirqd/1
> 6 root 10 -5 0 0 0 S 0 0.0 0:00.68 events/0
> 7 root 10 -5 0 0 0 S 0 0.0 0:00.01 events/1
> 8 root 10 -5 0 0 0 S 0 0.0 0:00.00 khelper
> 9 root 10 -5 0 0 0 S 0 0.0 0:00.00 kthread
> 13 root 10 -5 0 0 0 S 0 0.0 0:00.04 kblockd/0
> 14 root 19 -5 0 0 0 S 0 0.0 0:00.00 kblockd/1
> 15 root 15 -5 0 0 0 S 0 0.0 0:00.00 kacpid
> 111 root 10 -5 0 0 0 S 0 0.0 0:00.00 kseriod
>
>
> For the tcpdump, I have to apt-get install it first and then wait under the
> server's network becomes too slow again the next
> time.
> By the way, when the network becomes slow, the linux server can still run
> fine without any slowness. This Linux box is behind a router which has two
> computers ( one linux and one vista ) under its network.
my experience is when the network seems slow it because there is a lot
of data being push out it. The machine can be responsive aslong as the
program you are using doesn't talk to the network.
>
> How could I solve this problem? What worries me is that I am consistently
> having to reboot 2 - 3 days which means my server is still not ready for
> production.
when we find out what is causing the slow down we can fix the problem.
>
> Please help me.
>
> Thanks,
> Pete
can you also do a cat /proc/interrupts
A
--
"There's only one person who hugs the mothers and the widows, the wives and the
kids upon the death of their loved one. Others hug but having committed the
troops, I've got an additional responsibility to hug and that's me and I know
what it's like."
- George W. Bush
12/11/2002
Washington, DC
signature.asc
Description: Digital signature
