Messages in this thread | | | Date | Wed, 16 Jul 2014 17:49:37 -0700 (PDT) | From | David Rientjes <> | Subject | Re: [patch v2] mm, tmp: only collapse hugepages to nodes with affinity for zone_reclaim_mode |
| |
On Wed, 16 Jul 2014, Vlastimil Babka wrote:
> >> @@ -2545,6 +2571,11 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, > >> * hit record. > >> */ > >> node = page_to_nid(page); > >> + if (node != last_node) { > >> + if (khugepaged_scan_abort(node)) > >> + goto out_unmap; > > > > Nitpick: How about not break the loop but only reset the related > > khugepaged_node_load[] to zero. E.g. modify khugepaged_scan_abort() like > > this: > > if (node_distance(nid, i) > RECLAIM_DISTANCE) > > khugepaged_node_load[i] = 0; > > > > By this way, we may have a chance to find a more suitable node. > > Hm theoretically there might be a suitable node, but this approach wouldn't > work. By resetting it to zero you forget that there ever was node 'i'. If there > is no more base page from node 'i', the load remains zero and the next call with > 'nid' will think that 'nid' is OK. >
Right, the suggestion is wrong because we do not want to ever collapse to a node when the distance from the source page is > RECLAIM_DISTANCE, that's the entire point of the patch.
| |