perf tools: Introduce new sort type "socket" for the processor socket
This patch enable perf report to sort by processor socket:
$ perf report --stdio --sort socket,comm,dso,symbol
# To display the perf.data header info, please use --header/--header-only options.
#
# Total Lost Samples: 0
#
# Samples: 686 of event 'cycles'
# Event count (approx.): 349215462
#
# Overhead SOCKET Command Shared Object Symbol
# ........ ...... ....... ................ ............................
#
97.05% 000 test test [.] plusB_c
0.98% 000 test test [.] plusA_c
0.93% 001 perf [kernel.vmlinux] [k] smp_call_function_single
0.19% 001 perf [kernel.vmlinux] [k] page_fault
0.19% 001 swapper [kernel.vmlinux] [k] pm_qos_request
0.16% 000 test [kernel.vmlinux] [k] add_mm_counter_fast
Signed-off-by: Kan Liang <kan.liang@intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1441377946-44429-2-git-send-email-kan.liang@intel.com
[ Fix col calc, un-allcapsify col header & read the topology when not using perf.data ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 9c7981b..92361a7 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -68,7 +68,7 @@
--sort=::
Sort histogram entries by given key(s) - multiple keys can be specified
in CSV format. Following sort keys are available:
- pid, comm, dso, symbol, parent, cpu, srcline, weight, local_weight.
+ pid, comm, dso, symbol, parent, cpu, socket, srcline, weight, local_weight.
Each key has following meaning:
@@ -79,6 +79,7 @@
- parent: name of function matched to the parent regex filter. Unmatched
entries are displayed as "[other]".
- cpu: cpu number the task ran at the time of sample
+ - socket: processor socket number the task ran at the time of sample
- srcline: filename and line number executed at the time of sample. The
DWARF debugging info must be provided.
- srcfile: file name of the source file of the same. Requires dwarf
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index e5ca684..bdaf44f 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -963,6 +963,13 @@
machine__synthesize_threads(&top->session->machines.host, &opts->target,
top->evlist->threads, false, opts->proc_map_timeout);
+
+ if (sort__has_socket) {
+ ret = perf_env__read_cpu_topology_map(&perf_env);
+ if (ret < 0)
+ goto out_err_cpu_topo;
+ }
+
ret = perf_top__start_counters(top);
if (ret)
goto out_delete;
@@ -1020,6 +1027,14 @@
top->session = NULL;
return ret;
+
+out_err_cpu_topo: {
+ char errbuf[BUFSIZ];
+ const char *err = strerror_r(-ret, errbuf, sizeof(errbuf));
+
+ ui__error("Could not read the CPU topology map: %s\n", err);
+ goto out_delete;
+}
}
static int
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index d2b94c4..ba72a29 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -145,6 +145,7 @@
}
hists__new_col_len(hists, HISTC_CPU, 3);
+ hists__new_col_len(hists, HISTC_SOCKET, 6);
hists__new_col_len(hists, HISTC_MEM_LOCKED, 6);
hists__new_col_len(hists, HISTC_MEM_TLB, 22);
hists__new_col_len(hists, HISTC_MEM_SNOOP, 12);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index de6d58e..5d04d28 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -29,6 +29,7 @@
HISTC_COMM,
HISTC_PARENT,
HISTC_CPU,
+ HISTC_SOCKET,
HISTC_SRCLINE,
HISTC_SRCFILE,
HISTC_MISPREDICT,
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index a97bcee..6b9556d 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -21,6 +21,7 @@
int sort__has_parent = 0;
int sort__has_sym = 0;
int sort__has_dso = 0;
+int sort__has_socket = 0;
enum sort_mode sort__mode = SORT_MODE__NORMAL;
@@ -421,6 +422,27 @@
.se_width_idx = HISTC_CPU,
};
+/* --sort socket */
+
+static int64_t
+sort__socket_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+ return right->socket - left->socket;
+}
+
+static int hist_entry__socket_snprintf(struct hist_entry *he, char *bf,
+ size_t size, unsigned int width)
+{
+ return repsep_snprintf(bf, size, "%*.*d", width, width-3, he->socket);
+}
+
+struct sort_entry sort_socket = {
+ .se_header = "Socket",
+ .se_cmp = sort__socket_cmp,
+ .se_snprintf = hist_entry__socket_snprintf,
+ .se_width_idx = HISTC_SOCKET,
+};
+
/* sort keys for branch stacks */
static int64_t
@@ -1248,6 +1270,7 @@
DIM(SORT_SYM, "symbol", sort_sym),
DIM(SORT_PARENT, "parent", sort_parent),
DIM(SORT_CPU, "cpu", sort_cpu),
+ DIM(SORT_SOCKET, "socket", sort_socket),
DIM(SORT_SRCLINE, "srcline", sort_srcline),
DIM(SORT_SRCFILE, "srcfile", sort_srcfile),
DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
@@ -1550,6 +1573,8 @@
} else if (sd->entry == &sort_dso) {
sort__has_dso = 1;
+ } else if (sd->entry == &sort_socket) {
+ sort__has_socket = 1;
}
return __sort_dimension__add(sd);
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 7cf1cf7..c06b757 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -34,6 +34,7 @@
extern int sort__need_collapse;
extern int sort__has_parent;
extern int sort__has_sym;
+extern int sort__has_socket;
extern enum sort_mode sort__mode;
extern struct sort_entry sort_comm;
extern struct sort_entry sort_dso;
@@ -173,6 +174,7 @@
SORT_SYM,
SORT_PARENT,
SORT_CPU,
+ SORT_SOCKET,
SORT_SRCLINE,
SORT_SRCFILE,
SORT_LOCAL_WEIGHT,