Re: [squid-users] High CPU usage problem on Squid 2.6 STABLE9

Hi Robert,

This box seems to be running something a little MORE than squid -
could this be a firewall perhaps?

The huge number of interrupts then seem ok for this sort of a setup -
How many Megabits/ second are you pushing through this box?!

Sorry to be a pain - I have more quesions...

Is this box really an Intel box, or does it have Opterons installed?
(hostname name = sunfire)

what does
    mpstat -P ALL 5
output ?

I can believe that you are having problems, but I think that we are
interpreting the
output from top correctly. mpstat should show this, as we will see
whether one proc
is at 100%.

Is the latency on sites in the cache? or 'new' sites?
Could this be a DNS issue? Are you running a pair of caching DNS
servers on site?
or are they based at an ISP?

Are you running as a 'transperant' proxy? or have the users entered
the proxy details per
hand or per proxy.pak.... ?

I would probably run aufs rather than diskd - but this should not
make a real difference..
You have also only configured 3Gs of cache (3x 1G)...
You may want to try disabling the disk cache altogether and see how
that works - you need to
compile with -enable-storeio=diskd,aufs,null

I would also increase my cache size to perhaps, 2G.. (How much RAM
does the machine have?)

Sorry that I am not of more help,

Cheers

Andrew

On 30/01/2007, at 6:51 PM, Robert wrote:

> Hello
>>
>> Could you provide output from:
>>
>> uname -a
> Linux sunfire 2.6.16.18 #1 SMP Sun May 28 15:28:35 CEST 2006 i686
> Intel(R) Xeon(TM) CPU 3.06GHz unknown GNU/Linux
>
>> uptime
> 18:43:17 up 34 days, 18:23, 2 users, load average: 0.19, 0.25, 0.26
>
>> cat /proc/stat
> cpu 22026640 2986463 13117260 969305961 48952710 11917074 133184102 0
> cpu0 18485803 124174 6487455 120212583 10750643 11917074 132394904 0
> cpu1 2075984 1026798 4061285 266509416 26183716 0 515363 0
> cpu2 709030 881074 1226848 291263194 6155249 0 137101 0
> cpu3 755821 954415 1341672 291320765 5863101 0 136732 0
> intr 12235872444 750861279 6848 0 0 0 0 0 0 0 18 0 0 3 0 0 13
> 12898202 15 202625149 0 2286313786 1367523516 198156182 2918435476
> 446581860 57390769 1164771169 2830308159 0 0 0 0 0 0 0 0 0 0 0 0 0
> 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
> 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
> 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
> 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
> 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
> 0 0 0 0 0 0 0 0 0 0 0 0 0
> ctxt 2023522717
> btime 1167175183
> processes 13932161
> procs_running 1
> procs_blocked 0
>
>> What sort of network card do you have installed in your system?
> 05:06.1 Ethernet controller: Intel Corporation 82546EB Gigabit
> Ethernet Controller (rev 01)
> Subsystem: Intel Corporation PRO/1000 MT Quad Port Server
> Adapter
> Flags: bus master, 66Mhz, medium devsel, latency 64, IRQ 25
> Memory at fe5e0000 (64-bit, non-prefetchable) [size=128K]
> I/O ports at 3000 [size=64]
> Capabilities: [dc] Power Management version 2
> Capabilities: [e4] Capabilities: [f0] Message Signalled
> Interrupts: 64bit+ Queue=0/0 Enable-
>
> and
>
> 04:06.0 Ethernet controller: Digital Equipment Corporation DECchip
> 21142/43 (rev 41)
> Subsystem: Digital Equipment Corporation DE500B Fast Ethernet
> Flags: bus master, medium devsel, latency 64, IRQ 22
> I/O ports at 2080 [size=128]
> Memory at fe3e0000 (32-bit, non-prefetchable) [size=1K]
> Expansion ROM at fe340000 [disabled] [size=256K]
>
>> Or what is generating sooo many interupts.
> cat /proc/interrupts
> CPU0 CPU1 CPU2 CPU3
> 0: 750957679 0 0 0 IO-APIC-edge timer
> 1: 6848 0 0 0 IO-APIC-edge i8042
> 9: 18 0 0 0 IO-APIC-level acpi
> 15: 13 0 0 0 IO-APIC-edge ide1
> 16: 12899966 0 0 0 IO-APIC-level
> uhci_hcd:usb1
> 17: 15 0 0 0 IO-APIC-level
> aic79xx
> 18: 202627844 0 0 0 IO-APIC-level
> aic79xx
> 19: 0 0 0 0 IO-APIC-level
> uhci_hcd:usb2
> 20: 2286707542 0 0 0 IO-APIC-level eth0
> 21: 1367807235 0 0 0 IO-APIC-level eth1
> 22: 198760483 0 0 0 IO-APIC-level
> eth2, eth8
> 23: 2918917363 0 0 0 IO-APIC-level
> eth3, eth9
> 24: 446646975 0 0 0 IO-APIC-level eth4
> 25: 57410734 0 0 0 IO-APIC-level eth5
> 26: 1165863360 0 0 0 IO-APIC-level eth6
> 27: 2830951047 0 0 0 IO-APIC-level eth7
> NMI: 0 0 0 0
> LOC: 750980943 750980887 750980721 750980748
> ERR: 0
> MIS: 0
>
> all cards from eth0-eth6 are used eth7 and eth8 are not used and
> disabled.
>
>
> Regards
> Robert
>
Received on Tue Jan 30 2007 - 11:47:57 MST