From: Don Zickus <dzickus@redhat.com>
To: acme@ghostprotocols.net
Cc: LKML <linux-kernel@vger.kernel.org>,
jolsa@redhat.com, jmario@redhat.com, fowles@inreach.com,
eranian@google.com, Don Zickus <dzickus@redhat.com>
Subject: [PATCH 04/19] perf: Allow ability to map cpus to nodes easily
Date: Fri, 28 Feb 2014 12:42:53 -0500 [thread overview]
Message-ID: <1393609388-40489-5-git-send-email-dzickus@redhat.com> (raw)
In-Reply-To: <1393609388-40489-1-git-send-email-dzickus@redhat.com>
This patch figures out the max number of cpus and nodes that are on the
system and creates a map of cpu to node. This allows us to provide a cpu
and quickly get the node associated with it.
It was mostly copied from builtin-kmem.c and tweaked slightly to use less memory
(use possible cpus instead of max). It also calculates the max number of nodes.
Signed-off-by: Don Zickus <dzickus@redhat.com>
---
tools/perf/util/cpumap.c | 150 +++++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/cpumap.h | 35 +++++++++++
2 files changed, 185 insertions(+)
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 7fe4994..d19d5b3 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -317,3 +317,153 @@ int cpu_map__build_core_map(struct cpu_map *cpus, struct cpu_map **corep)
{
return cpu_map__build_map(cpus, corep, cpu_map__get_core);
}
+
+/* setup simple routines to easily access node numbers given a cpu number */
+
+
+#define PATH_SYS_NODE "/sys/devices/system/node"
+
+/* Determine highest possible cpu in the system for sparse allocation */
+static void set_max_cpu_num(void)
+{
+ FILE *fp;
+ char buf[256];
+ int num;
+
+ /* set up default */
+ max_cpu_num = 4096;
+
+ /* get the highest possible cpu number for a sparse allocation */
+ fp = fopen("/sys/devices/system/cpu/possible", "r");
+ if (!fp)
+ goto out;
+
+ num = fread(&buf, 1, sizeof(buf), fp);
+ if (!num)
+ goto out_close;
+ buf[num] = '\0';
+
+ /* start on the right, to find highest cpu num */
+ while (--num) {
+ if ((buf[num] == ',') || (buf[num] == '-')) {
+ num++;
+ break;
+ }
+ }
+ if (sscanf(&buf[num], "%d", &max_cpu_num) < 1)
+ goto out_close;
+
+ max_cpu_num++;
+
+ fclose(fp);
+ return;
+
+out_close:
+ fclose(fp);
+out:
+ pr_err("Failed to read max cpus, using default of %d\n",
+ max_cpu_num);
+ return;
+}
+
+/* Determine highest possible node in the system for sparse allocation */
+static void set_max_node_num(void)
+{
+ FILE *fp;
+ char buf[256];
+ int num;
+
+ /* set up default */
+ max_node_num = 8;
+
+ /* get the highest possible cpu number for a sparse allocation */
+ fp = fopen("/sys/devices/system/node/possible", "r");
+ if (!fp)
+ goto out;
+
+ num = fread(&buf, 1, sizeof(buf), fp);
+ if (!num)
+ goto out_close;
+ buf[num] = '\0';
+
+ /* start on the right, to find highest node num */
+ while (--num) {
+ if ((buf[num] == ',') || (buf[num] == '-')) {
+ num++;
+ break;
+ }
+ }
+ if (sscanf(&buf[num], "%d", &max_node_num) < 1)
+ goto out_close;
+
+ max_node_num++;
+
+ fclose(fp);
+ return;
+
+out_close:
+ fclose(fp);
+out:
+ pr_err("Failed to read max nodes, using default of %d\n",
+ max_node_num);
+ return;
+}
+
+static int init_cpunode_map(void)
+{
+ int i;
+
+ set_max_cpu_num();
+ set_max_node_num();
+
+ cpunode_map = calloc(max_cpu_num, sizeof(int));
+ if (!cpunode_map) {
+ pr_err("%s: calloc failed\n", __func__);
+ goto out;
+ }
+
+ for (i = 0; i < max_cpu_num; i++)
+ cpunode_map[i] = -1;
+
+ return 0;
+out:
+ return -1;
+}
+
+int cpu_map__setup_cpunode_map(void)
+{
+ struct dirent *dent1, *dent2;
+ DIR *dir1, *dir2;
+ unsigned int cpu, mem;
+ char buf[PATH_MAX];
+
+ /* initialize globals */
+ if (init_cpunode_map())
+ return -1;
+
+ dir1 = opendir(PATH_SYS_NODE);
+ if (!dir1)
+ return 0;
+
+ /* walk tree and setup map */
+ while ((dent1 = readdir(dir1)) != NULL) {
+ if (dent1->d_type != DT_DIR ||
+ sscanf(dent1->d_name, "node%u", &mem) < 1)
+ continue;
+
+ snprintf(buf, PATH_MAX, "%s/%s", PATH_SYS_NODE, dent1->d_name);
+ dir2 = opendir(buf);
+ if (!dir2)
+ continue;
+ while ((dent2 = readdir(dir2)) != NULL) {
+ if (dent2->d_type != DT_LNK ||
+ sscanf(dent2->d_name, "cpu%u", &cpu) < 1)
+ continue;
+ cpunode_map[cpu] = mem;
+ }
+ closedir(dir2);
+ }
+ closedir(dir1);
+ return 0;
+}
+
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index b123bb9..d6fde2b 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -4,6 +4,9 @@
#include <stdio.h>
#include <stdbool.h>
+#include "perf.h"
+#include "util/debug.h"
+
struct cpu_map {
int nr;
int map[];
@@ -46,4 +49,36 @@ static inline bool cpu_map__empty(const struct cpu_map *map)
return map ? map->map[0] == -1 : true;
}
+int max_cpu_num;
+int max_node_num;
+int *cpunode_map;
+
+int cpu_map__setup_cpunode_map(void);
+
+static inline int cpu_map__max_node(void)
+{
+ if (unlikely(!max_node_num))
+ pr_debug("cpu_map not initiailzed\n");
+
+ return max_node_num;
+}
+
+static inline int cpu_map__max_cpu(void)
+{
+ if (unlikely(!max_cpu_num))
+ pr_debug("cpu_map not initiailzed\n");
+
+ return max_cpu_num;
+}
+
+static inline int cpu_map__get_node(int cpu)
+{
+ if (unlikely(cpunode_map == NULL)) {
+ pr_debug("cpu_map not initialized\n");
+ return -1;
+ }
+
+ return cpunode_map[cpu];
+}
+
#endif /* __PERF_CPUMAP_H */
--
1.7.11.7
next prev parent reply other threads:[~2014-02-28 17:51 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-02-28 17:42 [PATCH 00/19 V2] perf, c2c: Add new tool to analyze cacheline contention on NUMA systems Don Zickus
2014-02-28 17:42 ` [PATCH 01/19] Revert "perf: Disable PERF_RECORD_MMAP2 support" Don Zickus
2014-02-28 17:42 ` [PATCH 02/19] perf, sort: Add physid sorting based on mmap2 data Don Zickus
2014-03-19 10:45 ` Jiri Olsa
2014-03-19 13:36 ` Don Zickus
2014-02-28 17:42 ` [PATCH 03/19] perf, sort: Allow unique sorting instead of combining hist_entries Don Zickus
2014-02-28 17:42 ` Don Zickus [this message]
2014-03-19 12:48 ` [PATCH 04/19] perf: Allow ability to map cpus to nodes easily Jiri Olsa
2014-03-19 13:38 ` Don Zickus
2014-03-19 13:22 ` Jiri Olsa
2014-02-28 17:42 ` [PATCH 05/19] perf, kmem: Utilize the new generic cpunode_map Don Zickus
2014-02-28 17:42 ` [PATCH 06/19] perf: Fix stddev calculation Don Zickus
2014-02-28 17:42 ` [PATCH 07/19] perf, callchain: Add generic callchain print handler for stdio Don Zickus
2014-02-28 17:42 ` [PATCH 08/19] perf c2c: Shared data analyser Don Zickus
2014-02-28 19:08 ` Andi Kleen
2014-02-28 19:46 ` Don Zickus
2014-02-28 21:03 ` Davidlohr Bueso
2014-02-28 22:28 ` Joe Mario
2014-03-01 0:50 ` Andi Kleen
2014-03-03 14:13 ` Don Zickus
2014-03-03 15:05 ` Don Zickus
2014-03-03 17:23 ` Andi Kleen
2014-03-03 18:07 ` Joe Mario
2014-03-03 18:41 ` Peter Zijlstra
2014-03-03 18:58 ` Andi Kleen
2014-03-03 19:48 ` Peter Zijlstra
2014-03-03 20:32 ` Don Zickus
2014-03-03 21:38 ` Andi Kleen
2014-03-03 21:41 ` Don Zickus
2014-03-03 20:30 ` Don Zickus
2014-03-03 20:26 ` Don Zickus
2014-03-03 21:36 ` Andi Kleen
2014-03-04 9:42 ` Peter Zijlstra
2014-03-03 18:21 ` Davidlohr Bueso
2014-02-28 17:42 ` [PATCH 09/19] perf c2c: Dump raw records, decode data_src bits Don Zickus
2014-02-28 17:42 ` [PATCH 10/19] perf, c2c: Rework setup code to prepare for features Don Zickus
2014-02-28 17:43 ` [PATCH 11/19] perf, c2c: Add in sort on physid Don Zickus
2014-02-28 18:59 ` Andi Kleen
2014-02-28 19:44 ` Don Zickus
2014-03-01 1:07 ` Andi Kleen
2014-03-01 1:27 ` Namhyung Kim
2014-02-28 17:43 ` [PATCH 12/19] perf, c2c: Add stats to track data source bits and cpu to node maps Don Zickus
2014-02-28 17:43 ` [PATCH 13/19] perf, c2c: Sort based on hottest cache line Don Zickus
2014-02-28 17:43 ` [PATCH 14/19] perf, c2c: Display cacheline HITM analysis to stdout Don Zickus
2014-02-28 17:43 ` [PATCH 15/19] perf, c2c: Add callchain support Don Zickus
2014-03-19 13:00 ` Jiri Olsa
2014-03-19 13:53 ` Don Zickus
2014-03-19 14:05 ` Jiri Olsa
2014-02-28 17:43 ` [PATCH 16/19] perf, c2c: Output summary stats Don Zickus
2014-02-28 17:43 ` [PATCH 17/19] perf, c2c: Dump rbtree for debugging Don Zickus
2014-02-28 17:43 ` [PATCH 18/19] perf, c2c: Add symbol count table Don Zickus
2014-02-28 17:43 ` [PATCH 19/19] perf, c2c: Add shared cachline summary table Don Zickus
2014-02-28 18:57 ` [PATCH 00/19 V2] perf, c2c: Add new tool to analyze cacheline contention on NUMA systems Andi Kleen
2014-02-28 19:42 ` Don Zickus
2014-02-28 21:54 ` Andi Kleen
2014-03-03 14:04 ` Don Zickus
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1393609388-40489-5-git-send-email-dzickus@redhat.com \
--to=dzickus@redhat.com \
--cc=acme@ghostprotocols.net \
--cc=eranian@google.com \
--cc=fowles@inreach.com \
--cc=jmario@redhat.com \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).