lkml.org 
[lkml]   [2014]   [Mar]   [24]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 15/15 V3] perf, c2c: Add shared cachline summary table
Date
This adds a quick summary of the hottest cache contention lines based
on the input data. This summarizes what the broken table shows you,
so you can see at a quick glance which cachelines are interesting.

Originally done by Dick Fowles, backported by me.

Sample output (width trimmed):

===================================================================================================================================================

Shared Data Cache Line Table

Total %All Total ---- Core Load Hit ---- -- LLC Load Hit -- ----- LLC Load Hitm -----
Index Phys Adrs Records Ld Miss %hitm Loads FB L1D L2D Lcl Rmt Total Lcl Rmt
====================================================================================================================================================
0 0xffff881fa55b0140 72006 16.97% 23.31% 43095 13591 16860 45 2651 25 9526 3288 6238
1 0xffff881fba47f000 21854 5.29% 7.26% 13938 3887 6941 15 1 7 3087 1143 1944
2 0xffff881fc21b9cc0 2153 1.61% 2.21% 862 32 70 0 15 1 740 148 592
3 0xffff881fc7d91cc0 1957 1.40% 1.92% 866 34 94 0 14 3 720 207 513
4 0xffff881fba539cc0 1813 1.35% 1.85% 808 33 84 3 14 1 665 170 495

Original-by: Dick Fowles <rfowles@redhat.com>
Signed-off-by: Don Zickus <dzickus@redhat.com>
---
tools/perf/builtin-c2c.c | 136 +++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 136 insertions(+)

diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index e30ce2f..e33f548 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -786,6 +786,141 @@ cleanup:
}
}

+static void print_c2c_shared_cacheline_report(struct rb_root *hitm_tree,
+ struct c2c_stats *shared_stats __maybe_unused,
+ struct c2c_stats *c2c_stats __maybe_unused)
+{
+#define SHM_TITLE "Shared Data Cache Line Table"
+
+ struct rb_node *next = rb_first(hitm_tree);
+ struct c2c_hit *h;
+ char header[256];
+ char delimit[256];
+ u32 crecords;
+ u32 lclmiss;
+ u32 ldcnt;
+ double p_hitm;
+ double p_all;
+ int totmiss;
+ int rmt_hitm;
+ int len;
+ int pad;
+ int i;
+
+ sprintf(header, "%28s %8s %8s %8s %8s %28s %18s %28s %18s %8s %28s",
+ " ",
+ "Total",
+ "%All ",
+ " ",
+ "Total",
+ "---- Core Load Hit ----",
+ "-- LLC Load Hit --",
+ "----- LLC Load Hitm -----",
+ "-- Load Dram --",
+ "LLC ",
+ "---- Store Reference ----");
+
+ len = strlen(header);
+ delimit[0] = '\0';
+
+ for (i = 0; i < len; i++)
+ strcat(delimit, "=");
+
+ printf("\n\n");
+ printf("%s\n", delimit);
+ printf("\n");
+ pad = (strlen(header)/2) - (strlen(SHM_TITLE)/2);
+ for (i = 0; i < pad; i++)
+ printf(" ");
+ printf("%s\n", SHM_TITLE);
+ printf("\n");
+ printf("%s\n", header);
+
+ sprintf(header, "%8s %18s %8s %8s %8s %8s %8s %8s %8s %8s %8s %8s %8s %8s %8s %8s %8s %8s %8s %8s",
+ "Index",
+ "Phys Adrs",
+ "Records",
+ "Ld Miss",
+ "%hitm",
+ "Loads",
+ "FB",
+ "L1D",
+ "L2D",
+ "Lcl",
+ "Rmt",
+ "Total",
+ "Lcl",
+ "Rmt",
+ "Lcl",
+ "Rmt",
+ "Ld Miss",
+ "Total",
+ "L1Hit",
+ "L1Miss");
+
+ printf("%s\n", header);
+ printf("%s\n", delimit);
+
+ rmt_hitm = c2c_stats->t.rmt_hitm;
+ totmiss = c2c_stats->t.lcl_dram +
+ c2c_stats->t.rmt_dram +
+ c2c_stats->t.rmt_hit +
+ c2c_stats->t.rmt_hitm;
+
+ i = 0;
+ while (next) {
+ h = rb_entry(next, struct c2c_hit, rb_node);
+ next = rb_next(&h->rb_node);
+
+ lclmiss = h->stats.t.lcl_dram +
+ h->stats.t.rmt_dram +
+ h->stats.t.rmt_hitm +
+ h->stats.t.rmt_hit;
+
+ ldcnt = lclmiss +
+ h->stats.t.ld_fbhit +
+ h->stats.t.ld_l1hit +
+ h->stats.t.ld_l2hit +
+ h->stats.t.ld_llchit +
+ h->stats.t.lcl_hitm;
+
+ crecords = ldcnt +
+ h->stats.t.st_l1hit +
+ h->stats.t.st_l1miss;
+
+ p_hitm = (double)h->stats.t.rmt_hitm / (double)rmt_hitm;
+ p_all = (double)h->stats.t.rmt_hitm / (double)totmiss;
+
+ /* stop when the percentage gets to low */
+ if (p_hitm < DISPLAY_LINE_LIMIT)
+ break;
+
+ printf("%8d %#18lx %8u %7.2f%% %7.2f%% %8u %8u %8u %8u %8u %8u %8u %8u %8u %8u %8u %8u %8u %8u %8u\n",
+ i,
+ h->cacheline,
+ crecords,
+ 100. * p_all,
+ 100. * p_hitm,
+ ldcnt,
+ h->stats.t.ld_fbhit,
+ h->stats.t.ld_l1hit,
+ h->stats.t.ld_l2hit,
+ h->stats.t.ld_llchit,
+ h->stats.t.rmt_hit,
+ h->stats.t.lcl_hitm + h->stats.t.rmt_hitm,
+ h->stats.t.lcl_hitm,
+ h->stats.t.rmt_hitm,
+ h->stats.t.lcl_dram,
+ h->stats.t.rmt_dram,
+ lclmiss,
+ h->stats.t.store,
+ h->stats.t.st_l1hit,
+ h->stats.t.st_l1miss);
+
+ i++;
+ }
+}
+
static void print_hitm_cacheline_header(void)
{
#define SHARING_REPORT_TITLE "Shared Cache Line Distribution Pareto"
@@ -1293,6 +1428,7 @@ static void c2c_analyze_hitms(struct perf_c2c *c2c)
free(h);

print_shared_cacheline_info(&hitm_stats, shared_clines);
+ print_c2c_shared_cacheline_report(&hitm_tree, &hitm_stats, &c2c->stats);
print_c2c_hitm_report(&hitm_tree, &hitm_stats, &c2c->stats);

cleanup:
--
1.7.11.7


\
 
 \ /
  Last update: 2014-03-25 00:01    [W:0.191 / U:10.888 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site