summaryrefslogtreecommitdiff
path: root/kernel/sysctl.c
diff options
context:
space:
mode:
authorJohannes Weiner <hannes@cmpxchg.org>2016-03-17 14:19:14 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-03-17 15:09:34 -0700
commit795ae7a0de6b834a0cc202aa55c190ef81496665 (patch)
treef76ff0f0a99242aee5048cc018c33f01fe299a1c /kernel/sysctl.c
parent3ed3a4f0ddffece942bb2661924d87be4ce63cb7 (diff)
downloadlinux-sh-795ae7a0de6b834a0cc202aa55c190ef81496665.tar.gz
mm: scale kswapd watermarks in proportion to memory
In machines with 140G of memory and enterprise flash storage, we have seen read and write bursts routinely exceed the kswapd watermarks and cause thundering herds in direct reclaim. Unfortunately, the only way to tune kswapd aggressiveness is through adjusting min_free_kbytes - the system's emergency reserves - which is entirely unrelated to the system's latency requirements. In order to get kswapd to maintain a 250M buffer of free memory, the emergency reserves need to be set to 1G. That is a lot of memory wasted for no good reason. On the other hand, it's reasonable to assume that allocation bursts and overall allocation concurrency scale with memory capacity, so it makes sense to make kswapd aggressiveness a function of that as well. Change the kswapd watermark scale factor from the currently fixed 25% of the tunable emergency reserve to a tunable 0.1% of memory. Beyond 1G of memory, this will produce bigger watermark steps than the current formula in default settings. Ensure that the new formula never chooses steps smaller than that, i.e. 25% of the emergency reserve. On a 140G machine, this raises the default watermark steps - the distance between min and low, and low and high - from 16M to 143M. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Mel Gorman <mgorman@suse.de> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'kernel/sysctl.c')
-rw-r--r--kernel/sysctl.c10
1 files changed, 10 insertions, 0 deletions
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index f5102fabef7f..725587f10667 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -126,6 +126,7 @@ static int __maybe_unused two = 2;
static int __maybe_unused four = 4;
static unsigned long one_ul = 1;
static int one_hundred = 100;
+static int one_thousand = 1000;
#ifdef CONFIG_PRINTK
static int ten_thousand = 10000;
#endif
@@ -1404,6 +1405,15 @@ static struct ctl_table vm_table[] = {
.extra1 = &zero,
},
{
+ .procname = "watermark_scale_factor",
+ .data = &watermark_scale_factor,
+ .maxlen = sizeof(watermark_scale_factor),
+ .mode = 0644,
+ .proc_handler = watermark_scale_factor_sysctl_handler,
+ .extra1 = &one,
+ .extra2 = &one_thousand,
+ },
+ {
.procname = "percpu_pagelist_fraction",
.data = &percpu_pagelist_fraction,
.maxlen = sizeof(percpu_pagelist_fraction),