summaryrefslogtreecommitdiff
path: root/mm/vmscan.c
diff options
context:
space:
mode:
authorDan Schatzberg <schatzberg.dan@gmail.com>2024-01-03 08:48:37 -0800
committerAndrew Morton <akpm@linux-foundation.org>2024-07-04 18:05:55 -0700
commit68cd9050d871e4db5433420b5ceb32f5512d18bc (patch)
treee90535e0d6599db132252100e6e643ffdaffbc67 /mm/vmscan.c
parent410abb20acaea9679fc1b2276d47e70fba331451 (diff)
mm: add swappiness= arg to memory.reclaim
Allow proactive reclaimers to submit an additional swappiness=<val> argument to memory.reclaim. This overrides the global or per-memcg swappiness setting for that reclaim attempt. For example: echo "2M swappiness=0" > /sys/fs/cgroup/memory.reclaim will perform reclaim on the rootcg with a swappiness setting of 0 (no swap) regardless of the vm.swappiness sysctl setting. Userspace proactive reclaimers use the memory.reclaim interface to trigger reclaim. The memory.reclaim interface does not allow for any way to effect the balance of file vs anon during proactive reclaim. The only approach is to adjust the vm.swappiness setting. However, there are a few reasons we look to control the balance of file vs anon during proactive reclaim, separately from reactive reclaim: * Swapout should be limited to manage SSD write endurance. In near-OOM situations we are fine with lots of swap-out to avoid OOMs. As these are typically rare events, they have relatively little impact on write endurance. However, proactive reclaim runs continuously and so its impact on SSD write endurance is more significant. Therefore it is desireable to control swap-out for proactive reclaim separately from reactive reclaim * Some userspace OOM killers like systemd-oomd[1] support OOM killing on swap exhaustion. This makes sense if the swap exhaustion is triggered due to reactive reclaim but less so if it is triggered due to proactive reclaim (e.g. one could see OOMs when free memory is ample but anon is just particularly cold). Therefore, it's desireable to have proactive reclaim reduce or stop swap-out before the threshold at which OOM killing occurs. In the case of Meta's Senpai proactive reclaimer, we adjust vm.swappiness before writes to memory.reclaim[2]. This has been in production for nearly two years and has addressed our needs to control proactive vs reactive reclaim behavior but is still not ideal for a number of reasons: * vm.swappiness is a global setting, adjusting it can race/interfere with other system administration that wishes to control vm.swappiness. In our case, we need to disable Senpai before adjusting vm.swappiness. * vm.swappiness is stateful - so a crash or restart of Senpai can leave a misconfigured setting. This requires some additional management to record the "desired" setting and ensure Senpai always adjusts to it. With this patch, we avoid these downsides of adjusting vm.swappiness globally. [1]https://www.freedesktop.org/software/systemd/man/latest/systemd-oomd.service.html [2]https://github.com/facebookincubator/oomd/blob/main/src/oomd/plugins/Senpai.cpp#L585-L598 Link: https://lkml.kernel.org/r/20240103164841.2800183-3-schatzberg.dan@gmail.com Signed-off-by: Dan Schatzberg <schatzberg.dan@gmail.com> Suggested-by: Yosry Ahmed <yosryahmed@google.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: David Rientjes <rientjes@google.com> Acked-by: Chris Li <chrisl@kernel.org> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Shakeel Butt <shakeel.butt@linux.dev> Cc: Shakeel Butt <shakeelb@google.com> Cc: Tejun Heo <tj@kernel.org> Cc: Yue Zhao <findns94@gmail.com> Cc: Zefan Li <lizefan.x@bytedance.com> Cc: Nhat Pham <nphamcs@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm/vmscan.c')
-rw-r--r--mm/vmscan.c25
1 files changed, 22 insertions, 3 deletions
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 91f99558650d..3d4c681c6d40 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -92,6 +92,11 @@ struct scan_control {
unsigned long anon_cost;
unsigned long file_cost;
+#ifdef CONFIG_MEMCG
+ /* Swappiness value for proactive reclaim. Always use sc_swappiness()! */
+ int *proactive_swappiness;
+#endif
+
/* Can active folios be deactivated as part of reclaim? */
#define DEACTIVATE_ANON 1
#define DEACTIVATE_FILE 2
@@ -236,6 +241,13 @@ static bool writeback_throttling_sane(struct scan_control *sc)
#endif
return false;
}
+
+static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg)
+{
+ if (sc->proactive && sc->proactive_swappiness)
+ return *sc->proactive_swappiness;
+ return mem_cgroup_swappiness(memcg);
+}
#else
static bool cgroup_reclaim(struct scan_control *sc)
{
@@ -251,6 +263,11 @@ static bool writeback_throttling_sane(struct scan_control *sc)
{
return true;
}
+
+static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg)
+{
+ return READ_ONCE(vm_swappiness);
+}
#endif
static void set_task_reclaim_state(struct task_struct *task,
@@ -2351,7 +2368,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
struct mem_cgroup *memcg = lruvec_memcg(lruvec);
unsigned long anon_cost, file_cost, total_cost;
- int swappiness = mem_cgroup_swappiness(memcg);
+ int swappiness = sc_swappiness(sc, memcg);
u64 fraction[ANON_AND_FILE];
u64 denominator = 0; /* gcc */
enum scan_balance scan_balance;
@@ -2632,7 +2649,7 @@ static int get_swappiness(struct lruvec *lruvec, struct scan_control *sc)
mem_cgroup_get_nr_swap_pages(memcg) < MIN_LRU_BATCH)
return 0;
- return mem_cgroup_swappiness(memcg);
+ return sc_swappiness(sc, memcg);
}
static int get_nr_gens(struct lruvec *lruvec, int type)
@@ -6549,12 +6566,14 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
unsigned long nr_pages,
gfp_t gfp_mask,
- unsigned int reclaim_options)
+ unsigned int reclaim_options,
+ int *swappiness)
{
unsigned long nr_reclaimed;
unsigned int noreclaim_flag;
struct scan_control sc = {
.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
+ .proactive_swappiness = swappiness,
.gfp_mask = (current_gfp_context(gfp_mask) & GFP_RECLAIM_MASK) |
(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK),
.reclaim_idx = MAX_NR_ZONES - 1,