Re: [Xen-devel] [PATCH RESEND 11/12] xl: numa-sched: enable getting/specifying per-vcpu node-affinity

[Ian Jackson <Ian.Jackson@xxxxxxxxxxxxx>]

Dario Faggioli writes ("Re: [PATCH RESEND 11/12] xl: numa-sched: enable 
getting/specifying per-vcpu node-affinity"):
> On gio, 2013-11-07 at 18:33 +0000, Ian Jackson wrote:
> > Dario Faggioli writes ("[PATCH RESEND 11/12] xl: numa-sched: enable 
> > getting/specifying per-vcpu node-affinity"):
> > > # xl vcpu-list -n
> > > 
> > > Name          ID  VCPU   CPU State   Time(s) CPU Affinity / NUMA Affinity
> > > Domain-0       0     0    8   -b-       4.4  any cpu / any node
> > > Domain-0       0     1    0   -b-       1.2  any cpu / any node
> > > vm-test        1     0    8   -b-       2.4  any cpu / 1
> > > vm-test        1     1   13   -b-       3.3  any cpu / 1
...
> > Can you use the same syntax for printing as would be legal in
> > the config file ?
> > 
> That is actually what is happening, for single cpu/node bitmaps.

Err, I meant always, not just in one special case.  Eg, "any cpu"
should be "all".

I don't know if you want to try to boil ranges cpumap ranges down to
node sets during printing - that's probably too hard.

> The problem arises when I need to print two bitmaps, one next to the
> other, like the cpumap for vCPU affinity and the nodemap for NUMA
> affinity above.

Separating them with a / is fine I think.

> (BTW, the new version of the series I'm preparing will be very
> different, considering we decided with George and Jan to change the
> fundamental architecture of the whole thing. However, there still may be
> the need to doing something like the above, independently whether it
> will be for printing hard and soft affinity, instead than CPU and NUMA
> affinity.)

Right.

> > > xl manual page is updated accordingly.
> > 
> > > -static int update_cpumap_range(const char *str, libxl_bitmap *cpumap)
> > > +static int update_bitmap_range(const char *str, libxl_bitmap *bitmap)
> > 
> > I don't understand how this set of changes relates to this patch.
> > 
> Well, I need to parse strings that may be very similar (the usual
> "1,2-7,^4" stuff), but with potentially different meaning for the
> various substrings (pcpus vs. nodes).

So perhaps there should be a pre-patch to change the names of these
functions.

> Anyway, in case I'm keeping this, or doing something similar to this for
> the new series, I'll try to figure out a way to make it more simple, or
> at minimum more readable and clarify why it is needed (by breaking the
> patch down, etc.).

Thanks,
Ian.

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel