[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] Question Also regarding interrupt balancing




On 22 May 2006, at 17:43, harish wrote:

Hi,
Was doing some netperf tests and noticed that all the interrupts (for network) were being serviced by pcp0 although dom0 was configured to use all the pcpus [4vcpus].
 Questions:
1) Is there a way dom0 can be configured to process the interrupts using 4pcpus instead of just one?

Running irqbalance daemon in dom0 should do the trick. If there's no other load in domain0 though, irqbalance may decide not to change irq affinity. There's no way to do fine-grained interrupt balancing (e.g., round-robin interrupts).

2) What is the recommended scheduling policy for a network I/O intensive workload?

If delivering to a domU, you want dom0 and domU running on different CPUs or CPU will be the bottleneck.

 -- Keir

 Sample output:

 cat /proc/xen/interrupts

  cat /proc/interrupts
            CPU0       CPU1       CPU2       CPU3
  1:          8          0          0          0        Phys-irq  i8042
   8:          1          0          0          0        Phys-irq  rtc
   9:          0          0          0          0        Phys-irq  acpi
 11:          0          0          0          0        Phys-irq  ohci_hcd:usb1  12:        105          0          0          0        Phys-irq  i8042
  14:     302432          0          0          0        Phys-irq  ide0
 16:        375          0          0          0        Phys-irq  aic7xxx  17:      34719          0          0          0        Phys-irq  cciss0
  18:      53158          0          0          0        Phys-irq  eth0
 19:          2          0          0          0        Phys-irq  peth1  20:    1062076          0          0          0        Phys-irq  peth2   <<< --------Was using this  21:      25189          0          0          0        Phys-irq  peth3  22:      18846          0          0          0        Phys-irq  peth4
  23:      18682          0          0          0        Phys-irq  eth5
256:    1456444          0          0          0     Dynamic-irq  timer0 257:      52873          0          0          0     Dynamic-irq  resched0 258:        282          0          0          0     Dynamic-irq  callfunc0 259:          0       7935          0          0     Dynamic-irq  resched1 260:          0      33665          0          0     Dynamic-irq  callfunc1 261:          0     508258          0          0     Dynamic-irq  timer1 262:          0          0       3827          0     Dynamic-irq  resched2 263:          0          0      33835          0     Dynamic-irq  callfunc2 264:          0          0     390316          0     Dynamic-irq  timer2 265:          0          0          0      43953     Dynamic-irq  resched3 266:          0          0          0      33870     Dynamic-irq  callfunc3 267:          0          0          0     311447     Dynamic-irq  timer3 268:       5091          0          0          0     Dynamic-irq  xenbus 269:          0          0          0          0     Dynamic-irq  console 270:      31532          0          0          0     Dynamic-irq  blkif-backend 271:    1107498          0          0          0     Dynamic-irq  vif7.0
 NMI:          0          0          0          0
 LOC:          0          0          0          0
 ERR:          0
 MIS:          0

Ran multiple while loops to confirm that dom0 can use all the 4pcpus if required. And so believe it must be something to do with the way the interrupts are being handled.

 Thanks in advance,
 hmv

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.