perf bench numa: Fix immediate meeting of convergence condition

Petr Holasek · acmel · commit 1d90a685eb75 · 2015-04-27T13:57:50.000-03:00
This patch fixes the race in the beginning of benchmark run when some threads hasn't got assigned curr_cpu yet so they don't occur in nodes-of-process stats and benchmark concludes that all remaining threads are converged already. The race can be reproduced with small amount of threads and some bigger amount of shared process memory, e.g. one process, two threads and 5GB of process memory. Signed-off-by: Petr Holasek <pholasek@redhat.com> Reviewed-by: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/1429198699-25039-4-git-send-email-pholasek@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
@@ -828,6 +828,9 @@ static int count_process_nodes(int process_nr)
 		td = g->threads + task_nr;
 
 		node = numa_node_of_cpu(td->curr_cpu);
+		if (node < 0) /* curr_cpu was likely still -1 */
+			return 0;
+
 		node_present[node] = 1;
 	}
 
@@ -882,6 +885,11 @@ static void calc_convergence_compression(int *strong)
 	for (p = 0; p < g->p.nr_proc; p++) {
 		unsigned int nodes = count_process_nodes(p);
 
+		if (!nodes) {
+			*strong = 0;
+			return;
+		}
+
 		nodes_min = min(nodes, nodes_min);
 		nodes_max = max(nodes, nodes_max);
 	}
