diff options
author | Jiri Olsa <jolsa@kernel.org> | 2019-08-29 13:31:48 +0200 |
---|---|---|
committer | Arnaldo Carvalho de Melo <acme@redhat.com> | 2019-11-06 15:49:39 -0300 |
commit | 389799a7a1e86c55f38897e679762efadcc9dedd (patch) | |
tree | 28910087dcd21c5b1c7eb856517b96447fbd617f /tools/perf/util/env.c | |
parent | perf vendor events intel: Update all the Intel JSON metrics from TMAM 3.6. (diff) | |
download | linux-389799a7a1e86c55f38897e679762efadcc9dedd.tar.gz linux-389799a7a1e86c55f38897e679762efadcc9dedd.tar.bz2 linux-389799a7a1e86c55f38897e679762efadcc9dedd.zip |
perf env: Add perf_env__numa_node()
To speed up cpu to node lookup, add perf_env__numa_node(), that creates
cpu array on the first lookup, that holds numa nodes for each stored
cpu.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Joe Mario <jmario@redhat.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20190904073415.723-3-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools/perf/util/env.c')
-rw-r--r-- | tools/perf/util/env.c | 40 |
1 files changed, 40 insertions, 0 deletions
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index 2a91a10ccfcc..6242a9215df7 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -180,6 +180,7 @@ void perf_env__exit(struct perf_env *env) zfree(&env->sibling_threads); zfree(&env->pmu_mappings); zfree(&env->cpu); + zfree(&env->numa_map); for (i = 0; i < env->nr_numa_nodes; i++) perf_cpu_map__put(env->numa_nodes[i].map); @@ -354,3 +355,42 @@ const char *perf_env__arch(struct perf_env *env) return normalize_arch(arch_name); } + + +int perf_env__numa_node(struct perf_env *env, int cpu) +{ + if (!env->nr_numa_map) { + struct numa_node *nn; + int i, nr = 0; + + for (i = 0; i < env->nr_numa_nodes; i++) { + nn = &env->numa_nodes[i]; + nr = max(nr, perf_cpu_map__max(nn->map)); + } + + nr++; + + /* + * We initialize the numa_map array to prepare + * it for missing cpus, which return node -1 + */ + env->numa_map = malloc(nr * sizeof(int)); + if (!env->numa_map) + return -1; + + for (i = 0; i < nr; i++) + env->numa_map[i] = -1; + + env->nr_numa_map = nr; + + for (i = 0; i < env->nr_numa_nodes; i++) { + int tmp, j; + + nn = &env->numa_nodes[i]; + perf_cpu_map__for_each_cpu(j, tmp, nn->map) + env->numa_map[j] = i; + } + } + + return cpu >= 0 && cpu < env->nr_numa_map ? env->numa_map[cpu] : -1; +} |