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

Re: [Xen-devel] [PATCH 05 of 11 v4] xen: allow for explicitly specifying node-affinity



>>> On 15.03.13 at 03:30, Dario Faggioli <dario.faggioli@xxxxxxxxxx> wrote:
> --- a/xen/include/xen/sched.h
> +++ b/xen/include/xen/sched.h
> @@ -360,8 +360,12 @@ struct domain
>      /* Various mem_events */
>      struct mem_event_per_domain *mem_event;
>  
> -    /* Currently computed from union of all vcpu cpu-affinity masks. */
> +    /*
> +     * Can be specified by the user. If that is not the case, it is
> +     * computed from the union of all the vcpu cpu-affinity masks.
> +     */
>      nodemask_t node_affinity;
> +    int auto_node_affinity;

bool_t, and put in a suitable slot without adding much extra
padding (if available).

Jan

>      unsigned int last_alloc_node;
>      spinlock_t node_affinity_lock;
>  };



_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel


 


Rackspace

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