X-Git-Url: http://git.liburcu.org/?a=blobdiff_plain;f=doc%2Fman%2Flttng-ust.3.txt;h=aa157019df41dd474fdeef02ed1984a9b79b6ae3;hb=e436e84d48332d559fe60c1a5eba81f03e9f38f9;hp=8ecda775b3477f363a8c234109e4d9a95802f67d;hpb=d1194248c71fd4767382b4ea40dfa1cea3db1fd7;p=lttng-ust.git diff --git a/doc/man/lttng-ust.3.txt b/doc/man/lttng-ust.3.txt index 8ecda775..aa157019 100644 --- a/doc/man/lttng-ust.3.txt +++ b/doc/man/lttng-ust.3.txt @@ -65,7 +65,7 @@ SYNOPSIS #define *tracepoint*('prov_name', 't_name', ...) #define *tracepoint_enabled*('prov_name', 't_name') -Link with `-llttng-ust -ldl`, following this man page. +Link with `-llttng-ust -llttng-ust-common -ldl`, following this man page. DESCRIPTION @@ -605,9 +605,9 @@ source: Create the tracepoint provider object file: [role="term"] --------------- -cc -c -I. tp.c --------------- +---- +$ cc -c -I. tp.c +---- NOTE: Although an application instrumented with LTTng-UST tracepoints can be compiled with a C++ compiler, tracepoint probes should be @@ -618,9 +618,9 @@ possibly with other object files of your application or with other tracepoint provider object files, as a static library: [role="term"] ---------------- -ar rc tp.a tp.o ---------------- +---- +$ ar rc tp.a tp.o +---- Using a static library does have the advantage of centralising the tracepoint providers objects so they can be shared between multiple @@ -635,9 +635,9 @@ library containing it) and with `liblttng-ust` and `libdl` (`libc` on a BSD system): [role="term"] -------------------------------------- -cc -o app tp.o app.o -llttng-ust -ldl -------------------------------------- +---- +$ cc -o app tp.o app.o -llttng-ust -llttng-ust-common -ldl +---- [[build-dynamic]] @@ -678,16 +678,16 @@ built like it is using the static linking method, but with the nloption:-fpic option: [role="term"] --------------------- -cc -c -fpic -I. tp.c --------------------- +---- +$ cc -c -fpic -I. tp.c +---- It is then linked as a shared library like this: [role="term"] -------------------------------------------------------- -cc -shared -Wl,--no-as-needed -o tp.so tp.o -llttng-ust -------------------------------------------------------- +---- +$ cc -shared -Wl,--no-as-needed -o tp.so tp.o -llttng-ust -llttng-ust-common +---- This tracepoint provider shared object isn't linked with the user application: it must be loaded manually. This is why the application is @@ -695,9 +695,9 @@ built with no mention of this tracepoint provider, but still needs libdl: [role="term"] --------------------------------- -cc -o app app.o tp-define.o -ldl --------------------------------- +---- +$ cc -o app app.o tp-define.o -ldl +---- There are two ways to dynamically load the tracepoint provider shared object: @@ -738,6 +738,12 @@ without a following man:exec(3) family system call. The library application with the `LD_PRELOAD` environment variable (see man:ld.so(8)). +To use `liblttng-ust` with a daemon application which closes file +descriptors that were not opened by it, preload the `liblttng-ust-fd.so` +library before you start the application. Typical use cases include +daemons closing all file descriptors after man:fork(2), and buggy +applications doing ``double-closes''. + Context information ~~~~~~~~~~~~~~~~~~~ @@ -749,7 +755,9 @@ man:lttng-add-context(1). The following context fields are supported by LTTng-UST: -`cpu_id`:: +General context fields:: ++ +`cpu_id`::: CPU ID. + NOTE: This context field is always enabled, and it cannot be added @@ -757,34 +765,106 @@ with man:lttng-add-context(1). Its main purpose is to be used for dynamic event filtering. See man:lttng-enable-event(1) for more information about event filtering. -`ip`:: +`ip`::: Instruction pointer: enables recording the exact address from which an event was emitted. This context field can be used to reverse-lookup the source location that caused the event to be emitted. -+perf:thread:COUNTER+:: +`pthread_id`::: + POSIX thread identifier. ++ +Can be used on architectures where `pthread_t` maps nicely to an +`unsigned long` type. + +Process context fields:: ++ +`procname`::: + Thread name, as set by man:exec(3) or man:prctl(2). It is + recommended that programs set their thread name with man:prctl(2) + before hitting the first tracepoint for that thread. + +`vpid`::: + Virtual process ID: process ID as seen from the point of view of the + current process ID namespace (see man:pid_namespaces(7)). + +`vtid`::: + Virtual thread ID: thread ID as seen from the point of view of the + current process ID namespace (see man:pid_namespaces(7)). + +perf context fields:: ++ +`perf:thread:COUNTER`::: perf counter named 'COUNTER'. Use `lttng add-context --list` to list the available perf counters. + Only available on IA-32 and x86-64 architectures. -`pthread_id`:: - POSIX thread identifier. Can be used on architectures where - `pthread_t` maps nicely to an `unsigned long` type. +`perf:thread:raw:rN:NAME`::: + perf counter with raw ID 'N' and custom name 'NAME'. See + man:lttng-add-context(1) for more details. -`procname`:: - Thread name, as set by man:exec(3) or man:prctl(2). It is - recommended that programs set their thread name with man:prctl(2) - before hitting the first tracepoint for that thread. +Namespace context fields (see man:namespaces(7)):: ++ +`cgroup_ns`::: + Inode number of the current control group namespace (see + man:cgroup_namespaces(7)) in the proc file system. + +`ipc_ns`::: + Inode number of the current IPC namespace (see + man:ipc_namespaces(7)) in the proc file system. + +`mnt_ns`::: + Inode number of the current mount point namespace (see + man:mount_namespaces(7)) in the proc file system. + +`net_ns`::: + Inode number of the current network namespace (see + man:network_namespaces(7)) in the proc file system. + +`pid_ns`::: + Inode number of the current process ID namespace (see + man:pid_namespaces(7)) in the proc file system. + +`time_ns`::: + Inode number of the current clock namespace (see + man:time_namespaces(7)) in the proc file system. + +`user_ns`::: + Inode number of the current user namespace (see + man:user_namespaces(7)) in the proc file system. + +`uts_ns`::: + Inode number of the current UTS namespace (see + man:uts_namespaces(7)) in the proc file system. + +Credential context fields (see man:credentials(7)):: ++ +`vuid`::: + Virtual real user ID: real user ID as seen from the point of view of + the current user namespace (see man:user_namespaces(7)). + +`vgid`::: + Virtual real group ID: real group ID as seen from the point of view + of the current user namespace (see man:user_namespaces(7)). + +`veuid`::: + Virtual effective user ID: effective user ID as seen from the point + of view of the current user namespace (see man:user_namespaces(7)). -`vpid`:: - Virtual process ID: process ID as seen from the point of view of - the process namespace. +`vegid`::: + Virtual effective group ID: effective group ID as seen from the + point of view of the current user namespace (see + man:user_namespaces(7)). -`vtid`:: - Virtual thread ID: thread ID as seen from the point of view of - the process namespace. +`vsuid`::: + Virtual saved set-user ID: saved set-user ID as seen from the point + of view of the current user namespace (see man:user_namespaces(7)). + +`vsgid`::: + Virtual saved set-group ID: saved set-group ID as seen from the + point of view of the current user namespace (see + man:user_namespaces(7)). [[state-dump]] @@ -886,6 +966,20 @@ Fields: |Debug link file name. |=== +`lttng_ust_statedump:procname`:: + The process procname at process start. ++ +Fields: ++ +[options="header"] +|=== +|Field name |Description + +|`procname` +|The process name. + +|=== + [[ust-lib]] Shared library load/unload tracking @@ -981,11 +1075,38 @@ Fields: |=== +Detect if LTTng-UST is loaded +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +To detect if `liblttng-ust` is loaded from an application: + +. Define the `lttng_ust_loaded` weak symbol globally: ++ +------------------------------------------------------------------------ +int lttng_ust_loaded __attribute__((weak)); +------------------------------------------------------------------------ ++ +This weak symbol is set by the constructor of `liblttng-ust`. + +. Test `lttng_ust_loaded` where needed: ++ +------------------------------------------------------------------------ +/* ... */ + +if (lttng_ust_loaded) { + /* LTTng-UST is loaded */ +} else { + /* LTTng-UST is NOT loaded */ +} + +/* ... */ +------------------------------------------------------------------------ + + [[example]] EXAMPLE ------- NOTE: A few examples are available in the -https://github.com/lttng/lttng-ust/tree/master/doc/examples[`doc/examples`] +https://github.com/lttng/lttng-ust/tree/v{lttng_version}/doc/examples[`doc/examples`] directory of LTTng-UST's source tree. This example shows all the features documented in the previous @@ -996,44 +1117,44 @@ You can compile the source files and link them together statically like this: [role="term"] -------------------------------------- -cc -c -I. tp.c -cc -c app.c -cc -o app tp.o app.o -llttng-ust -ldl -------------------------------------- +---- +$ cc -c -I. tp.c +$ cc -c app.c +$ cc -o app tp.o app.o -llttng-ust -llttng-ust-common -ldl +---- Using the man:lttng(1) tool, create an LTTng tracing session, enable all the events of this tracepoint provider, and start tracing: [role="term"] ----------------------------------------------- -lttng create my-session -lttng enable-event --userspace 'my_provider:*' -lttng start ----------------------------------------------- +---- +$ lttng create my-session +$ lttng enable-event --userspace 'my_provider:*' +$ lttng start +---- You may also enable specific events: [role="term"] ----------------------------------------------------------- -lttng enable-event --userspace my_provider:big_event -lttng enable-event --userspace my_provider:event_instance2 ----------------------------------------------------------- +---- +$ lttng enable-event --userspace my_provider:big_event +$ lttng enable-event --userspace my_provider:event_instance2 +---- Run the application: [role="term"] --------------------- -./app some arguments --------------------- +---- +$ ./app some arguments +---- Stop the current tracing session and inspect the recorded events: [role="term"] ----------- -lttng stop -lttng view ----------- +---- +$ lttng stop +$ lttng view +---- Tracepoint provider header file @@ -1255,44 +1376,38 @@ LTTng session and consumer daemons (part of the LTTng-tools project) are located in a specific directory under `$LTTNG_HOME` (or `$HOME` if `$LTTNG_HOME` is not set). -`LTTNG_UST_BLOCKING_RETRY_TIMEOUT`:: - Maximum duration (milliseconds) to retry event tracing when - there's no space left for the event record in the sub-buffer. +`LTTNG_UST_ALLOW_BLOCKING`:: + If set, allow the application to retry event tracing when there's + no space left for the event record in the sub-buffer, therefore + effectively blocking the application until space is made available + or the configured timeout is reached. + --- -`0` (default):: - Never block the application. - -Positive value:: - Block the application for the specified number of milliseconds. If - there's no space left after this duration, discard the event - record. - -Negative value:: - Block the application until there's space left for the event record. --- +To allow an application to block during tracing, you also need to +specify a blocking timeout when you create a channel with the +nloption:--blocking-timeout option of the man:lttng-enable-channel(1) +command. + This option can be useful in workloads generating very large trace data throughput, where blocking the application is an acceptable trade-off to prevent discarding event records. + -WARNING: Setting this environment variable to a non-zero value may -significantly affect application timings. +WARNING: Setting this environment variable may significantly +affect application timings. `LTTNG_UST_CLOCK_PLUGIN`:: Path to the shared object which acts as the clock override plugin. An example of such a plugin can be found in the LTTng-UST documentation under - https://github.com/lttng/lttng-ust/tree/master/doc/examples/clock-override[`examples/clock-override`]. + https://github.com/lttng/lttng-ust/tree/v{lttng_version}/doc/examples/clock-override[`examples/clock-override`]. `LTTNG_UST_DEBUG`:: - Activates `liblttng-ust`'s debug and error output if set to `1`. + If set, enable `liblttng-ust`'s debug and error output. `LTTNG_UST_GETCPU_PLUGIN`:: Path to the shared object which acts as the `getcpu()` override plugin. An example of such a plugin can be found in the LTTng-UST documentation under - https://github.com/lttng/lttng-ust/tree/master/doc/examples/getcpu-override[`examples/getcpu-override`]. + https://github.com/lttng/lttng-ust/tree/v{lttng_version}/doc/examples/getcpu-override[`examples/getcpu-override`]. `LTTNG_UST_REGISTER_TIMEOUT`:: Waiting time for the _registration done_ session daemon command @@ -1302,30 +1417,15 @@ The value `0` means _do not wait_. The value `-1` means _wait forever_. Setting this environment variable to `0` is recommended for applications with time constraints on the process startup time. + -Default: {lttng_ust_register_timeout}. - -`LTTNG_UST_BLOCKING_RETRY_TIMEOUT`:: - Maximum time during which event tracing retry is attempted on buffer - full condition (millliseconds). Setting this environment to non-zero - value effectively blocks the application on buffer full condition. - Setting this environment variable to non-zero values may - significantly affect application timings. Setting this to a negative - value may block the application indefinitely if there is no consumer - emptying the ring buffer. The delay between retry attempts is the - minimum between the specified timeout value and 100ms. This option - can be useful in workloads generating very large trace data - throughput, where blocking the application is an acceptable - trade-off to not discard events. _Use with caution_. -+ -The value `0` means _do not retry_. The value `-1` means _retry forever_. -Value > `0` means a maximum timeout of the given value. -+ -Default: {lttng_ust_blocking_retry_timeout}. +Default: 3000. `LTTNG_UST_WITHOUT_BADDR_STATEDUMP`:: - Prevents `liblttng-ust` from performing a base address state dump - (see the <> section above) if - set to `1`. + If set, prevents `liblttng-ust` from performing a base address state + dump (see the <> section above). + +`LTTNG_UST_WITHOUT_PROCNAME_STATEDUMP`:: + If set, prevents `liblttng-ust` from performing a procname state + dump (see the <> section above). include::common-footer.txt[]