mm, compaction: introduce kcompactd
Memory compaction can be currently performed in several contexts:
- kswapd balancing a zone after a high-order allocation failure
- direct compaction to satisfy a high-order allocation, including THP
page fault attemps
- khugepaged trying to collapse a hugepage
- manually from /proc
The purpose of compaction is two-fold. The obvious purpose is to
satisfy a (pending or future) high-order allocation, and is easy to
evaluate. The other purpose is to keep overal memory fragmentation low
and help the anti-fragmentation mechanism. The success wrt the latter
purpose is more
The current situation wrt the purposes has a few drawbacks:
- compaction is invoked only when a high-order page or hugepage is not
available (or manually). This might be too late for the purposes of
keeping memory fragmentation low.
- direct compaction increases latency of allocations. Again, it would
be better if compaction was performed asynchronously to keep
fragmentation low, before the allocation itself comes.
- (a special case of the previous) the cost of compaction during THP
page faults can easily offset the benefits of THP.
- kswapd compaction appears to be complex, fragile and not working in
some scenarios. It could also end up compacting for a high-order
allocation request when it should be reclaiming memory for a later
order-0 request.
To improve the situation, we should be able to benefit from an
equivalent of kswapd, but for compaction - i.e. a background thread
which responds to fragmentation and the need for high-order allocations
(including hugepages) somewhat proactively.
One possibility is to extend the responsibilities of kswapd, which could
however complicate its design too much. It should be better to let
kswapd handle reclaim, as order-0 allocations are often more critical
than high-order ones.
Another possibility is to extend khugepaged, but this kthread is a
single instance and tied to THP configs.
This patch goes with the option of a new set of per-node kthreads called
kcompactd, and lays the foundations, without introducing any new
tunables. The lifecycle mimics kswapd kthreads, including the memory
hotplug hooks.
For compaction, kcompactd uses the standard compaction_suitable() and
ompact_finished() criteria and the deferred compaction functionality.
Unlike direct compaction, it uses only sync compaction, as there's no
allocation latency to minimize.
This patch doesn't yet add a call to wakeup_kcompactd. The kswapd
compact/reclaim loop for high-order pages will be replaced by waking up
kcompactd in the next patch with the description of what's wrong with
the old approach.
Waking up of the kcompactd threads is also tied to kswapd activity and
follows these rules:
- we don't want to affect any fastpaths, so wake up kcompactd only from
the slowpath, as it's done for kswapd
- if kswapd is doing reclaim, it's more important than compaction, so
don't invoke kcompactd until kswapd goes to sleep
- the target order used for kswapd is passed to kcompactd
Future possible future uses for kcompactd include the ability to wake up
kcompactd on demand in special situations, such as when hugepages are
not available (currently not done due to __GFP_NO_KSWAPD) or when a
fragmentation event (i.e. __rmqueue_fallback()) occurs. It's also
possible to perform periodic compaction with kcompactd.
[arnd@arndb.de: fix build errors with kcompactd]
[paul.gortmaker@windriver.com: don't use modular references for non modular code]
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: David Rientjes <rientjes@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/compaction.c b/mm/compaction.c
index 93f71d9..5b2bfba 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -7,6 +7,7 @@
*
* Copyright IBM Corp. 2007-2010 Mel Gorman <mel@csn.ul.ie>
*/
+#include <linux/cpu.h>
#include <linux/swap.h>
#include <linux/migrate.h>
#include <linux/compaction.h>
@@ -17,6 +18,8 @@
#include <linux/balloon_compaction.h>
#include <linux/page-isolation.h>
#include <linux/kasan.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
#include "internal.h"
#ifdef CONFIG_COMPACTION
@@ -1736,4 +1739,223 @@
}
#endif /* CONFIG_SYSFS && CONFIG_NUMA */
+static inline bool kcompactd_work_requested(pg_data_t *pgdat)
+{
+ return pgdat->kcompactd_max_order > 0;
+}
+
+static bool kcompactd_node_suitable(pg_data_t *pgdat)
+{
+ int zoneid;
+ struct zone *zone;
+ enum zone_type classzone_idx = pgdat->kcompactd_classzone_idx;
+
+ for (zoneid = 0; zoneid < classzone_idx; zoneid++) {
+ zone = &pgdat->node_zones[zoneid];
+
+ if (!populated_zone(zone))
+ continue;
+
+ if (compaction_suitable(zone, pgdat->kcompactd_max_order, 0,
+ classzone_idx) == COMPACT_CONTINUE)
+ return true;
+ }
+
+ return false;
+}
+
+static void kcompactd_do_work(pg_data_t *pgdat)
+{
+ /*
+ * With no special task, compact all zones so that a page of requested
+ * order is allocatable.
+ */
+ int zoneid;
+ struct zone *zone;
+ struct compact_control cc = {
+ .order = pgdat->kcompactd_max_order,
+ .classzone_idx = pgdat->kcompactd_classzone_idx,
+ .mode = MIGRATE_SYNC_LIGHT,
+ .ignore_skip_hint = true,
+
+ };
+ bool success = false;
+
+ trace_mm_compaction_kcompactd_wake(pgdat->node_id, cc.order,
+ cc.classzone_idx);
+ count_vm_event(KCOMPACTD_WAKE);
+
+ for (zoneid = 0; zoneid < cc.classzone_idx; zoneid++) {
+ int status;
+
+ zone = &pgdat->node_zones[zoneid];
+ if (!populated_zone(zone))
+ continue;
+
+ if (compaction_deferred(zone, cc.order))
+ continue;
+
+ if (compaction_suitable(zone, cc.order, 0, zoneid) !=
+ COMPACT_CONTINUE)
+ continue;
+
+ cc.nr_freepages = 0;
+ cc.nr_migratepages = 0;
+ cc.zone = zone;
+ INIT_LIST_HEAD(&cc.freepages);
+ INIT_LIST_HEAD(&cc.migratepages);
+
+ status = compact_zone(zone, &cc);
+
+ if (zone_watermark_ok(zone, cc.order, low_wmark_pages(zone),
+ cc.classzone_idx, 0)) {
+ success = true;
+ compaction_defer_reset(zone, cc.order, false);
+ } else if (status == COMPACT_COMPLETE) {
+ /*
+ * We use sync migration mode here, so we defer like
+ * sync direct compaction does.
+ */
+ defer_compaction(zone, cc.order);
+ }
+
+ VM_BUG_ON(!list_empty(&cc.freepages));
+ VM_BUG_ON(!list_empty(&cc.migratepages));
+ }
+
+ /*
+ * Regardless of success, we are done until woken up next. But remember
+ * the requested order/classzone_idx in case it was higher/tighter than
+ * our current ones
+ */
+ if (pgdat->kcompactd_max_order <= cc.order)
+ pgdat->kcompactd_max_order = 0;
+ if (pgdat->kcompactd_classzone_idx >= cc.classzone_idx)
+ pgdat->kcompactd_classzone_idx = pgdat->nr_zones - 1;
+}
+
+void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx)
+{
+ if (!order)
+ return;
+
+ if (pgdat->kcompactd_max_order < order)
+ pgdat->kcompactd_max_order = order;
+
+ if (pgdat->kcompactd_classzone_idx > classzone_idx)
+ pgdat->kcompactd_classzone_idx = classzone_idx;
+
+ if (!waitqueue_active(&pgdat->kcompactd_wait))
+ return;
+
+ if (!kcompactd_node_suitable(pgdat))
+ return;
+
+ trace_mm_compaction_wakeup_kcompactd(pgdat->node_id, order,
+ classzone_idx);
+ wake_up_interruptible(&pgdat->kcompactd_wait);
+}
+
+/*
+ * The background compaction daemon, started as a kernel thread
+ * from the init process.
+ */
+static int kcompactd(void *p)
+{
+ pg_data_t *pgdat = (pg_data_t*)p;
+ struct task_struct *tsk = current;
+
+ const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
+
+ if (!cpumask_empty(cpumask))
+ set_cpus_allowed_ptr(tsk, cpumask);
+
+ set_freezable();
+
+ pgdat->kcompactd_max_order = 0;
+ pgdat->kcompactd_classzone_idx = pgdat->nr_zones - 1;
+
+ while (!kthread_should_stop()) {
+ trace_mm_compaction_kcompactd_sleep(pgdat->node_id);
+ wait_event_freezable(pgdat->kcompactd_wait,
+ kcompactd_work_requested(pgdat));
+
+ kcompactd_do_work(pgdat);
+ }
+
+ return 0;
+}
+
+/*
+ * This kcompactd start function will be called by init and node-hot-add.
+ * On node-hot-add, kcompactd will moved to proper cpus if cpus are hot-added.
+ */
+int kcompactd_run(int nid)
+{
+ pg_data_t *pgdat = NODE_DATA(nid);
+ int ret = 0;
+
+ if (pgdat->kcompactd)
+ return 0;
+
+ pgdat->kcompactd = kthread_run(kcompactd, pgdat, "kcompactd%d", nid);
+ if (IS_ERR(pgdat->kcompactd)) {
+ pr_err("Failed to start kcompactd on node %d\n", nid);
+ ret = PTR_ERR(pgdat->kcompactd);
+ pgdat->kcompactd = NULL;
+ }
+ return ret;
+}
+
+/*
+ * Called by memory hotplug when all memory in a node is offlined. Caller must
+ * hold mem_hotplug_begin/end().
+ */
+void kcompactd_stop(int nid)
+{
+ struct task_struct *kcompactd = NODE_DATA(nid)->kcompactd;
+
+ if (kcompactd) {
+ kthread_stop(kcompactd);
+ NODE_DATA(nid)->kcompactd = NULL;
+ }
+}
+
+/*
+ * It's optimal to keep kcompactd on the same CPUs as their memory, but
+ * not required for correctness. So if the last cpu in a node goes
+ * away, we get changed to run anywhere: as the first one comes back,
+ * restore their cpu bindings.
+ */
+static int cpu_callback(struct notifier_block *nfb, unsigned long action,
+ void *hcpu)
+{
+ int nid;
+
+ if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
+ for_each_node_state(nid, N_MEMORY) {
+ pg_data_t *pgdat = NODE_DATA(nid);
+ const struct cpumask *mask;
+
+ mask = cpumask_of_node(pgdat->node_id);
+
+ if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
+ /* One of our CPUs online: restore mask */
+ set_cpus_allowed_ptr(pgdat->kcompactd, mask);
+ }
+ }
+ return NOTIFY_OK;
+}
+
+static int __init kcompactd_init(void)
+{
+ int nid;
+
+ for_each_node_state(nid, N_MEMORY)
+ kcompactd_run(nid);
+ hotcpu_notifier(cpu_callback, 0);
+ return 0;
+}
+subsys_initcall(kcompactd_init)
+
#endif /* CONFIG_COMPACTION */