| 1 | \input texinfo @c -*-texinfo-*- |
| 2 | @c %**start of header |
| 3 | @setfilename ust.info |
| 4 | @settitle LTTng Userspace Tracer (UST) Manual |
| 5 | @c %**end of header |
| 6 | |
| 7 | @copying |
| 8 | This manual is for program, version version. |
| 9 | |
| 10 | Copyright @copyright{} copyright-owner. |
| 11 | |
| 12 | @quotation |
| 13 | Permission is granted to ... |
| 14 | @end quotation |
| 15 | @end copying |
| 16 | |
| 17 | @titlepage |
| 18 | @title LTTng Userspace Tracer (UST) Manual |
| 19 | @c @subtitle subtitle-if-any |
| 20 | @c @subtitle second-subtitle |
| 21 | @c @author author |
| 22 | |
| 23 | @c The following two commands |
| 24 | @c start the copyright page. |
| 25 | @c @page |
| 26 | @c @vskip 0pt plus 1filll |
| 27 | @c @insertcopying |
| 28 | |
| 29 | @c Published by ... |
| 30 | @end titlepage |
| 31 | |
| 32 | @c So the toc is printed at the start. |
| 33 | @contents |
| 34 | |
| 35 | @ifnottex |
| 36 | @node Top |
| 37 | @top LTTng Userspace Tracer |
| 38 | |
| 39 | This manual is for UST 0.4. |
| 40 | @end ifnottex |
| 41 | |
| 42 | @menu |
| 43 | * Overview:: |
| 44 | * Installation:: |
| 45 | * Quick start:: |
| 46 | * Instrumenting an application:: |
| 47 | * Recording a trace:: |
| 48 | * Viewing traces:: |
| 49 | * Performance:: |
| 50 | * Resource Usage:: |
| 51 | @c * Copying:: Your rights and freedoms. |
| 52 | @end menu |
| 53 | |
| 54 | @node Overview |
| 55 | @chapter Overview |
| 56 | |
| 57 | @menu |
| 58 | * What is UST?:: |
| 59 | * License:: |
| 60 | * Supported platforms:: |
| 61 | @end menu |
| 62 | |
| 63 | @node What is UST? |
| 64 | @section What is UST? |
| 65 | |
| 66 | The LTTng Userspace Tracer (UST) is a library accompanied by a set of tools to |
| 67 | trace userspace code. |
| 68 | |
| 69 | Code may be instrumented with either markers or tracepoints. A highly efficient |
| 70 | lockless tracer records these events to a trace buffers. These buffers are reaped |
| 71 | by a deamon which writes trace data to disk. |
| 72 | |
| 73 | High performance is achieved by the use of lockless buffering algorithms, RCU and |
| 74 | per-cpu buffers. In addition, special care is taken to minize cache impact. |
| 75 | |
| 76 | @node License |
| 77 | @section License |
| 78 | The LTTng Userspace Tracer is intended to be linkable to open source software |
| 79 | as well as to proprietary applications. This was accomplished by licensing |
| 80 | the code that needs to be linked to the traced program as @acronym{LGPL}. |
| 81 | |
| 82 | Components licensed as LGPL v2.1: |
| 83 | @itemize @bullet |
| 84 | @item libust |
| 85 | @item libinterfork |
| 86 | @item libustcomm |
| 87 | @end itemize |
| 88 | |
| 89 | Components licensed as GPL v2: |
| 90 | @itemize @bullet |
| 91 | @item ustctl |
| 92 | @item libustcmd |
| 93 | @item ustd |
| 94 | @end itemize |
| 95 | |
| 96 | @node Supported platforms |
| 97 | @section Supported platforms |
| 98 | |
| 99 | UST can currently trace applications running on Linux, on the x86-32, x86-64 |
| 100 | and PowerPC 32 architectures. |
| 101 | |
| 102 | @node Installation |
| 103 | @chapter Installation |
| 104 | |
| 105 | The LTTng userspace tracer is a library and a set of userspace tools. |
| 106 | |
| 107 | The following packages are required: |
| 108 | |
| 109 | @itemize @bullet |
| 110 | @item |
| 111 | ust |
| 112 | |
| 113 | This contains the tracing library, the ustd daemon, trace control tools |
| 114 | and other helper tools. |
| 115 | |
| 116 | Repository: http://git.dorsal.polymtl.ca |
| 117 | |
| 118 | @item |
| 119 | libkcompat |
| 120 | |
| 121 | This is a library that contains a userspace port of some kernel APIs. |
| 122 | |
| 123 | Repository: http://git.dorsal.polymtl.ca |
| 124 | |
| 125 | @item |
| 126 | liburcu |
| 127 | |
| 128 | This is the userspace read-copy update library by Mathieu Desnoyers. |
| 129 | |
| 130 | Available in Debian as package liburcu-dev. |
| 131 | |
| 132 | Home page: http://lttng.org/?q=node/18 |
| 133 | |
| 134 | @item |
| 135 | LTTV |
| 136 | |
| 137 | LTTV is a graphical (and text) viewer for LTTng traces. |
| 138 | |
| 139 | Home page: http://lttng.org |
| 140 | |
| 141 | @end itemize |
| 142 | |
| 143 | Libkcompat and liburcu should be installed first. UST may then be compiled |
| 144 | and installed. LTTV has no dependency on the other packages; it may therefore |
| 145 | be installed on a system which does not have UST installed. |
| 146 | |
| 147 | Refer to the README in each of these packages for installation instructions. |
| 148 | |
| 149 | @c @menu |
| 150 | @c @end menu |
| 151 | |
| 152 | @node Quick start |
| 153 | @chapter Quick start |
| 154 | |
| 155 | First, instrument a program with a marker. |
| 156 | |
| 157 | @example |
| 158 | @verbatim |
| 159 | |
| 160 | #include <ust/marker.h> |
| 161 | |
| 162 | int main(int argc, char **argv) |
| 163 | { |
| 164 | int v; |
| 165 | char *st; |
| 166 | |
| 167 | /* ... set values of v and st ... */ |
| 168 | |
| 169 | /* a marker: */ |
| 170 | trace_mark(ust, myevent, "firstarg %d secondarg %s", v, st); |
| 171 | |
| 172 | /* a marker without arguments: */ |
| 173 | trace_mark(ust, myotherevent, MARK_NOARGS); |
| 174 | |
| 175 | return 0; |
| 176 | } |
| 177 | |
| 178 | @end verbatim |
| 179 | @end example |
| 180 | |
| 181 | Then compile it in the regular way, linking it with libust. For example: |
| 182 | |
| 183 | @example |
| 184 | gcc -o foo -lust foo.c |
| 185 | @end example |
| 186 | |
| 187 | Run the program with @command{usttrace}. The @command{usttrace} output says where the trace |
| 188 | was written. |
| 189 | |
| 190 | @example |
| 191 | usttrace ./foo |
| 192 | @end example |
| 193 | |
| 194 | Finally, open the trace in LTTV. |
| 195 | |
| 196 | @example |
| 197 | lttv-gui -t /path/to/trace |
| 198 | @end example |
| 199 | |
| 200 | The trace can also be dumped as text in the console: |
| 201 | |
| 202 | @example |
| 203 | lttv -m textDump -t /path/to/trace |
| 204 | @end example |
| 205 | |
| 206 | @node Instrumenting an application |
| 207 | @chapter Instrumenting an application |
| 208 | |
| 209 | In order to record a trace of events occurring in a application, the |
| 210 | application must be instrumented. Instrumentation points resemble function |
| 211 | calls. When the program reaches an instrumentation point, an event is |
| 212 | generated. |
| 213 | |
| 214 | There are no limitations on the type of code that may be instrumented. |
| 215 | Multi-threaded programs may be instrumented without problem. Signal handlers |
| 216 | may be instrumented as well. |
| 217 | |
| 218 | There are two APIs to instrument programs: markers and tracepoints. Markers are |
| 219 | quick to add and are usually used for temporary instrumentation. Tracepoints |
| 220 | provide a way to instrument code more cleanly and are suited for permanent |
| 221 | instrumentation. |
| 222 | |
| 223 | In addition to executable programs, shared libraries may also be instrumented |
| 224 | with the methods described in this chapter. |
| 225 | |
| 226 | @menu |
| 227 | * Markers:: |
| 228 | * Tracepoints:: |
| 229 | @end menu |
| 230 | |
| 231 | @node Markers |
| 232 | @section Markers |
| 233 | |
| 234 | Adding a marker is simply a matter of inserting one line in the program. |
| 235 | |
| 236 | @example |
| 237 | @verbatim |
| 238 | #include <ust/marker.h> |
| 239 | |
| 240 | int main(int argc, char **argv) |
| 241 | { |
| 242 | int v; |
| 243 | char *st; |
| 244 | |
| 245 | /* ... set values of v and st ... */ |
| 246 | |
| 247 | /* a marker: */ |
| 248 | trace_mark(main, myevent, "firstarg %d secondarg %s", v, st); |
| 249 | |
| 250 | /* another marker without arguments: */ |
| 251 | trace_mark(main, myotherevent, MARK_NOARGS); |
| 252 | |
| 253 | return 0; |
| 254 | } |
| 255 | @end verbatim |
| 256 | @end example |
| 257 | |
| 258 | The invocation of the trace_mark() macro requires at least 3 arguments. The |
| 259 | first, here "main", is the name of the event category. It is also the name of |
| 260 | the channel the event will go in. The second, here "myevent" is the name of the |
| 261 | event. The third is a format string that announces the names and the types of |
| 262 | the event arguments. Its format resembles that of a printf() format string; it |
| 263 | is described thoroughly in Appendix x. |
| 264 | |
| 265 | A given Marker may appear more than once in the same program. Other Markers may |
| 266 | have the same name and a different format string, although this might induce |
| 267 | some confusion at analysis time. |
| 268 | |
| 269 | @node Tracepoints |
| 270 | @section Tracepoints |
| 271 | |
| 272 | The Tracepoints API uses the Markers, but provides a higher-level abstraction. |
| 273 | Whereas the markers API provides limited type checking, the Tracepoints API |
| 274 | provides more thorough type checking and discharges from the need to insert |
| 275 | format strings directly in the code and to have format strings appear more than |
| 276 | once if a given marker is reused. |
| 277 | |
| 278 | @quotation Note |
| 279 | Although this example uses @emph{mychannel} as the channel, the |
| 280 | only channel name currently supported with early tracing is @strong{ust}. The |
| 281 | @command{usttrace} tool always uses the early tracing mode. When using manual |
| 282 | mode without early tracing, any channel name may be used. |
| 283 | @end quotation |
| 284 | |
| 285 | A function instrumented with a tracepoint looks like this: |
| 286 | |
| 287 | @example |
| 288 | @verbatim |
| 289 | #include "tp.h" |
| 290 | |
| 291 | void function() |
| 292 | { |
| 293 | int v; |
| 294 | char *st; |
| 295 | |
| 296 | /* ... set values of v and st ... */ |
| 297 | |
| 298 | /* a tracepoint: */ |
| 299 | trace_mychannel_myevent(v, st); |
| 300 | } |
| 301 | @end verbatim |
| 302 | @end example |
| 303 | |
| 304 | Another file, here tp.h, contains declarations for the tracepoint. |
| 305 | |
| 306 | @example |
| 307 | @verbatim |
| 308 | #include <ust/tracepoint.h> |
| 309 | |
| 310 | DECLARE_TRACE(mychannel_myevent, TP_PROTO(int v, char *st), |
| 311 | TP_ARGS(v, st)); |
| 312 | @end verbatim |
| 313 | @end example |
| 314 | |
| 315 | A third file, here tp.c, contains definitions for the tracepoint. |
| 316 | |
| 317 | @example |
| 318 | @verbatim |
| 319 | #include <ust/marker.h> |
| 320 | #include "tp.h" |
| 321 | |
| 322 | DEFINE_TRACE(mychannel_myevent); |
| 323 | |
| 324 | void mychannel_myevent_probe(int v, char *st) |
| 325 | { |
| 326 | trace_mark(mychannel, myevent, "v %d st %s", v, st); |
| 327 | } |
| 328 | |
| 329 | static void __attribute__((constructor)) init() |
| 330 | { |
| 331 | register_trace_mychannel_myevent(mychannel_myevent_probe); |
| 332 | } |
| 333 | @end verbatim |
| 334 | @end example |
| 335 | |
| 336 | Here, tp.h and tp.c could contain declarations and definitions for other |
| 337 | tracepoints. The constructor would contain other register_* calls. |
| 338 | |
| 339 | @node Recording a trace |
| 340 | @chapter Recording a trace |
| 341 | |
| 342 | @menu |
| 343 | * Using @command{usttrace}:: |
| 344 | * Setting up the recording manually:: |
| 345 | * Using early tracing:: |
| 346 | * Crash recovery:: |
| 347 | * Tracing across @code{fork()} and @code{clone()}:: |
| 348 | * Tracing programs and libraries that were not linked to libust:: |
| 349 | @end menu |
| 350 | |
| 351 | @node Using @command{usttrace} |
| 352 | @section Using @command{usttrace} |
| 353 | |
| 354 | The simplest way to record a trace is to use the @command{usttrace} script. An |
| 355 | example is given in the quickstart above. |
| 356 | |
| 357 | The @command{usttrace} script automatically: |
| 358 | @itemize @bullet |
| 359 | @item creates a daemon |
| 360 | @item enables all markers |
| 361 | @item runs the command specified on the command line |
| 362 | @item after the command ends, prints the location where the trace was saved |
| 363 | @end itemize |
| 364 | |
| 365 | Each subdirectory of the save location contains the trace of one process that |
| 366 | was generated by the command. The name of a subdirectory consists in the the PID |
| 367 | of the process, followed by the timestamp of its creation. |
| 368 | |
| 369 | The save location also contains logs of the tracing. |
| 370 | |
| 371 | When using @command{usttrace}, the early tracing is always active, which means |
| 372 | that the tracing is guaranteed to be started by the time the process enters its |
| 373 | main() function. |
| 374 | |
| 375 | Several @command{usttrace}'s may be run simultaneously without risk of |
| 376 | conflict. This facilitates the use of the tracer by idependent users on a |
| 377 | system. Each instance of @command{usttrace} starts its own daemon which |
| 378 | collects the events of the processes it creates. |
| 379 | |
| 380 | @node Setting up the recording manually |
| 381 | @section Setting up the recording manually |
| 382 | |
| 383 | Instead of using @command{usttrace}, a trace may be recorded on an already |
| 384 | running process. |
| 385 | |
| 386 | First the daemon must be started. |
| 387 | |
| 388 | @example |
| 389 | @verbatim |
| 390 | # Make sure the directory for the communication sockets exists. |
| 391 | $ mkdir /tmp/ustsocks |
| 392 | |
| 393 | # Make sure the directory where ustd will write the trace exists. |
| 394 | $ mkdir /tmp/trace |
| 395 | |
| 396 | # Start the daemon |
| 397 | $ ustd |
| 398 | |
| 399 | # We assume the program we want to trace is already running and that |
| 400 | # it has pid 1234. |
| 401 | |
| 402 | # List the available markers |
| 403 | $ ustctl --list-markers 1234 |
| 404 | # A column indicates 0 for an inactive marker and 1 for an active marker. |
| 405 | |
| 406 | # Enable a marker |
| 407 | $ ustctl --enable-marker ust/mymark 1234 |
| 408 | |
| 409 | # Create a trace |
| 410 | $ ustctl --create-trace 1234 |
| 411 | |
| 412 | # Start tracing |
| 413 | $ ustctl --start-trace 1234 |
| 414 | |
| 415 | # Do things... |
| 416 | |
| 417 | # Stop tracing |
| 418 | $ ustctl --stop-trace 1234 |
| 419 | |
| 420 | # Destroy the trace |
| 421 | $ ustctl --destroy-trace 1234 |
| 422 | @end verbatim |
| 423 | @end example |
| 424 | |
| 425 | For more information about the manual mode, see the ustctl(1) man page. |
| 426 | |
| 427 | @node Using early tracing |
| 428 | @section Using early tracing |
| 429 | |
| 430 | Early tracing consists in starting the tracing as early as possible in the |
| 431 | program, so no events are lost between program start and the point where the |
| 432 | command to start the tracing is given. When using early tracing, it is |
| 433 | guaranteed that by the time the traced program enters its @code{main()} |
| 434 | function, the tracing will be started. |
| 435 | |
| 436 | When using @command{usttrace}, the early tracing is always active. |
| 437 | |
| 438 | When using the manual mode (@command{ustctl}), early tracing is enabled using |
| 439 | environment variables. Setting @env{UST_TRACE} to @code{1}, enables early |
| 440 | tracing, while setting @env{UST_AUTOPROBE} to @code{1} enables all markers |
| 441 | automatically. |
| 442 | |
| 443 | |
| 444 | @node Crash recovery |
| 445 | @section Crash recovery |
| 446 | |
| 447 | When a process being traced crashes, the daemon is able to recover all the |
| 448 | events in its buffers that were successfully commited. This is possible because |
| 449 | the buffers are in a shared memory segment which remains available to the |
| 450 | daemon even after the termination of the traced process. |
| 451 | |
| 452 | @node Tracing across @code{fork()} and @code{clone()} |
| 453 | @section Tracing across @code{fork()} and @code{clone()} |
| 454 | |
| 455 | Tracing across @code{clone()} when the @code{CLONE_VM} flag is specified is |
| 456 | supported without any particular action. |
| 457 | |
| 458 | When @code{clone()} is called without @code{CLONE_VM} or @code{fork()} is |
| 459 | called, a new address space is created and the tracer must be notified to |
| 460 | create new buffers for it. |
| 461 | |
| 462 | This can be done automatically, by @env{LD_PRELOAD}'ing @file{libinterfork.so}. |
| 463 | This library intercepts calls to @code{fork()} and informs the tracer it is |
| 464 | being called. When using @command{usttrace}, this is accomplied by specifying |
| 465 | the @option{-f} command line argument. |
| 466 | |
| 467 | Alternatively, the program can call @code{ust_before_fork()} before calling |
| 468 | @code{fork()} or @code{clone()} with @code{CLONE_VM}. After the call, |
| 469 | @code{ust_after_fork_parent()} must be called in the parent process and |
| 470 | @code{ust_after_fork_child()} must be called in the child process. |
| 471 | |
| 472 | |
| 473 | @node Tracing programs and libraries that were not linked to libust |
| 474 | @section Tracing programs and libraries that were not linked to libust |
| 475 | |
| 476 | Some programs need to be traced even though they were not linked to libust |
| 477 | either because they were not instrumented or because it was not practical. |
| 478 | |
| 479 | An executable that is not instrumented can still yield interesting traces when |
| 480 | at least one of its dynamic libraries is instrumented. It is also possible to |
| 481 | trace certain function calls by intercepting them with a specially crafted |
| 482 | library that is linked with @env{LD_PRELOAD} at program start. |
| 483 | |
| 484 | In any case, a program that was not linked to libust at compile time must be |
| 485 | linked to it at run time with @env{LD_PRELOAD}. This can be accomplished with |
| 486 | @command{usttrace}'s @option{-l} option. It can also be done by setting the |
| 487 | @env{LD_PRELOAD} environment variable on the command line. For example: |
| 488 | |
| 489 | @example |
| 490 | @verbatim |
| 491 | # Run ls with usttrace, LD_PRELOAD'ing libust |
| 492 | # (assuming one of the libraries used by ls is instrumented). |
| 493 | $ usttrace -l ls |
| 494 | |
| 495 | # Run ls, manually adding the LD_PRELOAD. |
| 496 | $ LD_PRELOAD=/usr/local/lib/libust.so.0 ls |
| 497 | @end verbatim |
| 498 | @end example |
| 499 | |
| 500 | |
| 501 | @node Performance |
| 502 | @chapter Performance |
| 503 | |
| 504 | Todo. |
| 505 | |
| 506 | @node Viewing traces |
| 507 | @chapter Viewing traces |
| 508 | |
| 509 | Traces may be viewed with LTTV. An example of command for launching LTTV is |
| 510 | given in the quickstart. |
| 511 | |
| 512 | @menu |
| 513 | * Viewing multiple traces:: |
| 514 | * Combined kernel-userspace tracing:: |
| 515 | @end menu |
| 516 | |
| 517 | @node Viewing multiple traces |
| 518 | @section Viewing multiple traces |
| 519 | |
| 520 | When tracing multi-process applications or several applications simultaneously, |
| 521 | more than one trace will be obtained. LTTV can open and display all these |
| 522 | traces simultaneously. |
| 523 | |
| 524 | @node Combined kernel-userspace tracing |
| 525 | @section Combined kernel-userspace tracing |
| 526 | |
| 527 | In addition to multiple userspace traces, LTTV can open a kernel trace recorded |
| 528 | with the LTTng kernel tracer. This provides events that enable the rendering of |
| 529 | the Control Flow View and the Resource View. |
| 530 | |
| 531 | When doing so, it is necessary to use the same time source for the kernel |
| 532 | tracer as well as the userspace tracer. Currently, the recommended method is to |
| 533 | use the timestamp counter for both. The TSC can however only be used on architectures |
| 534 | where it is synchronized across cores. |
| 535 | |
| 536 | @node Resource Usage |
| 537 | @chapter Resource Usage |
| 538 | |
| 539 | The purpose of this section is to give an overview of the resource usage of libust. For |
| 540 | a developer, knowing this can be important: because libust is linked with applications, it |
| 541 | needs to share some resources with it. Some applications may make some assumptions that are in |
| 542 | conflict with libust's usage of resources. |
| 543 | |
| 544 | In practice however, libust is designed to be transparent and is compatible |
| 545 | with the vast majority of applications. This means no changes are required in |
| 546 | the application (or library) being linked to libust. |
| 547 | |
| 548 | Libust is initialized by a constructor, which by definition runs before the main() function |
| 549 | of the application starts. This constructor creates a thread called the @emph{listener thread}. |
| 550 | The listener thread initializes a named socket and waits for connections for ustd or ustctl. |
| 551 | |
| 552 | Libust-specific code may: |
| 553 | @itemize @bullet |
| 554 | @item use @code{malloc()} and @code{free()} |
| 555 | @item map shared memory segment in the process adress space |
| 556 | @item intercept some library calls, specifically @code{fork()} and @code{clone()} |
| 557 | @item do interprocess communication with the daemon or ustctl |
| 558 | @item create and open named sockets |
| 559 | |
| 560 | @end itemize |
| 561 | |
| 562 | It will not: |
| 563 | @itemize @bullet |
| 564 | @item handle any signal (all signals are blocked in the listener thread) |
| 565 | @item change any process-wide setting that could confuse the application |
| 566 | @end itemize |
| 567 | |
| 568 | |
| 569 | @bye |