Li Zefan wrote:
quoted text
> Li Zefan 写道:
>> Balbir Singh wrote:
>>> A new configuration file called soft_limit_in_bytes is added. The parsing
>>> and configuration rules remain the same as for the limit_in_bytes user
>>> interface.
>>>
>>> A global list of all memory cgroups over their soft limit is maintained.
>>> This list is then used to reclaim memory on global pressure. A cgroup is
>>> removed from the list when the cgroup is deleted.
>>>
>>> The global list is protected with a read-write spinlock.
>>>
>> You are not using read-write spinlock..
>>
> 
> Ah, the spinlock is changed to r/w spinlock in [PATCH 3/4].
> 
>>> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
>>> ---
>>>
>>>  mm/memcontrol.c |   33 ++++++++++++++++++++++++++++++++-
>>>  1 file changed, 32 insertions(+), 1 deletion(-)
>>>
>>> diff -puN mm/memcontrol.c~memory-controller-add-soft-limit-interface mm/memcontrol.c
>>> --- linux-2.6.25-rc2/mm/memcontrol.c~memory-controller-add-soft-limit-interface	2008-02-19 12:31:49.000000000 +0530
>>> +++ linux-2.6.25-rc2-balbir/mm/memcontrol.c	2008-02-19 12:31:49.000000000 +0530
>>> @@ -35,6 +35,10 @@
>>>  
>>>  struct cgroup_subsys mem_cgroup_subsys;
>>>  static const int MEM_CGROUP_RECLAIM_RETRIES = 5;
>>> +static spinlock_t mem_cgroup_sl_list_lock;	/* spin lock that protects */
>>> +						/* the list of cgroups over*/
>>> +						/* their soft limit */
>>> +static struct list_head mem_cgroup_sl_exceeded_list;
>>>  
>>>  /*
>>>   * Statistics for memory cgroup.
>>> @@ -136,6 +140,10 @@ struct mem_cgroup {
>>>  	 * statistics.
>>>  	 */
>>>  	struct mem_cgroup_stat stat;
>>> +	/*
>>> +	 * List of all mem_cgroup's that exceed their soft limit
>>> +	 */
>>> +	struct list_head sl_exceeded_list;
>>>  };
>>>  
>>>  /*
>>> @@ -679,6 +687,18 @@ retry:
>>>  		goto retry;
>>>  	}
>>>  
>>> +	/*
>>> +	 * If we exceed our soft limit, we get added to the list of
>>> +	 * cgroups over their soft limit
>>> +	 */
>>> +	if (!res_counter_check_under_limit(&mem->res, RES_SOFT_LIMIT)) {
>>> +		spin_lock_irqsave(&mem_cgroup_sl_list_lock, flags);
>>> +		if (list_empty(&mem->sl_exceeded_list))
>>> +			list_add_tail(&mem->sl_exceeded_list,
>>> +						&mem_cgroup_sl_exceeded_list);
>>> +		spin_unlock_irqrestore(&mem_cgroup_sl_list_lock, flags);
>>> +	}
>>> +
>>>  	mz = page_cgroup_zoneinfo(pc);
>>>  	spin_lock_irqsave(&mz->lru_lock, flags);
>>>  	/* Update statistics vector */
>>> @@ -736,13 +756,14 @@ void mem_cgroup_uncharge(struct page_cgr
>>>  	if (atomic_dec_and_test(&pc->ref_cnt)) {
>>>  		page = pc->page;
>>>  		mz = page_cgroup_zoneinfo(pc);
>>> +		mem = pc->mem_cgroup;
>>>  		/*
>>>  		 * get page->cgroup and clear it under lock.
>>>  		 * force_empty can drop page->cgroup without checking refcnt.
>>>  		 */
>>>  		unlock_page_cgroup(page);
>>> +
>>>  		if (clear_page_cgroup(page, pc) == pc) {
>>> -			mem = pc->mem_cgroup;
>>>  			css_put(&mem->css);
>>>  			res_counter_uncharge(&mem->res, PAGE_SIZE);
>>>  			spin_lock_irqsave(&mz->lru_lock, flags);
>>> @@ -1046,6 +1067,12 @@ static struct cftype mem_cgroup_files[] 
>>>  		.name = "stat",
>>>  		.open = mem_control_stat_open,
>>>  	},
>>> +	{
>>> +		.name = "soft_limit_in_bytes",
>>> +		.private = RES_SOFT_LIMIT,
>>> +		.write = mem_cgroup_write,
>>> +		.read = mem_cgroup_read,
>>> +	},
>>>  };
>>>  
>>>  static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
>>> @@ -1097,6 +1124,9 @@ mem_cgroup_create(struct cgroup_subsys *
>>>  	if (unlikely((cont->parent) == NULL)) {
>>>  		mem = &init_mem_cgroup;
>>>  		init_mm.mem_cgroup = mem;
>>> +		INIT_LIST_HEAD(&mem->sl_exceeded_list);
>>> +		spin_lock_init(&mem_cgroup_sl_list_lock);
>>> +		INIT_LIST_HEAD(&mem_cgroup_sl_exceeded_list);
>>>  	} else
>>>  		mem = kzalloc(sizeof(struct mem_cgroup), GFP_KERNEL);
>>>  
>>> @@ -1104,6 +1134,7 @@ mem_cgroup_create(struct cgroup_subsys *
>>>  		return NULL;
>>>  
>>>  	res_counter_init(&mem->res);
>>> +	INIT_LIST_HEAD(&mem->sl_exceeded_list);
>>>  
>> mem->sl_exceeded_list initialized twice ?
>>

Good catch, yes for the root, it can be initialized twice. I'll fix it in v3.

quoted text
>>>  	memset(&mem->info, 0, sizeof(mem->info));
>>>  
>>> _
>>>
>> --


-- 
	Warm Regards,
	Balbir Singh
	Linux Technology Center
	IBM, ISTL

--
unsubscribe notice
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/