Linux kernel mirror (for testing)
git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel
os
linux
perf mem: Document new output fields (op, cache, mem, dtlb, snoop)
Update the documentation of the new fields with examples and caveats.
Also update the related documentation for AMD IBS.
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250610005742.2173050-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
authored by
Namhyung Kim
and committed by
Arnaldo Carvalho de Melo
bbeb1088
11cfaf37
+91
-16
+41
-16
tools/perf/Documentation/perf-amd-ibs.txt
+41
-16
tools/perf/Documentation/perf-amd-ibs.txt
···
171
171
# perf mem report
172
172
173
173
A normal perf mem report output will provide detailed memory access profile.
174
-
However, it can also be aggregated based on output fields. For example:
174
+
New output fields will show related access info together. For example:
175
175
176
-
# perf mem report -F mem,sample,snoop
177
-
Samples: 3M of event 'ibs_op//', Event count (approx.): 23524876
178
-
Memory access Samples Snoop
179
-
N/A 1903343 N/A
180
-
L1 hit 1056754 N/A
181
-
L2 hit 75231 N/A
182
-
L3 hit 9496 HitM
183
-
L3 hit 2270 N/A
184
-
RAM hit 8710 N/A
185
-
Remote node, same socket RAM hit 3241 N/A
186
-
Remote core, same node Any cache hit 1572 HitM
187
-
Remote core, same node Any cache hit 514 N/A
188
-
Remote node, same socket Any cache hit 1216 HitM
189
-
Remote node, same socket Any cache hit 350 N/A
190
-
Uncached hit 18 N/A
176
+
# perf mem report -F overhead,cache,snoop,comm
177
+
...
178
+
# Samples: 92K of event 'ibs_op//'
179
+
# Total weight : 531104
180
+
#
181
+
# ---------- Cache ----------- --- Snoop ----
182
+
# Overhead L1 L2 L1-buf Other HitM Other Command
183
+
# ........ ............................ .............. ..........
184
+
#
185
+
76.07% 5.8% 35.7% 0.0% 34.6% 23.3% 52.8% cc1
186
+
5.79% 0.2% 0.0% 0.0% 5.6% 0.1% 5.7% make
187
+
5.78% 0.1% 4.4% 0.0% 1.2% 0.5% 5.3% gcc
188
+
5.33% 0.3% 3.9% 0.0% 1.1% 0.2% 5.2% as
189
+
5.00% 0.1% 3.8% 0.0% 1.0% 0.3% 4.7% sh
190
+
1.56% 0.1% 0.1% 0.0% 1.4% 0.6% 0.9% ld
191
+
0.28% 0.1% 0.0% 0.0% 0.2% 0.1% 0.2% pkg-config
192
+
0.09% 0.0% 0.0% 0.0% 0.1% 0.0% 0.1% git
193
+
0.03% 0.0% 0.0% 0.0% 0.0% 0.0% 0.0% rm
194
+
...
195
+
196
+
Also, it can be aggregated based on various memory access info using the
197
+
sort keys. For example:
198
+
199
+
# perf mem report -s mem,snoop
200
+
...
201
+
# Samples: 92K of event 'ibs_op//'
202
+
# Total weight : 531104
203
+
# Sort order : mem,snoop
204
+
#
205
+
# Overhead Samples Memory access Snoop
206
+
# ........ ............ ....................................... ............
207
+
#
208
+
47.99% 1509 L2 hit N/A
209
+
25.08% 338 core, same node Any cache hit HitM
210
+
10.24% 54374 N/A N/A
211
+
6.77% 35938 L1 hit N/A
212
+
6.39% 101 core, same node Any cache hit N/A
213
+
3.50% 69 RAM hit N/A
214
+
0.03% 158 LFB/MAB hit N/A
215
+
0.00% 2 Uncached hit N/A
191
216
192
217
Please refer to their man page for more detail.
193
218
+50
tools/perf/Documentation/perf-mem.txt
+50
tools/perf/Documentation/perf-mem.txt
···
119
119
And the default sort keys are changed to local_weight, mem, sym, dso,
120
120
symbol_daddr, dso_daddr, snoop, tlb, locked, blocked, local_ins_lat.
121
121
122
+
-F::
123
+
--fields=::
124
+
Specify output field - multiple keys can be specified in CSV format.
125
+
Please see linkperf:perf-report[1] for details.
126
+
127
+
In addition to the default fields, 'perf mem report' will provide the
128
+
following fields to break down sample periods.
129
+
130
+
- op: operation in the sample instruction (load, store, prefetch, ...)
131
+
- cache: location in CPU cache (L1, L2, ...) where the sample hit
132
+
- mem: location in memory or other places the sample hit
133
+
- dtlb: location in Data TLB (L1, L2) where the sample hit
134
+
- snoop: snoop result for the sampled data access
135
+
136
+
Please take a look at the OUTPUT FIELD SELECTION section for caveats.
137
+
122
138
-T::
123
139
--type-profile::
124
140
Show data-type profile result instead of code symbols. This requires
···
171
155
$ perf mem report -F overhead,symbol
172
156
90% [k] memcpy
173
157
10% [.] strcmp
158
+
159
+
OUTPUT FIELD SELECTION
160
+
----------------------
161
+
"perf mem report" adds a number of new output fields specific to data source
162
+
information in the sample. Some of them have the same name with the existing
163
+
sort keys ("mem" and "snoop"). So unlike other fields and sort keys, they'll
164
+
behave differently when it's used by -F/--fields or -s/--sort.
165
+
166
+
Using those two as output fields will aggregate samples altogether and show
167
+
breakdown.
168
+
169
+
$ perf mem report -F mem,snoop
170
+
...
171
+
# ------ Memory ------- --- Snoop ----
172
+
# RAM Uncach Other HitM Other
173
+
# ..................... ..............
174
+
#
175
+
3.5% 0.0% 96.5% 25.1% 74.9%
176
+
177
+
But using the same name for sort keys will aggregate samples for each type
178
+
separately.
179
+
180
+
$ perf mem report -s mem,snoop
181
+
# Overhead Samples Memory access Snoop
182
+
# ........ ............ ....................................... ............
183
+
#
184
+
47.99% 1509 L2 hit N/A
185
+
25.08% 338 core, same node Any cache hit HitM
186
+
10.24% 54374 N/A N/A
187
+
6.77% 35938 L1 hit N/A
188
+
6.39% 101 core, same node Any cache hit N/A
189
+
3.50% 69 RAM hit N/A
190
+
0.03% 158 LFB/MAB hit N/A
191
+
0.00% 2 Uncached hit N/A
174
192
175
193
SEE ALSO
176
194
--------