Subject: [merged] vmscan-memcg-always-use-swappiness-of-the-reclaimed-memcg-swappiness-and-oom_control.patch removed from -mm tree To: mhocko@xxxxxxx,hannes@xxxxxxxxxxx,hughd@xxxxxxxxxx,tj@xxxxxxxxxx,mm-commits@xxxxxxxxxxxxxxx From: akpm@xxxxxxxxxxxxxxxxxxxx Date: Mon, 09 Jun 2014 12:40:21 -0700 The patch titled Subject: vmscan: memcg: always use swappiness of the reclaimed memcg has been removed from the -mm tree. Its filename was vmscan-memcg-always-use-swappiness-of-the-reclaimed-memcg-swappiness-and-oom_control.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Michal Hocko <mhocko@xxxxxxx> Subject: vmscan: memcg: always use swappiness of the reclaimed memcg Memory reclaim always uses swappiness of the reclaim target memcg (origin of the memory pressure) or vm_swappiness for global memory reclaim. This behavior was consistent (except for difference between global and hard limit reclaim) because swappiness was enforced to be consistent within each memcg hierarchy. After "mm: memcontrol: remove hierarchy restrictions for swappiness and oom_control" each memcg can have its own swappiness independent of hierarchical parents, though, so the consistency guarantee is gone. This can lead to an unexpected behavior. Say that a group is explicitly configured to not swapout by memory.swappiness=0 but its memory gets swapped out anyway when the memory pressure comes from its parent with a It is also unexpected that the knob is meaningless without setting the hard limit which would trigger the reclaim and enforce the swappiness. There are setups where the hard limit is configured higher in the hierarchy by an administrator and children groups are under control of somebody else who is interested in the swapout behavior but not necessarily about the memory limit. >From a semantic point of view swappiness is an attribute defining anon vs. file proportional scanning of LRU which is memcg specific (unlike charges which are propagated up the hierarchy) so it should be applied to the particular memcg's LRU regardless where the memory pressure comes from. This patch removes vmscan_swappiness() and stores the swappiness into the scan_control structure. mem_cgroup_swappiness is then used to provide the correct value before shrink_lruvec is called. The global vm_swappiness is used for the root memcg. [hughd@xxxxxxxxxx: oopses immediately when booted with cgroup_disable=memory] Signed-off-by: Michal Hocko <mhocko@xxxxxxx> Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx> Cc: Tejun Heo <tj@xxxxxxxxxx> Signed-off-by: Hugh Dickins <hughd@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- Documentation/cgroups/memory.txt | 13 ++++++------- mm/memcontrol.c | 2 +- mm/vmscan.c | 18 ++++++++---------- 3 files changed, 15 insertions(+), 18 deletions(-) diff -puN Documentation/cgroups/memory.txt~vmscan-memcg-always-use-swappiness-of-the-reclaimed-memcg-swappiness-and-oom_control Documentation/cgroups/memory.txt --- a/Documentation/cgroups/memory.txt~vmscan-memcg-always-use-swappiness-of-the-reclaimed-memcg-swappiness-and-oom_control +++ a/Documentation/cgroups/memory.txt @@ -540,14 +540,13 @@ Note: 5.3 swappiness -Similar to /proc/sys/vm/swappiness, but only affecting reclaim that is -triggered by this cgroup's hard limit. The tunable in the root cgroup -corresponds to the global swappiness setting. +Overrides /proc/sys/vm/swappiness for the particular group. The tunable +in the root cgroup corresponds to the global swappiness setting. -Please note that unlike the global swappiness, memcg knob set to 0 -really prevents from any swapping even if there is a swap storage -available. This might lead to memcg OOM killer if there are no file -pages to reclaim. +Please note that unlike during the global reclaim, limit reclaim +enforces that 0 swappiness really prevents from any swapping even if +there is a swap storage available. This might lead to memcg OOM killer +if there are no file pages to reclaim. 5.4 failcnt diff -puN mm/memcontrol.c~vmscan-memcg-always-use-swappiness-of-the-reclaimed-memcg-swappiness-and-oom_control mm/memcontrol.c --- a/mm/memcontrol.c~vmscan-memcg-always-use-swappiness-of-the-reclaimed-memcg-swappiness-and-oom_control +++ a/mm/memcontrol.c @@ -1550,7 +1550,7 @@ static unsigned long mem_cgroup_margin(s int mem_cgroup_swappiness(struct mem_cgroup *memcg) { /* root ? */ - if (!css_parent(&memcg->css)) + if (mem_cgroup_disabled() || !css_parent(&memcg->css)) return vm_swappiness; return memcg->swappiness; diff -puN mm/vmscan.c~vmscan-memcg-always-use-swappiness-of-the-reclaimed-memcg-swappiness-and-oom_control mm/vmscan.c --- a/mm/vmscan.c~vmscan-memcg-always-use-swappiness-of-the-reclaimed-memcg-swappiness-and-oom_control +++ a/mm/vmscan.c @@ -83,6 +83,9 @@ struct scan_control { /* Scan (total_size >> priority) pages at once */ int priority; + /* anon vs. file LRUs scanning "ratio" */ + int swappiness; + /* * The memory cgroup that hit its limit and as a result is the * primary target of this reclaim invocation. @@ -1845,13 +1848,6 @@ static unsigned long shrink_list(enum lr return shrink_inactive_list(nr_to_scan, lruvec, sc, lru); } -static int vmscan_swappiness(struct scan_control *sc) -{ - if (global_reclaim(sc)) - return vm_swappiness; - return mem_cgroup_swappiness(sc->target_mem_cgroup); -} - enum scan_balance { SCAN_EQUAL, SCAN_FRACT, @@ -1912,7 +1908,7 @@ static void get_scan_count(struct lruvec * using the memory controller's swap limit feature would be * too expensive. */ - if (!global_reclaim(sc) && !vmscan_swappiness(sc)) { + if (!global_reclaim(sc) && !sc->swappiness) { scan_balance = SCAN_FILE; goto out; } @@ -1922,7 +1918,7 @@ static void get_scan_count(struct lruvec * system is close to OOM, scan both anon and file equally * (unless the swappiness setting disagrees with swapping). */ - if (!sc->priority && vmscan_swappiness(sc)) { + if (!sc->priority && sc->swappiness) { scan_balance = SCAN_EQUAL; goto out; } @@ -1965,7 +1961,7 @@ static void get_scan_count(struct lruvec * With swappiness at 100, anonymous and file have the same priority. * This scanning priority is essentially the inverse of IO cost. */ - anon_prio = vmscan_swappiness(sc); + anon_prio = sc->swappiness; file_prio = 200 - anon_prio; /* @@ -2265,6 +2261,7 @@ static void shrink_zone(struct zone *zon lruvec = mem_cgroup_zone_lruvec(zone, memcg); + sc->swappiness = mem_cgroup_swappiness(memcg); shrink_lruvec(lruvec, sc); /* @@ -2731,6 +2728,7 @@ unsigned long mem_cgroup_shrink_node_zon .may_swap = !noswap, .order = 0, .priority = 0, + .swappiness = mem_cgroup_swappiness(memcg), .target_mem_cgroup = memcg, }; struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg); _ Patches currently in -mm which might be from mhocko@xxxxxxx are origin.patch pagewalk-update-page-table-walker-core.patch pagewalk-add-walk_page_vma.patch smaps-redefine-callback-functions-for-page-table-walker.patch clear_refs-redefine-callback-functions-for-page-table-walker.patch pagemap-redefine-callback-functions-for-page-table-walker.patch numa_maps-redefine-callback-functions-for-page-table-walker.patch memcg-redefine-callback-functions-for-page-table-walker.patch arch-powerpc-mm-subpage-protc-use-walk_page_vma-instead-of-walk_page_range.patch pagewalk-remove-argument-hmask-from-hugetlb_entry.patch mempolicy-apply-page-table-walker-on-queue_pages_range.patch linux-next.patch memcg-mm-introduce-lowlimit-reclaim.patch memcg-mm-introduce-lowlimit-reclaim-fix.patch memcg-mm-introduce-lowlimit-reclaim-fix2patch.patch memcg-allow-setting-low_limit.patch memcg-doc-clarify-global-vs-limit-reclaims.patch memcg-doc-clarify-global-vs-limit-reclaims-fix.patch memcg-document-memorylow_limit_in_bytes.patch vmscan-memcg-check-whether-the-low-limit-should-be-ignored.patch memcg-deprecate-memoryforce_empty-knob.patch memcg-deprecate-memoryforce_empty-knob-fix.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html