lkml.org 
[lkml]   [2012]   [Feb]   [13]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[PATCH 2/6 v4] memcg: simplify move_account() check
From 9cdb3b63dc8d08cc2220c54c80438c13433a0d12 Mon Sep 17 00:00:00 2001
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Date: Thu, 2 Feb 2012 10:02:39 +0900
Subject: [PATCH 2/6] memcg: simplify move_account() check.

In memcg, for avoiding take-lock-irq-off at accessing page_cgroup,
a logic, flag + rcu_read_lock(), is used. This works as following

CPU-A CPU-B
rcu_read_lock()
set flag
if(flag is set)
take heavy lock
do job.
synchronize_rcu() rcu_read_unlock()
In recent discussion, it's argued that using per-cpu value for this
flag just complicates the code because 'set flag' is very rare.

This patch changes 'flag' implementation from percpu to atomic_t.
This will be much simpler.

Changelog: v4
- fixed many typos.
- fixed return value to be bool
- add comments.
Changelog: v3
- this is a new patch since v3.

memcontrol.c | 65 ++++++++++++++++++++++-------------------------------------
1 file changed, 25 insertions(+), 40 deletions(-)
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
---
mm/memcontrol.c | 70 +++++++++++++++++++++++-------------------------------
1 files changed, 30 insertions(+), 40 deletions(-)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4c2b759..9f69679 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -89,7 +89,6 @@ enum mem_cgroup_stat_index {
MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */
MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */
MEM_CGROUP_STAT_DATA, /* end of data requires synchronization */
- MEM_CGROUP_ON_MOVE, /* someone is moving account between groups */
MEM_CGROUP_STAT_NSTATS,
};

@@ -278,6 +277,10 @@ struct mem_cgroup {
*/
unsigned long move_charge_at_immigrate;
/*
+ * set > 0 if pages under this cgroup are moving to other cgroup.
+ */
+ atomic_t moving_account;
+ /*
* percpu counter.
*/
struct mem_cgroup_stat_cpu *stat;
@@ -1253,36 +1256,37 @@ int mem_cgroup_swappiness(struct mem_cgroup *memcg)

return memcg->swappiness;
}
+/*
+ * memcg->moving_account is used for checking possibility that some thread is
+ * calling move_account(). When a thread on CPU-A starts moving pages under
+ * a memcg, other threads should check memcg->moving_account under
+ * rcu_read_lock(), like this:
+ *
+ * CPU-A CPU-B
+ * rcu_read_lock()
+ * memcg->moving_account+1 if (memcg->mocing_account)
+ * take heavy locks.
+ * synchronize_rcu() update something.
+ * rcu_read_unlock()
+ * start move here.
+ */

static void mem_cgroup_start_move(struct mem_cgroup *memcg)
{
- int cpu;
-
- get_online_cpus();
- spin_lock(&memcg->pcp_counter_lock);
- for_each_online_cpu(cpu)
- per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) += 1;
- memcg->nocpu_base.count[MEM_CGROUP_ON_MOVE] += 1;
- spin_unlock(&memcg->pcp_counter_lock);
- put_online_cpus();
-
+ atomic_inc(&memcg->moving_account);
synchronize_rcu();
}

static void mem_cgroup_end_move(struct mem_cgroup *memcg)
{
- int cpu;
-
- if (!memcg)
- return;
- get_online_cpus();
- spin_lock(&memcg->pcp_counter_lock);
- for_each_online_cpu(cpu)
- per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) -= 1;
- memcg->nocpu_base.count[MEM_CGROUP_ON_MOVE] -= 1;
- spin_unlock(&memcg->pcp_counter_lock);
- put_online_cpus();
+ /*
+ * Now, mem_cgroup_clear_mc() may call this function with NULL.
+ * We check NULL in callee rather than caller.
+ */
+ if (memcg)
+ atomic_dec(&memcg->moving_account);
}
+
/*
* 2 routines for checking "mem" is under move_account() or not.
*
@@ -1298,7 +1302,7 @@ static void mem_cgroup_end_move(struct mem_cgroup *memcg)
static bool mem_cgroup_stealed(struct mem_cgroup *memcg)
{
VM_BUG_ON(!rcu_read_lock_held());
- return this_cpu_read(memcg->stat->count[MEM_CGROUP_ON_MOVE]) > 0;
+ return atomic_read(&memcg->moving_account) > 0;
}

static bool mem_cgroup_under_move(struct mem_cgroup *memcg)
@@ -1849,8 +1853,8 @@ bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask)
* by flags.
*
* Considering "move", this is an only case we see a race. To make the race
- * small, we check MEM_CGROUP_ON_MOVE percpu value and detect there are
- * possibility of race condition. If there is, we take a lock.
+ * small, we check mm->moving_account and detect there are possibility of race
+ * If there is, we take a lock.
*/

void mem_cgroup_update_page_stat(struct page *page,
@@ -2067,17 +2071,6 @@ static void mem_cgroup_drain_pcp_counter(struct mem_cgroup *memcg, int cpu)
per_cpu(memcg->stat->events[i], cpu) = 0;
memcg->nocpu_base.events[i] += x;
}
- /* need to clear ON_MOVE value, works as a kind of lock. */
- per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) = 0;
- spin_unlock(&memcg->pcp_counter_lock);
-}
-
-static void synchronize_mem_cgroup_on_move(struct mem_cgroup *memcg, int cpu)
-{
- int idx = MEM_CGROUP_ON_MOVE;
-
- spin_lock(&memcg->pcp_counter_lock);
- per_cpu(memcg->stat->count[idx], cpu) = memcg->nocpu_base.count[idx];
spin_unlock(&memcg->pcp_counter_lock);
}

@@ -2089,11 +2082,8 @@ static int __cpuinit memcg_cpu_hotplug_callback(struct notifier_block *nb,
struct memcg_stock_pcp *stock;
struct mem_cgroup *iter;

- if ((action == CPU_ONLINE)) {
- for_each_mem_cgroup(iter)
- synchronize_mem_cgroup_on_move(iter, cpu);
+ if ((action == CPU_ONLINE))
return NOTIFY_OK;
- }

if ((action != CPU_DEAD) || action != CPU_DEAD_FROZEN)
return NOTIFY_OK;
--
1.7.4.1



\
 
 \ /
  Last update: 2012-02-14 04:11    [from the cache]
©2003-2014 Jasper Spaans. Advertise on this site