| 1 | .TH "LTTNG" "1" "December 3rd, 2012" "" "" |
| 2 | |
| 3 | .SH "NAME" |
| 4 | lttng \(em LTTng 2.x tracer control command line tool |
| 5 | |
| 6 | .SH "SYNOPSIS" |
| 7 | |
| 8 | .PP |
| 9 | .nf |
| 10 | lttng [OPTIONS] <COMMAND> |
| 11 | .fi |
| 12 | .SH "DESCRIPTION" |
| 13 | |
| 14 | .PP |
| 15 | The LTTng project aims at providing highly efficient tracing tools for Linux. |
| 16 | It's tracers help tracking down performance issues and debugging problems |
| 17 | involving multiple concurrent processes and threads. Tracing across multiple |
| 18 | systems is also possible. |
| 19 | |
| 20 | The \fBlttng\fP command line tool from the lttng-tools package is used to control |
| 21 | both kernel and user-space tracing. Every interactions with the tracer should |
| 22 | be done by this tool or by the liblttng-ctl provided with the lttng-tools |
| 23 | package. |
| 24 | |
| 25 | LTTng uses a session daemon (lttng-sessiond(8)), acting as a tracing registry, |
| 26 | which allows you to interact with multiple tracers (kernel and user-space) |
| 27 | inside the same container, a tracing session. Traces can be gathered from the |
| 28 | kernel and/or instrumented applications (lttng-ust(3)). Aggregating and reading |
| 29 | those traces is done using the babeltrace(1) text viewer. |
| 30 | |
| 31 | We introduce the notion of \fBtracing domains\fP which is essentially a type of |
| 32 | tracer (kernel or user space for now). In the future, we could see a third |
| 33 | tracer being for instance an hypervisor. For some commands, you'll need to |
| 34 | specify on which domain the command applies (-u or -k). For instance, enabling |
| 35 | a kernel event, you must specify the kernel domain to the command so we know |
| 36 | for which tracer this event is for. |
| 37 | |
| 38 | In order to trace the kernel, the session daemon needs to be running as root. |
| 39 | LTTng provides the use of a \fBtracing group\fP (default: tracing). Whomever is |
| 40 | in that group can interact with the root session daemon and thus trace the |
| 41 | kernel. Session daemons can co-exist meaning that you can have a session daemon |
| 42 | running as Alice that can be used to trace her applications along side with a |
| 43 | root daemon or even a Bob daemon. We highly recommend to start the session |
| 44 | daemon at boot time for stable and long term tracing. |
| 45 | |
| 46 | Every user-space applications instrumented with lttng-ust(3), will |
| 47 | automatically register to the session daemon. This feature gives you the |
| 48 | ability to list available traceable applications and tracepoints on a per user |
| 49 | basis. (See \fBlist\fP command). |
| 50 | .SH "OPTIONS" |
| 51 | |
| 52 | .PP |
| 53 | This program follow the usual GNU command line syntax with long options starting with |
| 54 | two dashes. Below is a summary of the available options. |
| 55 | .PP |
| 56 | |
| 57 | .TP |
| 58 | .BR "\-h, \-\-help" |
| 59 | Show summary of possible options and commands. |
| 60 | .TP |
| 61 | .BR "\-v, \-\-verbose" |
| 62 | Increase verbosity. |
| 63 | Three levels of verbosity are available which are triggered by putting additional v to |
| 64 | the option (\-vv or \-vvv) |
| 65 | .TP |
| 66 | .BR "\-q, \-\-quiet" |
| 67 | Suppress all messages (even errors). |
| 68 | .TP |
| 69 | .BR "\-g, \-\-group NAME" |
| 70 | Set unix tracing group name. (default: tracing) |
| 71 | .TP |
| 72 | .BR "\-n, \-\-no-sessiond" |
| 73 | Don't automatically spawn a session daemon. |
| 74 | .TP |
| 75 | .BR "\-\-sessiond\-path PATH" |
| 76 | Set session daemon full binary path. |
| 77 | .TP |
| 78 | .BR "\-\-list\-options" |
| 79 | Simple listing of lttng options. |
| 80 | .TP |
| 81 | .BR "\-\-list\-commands" |
| 82 | Simple listing of lttng commands. |
| 83 | .SH "COMMANDS" |
| 84 | |
| 85 | .PP |
| 86 | \fBadd-context\fP [OPTIONS] |
| 87 | .RS |
| 88 | Add context to event(s) and/or channel(s). |
| 89 | |
| 90 | A context is basically extra information appended to a channel. For instance, |
| 91 | you could ask the tracer to add the PID information for all events in a |
| 92 | channel. You can also add performance monitoring unit counters (perf PMU) using |
| 93 | the perf kernel API). |
| 94 | |
| 95 | For example, this command will add the context information 'prio' and two perf |
| 96 | counters (hardware branch misses and cache misses), to all events in the trace |
| 97 | data output: |
| 98 | |
| 99 | .nf |
| 100 | # lttng add-context \-k \-t prio \-t perf:branch-misses \\ |
| 101 | \-t perf:cache-misses |
| 102 | .fi |
| 103 | |
| 104 | Please take a look at the help (\-h/\-\-help) for a detailed list of available |
| 105 | contexts. |
| 106 | |
| 107 | If no channel is given (\-c), the context is added to all channels that were |
| 108 | already enabled. If the session has no channel, a default channel is created. |
| 109 | Otherwise the context will be added only to the given channel (\-c). |
| 110 | |
| 111 | If \fB\-s, \-\-session\fP is omitted, the session name is taken from the .lttngrc |
| 112 | file. |
| 113 | |
| 114 | .B OPTIONS: |
| 115 | |
| 116 | .TP |
| 117 | .BR "\-h, \-\-help" |
| 118 | Show summary of possible options and commands. |
| 119 | .TP |
| 120 | .BR "\-s, \-\-session NAME" |
| 121 | Apply on session name. |
| 122 | .TP |
| 123 | .BR "\-c, \-\-channel NAME" |
| 124 | Apply on channel name. |
| 125 | .TP |
| 126 | .BR "\-k, \-\-kernel" |
| 127 | Apply for the kernel tracer |
| 128 | .TP |
| 129 | .BR "\-u, \-\-userspace" |
| 130 | Apply for the user-space tracer |
| 131 | .TP |
| 132 | .BR "\-t, \-\-type TYPE" |
| 133 | Context type. You can repeat this option on the command line. Please |
| 134 | use "lttng add-context \-h" to list all available types. |
| 135 | .RE |
| 136 | .PP |
| 137 | |
| 138 | .PP |
| 139 | \fBcalibrate\fP [OPTIONS] |
| 140 | .RS |
| 141 | Quantify LTTng overhead |
| 142 | |
| 143 | The LTTng calibrate command can be used to find out the combined average |
| 144 | overhead of the LTTng tracer and the instrumentation mechanisms used. This |
| 145 | overhead can be calibrated in terms of time or using any of the PMU performance |
| 146 | counter available on the system. |
| 147 | |
| 148 | For now, the only calibration implemented is that of the kernel function |
| 149 | instrumentation (kretprobes). |
| 150 | |
| 151 | * Calibrate kernel function instrumentation |
| 152 | |
| 153 | Let's use an example to show this calibration. We use an i7 processor with 4 |
| 154 | general-purpose PMU registers. This information is available by issuing dmesg, |
| 155 | looking for "generic registers". |
| 156 | |
| 157 | This sequence of commands will gather a trace executing a kretprobe hooked on |
| 158 | an empty function, gathering PMU counters LLC (Last Level Cache) misses |
| 159 | information (see lttng add-context \-\-help to see the list of available PMU |
| 160 | counters). |
| 161 | |
| 162 | .nf |
| 163 | # lttng create calibrate-function |
| 164 | # lttng enable-event calibrate \-\-kernel \\ |
| 165 | \-\-function lttng_calibrate_kretprobe |
| 166 | # lttng add-context \-\-kernel \-t perf:LLC-load-misses \\ |
| 167 | \-t perf:LLC-store-misses \\ |
| 168 | \-t perf:LLC-prefetch-misses |
| 169 | # lttng start |
| 170 | # for a in $(seq 1 10); do \\ |
| 171 | lttng calibrate \-\-kernel \-\-function; |
| 172 | done |
| 173 | # lttng destroy |
| 174 | # babeltrace $(ls \-1drt ~/lttng-traces/calibrate-function-* \\ |
| 175 | | tail \-n 1) |
| 176 | .fi |
| 177 | |
| 178 | The output from babeltrace can be saved to a text file and opened in a |
| 179 | spreadsheet (e.g. oocalc) to focus on the per-PMU counter delta between |
| 180 | consecutive "calibrate_entry" and "calibrate_return" events. Note that these |
| 181 | counters are per-CPU, so scheduling events would need to be present to account |
| 182 | for migration between CPU. Therefore, for calibration purposes, only events |
| 183 | staying on the same CPU must be considered. |
| 184 | |
| 185 | The average result, for the i7, on 10 samples: |
| 186 | |
| 187 | .nf |
| 188 | Average Std.Dev. |
| 189 | perf_LLC_load_misses: 5.0 0.577 |
| 190 | perf_LLC_store_misses: 1.6 0.516 |
| 191 | perf_LLC_prefetch_misses: 9.0 14.742 |
| 192 | .fi |
| 193 | |
| 194 | As we can notice, the load and store misses are relatively stable across runs |
| 195 | (their standard deviation is relatively low) compared to the prefetch misses. |
| 196 | We can conclude from this information that LLC load and store misses can be |
| 197 | accounted for quite precisely, but prefetches within a function seems to behave |
| 198 | too erratically (not much causality link between the code executed and the CPU |
| 199 | prefetch activity) to be accounted for. |
| 200 | |
| 201 | .B OPTIONS: |
| 202 | |
| 203 | .TP |
| 204 | .BR "\-h, \-\-help" |
| 205 | Show summary of possible options and commands. |
| 206 | .TP |
| 207 | .BR "\-k, \-\-kernel" |
| 208 | Apply for the kernel tracer |
| 209 | .TP |
| 210 | .BR "\-u, \-\-userspace" |
| 211 | Apply for the user-space tracer |
| 212 | .TP |
| 213 | .BR "\-\-function" |
| 214 | Dynamic function entry/return probe (default) |
| 215 | .RE |
| 216 | .PP |
| 217 | |
| 218 | .PP |
| 219 | .IP \fBcreate\fP [NAME] [OPTIONS] |
| 220 | .RS |
| 221 | Create tracing session. |
| 222 | |
| 223 | A tracing session contains channel(s) which contains event(s). It is domain |
| 224 | agnostic meaning that you can enable channels and events for either the |
| 225 | user-space tracer and/or the kernel tracer. It acts like a container |
| 226 | aggregating multiple tracing sources. |
| 227 | |
| 228 | On creation, a \fB.lttngrc\fP file is created in your $HOME directory |
| 229 | containing the current session name. If NAME is omitted, a session name is |
| 230 | automatically created having this form: 'auto-yyyymmdd-hhmmss'. |
| 231 | |
| 232 | If no \fB\-o, \-\-output\fP is specified, the traces will be written in |
| 233 | $HOME/lttng-traces. |
| 234 | |
| 235 | The $HOME environment variable can be overridden by defining the environment |
| 236 | variable LTTNG_HOME. This is useful when the user running the commands has |
| 237 | a non-writeable home directory. |
| 238 | |
| 239 | .B OPTIONS: |
| 240 | |
| 241 | .TP |
| 242 | .BR "\-h, \-\-help" |
| 243 | Show summary of possible options and commands. |
| 244 | .TP |
| 245 | .BR "\-\-list-options" |
| 246 | Simple listing of options |
| 247 | .TP |
| 248 | .BR "\-o, \-\-output PATH" |
| 249 | Specify output path for traces |
| 250 | .TP |
| 251 | .BR "\-\-no-output" |
| 252 | Traces will not be outputed |
| 253 | .TP |
| 254 | .BR "\-\-snapshot" |
| 255 | Set the session in snapshot mode. Created in no-output mode and uses the |
| 256 | URL, if one, as the default snapshot output. Every channel will be set |
| 257 | in overwrite mode and with mmap output (splice not supported). |
| 258 | |
| 259 | .TP |
| 260 | .BR "\-U, \-\-set-url=URL" |
| 261 | Set URL for the consumer output destination. It is persistent for the |
| 262 | session lifetime. Redo the command to change it. This will set both data |
| 263 | and control URL for network. |
| 264 | .TP |
| 265 | .BR "\-C, \-\-ctrl-url=URL" |
| 266 | Set control path URL. (Must use -D also) |
| 267 | .TP |
| 268 | .BR "\-D, \-\-data-url=URL" |
| 269 | Set data path URL. (Must use -C also) |
| 270 | .PP |
| 271 | Using these options, each API call can be controlled individually. For |
| 272 | instance, \-C does not enable the consumer automatically. You'll need the \-e |
| 273 | option for that. |
| 274 | |
| 275 | .B URL FORMAT: |
| 276 | |
| 277 | proto://[HOST|IP][:PORT1[:PORT2]][/TRACE_PATH] |
| 278 | |
| 279 | Supported protocols are (proto): |
| 280 | .TP |
| 281 | .BR "file://..." |
| 282 | Local filesystem full path. |
| 283 | |
| 284 | .TP |
| 285 | .BR "net://..." |
| 286 | This will use the default network transport layer which is TCP for both |
| 287 | control (PORT1) and data port (PORT2). The default ports are |
| 288 | respectively 5342 and 5343. Note that net[6]:// is not yet supported. |
| 289 | |
| 290 | .TP |
| 291 | .BR "tcp[6]://..." |
| 292 | Can only be used with -C and -D together |
| 293 | |
| 294 | NOTE: IPv6 address MUST be enclosed in brackets '[]' (rfc2732) |
| 295 | |
| 296 | .B EXAMPLES: |
| 297 | |
| 298 | .nf |
| 299 | # lttng create -U net://192.168.1.42 |
| 300 | .fi |
| 301 | Uses TCP and default ports for the given destination. |
| 302 | |
| 303 | .nf |
| 304 | # lttng create -U net6://[fe80::f66d:4ff:fe53:d220] |
| 305 | .fi |
| 306 | Uses TCP, default ports and IPv6. |
| 307 | |
| 308 | .nf |
| 309 | # lttng create s1 -U net://myhost.com:3229 |
| 310 | .fi |
| 311 | Create session s1 and set its consumer to myhost.com on port 3229 for control. |
| 312 | .RE |
| 313 | .PP |
| 314 | |
| 315 | |
| 316 | .IP "\fBdestroy\fP [OPTIONS] [NAME]" |
| 317 | .nf |
| 318 | Teardown tracing session |
| 319 | |
| 320 | Free memory on the session daemon and tracer side. It's gone! |
| 321 | |
| 322 | If NAME is omitted, the session name is taken from the .lttngrc file. |
| 323 | .fi |
| 324 | |
| 325 | .B OPTIONS: |
| 326 | |
| 327 | .nf |
| 328 | \-h, \-\-help |
| 329 | Show summary of possible options and commands. |
| 330 | \-a, \-\-all |
| 331 | Destroy all sessions |
| 332 | \-\-list-options |
| 333 | Simple listing of options |
| 334 | .fi |
| 335 | |
| 336 | .IP |
| 337 | |
| 338 | .IP "\fBenable-channel\fP NAME[,NAME2,...] [-k|-u] [OPTIONS]" |
| 339 | .nf |
| 340 | Enable tracing channel |
| 341 | |
| 342 | To enable an event, you must enable both the event and the channel that |
| 343 | contains it. |
| 344 | |
| 345 | If \fB\-s, \-\-session\fP is omitted, the session name is taken from the .lttngrc |
| 346 | file. |
| 347 | |
| 348 | It is important to note that if a certain type of buffers is used, the session |
| 349 | will be set with that type and all other subsequent channel needs to have the |
| 350 | same type. |
| 351 | |
| 352 | Note that once the session has been started and enabled on the tracer side, |
| 353 | it's not possible anymore to enable a new channel for that session. |
| 354 | .fi |
| 355 | |
| 356 | .B OPTIONS: |
| 357 | |
| 358 | .nf |
| 359 | \-h, \-\-help |
| 360 | Show this help |
| 361 | \-\-list-options |
| 362 | Simple listing of options |
| 363 | \-s, \-\-session NAME |
| 364 | Apply on session name |
| 365 | \-k, \-\-kernel |
| 366 | Apply to the kernel tracer |
| 367 | \-u, \-\-userspace |
| 368 | Apply to the user-space tracer |
| 369 | |
| 370 | \-\-discard |
| 371 | Discard event when subbuffers are full (default) |
| 372 | \-\-overwrite |
| 373 | Flight recorder mode : overwrites events when subbuffers are full |
| 374 | \-\-subbuf-size SIZE |
| 375 | Subbuffer size in bytes {+k,+M,+G} |
| 376 | (default UST uid: 131072, UST pid: 4096, kernel: 262144, metadata: 4096) |
| 377 | Rounded up to the next power of 2. |
| 378 | |
| 379 | The minimum subbuffer size, for each tracer, is the max value between |
| 380 | the default above and the system page size. You can issue this command |
| 381 | to get the current page size on your system: \fB$ getconf PAGE_SIZE\fP |
| 382 | \-\-num-subbuf NUM |
| 383 | Number of subbuffers. (default UST uid: 4, UST pid: 4, kernel: 4, metadata: 2) |
| 384 | Rounded up to the next power of 2. |
| 385 | \-\-switch-timer USEC |
| 386 | Switch subbuffer timer interval in µsec. |
| 387 | (default UST uid: 0, UST pid: 0, kernel: 0, metadata: 0) |
| 388 | \-\-read-timer USEC |
| 389 | Read timer interval in µsec. |
| 390 | (default UST uid: 0, UST pid: 0, kernel: 200000, metadata: 0) |
| 391 | \-\-output TYPE |
| 392 | Channel output type. Possible values: mmap, splice |
| 393 | (default UST uid: mmap, UST pid: mmap, kernel: splice, metadata: mmap) |
| 394 | \-\-buffers-uid |
| 395 | Use per UID buffer (\-u only). Buffers are shared between applications |
| 396 | that have the same UID. |
| 397 | \-\-buffers-pid |
| 398 | Use per PID buffer (\-u only). Each application has its own buffers. |
| 399 | \-\-buffers-global |
| 400 | Use shared buffer for the whole system (\-k only) |
| 401 | \-C, \-\-tracefile-size SIZE |
| 402 | Maximum size of each tracefile within a stream (in bytes). |
| 403 | 0 means unlimited. (default: 0) |
| 404 | \-W, \-\-tracefile-count COUNT |
| 405 | Used in conjunction with \-C option, this will limit the number |
| 406 | of files created to the specified count. 0 means unlimited. (default: 0) |
| 407 | |
| 408 | .B EXAMPLES: |
| 409 | |
| 410 | $ lttng enable-channel -C 4096 -W 32 chan1 |
| 411 | For each stream, the maximum size of each trace file will be 4096 bytes, and |
| 412 | there will be a maximum of 32 different files. The file count is appended after |
| 413 | the stream number as seen in the following example. The last trace file is |
| 414 | smaller than 4096 since it was not completely filled. |
| 415 | |
| 416 | ~/lttng-traces/[...]/chan1_0_0 (4096) |
| 417 | ~/lttng-traces/[...]/chan1_0_1 (4096) |
| 418 | ~/lttng-traces/[...]/chan1_0_2 (3245) |
| 419 | ~/lttng-traces/[...]/chan1_1_0 (4096) |
| 420 | ... |
| 421 | |
| 422 | $ lttng enable-channel -C 4096 |
| 423 | This will create trace files of 4096 bytes and will create new ones as long as |
| 424 | there is data available. |
| 425 | .fi |
| 426 | |
| 427 | .IP |
| 428 | |
| 429 | .IP "\fBenable-event\fP NAME[,NAME2,...] [-k|-u] [OPTIONS]" |
| 430 | .nf |
| 431 | Enable tracing event |
| 432 | |
| 433 | A tracing event is always assigned to a channel. If \fB\-c, \-\-channel\fP is |
| 434 | omitted, a default channel named '\fBchannel0\fP' is created and the event is |
| 435 | added to it. For the user-space tracer, using \fB\-a, \-\-all\fP is the same as |
| 436 | using the wildcard "*". |
| 437 | |
| 438 | If \fB\-s, \-\-session\fP is omitted, the session name is taken from the .lttngrc |
| 439 | file. |
| 440 | .fi |
| 441 | |
| 442 | .B OPTIONS: |
| 443 | |
| 444 | .nf |
| 445 | \-h, \-\-help |
| 446 | Show summary of possible options and commands. |
| 447 | \-\-list-options |
| 448 | Simple listing of options |
| 449 | \-s, \-\-session NAME |
| 450 | Apply on session name |
| 451 | \-c, \-\-channel NAME |
| 452 | Apply on channel name |
| 453 | \-a, \-\-all |
| 454 | Enable all tracepoints and syscalls. This actually enable a single |
| 455 | wildcard event "*". |
| 456 | \-k, \-\-kernel |
| 457 | Apply for the kernel tracer |
| 458 | \-u, \-\-userspace |
| 459 | Apply for the user-space tracer |
| 460 | |
| 461 | \-\-tracepoint |
| 462 | Tracepoint event (default) |
| 463 | - userspace tracer supports wildcards at end of string. Don't forget to |
| 464 | quote to deal with bash expansion. |
| 465 | e.g.: |
| 466 | "*" |
| 467 | "app_component:na*" |
| 468 | \-\-loglevel NAME |
| 469 | Tracepoint loglevel range from 0 to loglevel. Listed in the help (\-h). |
| 470 | \-\-loglevel-only NAME |
| 471 | Tracepoint loglevel (only this loglevel). |
| 472 | |
| 473 | The loglevel or loglevel-only options should be combined with a |
| 474 | tracepoint name or tracepoint wildcard. |
| 475 | \-\-probe [addr | symbol | symbol+offset] |
| 476 | Dynamic probe. Addr and offset can be octal (0NNN...), decimal (NNN...) |
| 477 | or hexadecimal (0xNNN...) |
| 478 | \-\-function [addr | symbol | symbol+offset] |
| 479 | Dynamic function entry/return probe. Addr and offset can be octal |
| 480 | (0NNN...), decimal (NNN...) or hexadecimal (0xNNN...) |
| 481 | \-\-syscall |
| 482 | System call event. Enabling syscalls tracing (kernel tracer), you will |
| 483 | not be able to disable them with disable-event. This is a known |
| 484 | limitation. You can disable the entire channel to do the trick. |
| 485 | |
| 486 | \-\-filter 'expression' |
| 487 | Set a filter on a newly enabled event. Filter expression on event |
| 488 | fields and context. Event recording depends on evaluation. Only |
| 489 | specify on first activation of a given event within a session. |
| 490 | Filter only allowed when enabling events within a session before |
| 491 | tracing is started. If the filter fails to link with the event |
| 492 | within the traced domain, the event will be discarded. |
| 493 | Currently, filter is only implemented for the user-space tracer. |
| 494 | |
| 495 | Expression examples: |
| 496 | |
| 497 | 'intfield > 500 && intfield < 503' |
| 498 | '(stringfield == "test" || intfield != 10) && intfield > 33' |
| 499 | 'doublefield > 1.1 && intfield < 5.3' |
| 500 | |
| 501 | Wildcards are allowed at the end of strings: |
| 502 | 'seqfield1 == "te*"' |
| 503 | In string literals, the escape character is a '\\'. Use '\\*' for |
| 504 | the '*' character, and '\\\\' for the '\\' character. Wildcard |
| 505 | match any sequence of characters, including an empty sub-string |
| 506 | (match 0 or more characters). |
| 507 | |
| 508 | Context information can be used for filtering. The examples |
| 509 | below show usage of context filtering on process name (with a |
| 510 | wildcard), process ID range, and unique thread ID for filtering. |
| 511 | The process and thread ID of running applications can be found |
| 512 | under columns "PID" and "LWP" of the "ps -eLf" command. |
| 513 | |
| 514 | '$ctx.procname == "demo*"' |
| 515 | '$ctx.vpid >= 4433 && $ctx.vpid < 4455' |
| 516 | '$ctx.vtid == 1234' |
| 517 | .fi |
| 518 | |
| 519 | .IP "\fBdisable-channel\fP NAME[,NAME2,...] [\-k|\-u] [OPTIONS]" |
| 520 | .nf |
| 521 | Disable tracing channel |
| 522 | |
| 523 | Disabling a channel makes all event(s) in that channel to stop tracing. You can |
| 524 | enable it back by calling \fBlttng enable-channel NAME\fP again. |
| 525 | |
| 526 | If \fB\-s, \-\-session\fP is omitted, the session name is taken from the .lttngrc |
| 527 | file. |
| 528 | .fi |
| 529 | |
| 530 | .B OPTIONS: |
| 531 | |
| 532 | .nf |
| 533 | \-h, \-\-help |
| 534 | Show summary of possible options and commands. |
| 535 | \-\-list-options |
| 536 | Simple listing of options |
| 537 | \-s, \-\-session NAME |
| 538 | Apply on session name |
| 539 | \-k, \-\-kernel |
| 540 | Apply for the kernel tracer |
| 541 | \-u, \-\-userspace |
| 542 | Apply for the user-space tracer |
| 543 | .fi |
| 544 | |
| 545 | .IP "\fBdisable-event\fP NAME[,NAME2,...] [\-k|\-u] [OPTIONS]" |
| 546 | .nf |
| 547 | Disable tracing event |
| 548 | |
| 549 | The event, once disabled, can be re-enabled by calling \fBlttng enable-event |
| 550 | NAME\fP again. |
| 551 | |
| 552 | If \fB\-s, \-\-session\fP is omitted, the session name is taken from the .lttngrc |
| 553 | file. |
| 554 | .fi |
| 555 | |
| 556 | .B OPTIONS: |
| 557 | |
| 558 | .nf |
| 559 | \-h, \-\-help |
| 560 | Show summary of possible options and commands. |
| 561 | \-\-list-options |
| 562 | Simple listing of options |
| 563 | \-s, \-\-session NAME |
| 564 | Apply on session name |
| 565 | \-a, \-\-all-events |
| 566 | Disable all events. This does NOT disable "*" but rather |
| 567 | every known events of the session. |
| 568 | \-k, \-\-kernel |
| 569 | Apply for the kernel tracer |
| 570 | \-u, \-\-userspace |
| 571 | Apply for the user-space tracer |
| 572 | .fi |
| 573 | |
| 574 | .IP "\fBlist\fP [\-k|\-u] [SESSION [SESSION_OPTIONS]]" |
| 575 | .nf |
| 576 | List tracing session information. |
| 577 | |
| 578 | With no arguments, it will list available tracing session(s). |
| 579 | |
| 580 | With the session name, it will display the details of the session including |
| 581 | the trace file path, the associated channels and their state (activated |
| 582 | and deactivated), the activated events and more. |
| 583 | |
| 584 | With \-k alone, it will list all available kernel events (except the system |
| 585 | calls events). |
| 586 | With \-u alone, it will list all available user-space events from registered |
| 587 | applications. Here is an example of 'lttng list \-u': |
| 588 | |
| 589 | PID: 7448 - Name: /tmp/lttng-ust/tests/hello/.libs/lt-hello |
| 590 | ust_tests_hello:tptest_sighandler (type: tracepoint) |
| 591 | ust_tests_hello:tptest (type: tracepoint) |
| 592 | |
| 593 | You can now enable any event listed by using the name : |
| 594 | \fBust_tests_hello:tptest\fP. |
| 595 | .fi |
| 596 | |
| 597 | .B OPTIONS: |
| 598 | |
| 599 | .nf |
| 600 | \-h, \-\-help |
| 601 | Show summary of possible options and commands. |
| 602 | \-\-list-options |
| 603 | Simple listing of options |
| 604 | \-k, \-\-kernel |
| 605 | Select kernel domain |
| 606 | \-u, \-\-userspace |
| 607 | Select user-space domain. |
| 608 | |
| 609 | .B SESSION OPTIONS: |
| 610 | |
| 611 | \-c, \-\-channel NAME |
| 612 | List details of a channel |
| 613 | \-d, \-\-domain |
| 614 | List available domain(s) |
| 615 | .fi |
| 616 | |
| 617 | .IP "\fBset-session\fP NAME" |
| 618 | .nf |
| 619 | Set current session name |
| 620 | |
| 621 | Will change the session name in the .lttngrc file. |
| 622 | .fi |
| 623 | |
| 624 | .B OPTIONS: |
| 625 | |
| 626 | .nf |
| 627 | \-h, \-\-help |
| 628 | Show summary of possible options and commands. |
| 629 | \-\-list-options |
| 630 | Simple listing of options |
| 631 | .fi |
| 632 | |
| 633 | .IP |
| 634 | |
| 635 | .IP "\fBsnapshot\fP ACTION" |
| 636 | .nf |
| 637 | Snapshot command for LTTng session. |
| 638 | .fi |
| 639 | |
| 640 | .B OPTIONS: |
| 641 | |
| 642 | .nf |
| 643 | \-h, \-\-help |
| 644 | Show summary of possible options and commands. |
| 645 | \-\-list-options |
| 646 | Simple listing of options |
| 647 | .fi |
| 648 | |
| 649 | .B ACTION: |
| 650 | |
| 651 | .nf |
| 652 | \fBadd-output\fP [-m <SIZE>] [-s <NAME>] [-n <NAME>] <URL> | -C <URL> -D <URL> |
| 653 | |
| 654 | Setup and add an snapshot output for a session. Output are the destination |
| 655 | where the snapshot will be sent. Only one output is permitted. To change it, |
| 656 | you'll need to delete it and add back the new one. |
| 657 | |
| 658 | \fBdel-output\fP ID | NAME [-s <NAME>] |
| 659 | |
| 660 | Delete an output for a session using the ID. You can either specify the |
| 661 | output's ID that can be found with list-output or the name. |
| 662 | |
| 663 | \fBlist-output\fP [-s <NAME>] |
| 664 | |
| 665 | List the output of a session. Attributes of the output are printed. |
| 666 | |
| 667 | \fBrecord\fP [-m <SIZE>] [-s <NAME>] [-n <NAME>] [<URL> | -C <URL> -D <URL>] |
| 668 | |
| 669 | Snapshot a session's buffer(s) for all domains. If an URL is specified, it is |
| 670 | used instead of a previously added output. Specifying only a name or/and a max |
| 671 | size will override the current output values. For instance, you can record a |
| 672 | snapshot with a custom maximum size or with a different name. |
| 673 | |
| 674 | $ lttng add-output -n mysnapshot file:///data/snapshot |
| 675 | [...] |
| 676 | $ lttng snapshot record -n new_name_snapshot |
| 677 | |
| 678 | The above will create a snapshot in /data/snapshot/new_name_snapshot* directory |
| 679 | rather then in mysnapshot*/ |
| 680 | .fi |
| 681 | |
| 682 | .B LONG OPTIONS |
| 683 | |
| 684 | .nf |
| 685 | \-s, \-\-session NAME |
| 686 | Apply to session name. |
| 687 | \-n, \-\-name NAME |
| 688 | Name of the snapshot's output. |
| 689 | \-m, \-\-max-size SIZE |
| 690 | Maximum size in bytes of the snapshot. The maxium size does not |
| 691 | include the metadata file. |
| 692 | \-C, \-\-ctrl-url URL |
| 693 | Set control path URL. (Must use -D also) |
| 694 | \-D, \-\-data-url URL |
| 695 | Set data path URL. (Must use -C also) |
| 696 | .fi |
| 697 | |
| 698 | .IP |
| 699 | |
| 700 | .IP "\fBstart\fP [NAME] [OPTIONS]" |
| 701 | .nf |
| 702 | Start tracing |
| 703 | |
| 704 | It will start tracing for all tracers for a specific tracing session. |
| 705 | |
| 706 | If NAME is omitted, the session name is taken from the .lttngrc file. |
| 707 | .fi |
| 708 | |
| 709 | .B OPTIONS: |
| 710 | |
| 711 | .nf |
| 712 | \-h, \-\-help |
| 713 | Show summary of possible options and commands. |
| 714 | \-\-list-options |
| 715 | Simple listing of options |
| 716 | .fi |
| 717 | |
| 718 | .IP |
| 719 | |
| 720 | .IP "\fBstop\fP [NAME] [OPTIONS]" |
| 721 | .nf |
| 722 | Stop tracing |
| 723 | |
| 724 | It will stop tracing for all tracers for a specific tracing session. Before |
| 725 | returning, the command checks for data availability meaning that it will wait |
| 726 | until the trace is readable for the session. Use \-\-no-wait to avoid this |
| 727 | behavior. |
| 728 | |
| 729 | If NAME is omitted, the session name is taken from the .lttngrc file. |
| 730 | .fi |
| 731 | |
| 732 | .B OPTIONS: |
| 733 | |
| 734 | .nf |
| 735 | \-h, \-\-help |
| 736 | Show summary of possible options and commands. |
| 737 | \-\-list-options |
| 738 | Simple listing of options |
| 739 | \-\-no-wait |
| 740 | Don't wait for data availability. |
| 741 | .fi |
| 742 | |
| 743 | .IP |
| 744 | |
| 745 | .IP "\fBversion\fP" |
| 746 | .nf |
| 747 | Show version information |
| 748 | .fi |
| 749 | |
| 750 | .B OPTIONS: |
| 751 | |
| 752 | .nf |
| 753 | \-h, \-\-help |
| 754 | Show summary of possible options and commands. |
| 755 | \-\-list-options |
| 756 | Simple listing of options |
| 757 | .fi |
| 758 | |
| 759 | .IP |
| 760 | |
| 761 | .IP "\fBview\fP [SESSION_NAME] [OPTIONS]" |
| 762 | .nf |
| 763 | View traces of a tracing session |
| 764 | |
| 765 | By default, the babeltrace viewer will be used for text viewing. |
| 766 | |
| 767 | If SESSION_NAME is omitted, the session name is taken from the .lttngrc file. |
| 768 | |
| 769 | .fi |
| 770 | |
| 771 | .B OPTIONS: |
| 772 | |
| 773 | .nf |
| 774 | \-h, \-\-help |
| 775 | Show this help |
| 776 | \-\-list-options |
| 777 | Simple listing of options |
| 778 | \-t, \-\-trace-path PATH |
| 779 | Trace directory path for the viewer |
| 780 | \-e, \-\-viewer CMD |
| 781 | Specify viewer and/or options to use |
| 782 | This will completely override the default viewers so |
| 783 | please make sure to specify the full command. The trace |
| 784 | directory path of the session will be appended at the end |
| 785 | to the arguments |
| 786 | .fi |
| 787 | |
| 788 | .SH "EXIT VALUES" |
| 789 | On success 0 is returned and a positive value on error. Value of 1 means a command |
| 790 | error, 2 an undefined command, 3 a fatal error and 4 a command warning meaning that |
| 791 | something went wrong during the command. |
| 792 | |
| 793 | Any other value above 10, please refer to |
| 794 | .BR <lttng/lttng-error.h> |
| 795 | for a detailed list or use lttng_strerror() to get a human readable string of |
| 796 | the error code. |
| 797 | |
| 798 | .PP |
| 799 | .SH "ENVIRONMENT VARIABLES" |
| 800 | |
| 801 | .PP |
| 802 | Note that all command line options override environment variables. |
| 803 | .PP |
| 804 | |
| 805 | .PP |
| 806 | .IP "LTTNG_SESSIOND_PATH" |
| 807 | Allows one to specify the full session daemon binary path to lttng command line |
| 808 | tool. You can also use \-\-sessiond-path option having the same effect. |
| 809 | .SH "SEE ALSO" |
| 810 | .BR babeltrace(1), |
| 811 | .BR lttng-ust(3), |
| 812 | .BR lttng-sessiond(8), |
| 813 | .BR lttng-relayd(8), |
| 814 | .BR lttng-health-check(3) |
| 815 | .SH "BUGS" |
| 816 | |
| 817 | If you encounter any issues or usability problem, please report it on our |
| 818 | mailing list <lttng-dev@lists.lttng.org> to help improve this project or |
| 819 | at https://bugs.lttng.org which is a bugtracker. |
| 820 | .SH "CREDITS" |
| 821 | |
| 822 | .PP |
| 823 | lttng is distributed under the GNU General Public License version 2. See the file |
| 824 | COPYING for details. |
| 825 | .PP |
| 826 | A Web site is available at http://lttng.org for more information on the LTTng |
| 827 | project. |
| 828 | .PP |
| 829 | You can also find our git tree at http://git.lttng.org. |
| 830 | .PP |
| 831 | Mailing lists for support and development: <lttng-dev@lists.lttng.org>. |
| 832 | .PP |
| 833 | You can find us on IRC server irc.oftc.net (OFTC) in #lttng. |
| 834 | .PP |
| 835 | .SH "THANKS" |
| 836 | |
| 837 | .PP |
| 838 | Thanks to Yannick Brosseau without whom this project would never have been so |
| 839 | lean and mean! Also thanks to the Ericsson teams working on tracing which |
| 840 | helped us greatly with detailed bug reports and unusual test cases. |
| 841 | |
| 842 | Thanks to our beloved packager Alexandre Montplaisir-Goncalves (Ubuntu and PPA |
| 843 | maintainer) and Jon Bernard for our Debian packages. |
| 844 | |
| 845 | Special thanks to Michel Dagenais and the DORSAL laboratory at Polytechnique de |
| 846 | Montreal for the LTTng journey. |
| 847 | .PP |
| 848 | .SH "AUTHORS" |
| 849 | |
| 850 | .PP |
| 851 | lttng-tools was originally written by Mathieu Desnoyers, Julien Desfossez and |
| 852 | David Goulet. More people have since contributed to it. It is currently |
| 853 | maintained by David Goulet <dgoulet@efficios.com>. |
| 854 | .PP |