Re: [MMTests] IO metadata on XFS

On Mon, Jul 02, 2012 at 08:35:16PM +0100, Mel Gorman wrote:

...

<SNIP>

It was obvious very quickly that there were two distinct regression so I ran two bisections. One led to a XFS and the other led to an i915 patch that enables RC6 to reduce power usage.

[c999a223: xfs: introduce an allocation workqueue] [aa464191: drm/i915: enable plain RC6 on Sandy Bridge by default]

gdm was running on the machine so i915 would have been in use.

Bah, more PEBKAC. gdm was *not* running on this machine. i915 is loaded but X is not.