Re: [PATCH v4 1/1] perf/bench/numa: Fixup discontiguous/sparse numa nodes

2017-11-23 Thread Arnaldo Carvalho de Melo
Em Wed, Nov 22, 2017 at 10:18:13PM +0530, Satheesh Rajendran escreveu: > On Wed, 2017-11-22 at 21:39 +0530, Naveen N. Rao wrote: > > >   sum += nr; > > >   } > > >   BUG_ON(nr_min > nr_max); > > > - > > >   BUG_ON(sum > g->p.nr_tasks); > > > > Looks like that change to remo

Re: [PATCH v4 1/1] perf/bench/numa: Fixup discontiguous/sparse numa nodes

2017-11-22 Thread Satheesh Rajendran
On Wed, 2017-11-22 at 21:39 +0530, Naveen N. Rao wrote: > >   sum += nr; > >   } > >   BUG_ON(nr_min > nr_max); > > - > >   BUG_ON(sum > g->p.nr_tasks); > > Looks like that change to remove a blank line did slip in, but that's > a  > small nit. Apart from that, the patch lo

Re: [PATCH v4 1/1] perf/bench/numa: Fixup discontiguous/sparse numa nodes

2017-11-22 Thread Naveen N. Rao
sathn...@linux.vnet.ibm.com wrote: From: Satheesh Rajendran Certain systems are designed to have sparse/discontiguous nodes. On such systems, perf bench numa hangs, shows wrong number of nodes and shows values for non-existent nodes. Handle this by only taking nodes that are exposed by kernel t