RE: VTI hitting the blocked state (was RE:[PATCH][RESEND]RE:[Xen-ia64-devel] [PATCH 0/6] Add fullevtchnmechanism forxen/ia64)

["Tian, Kevin" <kevin.tian@xxxxxxxxx>]

>From: Alex Williamson [mailto:alex.williamson@xxxxxx]
>Sent: 2006年5月25日 10:26
>
>On Thu, 2006-05-25 at 10:04 +0800, Tian, Kevin wrote:
>>
>> VTI network has not been tested aggressively and thus your
>observation
>> is new and we'll take a look.
>>
>> I'll try again by following your steps. As a confirmation required from
>you:
>>      - Simple dom0+domVTI can trigger the block issue. DomU can
>> accelerate
>
>Correct
>
>>      - dom0 and domVTI are running on different processors.
>
>Correct, I disabled threads and had dom0 running on cpu0 and domVTI
>running on cpu3 (w/ affinity of any cpu. ie it was the default
>placement)
>>      - can that happen steadily? If not, how about the frequency.
>
>Yes, happened every time I exercised domVTI.
>
>>      - which test case do you propose to try? 'wget' or KB. Previously I
>> always try with wget.
>
>wget hit it much faster, within a few tries pulling a 512MB file.  The
>kernel build ran for maybe 30 minutes (very roughly).  Thanks,
>
>       Alex
>

OK, previous my test is based on a 128MB file, but that shouldn't matter 
since both copied to /dev/null. Anyway, I'll create a bigger file to see 
whether to reproduce.

Thanks,
Kevin

_______________________________________________
Xen-ia64-devel mailing list
Xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-ia64-devel