mirror of
https://github.com/torvalds/linux.git
synced 2024-12-04 18:13:04 +00:00
69392a403f
Memcg reclaim throttles on congestion if no reclaim progress is made. This makes little sense, it might be due to writeback or a host of other factors. For !memcg reclaim, it's messy. Direct reclaim primarily is throttled in the page allocator if it is failing to make progress. Kswapd throttles if too many pages are under writeback and marked for immediate reclaim. This patch explicitly throttles if reclaim is failing to make progress. [vbabka@suse.cz: Remove redundant code] Link: https://lkml.kernel.org/r/20211022144651.19914-4-mgorman@techsingularity.net Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: "Darrick J . Wong" <djwong@kernel.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: NeilBrown <neilb@suse.de> Cc: Rik van Riel <riel@surriel.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
499 lines
12 KiB
C
499 lines
12 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#undef TRACE_SYSTEM
|
|
#define TRACE_SYSTEM vmscan
|
|
|
|
#if !defined(_TRACE_VMSCAN_H) || defined(TRACE_HEADER_MULTI_READ)
|
|
#define _TRACE_VMSCAN_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/tracepoint.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/memcontrol.h>
|
|
#include <trace/events/mmflags.h>
|
|
|
|
#define RECLAIM_WB_ANON 0x0001u
|
|
#define RECLAIM_WB_FILE 0x0002u
|
|
#define RECLAIM_WB_MIXED 0x0010u
|
|
#define RECLAIM_WB_SYNC 0x0004u /* Unused, all reclaim async */
|
|
#define RECLAIM_WB_ASYNC 0x0008u
|
|
#define RECLAIM_WB_LRU (RECLAIM_WB_ANON|RECLAIM_WB_FILE)
|
|
|
|
#define show_reclaim_flags(flags) \
|
|
(flags) ? __print_flags(flags, "|", \
|
|
{RECLAIM_WB_ANON, "RECLAIM_WB_ANON"}, \
|
|
{RECLAIM_WB_FILE, "RECLAIM_WB_FILE"}, \
|
|
{RECLAIM_WB_MIXED, "RECLAIM_WB_MIXED"}, \
|
|
{RECLAIM_WB_SYNC, "RECLAIM_WB_SYNC"}, \
|
|
{RECLAIM_WB_ASYNC, "RECLAIM_WB_ASYNC"} \
|
|
) : "RECLAIM_WB_NONE"
|
|
|
|
#define _VMSCAN_THROTTLE_WRITEBACK (1 << VMSCAN_THROTTLE_WRITEBACK)
|
|
#define _VMSCAN_THROTTLE_ISOLATED (1 << VMSCAN_THROTTLE_ISOLATED)
|
|
#define _VMSCAN_THROTTLE_NOPROGRESS (1 << VMSCAN_THROTTLE_NOPROGRESS)
|
|
|
|
#define show_throttle_flags(flags) \
|
|
(flags) ? __print_flags(flags, "|", \
|
|
{_VMSCAN_THROTTLE_WRITEBACK, "VMSCAN_THROTTLE_WRITEBACK"}, \
|
|
{_VMSCAN_THROTTLE_ISOLATED, "VMSCAN_THROTTLE_ISOLATED"}, \
|
|
{_VMSCAN_THROTTLE_NOPROGRESS, "VMSCAN_THROTTLE_NOPROGRESS"} \
|
|
) : "VMSCAN_THROTTLE_NONE"
|
|
|
|
|
|
#define trace_reclaim_flags(file) ( \
|
|
(file ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \
|
|
(RECLAIM_WB_ASYNC) \
|
|
)
|
|
|
|
TRACE_EVENT(mm_vmscan_kswapd_sleep,
|
|
|
|
TP_PROTO(int nid),
|
|
|
|
TP_ARGS(nid),
|
|
|
|
TP_STRUCT__entry(
|
|
__field( int, nid )
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->nid = nid;
|
|
),
|
|
|
|
TP_printk("nid=%d", __entry->nid)
|
|
);
|
|
|
|
TRACE_EVENT(mm_vmscan_kswapd_wake,
|
|
|
|
TP_PROTO(int nid, int zid, int order),
|
|
|
|
TP_ARGS(nid, zid, order),
|
|
|
|
TP_STRUCT__entry(
|
|
__field( int, nid )
|
|
__field( int, zid )
|
|
__field( int, order )
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->nid = nid;
|
|
__entry->zid = zid;
|
|
__entry->order = order;
|
|
),
|
|
|
|
TP_printk("nid=%d order=%d",
|
|
__entry->nid,
|
|
__entry->order)
|
|
);
|
|
|
|
TRACE_EVENT(mm_vmscan_wakeup_kswapd,
|
|
|
|
TP_PROTO(int nid, int zid, int order, gfp_t gfp_flags),
|
|
|
|
TP_ARGS(nid, zid, order, gfp_flags),
|
|
|
|
TP_STRUCT__entry(
|
|
__field( int, nid )
|
|
__field( int, zid )
|
|
__field( int, order )
|
|
__field( gfp_t, gfp_flags )
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->nid = nid;
|
|
__entry->zid = zid;
|
|
__entry->order = order;
|
|
__entry->gfp_flags = gfp_flags;
|
|
),
|
|
|
|
TP_printk("nid=%d order=%d gfp_flags=%s",
|
|
__entry->nid,
|
|
__entry->order,
|
|
show_gfp_flags(__entry->gfp_flags))
|
|
);
|
|
|
|
DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template,
|
|
|
|
TP_PROTO(int order, gfp_t gfp_flags),
|
|
|
|
TP_ARGS(order, gfp_flags),
|
|
|
|
TP_STRUCT__entry(
|
|
__field( int, order )
|
|
__field( gfp_t, gfp_flags )
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->order = order;
|
|
__entry->gfp_flags = gfp_flags;
|
|
),
|
|
|
|
TP_printk("order=%d gfp_flags=%s",
|
|
__entry->order,
|
|
show_gfp_flags(__entry->gfp_flags))
|
|
);
|
|
|
|
DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_direct_reclaim_begin,
|
|
|
|
TP_PROTO(int order, gfp_t gfp_flags),
|
|
|
|
TP_ARGS(order, gfp_flags)
|
|
);
|
|
|
|
#ifdef CONFIG_MEMCG
|
|
DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_reclaim_begin,
|
|
|
|
TP_PROTO(int order, gfp_t gfp_flags),
|
|
|
|
TP_ARGS(order, gfp_flags)
|
|
);
|
|
|
|
DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_softlimit_reclaim_begin,
|
|
|
|
TP_PROTO(int order, gfp_t gfp_flags),
|
|
|
|
TP_ARGS(order, gfp_flags)
|
|
);
|
|
#endif /* CONFIG_MEMCG */
|
|
|
|
DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_end_template,
|
|
|
|
TP_PROTO(unsigned long nr_reclaimed),
|
|
|
|
TP_ARGS(nr_reclaimed),
|
|
|
|
TP_STRUCT__entry(
|
|
__field( unsigned long, nr_reclaimed )
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->nr_reclaimed = nr_reclaimed;
|
|
),
|
|
|
|
TP_printk("nr_reclaimed=%lu", __entry->nr_reclaimed)
|
|
);
|
|
|
|
DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_direct_reclaim_end,
|
|
|
|
TP_PROTO(unsigned long nr_reclaimed),
|
|
|
|
TP_ARGS(nr_reclaimed)
|
|
);
|
|
|
|
#ifdef CONFIG_MEMCG
|
|
DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_reclaim_end,
|
|
|
|
TP_PROTO(unsigned long nr_reclaimed),
|
|
|
|
TP_ARGS(nr_reclaimed)
|
|
);
|
|
|
|
DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_softlimit_reclaim_end,
|
|
|
|
TP_PROTO(unsigned long nr_reclaimed),
|
|
|
|
TP_ARGS(nr_reclaimed)
|
|
);
|
|
#endif /* CONFIG_MEMCG */
|
|
|
|
TRACE_EVENT(mm_shrink_slab_start,
|
|
TP_PROTO(struct shrinker *shr, struct shrink_control *sc,
|
|
long nr_objects_to_shrink, unsigned long cache_items,
|
|
unsigned long long delta, unsigned long total_scan,
|
|
int priority),
|
|
|
|
TP_ARGS(shr, sc, nr_objects_to_shrink, cache_items, delta, total_scan,
|
|
priority),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(struct shrinker *, shr)
|
|
__field(void *, shrink)
|
|
__field(int, nid)
|
|
__field(long, nr_objects_to_shrink)
|
|
__field(gfp_t, gfp_flags)
|
|
__field(unsigned long, cache_items)
|
|
__field(unsigned long long, delta)
|
|
__field(unsigned long, total_scan)
|
|
__field(int, priority)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->shr = shr;
|
|
__entry->shrink = shr->scan_objects;
|
|
__entry->nid = sc->nid;
|
|
__entry->nr_objects_to_shrink = nr_objects_to_shrink;
|
|
__entry->gfp_flags = sc->gfp_mask;
|
|
__entry->cache_items = cache_items;
|
|
__entry->delta = delta;
|
|
__entry->total_scan = total_scan;
|
|
__entry->priority = priority;
|
|
),
|
|
|
|
TP_printk("%pS %p: nid: %d objects to shrink %ld gfp_flags %s cache items %ld delta %lld total_scan %ld priority %d",
|
|
__entry->shrink,
|
|
__entry->shr,
|
|
__entry->nid,
|
|
__entry->nr_objects_to_shrink,
|
|
show_gfp_flags(__entry->gfp_flags),
|
|
__entry->cache_items,
|
|
__entry->delta,
|
|
__entry->total_scan,
|
|
__entry->priority)
|
|
);
|
|
|
|
TRACE_EVENT(mm_shrink_slab_end,
|
|
TP_PROTO(struct shrinker *shr, int nid, int shrinker_retval,
|
|
long unused_scan_cnt, long new_scan_cnt, long total_scan),
|
|
|
|
TP_ARGS(shr, nid, shrinker_retval, unused_scan_cnt, new_scan_cnt,
|
|
total_scan),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(struct shrinker *, shr)
|
|
__field(int, nid)
|
|
__field(void *, shrink)
|
|
__field(long, unused_scan)
|
|
__field(long, new_scan)
|
|
__field(int, retval)
|
|
__field(long, total_scan)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->shr = shr;
|
|
__entry->nid = nid;
|
|
__entry->shrink = shr->scan_objects;
|
|
__entry->unused_scan = unused_scan_cnt;
|
|
__entry->new_scan = new_scan_cnt;
|
|
__entry->retval = shrinker_retval;
|
|
__entry->total_scan = total_scan;
|
|
),
|
|
|
|
TP_printk("%pS %p: nid: %d unused scan count %ld new scan count %ld total_scan %ld last shrinker return val %d",
|
|
__entry->shrink,
|
|
__entry->shr,
|
|
__entry->nid,
|
|
__entry->unused_scan,
|
|
__entry->new_scan,
|
|
__entry->total_scan,
|
|
__entry->retval)
|
|
);
|
|
|
|
TRACE_EVENT(mm_vmscan_lru_isolate,
|
|
TP_PROTO(int highest_zoneidx,
|
|
int order,
|
|
unsigned long nr_requested,
|
|
unsigned long nr_scanned,
|
|
unsigned long nr_skipped,
|
|
unsigned long nr_taken,
|
|
isolate_mode_t isolate_mode,
|
|
int lru),
|
|
|
|
TP_ARGS(highest_zoneidx, order, nr_requested, nr_scanned, nr_skipped, nr_taken, isolate_mode, lru),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(int, highest_zoneidx)
|
|
__field(int, order)
|
|
__field(unsigned long, nr_requested)
|
|
__field(unsigned long, nr_scanned)
|
|
__field(unsigned long, nr_skipped)
|
|
__field(unsigned long, nr_taken)
|
|
__field(isolate_mode_t, isolate_mode)
|
|
__field(int, lru)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->highest_zoneidx = highest_zoneidx;
|
|
__entry->order = order;
|
|
__entry->nr_requested = nr_requested;
|
|
__entry->nr_scanned = nr_scanned;
|
|
__entry->nr_skipped = nr_skipped;
|
|
__entry->nr_taken = nr_taken;
|
|
__entry->isolate_mode = isolate_mode;
|
|
__entry->lru = lru;
|
|
),
|
|
|
|
/*
|
|
* classzone is previous name of the highest_zoneidx.
|
|
* Reason not to change it is the ABI requirement of the tracepoint.
|
|
*/
|
|
TP_printk("isolate_mode=%d classzone=%d order=%d nr_requested=%lu nr_scanned=%lu nr_skipped=%lu nr_taken=%lu lru=%s",
|
|
__entry->isolate_mode,
|
|
__entry->highest_zoneidx,
|
|
__entry->order,
|
|
__entry->nr_requested,
|
|
__entry->nr_scanned,
|
|
__entry->nr_skipped,
|
|
__entry->nr_taken,
|
|
__print_symbolic(__entry->lru, LRU_NAMES))
|
|
);
|
|
|
|
TRACE_EVENT(mm_vmscan_writepage,
|
|
|
|
TP_PROTO(struct page *page),
|
|
|
|
TP_ARGS(page),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(unsigned long, pfn)
|
|
__field(int, reclaim_flags)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->pfn = page_to_pfn(page);
|
|
__entry->reclaim_flags = trace_reclaim_flags(
|
|
page_is_file_lru(page));
|
|
),
|
|
|
|
TP_printk("page=%p pfn=0x%lx flags=%s",
|
|
pfn_to_page(__entry->pfn),
|
|
__entry->pfn,
|
|
show_reclaim_flags(__entry->reclaim_flags))
|
|
);
|
|
|
|
TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
|
|
|
|
TP_PROTO(int nid,
|
|
unsigned long nr_scanned, unsigned long nr_reclaimed,
|
|
struct reclaim_stat *stat, int priority, int file),
|
|
|
|
TP_ARGS(nid, nr_scanned, nr_reclaimed, stat, priority, file),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(int, nid)
|
|
__field(unsigned long, nr_scanned)
|
|
__field(unsigned long, nr_reclaimed)
|
|
__field(unsigned long, nr_dirty)
|
|
__field(unsigned long, nr_writeback)
|
|
__field(unsigned long, nr_congested)
|
|
__field(unsigned long, nr_immediate)
|
|
__field(unsigned int, nr_activate0)
|
|
__field(unsigned int, nr_activate1)
|
|
__field(unsigned long, nr_ref_keep)
|
|
__field(unsigned long, nr_unmap_fail)
|
|
__field(int, priority)
|
|
__field(int, reclaim_flags)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->nid = nid;
|
|
__entry->nr_scanned = nr_scanned;
|
|
__entry->nr_reclaimed = nr_reclaimed;
|
|
__entry->nr_dirty = stat->nr_dirty;
|
|
__entry->nr_writeback = stat->nr_writeback;
|
|
__entry->nr_congested = stat->nr_congested;
|
|
__entry->nr_immediate = stat->nr_immediate;
|
|
__entry->nr_activate0 = stat->nr_activate[0];
|
|
__entry->nr_activate1 = stat->nr_activate[1];
|
|
__entry->nr_ref_keep = stat->nr_ref_keep;
|
|
__entry->nr_unmap_fail = stat->nr_unmap_fail;
|
|
__entry->priority = priority;
|
|
__entry->reclaim_flags = trace_reclaim_flags(file);
|
|
),
|
|
|
|
TP_printk("nid=%d nr_scanned=%ld nr_reclaimed=%ld nr_dirty=%ld nr_writeback=%ld nr_congested=%ld nr_immediate=%ld nr_activate_anon=%d nr_activate_file=%d nr_ref_keep=%ld nr_unmap_fail=%ld priority=%d flags=%s",
|
|
__entry->nid,
|
|
__entry->nr_scanned, __entry->nr_reclaimed,
|
|
__entry->nr_dirty, __entry->nr_writeback,
|
|
__entry->nr_congested, __entry->nr_immediate,
|
|
__entry->nr_activate0, __entry->nr_activate1,
|
|
__entry->nr_ref_keep, __entry->nr_unmap_fail,
|
|
__entry->priority,
|
|
show_reclaim_flags(__entry->reclaim_flags))
|
|
);
|
|
|
|
TRACE_EVENT(mm_vmscan_lru_shrink_active,
|
|
|
|
TP_PROTO(int nid, unsigned long nr_taken,
|
|
unsigned long nr_active, unsigned long nr_deactivated,
|
|
unsigned long nr_referenced, int priority, int file),
|
|
|
|
TP_ARGS(nid, nr_taken, nr_active, nr_deactivated, nr_referenced, priority, file),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(int, nid)
|
|
__field(unsigned long, nr_taken)
|
|
__field(unsigned long, nr_active)
|
|
__field(unsigned long, nr_deactivated)
|
|
__field(unsigned long, nr_referenced)
|
|
__field(int, priority)
|
|
__field(int, reclaim_flags)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->nid = nid;
|
|
__entry->nr_taken = nr_taken;
|
|
__entry->nr_active = nr_active;
|
|
__entry->nr_deactivated = nr_deactivated;
|
|
__entry->nr_referenced = nr_referenced;
|
|
__entry->priority = priority;
|
|
__entry->reclaim_flags = trace_reclaim_flags(file);
|
|
),
|
|
|
|
TP_printk("nid=%d nr_taken=%ld nr_active=%ld nr_deactivated=%ld nr_referenced=%ld priority=%d flags=%s",
|
|
__entry->nid,
|
|
__entry->nr_taken,
|
|
__entry->nr_active, __entry->nr_deactivated, __entry->nr_referenced,
|
|
__entry->priority,
|
|
show_reclaim_flags(__entry->reclaim_flags))
|
|
);
|
|
|
|
TRACE_EVENT(mm_vmscan_node_reclaim_begin,
|
|
|
|
TP_PROTO(int nid, int order, gfp_t gfp_flags),
|
|
|
|
TP_ARGS(nid, order, gfp_flags),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(int, nid)
|
|
__field(int, order)
|
|
__field(gfp_t, gfp_flags)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->nid = nid;
|
|
__entry->order = order;
|
|
__entry->gfp_flags = gfp_flags;
|
|
),
|
|
|
|
TP_printk("nid=%d order=%d gfp_flags=%s",
|
|
__entry->nid,
|
|
__entry->order,
|
|
show_gfp_flags(__entry->gfp_flags))
|
|
);
|
|
|
|
DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_node_reclaim_end,
|
|
|
|
TP_PROTO(unsigned long nr_reclaimed),
|
|
|
|
TP_ARGS(nr_reclaimed)
|
|
);
|
|
|
|
TRACE_EVENT(mm_vmscan_throttled,
|
|
|
|
TP_PROTO(int nid, int usec_timeout, int usec_delayed, int reason),
|
|
|
|
TP_ARGS(nid, usec_timeout, usec_delayed, reason),
|
|
|
|
TP_STRUCT__entry(
|
|
__field(int, nid)
|
|
__field(int, usec_timeout)
|
|
__field(int, usec_delayed)
|
|
__field(int, reason)
|
|
),
|
|
|
|
TP_fast_assign(
|
|
__entry->nid = nid;
|
|
__entry->usec_timeout = usec_timeout;
|
|
__entry->usec_delayed = usec_delayed;
|
|
__entry->reason = 1U << reason;
|
|
),
|
|
|
|
TP_printk("nid=%d usec_timeout=%d usect_delayed=%d reason=%s",
|
|
__entry->nid,
|
|
__entry->usec_timeout,
|
|
__entry->usec_delayed,
|
|
show_throttle_flags(__entry->reason))
|
|
);
|
|
#endif /* _TRACE_VMSCAN_H */
|
|
|
|
/* This part must be outside protection */
|
|
#include <trace/define_trace.h>
|