[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [Xen-devel] [PATCH v3 01/10] page-alloc: Clamp get_free_buddy() to online nodes
d->node_affinity defaults to NODE_MASK_ALL which has bits set outside of node_online_map. This in turn causes the loop in get_free_buddy() to waste effort iterating over offline nodes. Always clamp d->node_affinity to node_online_map when in use. Signed-off-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx> Acked-by: Jan Beulich <jbeulich@xxxxxxxx> --- CC: Jan Beulich <JBeulich@xxxxxxxx> CC: Wei Liu <wl@xxxxxxx> CC: Roger Pau Monné <roger.pau@xxxxxxxxxx> CC: Stefano Stabellini <sstabellini@xxxxxxxxxx> CC: Julien Grall <julien.grall@xxxxxxx> CC: George Dunlap <george.dunlap@xxxxxxxxxxxxx> v3: * Rebase to before the nodemask API cleanup, to make it easier to backport. v2: * Rebase over the nodemask API change, and implement with a single nodes_and() --- xen/common/page_alloc.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/xen/common/page_alloc.c b/xen/common/page_alloc.c index 44a72d0b19..efa437c7df 100644 --- a/xen/common/page_alloc.c +++ b/xen/common/page_alloc.c @@ -811,11 +811,18 @@ static struct page_info *get_free_buddy(unsigned int zone_lo, const struct domain *d) { nodeid_t first, node = MEMF_get_node(memflags), req_node = node; - nodemask_t nodemask = d ? d->node_affinity : node_online_map; + nodemask_t nodemask = node_online_map; unsigned int j, zone, nodemask_retry = 0; struct page_info *pg; bool use_unscrubbed = (memflags & MEMF_no_scrub); + /* + * d->node_affinity is our preferred allocation set if provided, but it + * may have bit set outside of node_online_map. Clamp it. + */ + if ( d ) + nodes_and(nodemask, nodemask, d->node_affinity); + if ( node == NUMA_NO_NODE ) { if ( d != NULL ) -- 2.11.0 _______________________________________________ Xen-devel mailing list Xen-devel@xxxxxxxxxxxxxxxxxxxx https://lists.xenproject.org/mailman/listinfo/xen-devel
|
Lists.xenproject.org is hosted with RackSpace, monitoring our |