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 10/21] perf, c2c: Add stats to track data source bits and cpu to node maps
Date: Mon, 10 Feb 2014 12:29:05 -0500 [thread overview]
Message-ID: <1392053356-23024-11-git-send-email-dzickus@redhat.com> (raw)
In-Reply-To: <1392053356-23024-1-git-send-email-dzickus@redhat.com>
This patch adds a bunch of stats that will be used later in post-processing
to determine where and with what frequency the HITMs are coming from.
Most of the stats are decoded from the data source response. Another
piece of the stats is tracking which cpu the record came in on.
In order to properly build a cpu map to map where interesting events are coming
from, I shamelessly copy-n-pasted the cpu->NUMA node code from builtin-kmem.c.
As HITMs are most expensive when going across NUMA nodes, it only made sense
to create a quick cpu->NUMA lookup for when processing the records.
Credit to Dick Fowles for determining which bits are important and how to
properly track them. Ported to perf by me.
Original-by: Dick Fowles <rfowles@redhat.com>
Signed-off-by: Don Zickus <dzickus@redhat.com>
---
tools/perf/builtin-c2c.c | 327 ++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 326 insertions(+), 1 deletion(-)
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index a9c536b..360fbcf 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -5,15 +5,54 @@
#include "util/parse-options.h"
#include "util/session.h"
#include "util/tool.h"
+#include "util/stat.h"
+#include "util/cpumap.h"
#include "util/debug.h"
#include <linux/compiler.h>
#include <linux/kernel.h>
+#include <sched.h>
+
+typedef struct {
+ int locks; /* count of 'lock' transactions */
+ int store; /* count of all stores in trace */
+ int st_uncache; /* stores to uncacheable address */
+ int st_noadrs; /* cacheable store with no address */
+ int st_l1hit; /* count of stores that hit L1D */
+ int st_l1miss; /* count of stores that miss L1D */
+ int load; /* count of all loads in trace */
+ int ld_excl; /* exclusive loads, rmt/lcl DRAM - snp none/miss */
+ int ld_shared; /* shared loads, rmt/lcl DRAM - snp hit */
+ int ld_uncache; /* loads to uncacheable address */
+ int ld_noadrs; /* cacheable load with no address */
+ int ld_fbhit; /* count of loads hitting Fill Buffer */
+ int ld_l1hit; /* count of loads that hit L1D */
+ int ld_l2hit; /* count of loads that hit L2D */
+ int ld_llchit; /* count of loads that hit LLC */
+ int lcl_hitm; /* count of loads with local HITM */
+ int rmt_hitm; /* count of loads with remote HITM */
+ int rmt_hit; /* count of loads with remote hit clean; */
+ int lcl_dram; /* count of loads miss to local DRAM */
+ int rmt_dram; /* count of loads miss to remote DRAM */
+ int nomap; /* count of load/stores with no phys adrs */
+ int remap; /* count of virt->phys remappings */
+} trinfo_t;
+
+struct c2c_stats {
+ cpu_set_t cpuset;
+ int nr_entries;
+ u64 total_period;
+ trinfo_t t;
+ struct stats stats;
+};
struct perf_c2c {
struct perf_tool tool;
bool raw_records;
struct rb_root tree_physid;
+
+ /* stats */
+ struct c2c_stats stats;
};
#define REGION_SAME 1 << 0;
@@ -31,6 +70,179 @@ struct c2c_entry {
enum { OP, LVL, SNP, LCK, TLB };
+#define RMT_RAM (PERF_MEM_LVL_REM_RAM1 | PERF_MEM_LVL_REM_RAM2)
+#define RMT_LLC (PERF_MEM_LVL_REM_CCE1 | PERF_MEM_LVL_REM_CCE2)
+
+#define L1CACHE_HIT(a) (((a) & PERF_MEM_LVL_L1 ) && ((a) & PERF_MEM_LVL_HIT))
+#define FILLBUF_HIT(a) (((a) & PERF_MEM_LVL_LFB) && ((a) & PERF_MEM_LVL_HIT))
+#define L2CACHE_HIT(a) (((a) & PERF_MEM_LVL_L2 ) && ((a) & PERF_MEM_LVL_HIT))
+#define L3CACHE_HIT(a) (((a) & PERF_MEM_LVL_L3 ) && ((a) & PERF_MEM_LVL_HIT))
+
+#define L1CACHE_MISS(a) (((a) & PERF_MEM_LVL_L1 ) && ((a) & PERF_MEM_LVL_MISS))
+#define L3CACHE_MISS(a) (((a) & PERF_MEM_LVL_L3 ) && ((a) & PERF_MEM_LVL_MISS))
+
+#define LD_UNCACHED(a) (((a) & PERF_MEM_LVL_UNC) && ((a) & PERF_MEM_LVL_HIT))
+#define ST_UNCACHED(a) (((a) & PERF_MEM_LVL_UNC) && ((a) & PERF_MEM_LVL_HIT))
+
+#define RMT_LLCHIT(a) (((a) & RMT_LLC) && ((a) & PERF_MEM_LVL_HIT))
+#define RMT_HIT(a,b) (((a) & RMT_LLC) && ((b) & PERF_MEM_SNOOP_HIT))
+#define RMT_HITM(a,b) (((a) & RMT_LLC) && ((b) & PERF_MEM_SNOOP_HITM))
+#define RMT_MEM(a) (((a) & RMT_RAM) && ((a) & PERF_MEM_LVL_HIT))
+
+#define LCL_HIT(a,b) (L3CACHE_HIT(a) && ((b) & PERF_MEM_SNOOP_HIT))
+#define LCL_HITM(a,b) (L3CACHE_HIT(a) && ((b) & PERF_MEM_SNOOP_HITM))
+#define LCL_MEM(a) (((a) & PERF_MEM_LVL_LOC_RAM) && ((a) & PERF_MEM_LVL_HIT))
+
+static int max_cpu_num;
+static int max_node_num;
+static int *cpunode_map;
+
+#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;
+}
+
+static int 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;
+}
+
static int perf_c2c__scnprintf_data_src(char *bf, size_t size, uint64_t val)
{
#define PREFIX "["
@@ -303,17 +515,120 @@ static struct c2c_entry *c2c_entry__new(struct perf_sample *sample,
return entry;
}
+static int c2c_decode_stats(struct c2c_stats *stats, struct c2c_entry *entry)
+{
+ union perf_mem_data_src *data_src = &entry->mi->data_src;
+ u64 daddr = entry->mi->daddr.addr;
+ u64 weight = entry->weight;
+ int err = 0;
+
+ u64 op = data_src->mem_op;
+ u64 lvl = data_src->mem_lvl;
+ u64 snoop = data_src->mem_snoop;
+ u64 lock = data_src->mem_lock;
+
+#define P(a,b) PERF_MEM_##a##_##b
+
+ stats->nr_entries++;
+ stats->total_period += entry->period;
+
+ if (lock & P(LOCK,LOCKED)) stats->t.locks++;
+
+ if (op & P(OP,LOAD)) {
+ stats->t.load++;
+
+ if (!daddr) {
+ stats->t.ld_noadrs++;
+ return -1;
+ }
+
+ if (lvl & P(LVL,HIT)) {
+ if (lvl & P(LVL,UNC)) stats->t.ld_uncache++;
+ if (lvl & P(LVL,LFB)) stats->t.ld_fbhit++;
+ if (lvl & P(LVL,L1 )) stats->t.ld_l1hit++;
+ if (lvl & P(LVL,L2 )) stats->t.ld_l2hit++;
+ if (lvl & P(LVL,L3 )) {
+ if (snoop & P(SNOOP,HITM))
+ stats->t.lcl_hitm++;
+ else
+ stats->t.ld_llchit++;
+ }
+
+ if (lvl & P(LVL,LOC_RAM)) {
+ stats->t.lcl_dram++;
+ if (snoop & P(SNOOP,HIT))
+ stats->t.ld_shared++;
+ else
+ stats->t.ld_excl++;
+ }
+
+ if ((lvl & P(LVL,REM_RAM1)) ||
+ (lvl & P(LVL,REM_RAM2))) {
+ stats->t.rmt_dram++;
+ if (snoop & P(SNOOP,HIT))
+ stats->t.ld_shared++;
+ else
+ stats->t.ld_excl++;
+ }
+ }
+
+ if ((lvl & P(LVL,REM_CCE1)) ||
+ (lvl & P(LVL,REM_CCE2))) {
+ if (snoop & P(SNOOP, HIT))
+ stats->t.rmt_hit++;
+ else if (snoop & P(SNOOP, HITM)) {
+ stats->t.rmt_hitm++;
+ update_stats(&stats->stats, weight);
+ }
+ }
+
+ } else if (op & P(OP,STORE)) {
+ /* store */
+ stats->t.store++;
+
+ if (!daddr) {
+ stats->t.st_noadrs++;
+ return -1;
+ }
+
+ if (lvl & P(LVL,HIT)) {
+ if (lvl & P(LVL,UNC)) stats->t.st_uncache++;
+ if (lvl & P(LVL,L1 )) stats->t.st_l1hit++;
+ }
+ if (lvl & P(LVL,MISS))
+ if (lvl & P(LVL,L1)) stats->t.st_l1miss++;
+ } else {
+ /* unparsable data_src? */
+ return -1;
+ }
+
+ if (!entry->mi->daddr.map || !entry->mi->iaddr.map)
+ return -1;
+
+ return err;
+}
+
static int perf_c2c__process_load_store(struct perf_c2c *c2c,
struct perf_sample *sample __maybe_unused,
struct c2c_entry *entry)
{
+ int err = 0;
+
+ err = c2c_decode_stats(&c2c->stats, entry);
+ if (err < 0) {
+ err = 1;
+ goto err;
+ }
+ err = 0;
+
c2c_entry__add_to_list(c2c, entry);
/* don't lose the maps if remapped */
entry->mi->iaddr.map->referenced = true;
entry->mi->daddr.map->referenced = true;
- return 0;
+err:
+ return err;
}
static const struct perf_evsel_str_handler handlers[] = {
@@ -403,6 +718,9 @@ static int perf_c2c__read_events(struct perf_c2c *c2c)
goto out;
}
+ if (symbol__init() < 0)
+ goto out_delete;
+
if (perf_evlist__set_handlers(session->evlist, handlers))
goto out_delete;
@@ -416,6 +734,13 @@ out:
static int perf_c2c__init(struct perf_c2c *c2c)
{
+ /* setup cpu map */
+ if (setup_cpunode_map() < 0) {
+ pr_err("can not setup cpu map\n");
+ return -1;
+ }
+
+ CPU_ZERO(&c2c->stats.cpuset);
c2c->tree_physid = RB_ROOT;
return 0;
--
1.7.11.7
next prev parent reply other threads:[~2014-02-10 17:31 UTC|newest]
Thread overview: 72+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-02-10 17:28 [PATCH 00/21] perf, c2c: Add new tool to analyze cacheline contention on NUMA systems Don Zickus
2014-02-10 17:28 ` [PATCH 03/21] Revert "perf: Disable PERF_RECORD_MMAP2 support" Don Zickus
2014-02-10 17:28 ` [PATCH 04/21] perf, machine: Use map as success in ip__resolve_ams Don Zickus
2014-02-10 17:29 ` [PATCH 05/21] perf, session: Change header.misc dump from decimal to hex Don Zickus
2014-02-18 12:56 ` Jiri Olsa
2014-02-19 2:40 ` Don Zickus
2014-02-10 17:29 ` [PATCH 06/21] perf, stat: FIXME Stddev calculation is incorrect Don Zickus
2014-02-10 17:29 ` [PATCH 07/21] perf, callchain: Add generic callchain print handler for stdio Don Zickus
2014-02-10 17:29 ` [PATCH 08/21] perf, c2c: Rework setup code to prepare for features Don Zickus
2014-02-18 13:02 ` Jiri Olsa
2014-02-19 2:45 ` Don Zickus
2014-02-10 17:29 ` [PATCH 09/21] perf, c2c: Add rbtree sorted on mmap2 data Don Zickus
2014-02-18 13:04 ` Jiri Olsa
2014-02-19 2:48 ` Don Zickus
2014-02-21 2:45 ` Don Zickus
2014-02-21 16:59 ` Jiri Olsa
2014-02-26 3:12 ` Don Zickus
2014-02-10 17:29 ` Don Zickus [this message]
2014-02-18 13:05 ` [PATCH 10/21] perf, c2c: Add stats to track data source bits and cpu to node maps Jiri Olsa
2014-02-19 2:51 ` Don Zickus
2014-02-10 17:29 ` [PATCH 11/21] perf, c2c: Sort based on hottest cache line Don Zickus
2014-02-10 17:29 ` [PATCH 12/21] perf, c2c: Display cacheline HITM analysis to stdout Don Zickus
2014-02-10 17:29 ` [PATCH 13/21] perf, c2c: Add callchain support Don Zickus
2014-02-18 13:07 ` Jiri Olsa
2014-02-19 2:54 ` Don Zickus
2014-02-10 17:29 ` [PATCH 14/21] perf, c2c: Output summary stats Don Zickus
2014-02-10 17:29 ` [PATCH 15/21] perf, c2c: Dump rbtree for debugging Don Zickus
2014-02-10 17:29 ` [PATCH 16/21] perf, c2c: Fixup tid because of perf map is broken Don Zickus
2014-02-10 17:29 ` [PATCH 17/21] perf, c2c: Add symbol count table Don Zickus
2014-02-18 13:09 ` Jiri Olsa
2014-02-19 2:56 ` Don Zickus
2014-02-10 17:29 ` [PATCH 18/21] perf, c2c: Add shared cachline summary table Don Zickus
2014-02-10 17:29 ` [PATCH 19/21] perf, c2c: Add framework to analyze latency and display summary stats Don Zickus
2014-02-10 17:29 ` [PATCH 20/21] perf, c2c: Add selected extreme latencies to output cacheline stats table Don Zickus
2014-02-10 17:29 ` [PATCH 21/21] perf, c2c: Add summary latency table for various parts of caches Don Zickus
2014-02-10 18:59 ` [PATCH 00/21] perf, c2c: Add new tool to analyze cacheline contention on NUMA systems Davidlohr Bueso
2014-02-10 19:17 ` Don Zickus
2014-02-10 19:18 ` [PATCH 01/21] perf c2c: Shared data analyser Don Zickus
2014-02-10 22:10 ` Davidlohr Bueso
2014-02-11 11:24 ` Jiri Olsa
2014-02-11 11:31 ` Arnaldo Carvalho de Melo
2014-02-11 13:54 ` Don Zickus
2014-02-11 14:36 ` Don Zickus
2014-02-11 15:41 ` Arnaldo Carvalho de Melo
2014-02-10 19:18 ` [PATCH 02/21] perf c2c: Dump raw records, decode data_src bits Don Zickus
2014-02-10 21:18 ` [PATCH 00/21] perf, c2c: Add new tool to analyze cacheline contention on NUMA systems Peter Zijlstra
2014-02-10 22:11 ` Don Zickus
2014-02-10 21:29 ` Peter Zijlstra
2014-02-10 22:20 ` Don Zickus
2014-02-10 22:21 ` Stephane Eranian
2014-02-11 7:14 ` Peter Zijlstra
2014-02-11 10:35 ` Stephane Eranian
2014-02-11 10:52 ` Peter Zijlstra
2014-02-11 10:58 ` Stephane Eranian
2014-02-11 11:02 ` Peter Zijlstra
2014-02-11 11:04 ` Stephane Eranian
2014-02-11 11:08 ` Peter Zijlstra
2014-02-11 11:08 ` Stephane Eranian
2014-02-11 11:14 ` Peter Zijlstra
2014-02-11 11:28 ` Stephane Eranian
2014-02-11 11:31 ` Peter Zijlstra
2014-02-11 11:51 ` Peter Zijlstra
2014-02-11 11:50 ` Arnaldo Carvalho de Melo
2014-02-11 12:09 ` Peter Zijlstra
2014-02-13 13:02 ` Jiri Olsa
2014-02-13 13:10 ` Stephane Eranian
[not found] ` <1392053356-23024-2-git-send-email-dzickus@redhat.com>
2014-02-18 12:52 ` [PATCH 01/21] perf c2c: Shared data analyser Jiri Olsa
2014-02-18 12:56 ` Arnaldo Carvalho de Melo
2014-02-19 2:42 ` Don Zickus
[not found] ` <1392053356-23024-3-git-send-email-dzickus@redhat.com>
2014-02-18 12:53 ` [PATCH 02/21] perf c2c: Dump raw records, decode data_src bits Jiri Olsa
2014-02-18 13:49 ` Arnaldo Carvalho de Melo
2014-02-19 3:04 ` 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=1392053356-23024-11-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
all inboxes | Powered by JetHome®