User-space Probing
SystemTap initially focused on kernel-space probing. Because
there are many instances where user-space probing can help diagnose
a problem, SystemTap 0.6 added support to allow probing user-space processes.
SystemTap can probe the entry into and return from a
function in user-space processes, probe predefined markers in
user-space code, and monitor user-process events.
SystemTap requires the uprobes module to perform user-space probing. If your
Linux kernel is version 3.5 or higher, it already includes uprobes.
To verify that the current kernel supports uprobes natively, run the following command:
grep CONFIG_UPROBES /boot/config-`uname -r`
If uprobes is integrated, the output of this command is as follows:
CONFIG_UPROBES=yUser-Space EventsEventsuser-space
All user-space event probes begin with process.
You can limit the process events to a specific running process by specifying the process ID.
You can also limit the process events to monitor a particular executable
by specifying the path to the executable (PATH).
SystemTap makes use of the PATH environment variable, which allows
you to use both the name used on the command-line to start the executable and
the absolute path to the executable.
Several of the user-space probe events limit their scope to a
particular executable name (PATH), because
SystemTap must use debug information to statically analyze where to
place the probes. But for many user-space probe events, the process ID
and executable name are optional.
Any process event in the list below that include process ID or
the path to the executable must include those arguments.
The process ID and path to the executable are optional for the
process events that do not list them:
process("PATH").function("function")
The entry to the user-space function function for the executable PATH.
This event is the user-space analogue of the
kernel.function("function") event.
It allows wildcards for the function function
and .return suffix.
process("PATH").statement("statement")
The earliest instruction in the code for statement. This is the user-space analogue of
kernel.statement("statement").
process("PATH").mark("marker")The static probe point marker defined in
PATH.
You can use wildcards for marker to specify
multiple marks with a single probe.
The static probe points may also have numbered arguments ($1, $2, and so on)
available to the probe.A variety of user-space packages such as Java include these static
probe points.
Most packages that provide static probe points also
provide aliases for the raw user-space mark events.
Below is one such alias for the x86_64 Java hotspot JVM:
probe hotspot.gc_begin =
process("/usr/lib/jvm/java-1.6.0-openjdk-1.6.0.0.x86_64/jre/lib/amd64/server/libjvm.so").mark("gc__begin")process.beginA user-space process is created.
You can limit this to a particular process ID or a full path to the
executable.process.thread.beginA user-space thread is created.
You can limit this to a particular process ID or a full path to the
executable.process.endA user-space process dies.
You can limit this to a particular process ID or a full path to the
executable.process.thread.endA user-space thread is destroyed.
You can limit this to a particular process ID or a full path to the
executable.process.syscallA user-space process makes a system call.
The system call number is available in the $syscall context variable, and
the fist six arguments are available in $arg1 through $arg6.
The .return suffix places the probe at the return from the system call.
For syscall.return, the return value is available through the
$return context variable.You can limit this to a particular process ID or a full path to the
executable.Accessing User-Space Target Variablestarget variablesuser-space
You can access user-space target variables in the same manner as described in
.
In Linux, however, there are separate address spaces for the user and
kernel code.
When using the -> operator, SystemTap accesses the appropriate address space.
For pointers to base types such as integers and strings,
there are a number of functions listed below to access user-space data.
The first argument for each functions is the pointer to the data item.
user_char(address)
Obtains the character at address for the current
user process.
user_short(address)
Obtains the short integer at address for the current
user process.
user_int(address)
Obtains the integer at address for the current
user process.
user_long(address)
Obtains the long integer at address for the current
user process.
user_string(address)
Obtains the string at address for the current
user process.
user_string_n(address, n)
Obtains the string at address for the current
user process and limits the string to n bytes.
User-Space Stack BacktracesStack backtraceuser-space
The probe point (pp) function indicates which
particular event triggered the SystemTap event handler.
A probe on the entry into a function would list the function name.
However, in many cases the same probe point event may be triggered by
many different modules in the program; this is particularly true for
functions in shared libraries. A SystemTap backtrace of the user-space
stack can provide additional context on how the probe point event is
triggered.
The user-space stack backtrace generation is complicated
by the compiler producing code optimized to eliminate stack frame
pointers.
However, the compiler also includes information in the debug information
section to allow debugging tools to produce stack backtraces.
SystemTap user-space stack backtrace mechanism makes use of that
debug information to walk the stack to generate stack traces for 32-bit
and 64-bit x86 processors; other processor architectures do not yet
support the use of debug information to unwind the user-space stack.
To ensure that the needed debug information is used to produce the
user-space stack backtraces, use the
option for
executables and for shared libraries.
For example, you can use the user-space backtrack functions to see how
the xmalloc function is
being called by the ls command. With the
debuginfo for the ls command installed, the following
SystemTap command provides a backtrace each time the
xmalloc function is called:
stap -d /bin/ls --ldd \-e 'probe process("ls").function("xmalloc") {print_usyms(ubacktrace())}' \-c "ls /"
When executed, this command produces output similar to the following:
bin dev lib media net proc sbin sys var
boot etc lib64 misc op_session profilerc selinux tmp
cgroup home lost+found mnt opt root srv usr
0x4116c0 : xmalloc+0x0/0x20 [/bin/ls]
0x4116fc : xmemdup+0x1c/0x40 [/bin/ls]
0x40e68b : clone_quoting_options+0x3b/0x50 [/bin/ls]
0x4087e4 : main+0x3b4/0x1900 [/bin/ls]
0x3fa441ec5d : __libc_start_main+0xfd/0x1d0 [/lib64/libc-2.12.so]
0x402799 : _start+0x29/0x2c [/bin/ls]
0x4116c0 : xmalloc+0x0/0x20 [/bin/ls]
0x4116fc : xmemdup+0x1c/0x40 [/bin/ls]
0x40e68b : clone_quoting_options+0x3b/0x50 [/bin/ls]
0x40884a : main+0x41a/0x1900 [/bin/ls]
0x3fa441ec5d : __libc_start_main+0xfd/0x1d0 [/lib64/libc-2.12.so]
...
For more details on the functions available for user-space stack
backtraces, refer to ucontext-symbols.stp and
ucontext-unwind.stp tapsets. You can also find
the description of the functions in the aforementioned tapsets in the
SystemTap Tapset Reference Manual.