[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20240731235505.710436-7-namhyung@kernel.org>
Date: Wed, 31 Jul 2024 16:55:05 -0700
From: Namhyung Kim <namhyung@...nel.org>
To: Arnaldo Carvalho de Melo <acme@...nel.org>,
Ian Rogers <irogers@...gle.com>,
Kan Liang <kan.liang@...ux.intel.com>
Cc: Jiri Olsa <jolsa@...nel.org>,
Adrian Hunter <adrian.hunter@...el.com>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...nel.org>,
LKML <linux-kernel@...r.kernel.org>,
linux-perf-users@...r.kernel.org,
Stephane Eranian <eranian@...gle.com>,
Athira Rajeev <atrajeev@...ux.vnet.ibm.com>
Subject: [PATCH 6/6] perf mem: Add -T/--data-type option to report subcommand
This is just a shortcut to have 'type' in the sort key and use more
compact output format like below.
$ perf mem report -T
...
#
# Overhead Samples Memory access Snoop TLB access Data Type
# ........ ............ ....................................... ............ ...................... .........
#
14.84% 22 L1 hit None L1 or L2 hit (unknown)
7.68% 8 LFB/MAB hit None L1 or L2 hit (unknown)
7.17% 3 RAM hit Hit L2 miss (unknown)
6.29% 12 L1 hit None L1 or L2 hit (stack operation)
4.85% 5 RAM hit Hit L1 or L2 hit (unknown)
3.97% 5 LFB/MAB hit None L1 or L2 hit struct psi_group_cpu
3.18% 3 LFB/MAB hit None L1 or L2 hit (stack operation)
2.58% 3 L1 hit None L1 or L2 hit unsigned int
2.36% 2 L1 hit None L1 or L2 hit struct
2.31% 2 L1 hit None L1 or L2 hit struct psi_group_cpu
...
Users also can use their own sort keys and -T option makes sure it has
the 'type' sort key at the end.
$ perf mem report -T -s mem
Signed-off-by: Namhyung Kim <namhyung@...nel.org>
---
tools/perf/builtin-mem.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 24a4f0084f49..efa700d14c98 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -38,6 +38,7 @@ struct perf_mem {
bool data_page_size;
bool all_kernel;
bool all_user;
+ bool data_type;
int operation;
const char *cpu_list;
DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -317,6 +318,8 @@ static char *get_sort_order(struct perf_mem *mem)
if (mem->sort_key)
scnprintf(sort, sizeof(sort), "--sort=%s", mem->sort_key);
+ else if (mem->data_type)
+ strcpy(sort, "--sort=mem,snoop,tlb,type");
/*
* there is no weight (cost) associated with stores, so don't print
* the column
@@ -336,6 +339,10 @@ static char *get_sort_order(struct perf_mem *mem)
if (mem->data_page_size)
strcat(sort, ",data_page_size");
+ /* make sure it has 'type' sort key even -s option is used */
+ if (mem->data_type && !strstr(sort, "type"))
+ strcat(sort, ",type");
+
return strdup(sort);
}
@@ -508,6 +515,8 @@ int cmd_mem(int argc, const char **argv)
" between columns '.' is reserved."),
OPT_STRING('s', "sort", &mem.sort_key, "key[,key2...]",
sort_order_help),
+ OPT_BOOLEAN('T', "type-profile", &mem.data_type,
+ "Show data-type profile result"),
OPT_PARENT(mem_options)
};
const char *const mem_subcommands[] = { "record", "report", NULL };
--
2.46.0.rc1.232.g9752f9e123-goog
Powered by blists - more mailing lists