diff options
author | Johannes Weiner <hannes@cmpxchg.org> | 2017-05-03 23:52:07 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-05-04 00:52:08 +0200 |
commit | 688035f729dcd9a98152c827338805a061f5c6fa (patch) | |
tree | 2c2def8c77d297e36d4a757f12c1b12211b38eee /mm | |
parent | mm: don't avoid high-priority reclaim on unreclaimable nodes (diff) | |
download | linux-688035f729dcd9a98152c827338805a061f5c6fa.tar.xz linux-688035f729dcd9a98152c827338805a061f5c6fa.zip |
mm: don't avoid high-priority reclaim on memcg limit reclaim
Commit 246e87a93934 ("memcg: fix get_scan_count() for small targets")
sought to avoid high reclaim priorities for memcg by forcing it to scan
a minimum amount of pages when lru_pages >> priority yielded nothing.
This was done at a time when reclaim decisions like dirty throttling
were tied to the priority level.
Nowadays, the only meaningful thing still tied to priority dropping
below DEF_PRIORITY - 2 is gating whether laptop_mode=1 is generally
allowed to write. But that is from an era where direct reclaim was
still allowed to call ->writepage, and kswapd nowadays avoids writes
until it's scanned every clean page in the system. Potential changes to
how quick sc->may_writepage could trigger are of little concern.
Remove the force_scan stuff, as well as the ugly multi-pass target
calculation that it necessitated.
Link: http://lkml.kernel.org/r/20170228214007.5621-7-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Jia He <hejianet@gmail.com>
Cc: Mel Gorman <mgorman@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r-- | mm/vmscan.c | 94 |
1 files changed, 37 insertions, 57 deletions
diff --git a/mm/vmscan.c b/mm/vmscan.c index 2fd50ca88016..9117ae8d49ee 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2123,21 +2123,8 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, unsigned long anon_prio, file_prio; enum scan_balance scan_balance; unsigned long anon, file; - bool force_scan = false; unsigned long ap, fp; enum lru_list lru; - bool some_scanned; - int pass; - - /* - * If the zone or memcg is small, nr[l] can be 0. When - * reclaiming for a memcg, a priority drop can cause high - * latencies, so it's better to scan a minimum amount. When a - * cgroup has already been deleted, scrape out the remaining - * cache forcefully to get rid of the lingering state. - */ - if (!global_reclaim(sc) || !mem_cgroup_online(memcg)) - force_scan = true; /* If we have no swap space, do not bother scanning anon pages. */ if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) { @@ -2268,55 +2255,48 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, fraction[1] = fp; denominator = ap + fp + 1; out: - some_scanned = false; - /* Only use force_scan on second pass. */ - for (pass = 0; !some_scanned && pass < 2; pass++) { - *lru_pages = 0; - for_each_evictable_lru(lru) { - int file = is_file_lru(lru); - unsigned long size; - unsigned long scan; - - size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); - scan = size >> sc->priority; - - if (!scan && pass && force_scan) - scan = min(size, SWAP_CLUSTER_MAX); - - switch (scan_balance) { - case SCAN_EQUAL: - /* Scan lists relative to size */ - break; - case SCAN_FRACT: - /* - * Scan types proportional to swappiness and - * their relative recent reclaim efficiency. - */ - scan = div64_u64(scan * fraction[file], - denominator); - break; - case SCAN_FILE: - case SCAN_ANON: - /* Scan one type exclusively */ - if ((scan_balance == SCAN_FILE) != file) { - size = 0; - scan = 0; - } - break; - default: - /* Look ma, no brain */ - BUG(); - } + *lru_pages = 0; + for_each_evictable_lru(lru) { + int file = is_file_lru(lru); + unsigned long size; + unsigned long scan; - *lru_pages += size; - nr[lru] = scan; + size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); + scan = size >> sc->priority; + /* + * If the cgroup's already been deleted, make sure to + * scrape out the remaining cache. + */ + if (!scan && !mem_cgroup_online(memcg)) + scan = min(size, SWAP_CLUSTER_MAX); + switch (scan_balance) { + case SCAN_EQUAL: + /* Scan lists relative to size */ + break; + case SCAN_FRACT: /* - * Skip the second pass and don't force_scan, - * if we found something to scan. + * Scan types proportional to swappiness and + * their relative recent reclaim efficiency. */ - some_scanned |= !!scan; + scan = div64_u64(scan * fraction[file], + denominator); + break; + case SCAN_FILE: + case SCAN_ANON: + /* Scan one type exclusively */ + if ((scan_balance == SCAN_FILE) != file) { + size = 0; + scan = 0; + } + break; + default: + /* Look ma, no brain */ + BUG(); } + + *lru_pages += size; + nr[lru] = scan; } } |