1trace(8) System Manager's Manual trace(8)
2
6 trace - Trace a function and print its arguments or return value,
7 optionally evaluating a filter. Uses Linux eBPF/bcc.
8
10 trace [-h] [-b BUFFER_PAGES] [-p PID] [-L TID] [-v] [-Z STRING_SIZE]
11 [-S] [-s SYM_FILE_LIST]
12 [-M MAX_EVENTS] [-t] [-u] [-T] [-C] [-K] [-U] [-a] [-I header]
13 probe [probe ...]
14
16 trace probes functions you specify and displays trace messages if a
17 particular condition is met. You can control the message format to dis‐
18 play function arguments and return values.
19 Since this uses BPF, only the root user can use this tool.
21
23 CONFIG_BPF and bcc.
24
26 -h Print usage message.
27 -p PID Trace only functions in the process PID.
29 -L TID Trace only functions in the thread TID.
31 -v Display the generated BPF program, for debugging purposes.
33 -z STRING_SIZE
35 When collecting string arguments (of type char*), collect up to
36 STRING_SIZE characters. Longer strings will be truncated.
37 -s SYM_FILE_LIST
39 When collecting stack trace in build id format, use the coma
40 separated list for symbol resolution.
41 -S If set, trace messages from trace's own process. By default,
43 this is off to avoid tracing storms -- for example, if you trace
44 the write system call, and consider that trace is writing to the
45 standard output.
46 -M MAX_EVENTS
48 Print up to MAX_EVENTS trace messages and then exit.
49 -t Print times relative to the beginning of the trace (offsets), in
51 seconds.
52 -u Print UNIX timestamps instead of offsets from trace beginning,
54 requires -t.
55 -T Print the time column.
57 -C Print CPU id.
59 -c CGROUP_PATH
61 Trace only functions in processes under CGROUP_PATH hierarchy.
62 -n NAME
64 Only print process names containing this name.
65 -f MSG_FILTER
67 Only print message of event containing this string.
68 -B Treat argument of STRCMP helper as a binary value
70 -K Print the kernel stack for each event.
72 -U Print the user stack for each event. -a Print virtual address
74 in kernel and user stacks.
75 -I header
77 Additional header files to include in the BPF program. This is
78 needed if your filter or print expressions use types or data
79 structures that are not available in the standard headers. For
80 example: 'linux/mm.h'
81 probe [probe ...]
83 One or more probes that attach to functions, filter conditions,
84 and print information. See PROBE SYNTAX below.
85
87 The general probe syntax is as follows:
88 [{p,r}]:[library]:function[+offset][(signature)] [(predicate)] ["format
90 string"[, arguments]]
91 {t:category:event,u:library:probe} [(predicate)] ["format string"[,
93 arguments]]
94 {[{p,r}],t,u}
96 Probe type - "p" for function entry, "r" for function return,
97 "t" for kernel tracepoint, "u" for USDT probe. The default probe
98 type is "p".
99 [library]
101 Library containing the probe. Specify the full path to the .so
102 or executable file where the function to probe resides. Alterna‐
103 tively, you can specify just the lib name: for example, "c"
104 refers to libc. If no library name is specified, the kernel is
105 assumed. Also, you can specify an executable name (without a
106 full path) if it is in the PATH. For example, "bash".
107 category
109 The tracepoint category. For example, "sched" or "irq".
110 function
112 The function to probe. offset The offset after the address of
113 the function where the probe should injected. For example
114 "kfree_skb+56" in decimal or hexadecimal "kfree_skb+0x38" for‐
115 mat. Only works with kprobes and uprobes. Zero if omitted.
116 signature
118 The optional signature of the function to probe. This can make
119 it easier to access the function's arguments, instead of using
120 the "arg1", "arg2" etc. argument specifiers. For example,
121 "(struct timespec *ts)" in the signature position lets you use
122 "ts" in the filter or print expressions.
123 event The tracepoint event. For example, "block_rq_complete".
125 probe The USDT probe name. For example, "pthread_create".
127 [(predicate)]
129 The filter applied to the captured data. Only if the filter
130 evaluates as true, the trace message will be printed. The filter
131 can use any valid C expression that refers to the argument val‐
132 ues: arg1, arg2, etc., or to the return value retval in a return
133 probe. If necessary, use C cast operators to coerce the argu‐
134 ments to the desired type. For example, if arg1 is of type int,
135 use the expression ((int)arg1 < 0) to trace only invocations
136 where arg1 is negative. Note that only arg1-arg6 are supported,
137 and only if the function is using the standard x86_64 convention
138 where the first six arguments are in the RDI, RSI, RDX, RCX, R8,
139 R9 registers. If no predicate is specified, all function invoca‐
140 tions are traced.
141 The predicate expression may also use the STRCMP pseudo-function
143 to compare a predefined string to a string argument. For exam‐
144 ple: STRCMP("test", arg1). The order of arguments is important:
145 the first argument MUST be a quoted literal string, and the sec‐
146 ond argument can be a runtime string, most typically an argu‐
147 ment.
148 ["format string"[, arguments]]
150 A printf-style format string that will be used for the trace
151 message. You can use the following format specifiers: %s, %d,
152 %u, %lld, %llu, %hd, %hu, %c, %x, %llx -- with the same seman‐
153 tics as printf's. Make sure to pass the exact number of argu‐
154 ments as there are placeholders in the format string. The format
155 specifier replacements may be any C expressions, and may refer
156 to the same special keywords as in the predicate (arg1, arg2,
157 etc.).
158 In addition to the above format specifiers, you can also use %K
160 and %U when the expression is an address that potentially points
161 to executable code (i.e., a symbol). trace will resolve %K spec‐
162 ifiers to a kernel symbol, such as vfs__read, and will resolve
163 %U specifiers to a user-space symbol in that process, such as
164 sprintf.
165 In tracepoints, both the predicate and the arguments may refer
167 to the tracepoint format structure, which is stored in the spe‐
168 cial "args" variable. For example, the block:block_rq_complete
169 tracepoint can print or filter by args->nr_sector. To discover
170 the format of your tracepoint, use the tplist tool.
171 In USDT probes, the arg1, ..., argN variables refer to the
173 probe's arguments. To determine which arguments your probe has,
174 use the tplist tool.
175 The predicate expression and the format specifier replacements
177 for printing may also use the following special keywords: $pid,
178 $tgid to refer to the current process' pid and tgid; $uid, $gid
179 to refer to the current user's uid and gid; $cpu to refer to the
180 current processor number.
181
183 Trace all invocations of the open system call with the name of the file
184 being opened:
185 # trace '::do_sys_open "%s", arg2'
186 Trace all invocations of the read system call where the number of bytes
188 requested is greater than 20,000:
189 # trace '::sys_read (arg3 > 20000) "read %d bytes", arg3'
190 Trace all malloc calls and print the size of the requested allocation:
192 # trace ':c:malloc "size = %d", arg1'
193 Trace returns from the readline function in bash and print the return
195 value as a string:
196 # trace 'r:bash:readline "%s", retval'
197 Trace the block:block_rq_complete tracepoint and print the number of
199 sectors completed:
200 # trace 't:block:block_rq_complete "%d sectors", args->nr_sec‐
201 tor'
202 Trace the pthread_create USDT probe from the pthread library and print
204 the address of the thread's start function:
205 # trace 'u:pthread:pthread_create "start addr = %llx", arg3'
206 Trace the nanosleep system call and print the sleep duration in
208 nanoseconds:
209 # trace 'p::SyS_nanosleep(struct timespec *ts) sleep for %lld ns
210 , ts->tv_nsec'
211 Trace the inet_pton system call using build id mechanism and print the
213 stack
214 # trace -s /lib/x86_64-linux-gnu/libc.so.6,/bin/ping
215 'p:c:inet_pton' -U
216
218 This is from bcc.
219 https://github.com/iovisor/bcc
221 Also look in the bcc distribution for a companion _examples.txt file
223 containing example usage, output, and commentary for this tool.
224
226 Linux
227
229 Unstable - in development.
230
232 Sasha Goldshtein
233USER COMMANDS 2016-02-18 trace(8)