+ * `--force-switch`:
+ Force a subbuffer switch. This will flush all the data currently held.
+
+## LIFE CYCLE OF A TRACE
+
+Typically, the first step is to enable markers with `--enable-marker`. An
+enabled marker generates an event when the control flow passes over it
+(assuming the trace is recording). A disabled marker produces nothing. Enabling
+and disabling markers may however be done at any point, including while the
+trace is being recorded.
+
+In order to record events, a trace is first created with `--create-trace`. At
+this point, the subbuffer count and size may be changed with `--set-subbuf-num`
+and `--set-subbuf-size`.
+
+Afterward, the trace may be allocated with `--alloc-trace`. This allocates the
+buffers in memory, so once this is done, the subbuffer size and count can not
+be changed. Trace allocation also causes the daemon to connect to the trace
+buffers and wait for data to arrive. Explicit allocation is optional, as it is
+done automatically at trace start.
+
+The trace may then be started with `--start-trace`. This results in events
+being recorded in the buffer. The daemon automatically collects these events.
+
+The trace may be stopped with `--stop-trace`, either definitely after all the
+wanted information is collected, or temporarily, before being started again
+with `--start-trace`. This results in effectively 'pausing' the recording.
+After using `--stop-trace`, if a daemon is collecting the trace, it may not
+have flushed to the disk the full contents of the buffer yet.
+
+Finally, when `--destroy-trace` is used, the trace buffers are unallocated.
+However, the memory may not be effectively freed until the daemon finishes to
+collect them. When the trace is being collected by `ustd`, this command
+guarantees its full contents is flushed to the disk.
+
+## STRUCTURE OF A TRACE
+
+Each instrumentation point that is added in a program is associated to a
+channel.
+
+Trace events are put in buffers. There is one buffer per channel, per cpu.
+For example, on a system with 4 cores and tracing an application with 3
+channels, there will be 12 buffers in total. The content of each of these
+buffers is put in a distinct file in the trace directory. For example, the
+`metadata_2` file contains the data that was extracted from the buffer that
+contained the events from the metadata channel and having occurred on cpu 2.
+
+In memory, each buffer is divided in subbuffers. Subbuffers are equally-sized,
+contiguous parts of a buffer. The size of a buffer is equal to the number of
+subbuffers it contains times the size of each subbuffer. When a subbuffer is
+full, it is collected by the daemon while the others are filled. If, however,
+the buffer size is too small, buffer overflows may occur and result in event
+loss. By default, the number of subbuffers per buffer is 2. Subbuffer size
+for a given channel may be chosen with `--set-subbuf-size` while the subbuffer
+count is set with `--set-subbuf-num`.
+
+## SEE ALSO
+
+usttrace(1), ustd(1)
+