Andrea Arcangeli wrote:
On Mon, Aug 18, 2008 at 05:04:25PM -0500, Anthony Liguori wrote:
+if (!kvm_enabled() || !qemu_kvm_has_mmu_notifiers())
+madvise(addr, TARGET_PAGE_SIZE,
+deflate ? MADV_WILLNEED : MADV_DONTNEED);
The check was reversed so madvise wasn'
On Mon, Aug 18, 2008 at 05:04:25PM -0500, Anthony Liguori wrote:
> +if (!kvm_enabled() || !qemu_kvm_has_mmu_notifiers())
> +madvise(addr, TARGET_PAGE_SIZE,
> +deflate ? MADV_WILLNEED : MADV_DONTNEED);
The check was reversed so madvise wasn't invoked in the first place i
Marcelo Tosatti wrote:
Hi Anthony,
On Mon, Aug 18, 2008 at 05:04:25PM -0500, Anthony Liguori wrote:
Attached is an updated migration patch. It does not appear, however,
that madvise() is triggering discarding of pages even with an
MMU-notifier enabled kernel. I take it that this is beca
Hi Anthony,
On Mon, Aug 18, 2008 at 05:04:25PM -0500, Anthony Liguori wrote:
> Attached is an updated migration patch. It does not appear, however,
> that madvise() is triggering discarding of pages even with an
> MMU-notifier enabled kernel. I take it that this is because we're still
> ho
Attached is an updated migration patch. It does not appear, however,
that madvise() is triggering discarding of pages even with an
MMU-notifier enabled kernel. I take it that this is because we're still
holding a reference count to the page when it is in the shadow page
table? Any ETA on whe