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

Re: [Xen-devel] [PATCH 0 of 5] xentrace: non-contiguous allocation of per-cpu buffer

On Fri, May 06, Olaf Hering wrote:

> For some reason its not possible to allocate more than 128MB with repeated
> calls to alloc_xen_heappage(). Any ideas how to reach the theoretical limit of
> 256MB per cpu?

The dom0 needs to be ballooned down to make room for the tracebuffers.

> Also the error path in alloc_trace_bufs() needs a fix, I always run into the
> assert there.

Beside this issue, the checks in the bogus() function trigger with a
256MB per-cpu buffer.

I will revisit the series and post a new version once I have fixes for
these issues.


Xen-devel mailing list



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