Lines Matching +full:system +full:- +full:trace

1 .TH trace 8  "2016-02-18" "USER COMMANDS"
3 trace \- Trace a function and print its arguments or return value, optionally evaluating a filter. …
5 .B trace [-h] [-b BUFFER_PAGES] [-p PID] [-L TID] [--uid UID] [-v] [-Z STRING_SIZE] [-S] [-s SYM_FI…
6          [-M MAX_EVENTS] [-t] [-u] [-T] [-C] [-K] [-U] [-a] [-I header] [-A]
9 trace probes functions you specify and displays trace messages if a particular
18 \-h
21 \-p PID
22 Trace only functions in the process PID.
24 \-L TID
25 Trace only functions in the thread TID.
27 \--uid UID
28 Trace only functions from user UID.
30 \-v
33 \-z STRING_SIZE
37 \-s SYM_FILE_LIST
38 When collecting stack trace in build id format, use the coma separated list for
41 \-S
42 If set, trace messages from trace's own process. By default, this is off to
43 avoid tracing storms -- for example, if you trace the write system call, and
44 consider that trace is writing to the standard output.
46 \-M MAX_EVENTS
47 Print up to MAX_EVENTS trace messages and then exit.
49 \-t
50 Print times relative to the beginning of the trace (offsets), in seconds.
52 \-u
53 Print UNIX timestamps instead of offsets from trace beginning, requires -t.
55 \-T
58 \-C
61 \-c CGROUP_PATH
62 Trace only functions in processes under CGROUP_PATH hierarchy.
64 \-n NAME
67 \-f MSG_FILTER
70 \-B
73 \-K
76 \-U
78 \-a
81 \-I header
86 \-A
87 Print aggregated amount of each trace. This should be used with -M/--max-events together.
100 Probe type \- "p" for function entry, "r" for function return, "t" for kernel
135 the trace message will be printed. The filter can use any valid C expression
139 expression ((int)arg1 < 0) to trace only invocations where arg1 is negative.
140 Note that only arg1-arg6 are supported, and only if the function is using the
145 The predicate expression may also use the STRCMP pseudo-function to compare
152 A printf-style format string that will be used for the trace message. You can
154 %x, %llx -- with the same semantics as printf's. Make sure to pass the exact
161 a symbol). trace will resolve %K specifiers to a kernel symbol, such as
162 vfs__read, and will resolve %U specifiers to a user-space symbol in that
167 block:block_rq_complete tracepoint can print or filter by args->nr_sector. To 
179 Trace all invocations of the open system call with the name of the file (from userspace) being open…
181 .B trace '::do_sys_open """%s"", arg2@user'
183 Trace all invocations of the read system call where the number of bytes requested is greater than 2…
185 .B trace '::sys_read (arg3 > 20000) """read %d bytes"", arg3'
187 Trace all malloc calls and print the size of the requested allocation:
189 .B trace ':c:malloc """size = %d"", arg1'
191 Trace returns from the readline function in bash and print the return value as a string:
193 .B trace 'r:bash:readline """%s"", retval' 
195 Trace the block:block_rq_complete tracepoint and print the number of sectors completed:
197 .B trace 't:block:block_rq_complete """%d sectors"", args->nr_sector'
199 Trace the pthread_create USDT probe from the pthread library and print the address of the thread's …
201 .B trace 'u:pthread:pthread_create """start addr = %llx"", arg3'
203 Trace the nanosleep system call and print the sleep duration in nanoseconds:
205 .B trace 'p::SyS_nanosleep(struct timespec *ts) "sleep for %lld ns", ts->tv_nsec'
207 Trace the inet_pton system call using build id mechanism and print the stack
209 .B trace -s /lib/x86_64-linux-gnu/libc.so.6,/bin/ping 'p:c:inet_pton' -U
220 Unstable - in development.