Hi Adrian,
Here's a few lines of vmstat output..
Taken from when it were serving 900+ req/sec.
[root]# vmstat 1 100
   procs                      memory    swap          io     system
cpu
 r  b  w   swpd   free   buff  cache  si  so    bi    bo   in    cs  us  sy
id
 1  0  1   4344 241360  73008 581044   0   0     0     0 18347   218  35
23  41
 1  0  1   4344 241368  73008 581036   0   0     0     0 18384   225  31
29  40
 1  0  1   4344 241340  73008 581052   0   0     0   812 18344   255  30
28  41
 1  0  1   4344 241256  73008 581052   0   0     0     0 18152   347  30
27  43
 0  0  1   4344 241180  73008 581084   0   0    16     0 18222   245  38
20  43
 1  0  0   4344 241044  73008 581084   0   0     0     0 18212   232  38
20  42
 1  0  1   4344 241040  73008 581088   0   0     0     0 18245   368  30
27  43
 1  0  1   4344 241040  73008 581088   0   0     0   588 18232   282  34
25  41
 1  0  0   4344 241028  73008 581088   0   0     0     0 18134   398  37
24  40
 1  0  1   4344 241020  73008 581096   0   0     0     0 18322   327  33
25  42
 1  0  1   4344 240972  73008 581108   0   0     0     0 18465   306  38
20  42
 2  0  1   4344 240972  73008 581108   0   0     0     0 18028   400  32
26  41
 1  0  1   4344 240972  73008 581108   0   0     0   780 18207   342  34
24  42
 2  0  1   4344 240968  73008 581112   0   0     0     0 18000   428  37
21  42
 1  0  1   4344 240960  73008 581120   0   0     0     0 18059   335  40
-------------| This mail has been sent to you by: |------------
Klavs Klavsen, IT-coordinator and Systems Administrator at
Metropol Online - http://www.metropol.dk
Tlf. 33752700, Fax 33752720, Email ktk@metropol.dk
Private-  Email klavs@klavsen.net - http://www.vsen.dk
--------------------[ I believe that... ]-----------------------
It is a myth that people resist change. People resist what other
people make them do, not what they themselves choose to do...
That's why companies that innovate successfully year after year
seek their peopl's ideas, let them initiate new projects and
encourage more experiments.            -- Rosabeth Moss Kanter
                                                                                                                       
                    Adrian Chadd                                                                                       
                    <adrian@squid-        Til:    Klavs Klavsen <ktk@metropol.dk>                                      
                    cache.org>            cc:     squid-users@squid-cache.org                                          
                                          Vedr.:  Re: [squid-users] Vedr.: Re: [squid-users] Big IO load.. with only   
                    13-11-2001            few files.. how come?                                                        
                    04:16                                                                                              
                                                                                                                       
                                                                                                                       
On Mon, Nov 12, 2001, Klavs Klavsen wrote:
>
> I read it wrong..
>
> it's not the IO that was heavily loaded.. (at approx 18.000 pr. sec) - it
> was interrupts..
>
> Do any of you know how many I can expect - before the machine stalls..
and
> what I can do to increase the ability to handle more interrupts?
>
> btw. it's a linux-2.4 kernel.
>
> I hope you have some tuning tips for me..
>
> and to Torsten.. thanks for all your help so far..
>
Uhm, if you're using iDE anywhere, make sure you've turned DMA on.
That's burnt me a few times when doing squid work under Linux.
A few lines of vmstat output when the cache is heavily loaded will
tell us where the bottleneck may be.
Adrian
Received on Tue Nov 13 2001 - 00:01:35 MST
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 17:04:04 MST