alistair23-linux/kernel/res_counter.c
KAMEZAWA Hiroyuki 4e649152cb memcg: some modification to softlimit under hierarchical memory reclaim.
This patch clean up/fixes for memcg's uncharge soft limit path.

Problems:
  Now, res_counter_charge()/uncharge() handles softlimit information at
  charge/uncharge and softlimit-check is done when event counter per memcg
  goes over limit. Now, event counter per memcg is updated only when
  memory usage is over soft limit. Here, considering hierarchical memcg
  management, ancesotors should be taken care of.

  Now, ancerstors(hierarchy) are handled in charge() but not in uncharge().
  This is not good.

  Prolems:
  1. memcg's event counter incremented only when softlimit hits. That's bad.
     It makes event counter hard to be reused for other purpose.

  2. At uncharge, only the lowest level rescounter is handled. This is bug.
     Because ancesotor's event counter is not incremented, children should
     take care of them.

  3. res_counter_uncharge()'s 3rd argument is NULL in most case.
     ops under res_counter->lock should be small. No "if" sentense is better.

Fixes:
  * Removed soft_limit_xx poitner and checks in charge and uncharge.
    Do-check-only-when-necessary scheme works enough well without them.

  * make event-counter of memcg incremented at every charge/uncharge.
    (per-cpu area will be accessed soon anyway)

  * All ancestors are checked at soft-limit-check. This is necessary because
    ancesotor's event counter may never be modified. Then, they should be
    checked at the same time.

Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Paul Menage <menage@google.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-10-01 16:11:13 -07:00

179 lines
3.8 KiB
C

/*
* resource cgroups
*
* Copyright 2007 OpenVZ SWsoft Inc
*
* Author: Pavel Emelianov <xemul@openvz.org>
*
*/
#include <linux/types.h>
#include <linux/parser.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/res_counter.h>
#include <linux/uaccess.h>
#include <linux/mm.h>
void res_counter_init(struct res_counter *counter, struct res_counter *parent)
{
spin_lock_init(&counter->lock);
counter->limit = RESOURCE_MAX;
counter->soft_limit = RESOURCE_MAX;
counter->parent = parent;
}
int res_counter_charge_locked(struct res_counter *counter, unsigned long val)
{
if (counter->usage + val > counter->limit) {
counter->failcnt++;
return -ENOMEM;
}
counter->usage += val;
if (counter->usage > counter->max_usage)
counter->max_usage = counter->usage;
return 0;
}
int res_counter_charge(struct res_counter *counter, unsigned long val,
struct res_counter **limit_fail_at)
{
int ret;
unsigned long flags;
struct res_counter *c, *u;
*limit_fail_at = NULL;
local_irq_save(flags);
for (c = counter; c != NULL; c = c->parent) {
spin_lock(&c->lock);
ret = res_counter_charge_locked(c, val);
spin_unlock(&c->lock);
if (ret < 0) {
*limit_fail_at = c;
goto undo;
}
}
ret = 0;
goto done;
undo:
for (u = counter; u != c; u = u->parent) {
spin_lock(&u->lock);
res_counter_uncharge_locked(u, val);
spin_unlock(&u->lock);
}
done:
local_irq_restore(flags);
return ret;
}
void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
{
if (WARN_ON(counter->usage < val))
val = counter->usage;
counter->usage -= val;
}
void res_counter_uncharge(struct res_counter *counter, unsigned long val)
{
unsigned long flags;
struct res_counter *c;
local_irq_save(flags);
for (c = counter; c != NULL; c = c->parent) {
spin_lock(&c->lock);
res_counter_uncharge_locked(c, val);
spin_unlock(&c->lock);
}
local_irq_restore(flags);
}
static inline unsigned long long *
res_counter_member(struct res_counter *counter, int member)
{
switch (member) {
case RES_USAGE:
return &counter->usage;
case RES_MAX_USAGE:
return &counter->max_usage;
case RES_LIMIT:
return &counter->limit;
case RES_FAILCNT:
return &counter->failcnt;
case RES_SOFT_LIMIT:
return &counter->soft_limit;
};
BUG();
return NULL;
}
ssize_t res_counter_read(struct res_counter *counter, int member,
const char __user *userbuf, size_t nbytes, loff_t *pos,
int (*read_strategy)(unsigned long long val, char *st_buf))
{
unsigned long long *val;
char buf[64], *s;
s = buf;
val = res_counter_member(counter, member);
if (read_strategy)
s += read_strategy(*val, s);
else
s += sprintf(s, "%llu\n", *val);
return simple_read_from_buffer((void __user *)userbuf, nbytes,
pos, buf, s - buf);
}
u64 res_counter_read_u64(struct res_counter *counter, int member)
{
return *res_counter_member(counter, member);
}
int res_counter_memparse_write_strategy(const char *buf,
unsigned long long *res)
{
char *end;
/* return RESOURCE_MAX(unlimited) if "-1" is specified */
if (*buf == '-') {
*res = simple_strtoull(buf + 1, &end, 10);
if (*res != 1 || *end != '\0')
return -EINVAL;
*res = RESOURCE_MAX;
return 0;
}
/* FIXME - make memparse() take const char* args */
*res = memparse((char *)buf, &end);
if (*end != '\0')
return -EINVAL;
*res = PAGE_ALIGN(*res);
return 0;
}
int res_counter_write(struct res_counter *counter, int member,
const char *buf, write_strategy_fn write_strategy)
{
char *end;
unsigned long flags;
unsigned long long tmp, *val;
if (write_strategy) {
if (write_strategy(buf, &tmp))
return -EINVAL;
} else {
tmp = simple_strtoull(buf, &end, 10);
if (*end != '\0')
return -EINVAL;
}
spin_lock_irqsave(&counter->lock, flags);
val = res_counter_member(counter, member);
*val = tmp;
spin_unlock_irqrestore(&counter->lock, flags);
return 0;
}