From 71fdbce075d9091259086c87af3fab7d7c73947c Mon Sep 17 00:00:00 2001 From: Charan Teja Reddy Date: Mon, 31 May 2021 16:24:51 +0530 Subject: [PATCH] FROMLIST: mm: compaction: support triggering of proactive compaction by user The proactive compaction[1] gets triggered for every 500msec and run compaction on the node for COMPACTION_HPAGE_ORDER (usually order-9) pages based on the value set to sysctl.compaction_proactiveness. Triggering the compaction for every 500msec in search of COMPACTION_HPAGE_ORDER pages is not needed for all applications, especially on the embedded system usecases which may have few MB's of RAM. Enabling the proactive compaction in its state will endup in running almost always on such systems. Other side, proactive compaction can still be very much useful for getting a set of higher order pages in some controllable manner(controlled by using the sysctl.compaction_proactiveness). Thus on systems where enabling the proactive compaction always may proove not required, can trigger the same from user space on write to its sysctl interface. As an example, say app launcher decide to launch the memory heavy application which can be launched fast if it gets more higher order pages thus launcher can prepare the system in advance by triggering the proactive compaction from userspace. This triggering of proactive compaction is done on a write to sysctl.compaction_proactiveness by user. [1]https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit?id=facdaa917c4d5a376d09d25865f5a863f906234a Bug: 186387247 Link: https://lore.kernel.org/patchwork/patch/1438211/ Signed-off-by: Charan Teja Reddy Change-Id: Ie5208e274b9d7e7354471bb98ff1f10becf93595 --- Documentation/admin-guide/sysctl/vm.rst | 3 +- include/linux/compaction.h | 2 ++ include/linux/mmzone.h | 1 + kernel/sysctl.c | 2 +- mm/compaction.c | 44 +++++++++++++++++++++++-- 5 files changed, 47 insertions(+), 5 deletions(-) diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index 996bb3c5e16d..9c321c7ddc18 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -127,7 +127,8 @@ compaction_proactiveness This tunable takes a value in the range [0, 100] with a default value of 20. This tunable determines how aggressively compaction is done in the -background. Setting it to 0 disables proactive compaction. +background. On write of non zero value to this tunable will immediately +trigger the proactive compaction. Setting it to 0 disables proactive compaction. Note that compaction has a non-trivial system-wide impact as pages belonging to different processes are moved around, which could also lead diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 5734e3cf4792..f1eb9f943357 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -85,6 +85,8 @@ extern int sysctl_compact_memory; extern unsigned int sysctl_compaction_proactiveness; extern int sysctl_compaction_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); +extern int compaction_proactiveness_sysctl_handler(struct ctl_table *table, + int write, void *buffer, size_t *length, loff_t *ppos); extern int sysctl_extfrag_threshold; extern int sysctl_compact_unevictable_allowed; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index b002e9b4abc0..6aaebd16ba6d 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -783,6 +783,7 @@ typedef struct pglist_data { enum zone_type kcompactd_highest_zoneidx; wait_queue_head_t kcompactd_wait; struct task_struct *kcompactd; + bool proactive_compact_trigger; #endif /* * This is a per-node reserve of pages that are not available diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 20dfb9427fdf..7aed10c7dea9 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2858,7 +2858,7 @@ static struct ctl_table vm_table[] = { .data = &sysctl_compaction_proactiveness, .maxlen = sizeof(sysctl_compaction_proactiveness), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = compaction_proactiveness_sysctl_handler, .extra1 = SYSCTL_ZERO, .extra2 = &one_hundred, }, diff --git a/mm/compaction.c b/mm/compaction.c index 8f28896cfc6c..8284fb8cb896 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -2650,6 +2650,30 @@ int sysctl_compact_memory; */ unsigned int __read_mostly sysctl_compaction_proactiveness = 20; +int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ + int rc, nid; + + rc = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (rc) + return rc; + + if (write && sysctl_compaction_proactiveness) { + for_each_online_node(nid) { + pg_data_t *pgdat = NODE_DATA(nid); + + if (pgdat->proactive_compact_trigger) + continue; + + pgdat->proactive_compact_trigger = true; + wake_up_interruptible(&pgdat->kcompactd_wait); + } + } + + return 0; +} + /* * This is the entry point for compacting all nodes via * /proc/sys/vm/compact_memory @@ -2694,7 +2718,8 @@ void compaction_unregister_node(struct node *node) static inline bool kcompactd_work_requested(pg_data_t *pgdat) { - return pgdat->kcompactd_max_order > 0 || kthread_should_stop(); + return pgdat->kcompactd_max_order > 0 || kthread_should_stop() || + pgdat->proactive_compact_trigger; } static bool kcompactd_node_suitable(pg_data_t *pgdat) @@ -2847,7 +2872,8 @@ static int kcompactd(void *p) trace_mm_compaction_kcompactd_sleep(pgdat->node_id); if (wait_event_freezable_timeout(pgdat->kcompactd_wait, kcompactd_work_requested(pgdat), - msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC))) { + msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC)) && + !pgdat->proactive_compact_trigger) { psi_memstall_enter(&pflags); kcompactd_do_work(pgdat); @@ -2859,10 +2885,20 @@ static int kcompactd(void *p) if (should_proactive_compact_node(pgdat)) { unsigned int prev_score, score; - if (proactive_defer) { + /* + * On wakeup of proactive compaction by sysctl + * write, ignore the accumulated defer score. + * Anyway, if the proactive compaction didn't + * make any progress for the new value, it will + * be further deferred by 2^COMPACT_MAX_DEFER_SHIFT + * times. + */ + if (proactive_defer && + !pgdat->proactive_compact_trigger) { proactive_defer--; continue; } + prev_score = fragmentation_score_node(pgdat); proactive_compact_node(pgdat); score = fragmentation_score_node(pgdat); @@ -2873,6 +2909,8 @@ static int kcompactd(void *p) proactive_defer = score < prev_score ? 0 : 1 << COMPACT_MAX_DEFER_SHIFT; } + if (pgdat->proactive_compact_trigger) + pgdat->proactive_compact_trigger = false; } return 0;