[PATCH v5 3/3] mm/page_alloc: Keep memoryless cpuless node 0 offline

[Srikar Dronamraju]

* Michal Hocko <mhocko at kernel.org> [2020-07-02 10:41:23]:

> On Thu 02-07-20 12:14:08, Srikar Dronamraju wrote:
> > * Michal Hocko <mhocko at kernel.org> [2020-07-01 14:21:10]:
> > 
> > > > >>>>> The autonuma problem sounds interesting but again this patch doesn't
> > > > >>>>> really solve the underlying problem because I strongly suspect that the
> > > > >>>>> problem is still there when a numa node gets all its memory offline as
> > > > >>>>> mentioned above.
> > > 
> > > I would really appreciate a feedback to these two as well.
> > 
> > 1. Its not just numactl that's to be fixed but all tools/utilities that
> > depend on /sys/devices/system/node/online. Are we saying to not rely/believe
> > in the output given by the kernel but do further verification?  
> 
> No, what we are saying is that even an online node might have zero
> number of online pages/cpus. So the online status is not really
> something that matters. If people are confused by that output then user
> space tools can make their confusion go away. I really do not understand
> why the kernel should do any logic there.

The user facing teams are saying they are getting queries from the users who
are unable to understand from the tools/sysfs files why a node is online and
but has no attached resources. Its the amount of time that is being spent on
these issues that triggered the patch. Initially even I was skeptical that
this was a non-issue.

> 
> > Also how would the user space differentiate between the case where the
> > Kernel missed marking a node as offline to the case where the memory was
> > offlined on a cpuless node but node wasn't offline?.
> 
> What I am arguing is that those two shouldn't be any different. Really!
> 
> > 2. Regarding the autonuma, the case of offline memory is user/admin driven,
> > so if there is a performance hit, its something that's driven by his
> > user/admin actions. Also how often do we see users offline complete memory
> > of cpuless node on a 2 node system?
> 
> How often do we see crippled HW configurations like that? Really if
> autonuma should be made more clever for one case it should recognize the
> other as well.
> 

Lets take a 16 socket PowerVM system and assume that 32 lpars are created
on that socket, i.e 2 lpars for each socket. (PowerVM has the final say on
how the lpars are created.) In such a case, we can expect 30 out of the 32
lpars to face this problem, with the only 2 lpars that actually run on
socket 0 having the correct configuration.

> > > 
> > > This begs a question whether ppc can do the same thing?
> > 
> > Certainly ppc can be made to adapt to this situation but that would be a
> > workaround. Do we have a reason why we think node 0 is unique and special?
> 
> It is not. As replied in other email in this thread. I would hope for
> having less hacks in the numa initialization. Cleaning up the mess is
> would be a lot of work and testing on all NUMA capable architectures.
> This is a heritage from the past I am afraid. All that I am arguing here
> is that your touch to the generic code with a very simple looking patch
> might have side effects which are pretty much impossible to review.
> Moreover it seems that nothing but ppc really needs this treatment.
> So fixing it in ppc specific code sounds much more safe.
> 
> Normally I would really push for a generic solution but after getting
> burned several times in this area I do not dare anymore. The problem is
> not in the code complexity but in how spread it is in places where you
> do not expect side effects.
> 

I do understand and respect your viewpoint.

> -- 
> Michal Hocko
> SUSE Labs

-- 
Thanks and Regards
Srikar Dronamraju