1perf-stat(1) 2============ 3 4NAME 5---- 6perf-stat - Run a command and gather performance counter statistics 7 8SYNOPSIS 9-------- 10[verse] 11'perf stat' [-e <EVENT> | --event=EVENT] [-a] <command> 12'perf stat' [-e <EVENT> | --event=EVENT] [-a] -- <command> [<options>] 13'perf stat' [-e <EVENT> | --event=EVENT] [-a] record [-o file] -- <command> [<options>] 14'perf stat' report [-i file] 15 16DESCRIPTION 17----------- 18This command runs a command and gathers performance counter statistics 19from it. 20 21 22OPTIONS 23------- 24<command>...:: 25 Any command you can specify in a shell. 26 27record:: 28 See STAT RECORD. 29 30report:: 31 See STAT REPORT. 32 33-e:: 34--event=:: 35 Select the PMU event. Selection can be: 36 37 - a symbolic event name (use 'perf list' to list all events) 38 39 - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a 40 hexadecimal event descriptor. 41 42 - a symbolically formed event like 'pmu/param1=0x3,param2/' where 43 param1 and param2 are defined as formats for the PMU in 44 /sys/bus/event_source/devices/<pmu>/format/* 45 46 - a symbolically formed event like 'pmu/config=M,config1=N,config2=K/' 47 where M, N, K are numbers (in decimal, hex, octal format). 48 Acceptable values for each of 'config', 'config1' and 'config2' 49 parameters are defined by corresponding entries in 50 /sys/bus/event_source/devices/<pmu>/format/* 51 52-i:: 53--no-inherit:: 54 child tasks do not inherit counters 55-p:: 56--pid=<pid>:: 57 stat events on existing process id (comma separated list) 58 59-t:: 60--tid=<tid>:: 61 stat events on existing thread id (comma separated list) 62 63 64-a:: 65--all-cpus:: 66 system-wide collection from all CPUs (default if no target is specified) 67 68-c:: 69--scale:: 70 scale/normalize counter values 71 72-d:: 73--detailed:: 74 print more detailed statistics, can be specified up to 3 times 75 76 -d: detailed events, L1 and LLC data cache 77 -d -d: more detailed events, dTLB and iTLB events 78 -d -d -d: very detailed events, adding prefetch events 79 80-r:: 81--repeat=<n>:: 82 repeat command and print average + stddev (max: 100). 0 means forever. 83 84-B:: 85--big-num:: 86 print large numbers with thousands' separators according to locale 87 88-C:: 89--cpu=:: 90Count only on the list of CPUs provided. Multiple CPUs can be provided as a 91comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2. 92In per-thread mode, this option is ignored. The -a option is still necessary 93to activate system-wide monitoring. Default is to count on all CPUs. 94 95-A:: 96--no-aggr:: 97Do not aggregate counts across all monitored CPUs. 98 99-n:: 100--null:: 101 null run - don't start any counters 102 103-v:: 104--verbose:: 105 be more verbose (show counter open errors, etc) 106 107-x SEP:: 108--field-separator SEP:: 109print counts using a CSV-style output to make it easy to import directly into 110spreadsheets. Columns are separated by the string specified in SEP. 111 112-G name:: 113--cgroup name:: 114monitor only in the container (cgroup) called "name". This option is available only 115in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to 116container "name" are monitored when they run on the monitored CPUs. Multiple cgroups 117can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup 118to first event, second cgroup to second event and so on. It is possible to provide 119an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have 120corresponding events, i.e., they always refer to events defined earlier on the command 121line. 122 123-o file:: 124--output file:: 125Print the output into the designated file. 126 127--append:: 128Append to the output file designated with the -o option. Ignored if -o is not specified. 129 130--log-fd:: 131 132Log output to fd, instead of stderr. Complementary to --output, and mutually exclusive 133with it. --append may be used here. Examples: 134 3>results perf stat --log-fd 3 -- $cmd 135 3>>results perf stat --log-fd 3 --append -- $cmd 136 137--pre:: 138--post:: 139 Pre and post measurement hooks, e.g.: 140 141perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' -- make -s -j64 O=defconfig-build/ bzImage 142 143-I msecs:: 144--interval-print msecs:: 145Print count deltas every N milliseconds (minimum: 10ms) 146The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals. Use with caution. 147 example: 'perf stat -I 1000 -e cycles -a sleep 5' 148 149--metric-only:: 150Only print computed metrics. Print them in a single line. 151Don't show any raw values. Not supported with --per-thread. 152 153--per-socket:: 154Aggregate counts per processor socket for system-wide mode measurements. This 155is a useful mode to detect imbalance between sockets. To enable this mode, 156use --per-socket in addition to -a. (system-wide). The output includes the 157socket number and the number of online processors on that socket. This is 158useful to gauge the amount of aggregation. 159 160--per-core:: 161Aggregate counts per physical processor for system-wide mode measurements. This 162is a useful mode to detect imbalance between physical cores. To enable this mode, 163use --per-core in addition to -a. (system-wide). The output includes the 164core number and the number of online logical processors on that physical processor. 165 166--per-thread:: 167Aggregate counts per monitored threads, when monitoring threads (-t option) 168or processes (-p option). 169 170-D msecs:: 171--delay msecs:: 172After starting the program, wait msecs before measuring. This is useful to 173filter out the startup phase of the program, which is often very different. 174 175-T:: 176--transaction:: 177 178Print statistics of transactional execution if supported. 179 180STAT RECORD 181----------- 182Stores stat data into perf data file. 183 184-o file:: 185--output file:: 186Output file name. 187 188STAT REPORT 189----------- 190Reads and reports stat data from perf data file. 191 192-i file:: 193--input file:: 194Input file name. 195 196--per-socket:: 197Aggregate counts per processor socket for system-wide mode measurements. 198 199--per-core:: 200Aggregate counts per physical processor for system-wide mode measurements. 201 202-M:: 203--metrics:: 204Print metrics or metricgroups specified in a comma separated list. 205For a group all metrics from the group are added. 206The events from the metrics are automatically measured. 207See perf list output for the possble metrics and metricgroups. 208 209-A:: 210--no-aggr:: 211Do not aggregate counts across all monitored CPUs. 212 213--topdown:: 214Print top down level 1 metrics if supported by the CPU. This allows to 215determine bottle necks in the CPU pipeline for CPU bound workloads, 216by breaking the cycles consumed down into frontend bound, backend bound, 217bad speculation and retiring. 218 219Frontend bound means that the CPU cannot fetch and decode instructions fast 220enough. Backend bound means that computation or memory access is the bottle 221neck. Bad Speculation means that the CPU wasted cycles due to branch 222mispredictions and similar issues. Retiring means that the CPU computed without 223an apparently bottleneck. The bottleneck is only the real bottleneck 224if the workload is actually bound by the CPU and not by something else. 225 226For best results it is usually a good idea to use it with interval 227mode like -I 1000, as the bottleneck of workloads can change often. 228 229The top down metrics are collected per core instead of per 230CPU thread. Per core mode is automatically enabled 231and -a (global monitoring) is needed, requiring root rights or 232perf.perf_event_paranoid=-1. 233 234Topdown uses the full Performance Monitoring Unit, and needs 235disabling of the NMI watchdog (as root): 236echo 0 > /proc/sys/kernel/nmi_watchdog 237for best results. Otherwise the bottlenecks may be inconsistent 238on workload with changing phases. 239 240This enables --metric-only, unless overriden with --no-metric-only. 241 242To interpret the results it is usually needed to know on which 243CPUs the workload runs on. If needed the CPUs can be forced using 244taskset. 245 246--no-merge:: 247Do not merge results from same PMUs. 248 249--smi-cost:: 250Measure SMI cost if msr/aperf/ and msr/smi/ events are supported. 251 252During the measurement, the /sys/device/cpu/freeze_on_smi will be set to 253freeze core counters on SMI. 254The aperf counter will not be effected by the setting. 255The cost of SMI can be measured by (aperf - unhalted core cycles). 256 257In practice, the percentages of SMI cycles is very useful for performance 258oriented analysis. --metric_only will be applied by default. 259The output is SMI cycles%, equals to (aperf - unhalted core cycles) / aperf 260 261Users who wants to get the actual value can apply --no-metric-only. 262 263EXAMPLES 264-------- 265 266$ perf stat -- make -j 267 268 Performance counter stats for 'make -j': 269 270 8117.370256 task clock ticks # 11.281 CPU utilization factor 271 678 context switches # 0.000 M/sec 272 133 CPU migrations # 0.000 M/sec 273 235724 pagefaults # 0.029 M/sec 274 24821162526 CPU cycles # 3057.784 M/sec 275 18687303457 instructions # 2302.138 M/sec 276 172158895 cache references # 21.209 M/sec 277 27075259 cache misses # 3.335 M/sec 278 279 Wall-clock time elapsed: 719.554352 msecs 280 281CSV FORMAT 282---------- 283 284With -x, perf stat is able to output a not-quite-CSV format output 285Commas in the output are not put into "". To make it easy to parse 286it is recommended to use a different character like -x \; 287 288The fields are in this order: 289 290 - optional usec time stamp in fractions of second (with -I xxx) 291 - optional CPU, core, or socket identifier 292 - optional number of logical CPUs aggregated 293 - counter value 294 - unit of the counter value or empty 295 - event name 296 - run time of counter 297 - percentage of measurement time the counter was running 298 - optional variance if multiple values are collected with -r 299 - optional metric value 300 - optional unit of metric 301 302Additional metrics may be printed with all earlier fields being empty. 303 304SEE ALSO 305-------- 306linkperf:perf-top[1], linkperf:perf-list[1] 307