From: Johannes Weiner <hannes@cmpxchg.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Jia He <hejianet@gmail.com>, Michal Hocko <mhocko@suse.cz>,
Mel Gorman <mgorman@suse.de>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
kernel-team@fb.com
Subject: [PATCH 6/9] mm: don't avoid high-priority reclaim on memcg limit reclaim
Date: Tue, 28 Feb 2017 16:40:04 -0500 [thread overview]
Message-ID: <20170228214007.5621-7-hannes@cmpxchg.org> (raw)
In-Reply-To: <20170228214007.5621-1-hannes@cmpxchg.org>
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.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
---
mm/vmscan.c | 94 ++++++++++++++++++++++++-------------------------------------
1 file changed, 37 insertions(+), 57 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 46b6223fe7f3..8cff6e2cd02c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2122,21 +2122,8 @@ 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) {
@@ -2267,55 +2254,48 @@ 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;
}
}
--
2.11.1
next prev parent reply other threads:[~2017-03-01 7:55 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-02-28 21:39 [PATCH 0/9] mm: kswapd spinning on unreclaimable nodes - fixes and cleanups Johannes Weiner
2017-02-28 21:39 ` [PATCH 1/9] mm: fix 100% CPU kswapd busyloop on unreclaimable nodes Johannes Weiner
2017-03-02 3:23 ` Hillf Danton
2017-03-02 23:30 ` Shakeel Butt
2017-03-03 1:26 ` Minchan Kim
2017-03-03 7:59 ` Michal Hocko
2017-03-06 1:37 ` Minchan Kim
2017-03-06 16:24 ` Johannes Weiner
2017-03-07 0:59 ` Hillf Danton
2017-03-07 7:28 ` Minchan Kim
2017-03-07 10:17 ` Michal Hocko
2017-03-07 16:56 ` Johannes Weiner
2017-03-09 14:20 ` Mel Gorman
2017-02-28 21:40 ` [PATCH 2/9] mm: fix check for reclaimable pages in PF_MEMALLOC reclaim throttling Johannes Weiner
2017-03-01 15:02 ` Michal Hocko
2017-03-02 3:25 ` Hillf Danton
2017-02-28 21:40 ` [PATCH 3/9] mm: remove seemingly spurious reclaimability check from laptop_mode gating Johannes Weiner
2017-03-01 15:06 ` Michal Hocko
2017-03-01 15:17 ` Mel Gorman
2017-03-02 3:27 ` Hillf Danton
2017-02-28 21:40 ` [PATCH 4/9] mm: remove unnecessary reclaimability check from NUMA balancing target Johannes Weiner
2017-03-01 15:14 ` Michal Hocko
2017-03-02 3:28 ` Hillf Danton
2017-02-28 21:40 ` [PATCH 5/9] mm: don't avoid high-priority reclaim on unreclaimable nodes Johannes Weiner
2017-03-01 15:21 ` Michal Hocko
2017-03-02 3:31 ` Hillf Danton
2017-02-28 21:40 ` Johannes Weiner [this message]
2017-03-01 15:40 ` [PATCH 6/9] mm: don't avoid high-priority reclaim on memcg limit reclaim Michal Hocko
2017-03-01 17:36 ` Johannes Weiner
2017-03-01 19:13 ` Michal Hocko
2017-03-02 3:32 ` Hillf Danton
2017-02-28 21:40 ` [PATCH 7/9] mm: delete NR_PAGES_SCANNED and pgdat_reclaimable() Johannes Weiner
2017-03-01 15:41 ` Michal Hocko
2017-03-02 3:34 ` Hillf Danton
2017-02-28 21:40 ` [PATCH 8/9] Revert "mm, vmscan: account for skipped pages as a partial scan" Johannes Weiner
2017-03-01 15:51 ` Michal Hocko
2017-03-02 3:36 ` Hillf Danton
2017-02-28 21:40 ` [PATCH 9/9] mm: remove unnecessary back-off function when retrying page reclaim Johannes Weiner
2017-03-01 14:56 ` Michal Hocko
2017-03-02 3:37 ` Hillf Danton
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20170228214007.5621-7-hannes@cmpxchg.org \
--to=hannes@cmpxchg.org \
--cc=akpm@linux-foundation.org \
--cc=hejianet@gmail.com \
--cc=kernel-team@fb.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=mhocko@suse.cz \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).