From 80b18dfa53bbb03085eba6401f5d29dad49205b7 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 6 Jul 2017 15:37:08 -0700 Subject: [PATCH] ksm: optimize refile of stable_node_dup at the head of the chain If a candidate stable_node_dup has been found and it can accept further merges it can be refiled to the head of the list to speedup next searches without altering which dup is found and how the dups accumulate in the chain. We already refiled it back to the head in the prune_stale_stable_nodes case, but we didn't refile it if not pruning (which is more common). And we also refiled it when it was already at the head which is unnecessary (in the prune_stale_stable_nodes case, nr > 1 means there's more than one dup in the chain, it doesn't mean it's not already at the head of the chain). The stable_node_chain list is single threaded and there's no SMP locking contention so it should be faster to refile it to the head of the list also if prune_stale_stable_nodes is false. Profiling shows the refile happens 1.9% of the time when a dup is found with a max_page_sharing limit setting of 3 (with max_page_sharing of 2 the refile never happens of course as there's never space for one more merge) which is reasonably low. At higher max_page_sharing values it should be much less frequent. This is just an optimization. Link: http://lkml.kernel.org/r/20170518173721.22316-4-aarcange@redhat.com Signed-off-by: Andrea Arcangeli Cc: Evgheni Dereveanchin Cc: Andrey Ryabinin Cc: Petr Holasek Cc: Hugh Dickins Cc: Arjan van de Ven Cc: Davidlohr Bueso Cc: Gavin Guo Cc: Jay Vosburgh Cc: Mel Gorman Cc: Dan Carpenter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/ksm.c | 35 +++++++++++++++++++++++------------ 1 file changed, 23 insertions(+), 12 deletions(-) diff --git a/mm/ksm.c b/mm/ksm.c index f4bd1e761e3f..4dc92f138786 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -1367,13 +1367,14 @@ struct page *stable_node_dup(struct stable_node **_stable_node_dup, put_page(_tree_page); } - /* - * nr is relevant only if prune_stale_stable_nodes is true, - * otherwise we may break the loop at nr == 1 even if there - * are multiple entries. - */ - if (prune_stale_stable_nodes && found) { - if (nr == 1) { + if (found) { + /* + * nr is counting all dups in the chain only if + * prune_stale_stable_nodes is true, otherwise we may + * break the loop at nr == 1 even if there are + * multiple entries. + */ + if (prune_stale_stable_nodes && nr == 1) { /* * If there's not just one entry it would * corrupt memory, better BUG_ON. In KSM @@ -1404,12 +1405,22 @@ struct page *stable_node_dup(struct stable_node **_stable_node_dup, * time. */ stable_node = NULL; - } else if (__is_page_sharing_candidate(found, 1)) { + } else if (stable_node->hlist.first != &found->hlist_dup && + __is_page_sharing_candidate(found, 1)) { /* - * Refile our candidate at the head - * after the prune if our candidate - * can accept one more future sharing - * in addition to the one underway. + * If the found stable_node dup can accept one + * more future merge (in addition to the one + * that is underway) and is not at the head of + * the chain, put it there so next search will + * be quicker in the !prune_stale_stable_nodes + * case. + * + * NOTE: it would be inaccurate to use nr > 1 + * instead of checking the hlist.first pointer + * directly, because in the + * prune_stale_stable_nodes case "nr" isn't + * the position of the found dup in the chain, + * but the total number of dups in the chain. */ hlist_del(&found->hlist_dup); hlist_add_head(&found->hlist_dup, -- 2.20.1