[Xen-devel] RE: [PATCH] Xenoprof passive domain support

["Yang, Xiaowei" <xiaowei.yang@xxxxxxxxx>]

Resent the patch due to cset 9866 change (Rename *GUEST_HANDLE to 
*XEN_GUEST_HANDLE).
Thanks,
xiaowei


>-----Original Message-----
>From: Yang, Xiaowei
>Sent: 2006年4月28日 15:59
>To: 'Santos, Jose Renato G'
>Cc: 'xen-devel@xxxxxxxxxxxxxxxxxxx'
>Subject: [PATCH] Xenoprof passive domain support
>
>Hi Renato,
>This patch is to add Xenoprof passive domain support in SMP environment.
>Basically:
>- It allocates per vcpu buffers for passive domain and maps them into primary
>domain's space.
>- When primary domain gets sampled and triggers virq, its kernel module will
>handle passive domain' samples besides its owns. There is potential buffer
>overflow if passive is very busy while primary is idle. The simple workaround
>is to allocate a rather big buffer for passive. For now it works fine. A better
>way is to notify primary when passive buffer exceeds the threshold.
>- When oprofile gets passive domain samples, it splits them in to 3 parts by
>PC ranges pre-definition: xen/kernel/application and maps the first two into
>functions. The oprofile version is a little old, for the patch was made last
>August.
>
>The main usage is to use Xenoprof to profile HVM domain as passive domain, 
>which
>provides enough information for low level performance tuning while no change
>in HVM is needed.
>
>Thanks,
>Xiaowei

Attachment: xenoprof.patch
Description: xenoprof.patch

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