On Wed, 2015-03-11 at 15:01 +, George Dunlap wrote:
> On 03/09/2015 04:49 PM, Dario Faggioli wrote:
> > 93be8285 ("update domU's node-affinity on the cpupool_unassign_cpu()
> > path") does the right thing, but does it too early. In fact, it
> > is necessary to call domain_update_node_affinity(
On 03/09/2015 04:49 PM, Dario Faggioli wrote:
> 93be8285 ("update domU's node-affinity on the cpupool_unassign_cpu()
> path") does the right thing, but does it too early. In fact, it
> is necessary to call domain_update_node_affinity() when a pCPU is
> removed from a cpupool, but that must happen
On Mon, 2015-03-09 at 17:49 +0100, Dario Faggioli wrote:
> 93be8285 ("update domU's node-affinity on the cpupool_unassign_cpu()
> path") does the right thing, but does it too early. In fact, it
> is necessary to call domain_update_node_affinity() when a pCPU is
> removed from a cpupool, but that m
93be8285 ("update domU's node-affinity on the cpupool_unassign_cpu()
path") does the right thing, but does it too early. In fact, it
is necessary to call domain_update_node_affinity() when a pCPU is
removed from a cpupool, but that must happen after the pCPU is
really gone from there.
More specif