| Re: [ckrm-tech] [patch00/05]: Containers(V2)- Introduction [message #6652] |
Thu, 21 September 2006 00:30  |
Chandra Seetharaman
Messages: 88
Registered: August 2006
|
Member |
|
|
On Wed, 2006-09-20 at 12:57 -0700, Paul Menage wrote:
> On 9/20/06, Chandra Seetharaman <sekharan@us.ibm.com> wrote:
> > > At its most crude, this could be something like:
> > >
> > > struct container {
> > > #ifdef CONFIG_CPUSETS
> > > struct cpuset cs;
> > > #endif
> > > #ifdef CONFIG_RES_GROUPS
> > > struct resource_group rg;
> > > #endif
> > > };
> >
> > Won't it restrict the user to choose one of these, and not both.
>
> Not necessarily - you could have both compiled in, and each would only
> worry about the resource management that they cared about - e.g. you
> could use the memory node isolation portion of cpusets (in conjunction
> with fake numa nodes/zones) for memory containment, but give every
> cpuset access to all CPUs and control CPU usage via the resource
> groups CPU controller.
>
> The generic code would take care of details like container
> creation/destruction (with appropriate callbacks into cpuset and/or
> res_group code, tracking task membership of containers, etc.
What I am wondering is that whether the tight coupling of rg and cpuset
(into a container data structure) is ok.
>
> Paul
--
------------------------------------------------------------ ----------
Chandra Seetharaman | Be careful what you choose....
- sekharan@us.ibm.com | .......you may get it.
------------------------------------------------------------ ----------
|
|
|
|
|
|
| Re: [ckrm-tech] [patch00/05]: Containers(V2)- Introduction [message #6660 is a reply to message #6654] |
Thu, 21 September 2006 00:50  |
Chandra Seetharaman
Messages: 88
Registered: August 2006
|
Member |
|
|
On Wed, 2006-09-20 at 17:33 -0700, Paul Jackson wrote:
> Chandra wrote:
> > What I am wondering is that whether the tight coupling of rg and cpuset
> > (into a container data structure) is ok.
>
> Just guessing wildly here, but I'd anticipate that at best we
> (resource groups and cpusets) would share container mechanisms,
> but not share the same container instances.
That is what my thinking too.
>
--
------------------------------------------------------------ ----------
Chandra Seetharaman | Be careful what you choose....
- sekharan@us.ibm.com | .......you may get it.
------------------------------------------------------------ ----------
|
|
|
|
| Re: [ckrm-tech] [patch00/05]: Containers(V2)- Introduction [message #6747 is a reply to message #6652] |
Thu, 21 September 2006 00:34 |
Paul Menage
Messages: 642
Registered: September 2006
|
Senior Member |
|
|
On 9/20/06, Chandra Seetharaman <sekharan@us.ibm.com> wrote:
>
> What I am wondering is that whether the tight coupling of rg and cpuset
> (into a container data structure) is ok.
Can you suggest a realistic scenario in which it's not? Don't forget
that since the container abstraction is hierarchical, you don't have
to use both at the same level. So you could easily e.g. have a parent
container in which you bound to a set of memory/cpu nodes, but had no
rg limits, and several subcontainers where you configured nothing
special for cpuset parameters (so inherited the parent params) but
tweaked different rg parameters.
Paul
|
|
|
|
OpenVZ Forum
Members
Search
Help
Register
Login
Home
