On Sun 02-02-14 20:33:46, Vladimir Davydov wrote:
Per-memcg kmem caches are named as follows:
global-cache-name(cgroup-kmem-id:cgroup-name)
where cgroup-kmem-id is the unique id of the memcg the cache belongs
to, cgroup-name is the relative name of the memcg on the cgroup fs.
Cache
On Mon 03-02-14 10:57:03, Vladimir Davydov wrote:
On 02/03/2014 10:21 AM, David Rientjes wrote:
On Sun, 2 Feb 2014, Vladimir Davydov wrote:
Per-memcg kmem caches are named as follows:
global-cache-name(cgroup-kmem-id:cgroup-name)
where cgroup-kmem-id is the unique id of the memcg
On 02/04/2014 06:40 PM, Michal Hocko wrote:
On Sun 02-02-14 20:33:46, Vladimir Davydov wrote:
Per-memcg kmem caches are named as follows:
global-cache-name(cgroup-kmem-id:cgroup-name)
where cgroup-kmem-id is the unique id of the memcg the cache belongs
to, cgroup-name is the relative name
On 02/04/2014 06:52 PM, Michal Hocko wrote:
On Sun 02-02-14 20:33:48, Vladimir Davydov wrote:
Suppose we are creating memcg cache A that could be merged with cache B
of the same memcg. Since any memcg cache has the same parameters as its
parent cache, parent caches PA and PB of memcg caches A
On Sun 02-02-14 20:33:47, Vladimir Davydov wrote:
The cgroup name is not informative at all in case the cgroup hierarchy
is not flat. Besides, we can always find the memcg a particular cache
belongs to by its kmemcg id, which is now exported via memory.kmem.id
cgroup fs file for each memcg.
On Sun 02-02-14 20:33:48, Vladimir Davydov wrote:
Suppose we are creating memcg cache A that could be merged with cache B
of the same memcg. Since any memcg cache has the same parameters as its
parent cache, parent caches PA and PB of memcg caches A and B must be
mergeable too. That means PA
On Tue 04-02-14 18:59:23, Vladimir Davydov wrote:
On 02/04/2014 06:52 PM, Michal Hocko wrote:
On Sun 02-02-14 20:33:48, Vladimir Davydov wrote:
Suppose we are creating memcg cache A that could be merged with cache B
of the same memcg. Since any memcg cache has the same parameters as its
On 02/04/2014 06:45 PM, Michal Hocko wrote:
On Sun 02-02-14 20:33:47, Vladimir Davydov wrote:
The cgroup name is not informative at all in case the cgroup hierarchy
is not flat. Besides, we can always find the memcg a particular cache
belongs to by its kmemcg id, which is now exported via
On Tue 04-02-14 19:11:24, Vladimir Davydov wrote:
On 02/04/2014 06:45 PM, Michal Hocko wrote:
On Sun 02-02-14 20:33:47, Vladimir Davydov wrote:
The cgroup name is not informative at all in case the cgroup hierarchy
is not flat. Besides, we can always find the memcg a particular cache
On 02/04/2014 07:11 PM, Michal Hocko wrote:
On Tue 04-02-14 18:59:23, Vladimir Davydov wrote:
On 02/04/2014 06:52 PM, Michal Hocko wrote:
On Sun 02-02-14 20:33:48, Vladimir Davydov wrote:
Suppose we are creating memcg cache A that could be merged with cache B
of the same memcg. Since any
On Tue 04-02-14 11:39:07, Vladimir Davydov wrote:
This patch cleanups the memcg cache creation path as follows:
- Move memcg cache name creation to a separate function to be called
from kmem_cache_create_memcg(). This allows us to get rid of the
mutex protecting the temporary buffer
On Tue, Feb 4, 2014 at 7:27 PM, Vladimir Davydov vdavy...@parallels.com wrote:
On 02/04/2014 07:11 PM, Michal Hocko wrote:
On Tue 04-02-14 18:59:23, Vladimir Davydov wrote:
On 02/04/2014 06:52 PM, Michal Hocko wrote:
On Sun 02-02-14 20:33:48, Vladimir Davydov wrote:
Suppose we are creating
On 02/04/2014 07:43 PM, Glauber Costa wrote:
On Tue, Feb 4, 2014 at 7:27 PM, Vladimir Davydov vdavy...@parallels.com
wrote:
On 02/04/2014 07:11 PM, Michal Hocko wrote:
On Tue 04-02-14 18:59:23, Vladimir Davydov wrote:
On 02/04/2014 06:52 PM, Michal Hocko wrote:
On Sun 02-02-14 20:33:48,
On 02/04/2014 07:33 PM, Michal Hocko wrote:
On Tue 04-02-14 11:39:07, Vladimir Davydov wrote:
This patch cleanups the memcg cache creation path as follows:
- Move memcg cache name creation to a separate function to be called
from kmem_cache_create_memcg(). This allows us to get rid of the
On Mon 03-02-14 19:54:38, Vladimir Davydov wrote:
Memcg-awareness turned kmem_cache_create() into a dirty interweaving of
memcg-only and except-for-memcg calls. To clean this up, let's create a
separate function handling memcg caches creation. Although this will
result in the two functions
On 02/04/2014 08:03 PM, Michal Hocko wrote:
On Mon 03-02-14 19:54:38, Vladimir Davydov wrote:
Memcg-awareness turned kmem_cache_create() into a dirty interweaving of
memcg-only and except-for-memcg calls. To clean this up, let's create a
separate function handling memcg caches creation.
On Fri, 17 Jan 2014 23:25:30 +0400 Vladimir Davydov vdavy...@parallels.com
wrote:
Each shrinker must define the number of seeks it takes to recreate a
shrinkable cache object. It is used to balance slab reclaim vs page
reclaim: assuming it costs one seek to replace an LRU page, we age equal
17 matches
Mail list logo