irqbalance on HT capable PE4600?

jason andrade jason at rtfmconsult.com
Sat Oct 18 17:20:00 CDT 2003


On Sat, 18 Oct 2003, Arjan van de Ven wrote:

i'm continuing to CC this to the PE list as i assume it'll be useful
for someone down the track for performance tuning information assuming
Arjan continues to reply :-)

> First of all; several network cards have ways of
> reducing the irq rate via so called interrupt mitigation; this is not
> always enabled since it CAN reduce network performance
> on low-use networking.

the current network is gigE which is pushing around 100-140Mbit/sec on
an Intel Pro/1000.  it is anticipated this may need to double over the
next year.  my own testing of the pro/1000 is that you can achieve full
line rate gigE on the card (if the machine is doing nothing else) so
i'm pretty confident it can handle 300-400Mbit/sec in normal operation.
however i need to try to do some more work to see why the current
config spends 70-80% of time in 'system' - i assume a chunk of that
is the nfsd but wanted to make sure there wasn't other things i'd
been overlooking previously (like the irq rate)

> For example, e1000 has several module parameters to enable this:
> parm:        TxIntDelay 	description "Transmit Interrupt Delay"
> parm:        TxAbsIntDelay 	description "Transmit Absolute Interrupt Delay"
> parm:        RxIntDelay 	description "Receive Interrupt Delay"
> parm:        RxAbsIntDelay 	description "Receive Absolute Interrupt Delay"
>
> setting these values to > 0 (eg somewhere between 2 and 10) will
> probably reduce your rate of interrupts quite significant (and
> increase performance due to better irq grouping)

the server in question is a NFS server so i'd definitely like to
improve performance (but not obviously at the cost of serving
less bytes to the front end boxes).  i'll do some testing with
the above.

> Another thing you can do is install the RHL8 erratum or RHL9
> kernel-utils rpm and make sure the irqbalance service is started during
> boot (default for RHL9, the RHL8 erratum defaults to off)

(i assume the values below have wrapped)

  8:17am  up 59 days, 18:59,  5 users,  load average: 11.25, 11.44, 12.11

           CPU0       CPU1
  0: 1322107066 1322871970    IO-APIC-edge  timer
  1:        273        264    IO-APIC-edge  keyboard
  2:          0          0          XT-PIC  cascade
  8:          0          1    IO-APIC-edge  rtc
 16:  253487196  253651272   IO-APIC-level  eth0
 20:  799452491  799875894   IO-APIC-level  qla2200
 22: 2366882687 2368370608   IO-APIC-level  qla2200
 24: 1316729851 1317548294   IO-APIC-level  qla2200
 26: 1147601730 1148380357   IO-APIC-level  eth2
 28:  959647645 1005132173   IO-APIC-level  eth1
 30:       2022       1991   IO-APIC-level  aic7xxx
 31:  518955144  519175867   IO-APIC-level  aacraid
NMI:          0          0
LOC: 2645057853 2645057854
ERR:          0
MIS:          0

i am looking at replacing the current box (PE2400 w/ 2 933 P3s w/ 1G ram w/ RH7.3)
with a dual xeon P4/2.4 w/ 4G of ram and using RHEL 3 on it.

regards,

-jason




More information about the Linux-PowerEdge mailing list