Re: [RFC PATCH 3/6] memcg: restructure shrink_slab to walk memcg hierarchy

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On 08/17/2012 09:53 AM, Ying Han wrote:
>> > If the other shrinkers are not memcg aware, they will end up discarding
>> > random objects that may or may not have anything to do with the group
>> > under pressure, right?
> The main contributor of the accounted slabs and also reclaimable are
> vfs objects. Also we know dentry pins inode,
> so I wonder how bad the problem would be. Do you have specific example
> on which shrinker could cause the problem?
> 

I don't have any specific shrinkers in mind, but as you said yourself:
the main contributors comes from the VFS. So as long as we shrink the
VFS objects - and those will be memcg aware, why bother with the others?

It seems to me that we're just risking breaking isolation for very
little gain.


--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>


[Index of Archives]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Bugtraq]     [Linux]     [Linux OMAP]     [Linux MIPS]     [ECOS]     [Asterisk Internet PBX]     [Linux API]