Commit 879336c3 authored by Christoph Lameter's avatar Christoph Lameter Committed by Linus Torvalds
Browse files

[PATCH] drain_node_pages: interrupt latency reduction / optimization

1. Only disable interrupts if there is actually something to free

2. Only dirty the pcp cacheline if we actually freed something.

3. Disable interrupts for each single pcp and not for cleaning
  all the pcps in all zones of a node.

drain_node_pages is called every 2 seconds from cache_reap. This
fix should avoid most disabling of interrupts.
Signed-off-by: default avatarChristoph Lameter <>
Signed-off-by: default avatarAndrew Morton <>
Signed-off-by: default avatarLinus Torvalds <>
parent b18e7e65
......@@ -603,13 +603,14 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
* Called from the slab reaper to drain pagesets on a particular node that
* belong to the currently executing processor.
* Note that this function must be called with the thread pinned to
* a single processor.
void drain_node_pages(int nodeid)
int i, z;
unsigned long flags;
for (z = 0; z < MAX_NR_ZONES; z++) {
struct zone *zone = NODE_DATA(nodeid)->node_zones + z;
struct per_cpu_pageset *pset;
......@@ -619,11 +620,14 @@ void drain_node_pages(int nodeid)
struct per_cpu_pages *pcp;
pcp = &pset->pcp[i];
free_pages_bulk(zone, pcp->count, &pcp->list, 0);
pcp->count = 0;
if (pcp->count) {
free_pages_bulk(zone, pcp->count, &pcp->list, 0);
pcp->count = 0;
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment