austin
Austin is a Python frame stack sampler for CPython written in pure C. Samples are collected by reading the CPython interpreter virtual memory space in order to retrieve information about the currently running threads along with the stack of the frames that are being executed. Hence, one can use Austin to easily make powerful statistical profilers that have minimal impact on the target application and that don't require any instrumentation.
The key features of Austin are:
- Zero instrumentation;
- Minimal impact;
- Fast and lightweight;
- Time and memory profiling;
- Built-in support for multi-process applications (e.g.
mod_wsgi
).
The simplest way to turn Austin into a full-fledged profiler is to combine it
with FlameGraph. However, Austin's
simple output format can be piped into any other external or custom tool for
further processing. Look, for instance, at the following Python TUI
Keep reading for more tools ideas and examples!
Installation
Austin is available from the major software repositories of the most popular
platforms.
On Linux, it can be installed using autotools
or as a snap from the Snap
Store. The latter will automatically perform the steps of the autotools
method
with a single command. On distributions derived from Debian, Austin can be
installed from the official repositores with Aptitude.
On Windows, Austin can be easily installed from the command line from the
Chocolatey repositories.
For any other platform, compiling Austin from sources is as easy as cloning the
repository and running the C compiler.
With autotools
Installing Austin using autotools
amounts to the usual ./configure
, make
and make install
finger gymnastic. The only dependency is the standard C
library.
git clone --depth=1 https://github.com/P403n1x87/austin.git
autoreconf --install
./configure
make
make install
Alternatively, sources can be compiled with just a C compiler (see below).
From the Snap Store
Austin can be installed on many major Linux
distributions from the Snap Store
with the following command
sudo snap install austin --classic
On Debian and Derivatives
On March 30 2019 Austin was accepted into the official Debian
repositories and can therefore be installed with the apt
utility.
From Chocolatey
To install Austin from Chocolatey, run
the following command from the command line or from PowerShell
choco install austin
To upgrade run the following command from the command line or from PowerShell:
choco upgrade austin
From Sources
To install Austin from sources using the GNU C compiler, without autotools
,
clone the repository with
git clone --depth=1 https://github.com/P403n1x87/austin.git
On Linux one can then use the command
gcc -O3 -Wall -pthread src/*.c -o src/austin
whereas on Mac OS it is enough to run
gcc -O3 -Wall src/*.c -o src/austin
On Windows, the -lpsapi
switch is needed
gcc -O3 -Wall -lpsapi src/*.c -o src/austin
Add -DDEBUG
if you need a more verbose log. This is useful if you encounter a
bug with Austin and you want to report it here.
Usage
Usage: austin [OPTION...] command [ARG...]
Austin -- A frame stack sampler for Python.
-a, --alt-format Alternative collapsed stack sample format.
-C, --children Attach to child processes.
-e, --exclude-empty Do not output samples of threads with no frame
stacks.
-f, --full Produce the full set of metrics (time +mem -mem).
-i, --interval=n_us Sampling interval (default is 500us).
-m, --memory Profile memory usage.
-o, --output=FILE Specify an output file for the collected samples.
-p, --pid=PID The the ID of the process to which Austin should
attach.
-s, --sleepless Suppress idle samples.
-t, --timeout=n_ms Approximate start up wait time. Increase on slow
machines (default is 100ms).
-?, --help Give this help list
--usage Give a short usage message
-V, --version Print program version
Mandatory or optional arguments to long options are also mandatory or optional
for any corresponding short options.
Report bugs to <https://github.com/P403n1x87/austin/issues>.
The output is a sequence of frame stack samples, one on each line. The format is
the collapsed one that is recognised by
FlameGraph so that it can be piped
straight to flamegraph.pl
for a quick visualisation, or redirected to a file
for some further processing.
By default, each line has the following structure:
[Process <pid>;]?Thread <tid>[;[frame]]* [metric]*
where the presence of the process ID, the structure of [frame]
and the number
and type of metrics on each line depend on the mode.
Normal Mode
When no special switch are passed to Austin from the command line, the process
identifier is omitted and [frame]
has the structure
[frame] := <function> (<module>);L<line number>
The reason for not including the line number in the ([module])
part, as one
might have expected, is that this way the flame graph will show the total time
spent in each function, plus the finer detail of the time spent on each line. A
drawback of this format is that frame stacks double in height. If you prefer
something more conventional, you can use the -a
option to switch to the
alternative format in which [frame]
has the structure
[frame] := <function> (<module>:<line number>)
Each line then ends with a single [metric]
, i.e. the sampling time measured in
microseconds.
Memory and Full Metrics
When profiling in memory mode with the -m
or --memory
switch, the metric
value at the end of each line is the memory delta between samples, measured in
KB. In full mode (-f
or --full
switches), each samples ends with three
values: the time delta, any positive memory delta (memory allocations) or zero
and any negative memory delta (memory releases) or zero.
Multi-process Applications
Austin can be told to profile multi-process applications with the -C
or
--children
switch. This way Austin will look for new children of the parent
process. In this case, each sample will contain the process identifier to help
determine from which process the sample came from.
Logging
Austin uses syslog
on Linux and Mac OS, and %TEMP%\austin.log
on Windows
for log messages, so make sure to watch these to get execution details and
statistics. Bad frames are output together with the other frames. In general,
entries for bad frames will not be visible in a flame graph as all tests show
error rates below 1% on average.
Compatibility
Austin supports Python 2.3-2.7 and 3.3-3.8 and has been tested on the following
platforms and architectures
x86_64 | ✓ | ✓ | ✓ |
i686 | ✓ | ✓ | |
arm | ✓ | ||
armv7 | ✓ |
Due to the System Integrity Protection introduced in MacOS with El
Capitan, Austin cannot profile Python processes that use an executable located
in the /bin
folder, even with sudo
. Hence, either run the interpreter from a
virtual environment or use a Python interpreter that is installed in, e.g.,
/Applications
or via brew
with the default prefix (/usr/local
). Even in
these cases, though, the use of sudo
is required.
NOTE Austin might work with other versions of Python on all the
platforms and architectures above. So it is worth giving it a try even if
your system is not listed below.
Why Austin
When there already are similar tools out there, it's normal to wonder why one
should be interested in yet another one. So here is a list of features that
currently distinguish Austin.
-
Written in pure C Austin is written in pure C code. There are no
dependencies on third-party libraries with the exception of the standard C
library and the API provided by the Operating System. -
Just a sampler Austin is just a frame stack sampler. It looks into a
running Python application at regular intervals of time and dumps whatever
frame stack it finds. The samples can then be analysed at a later time so that
Austin can sample at rates higher than other non-C alternative that also
analyse the samples as they run. -
Simple output, powerful tools Austin uses the collapsed stack format of
FlameGraph that is easy to parse. You can then go and build your own tool to
analyse Austin's output. You could even make a player that replays the
application execution in slow motion, so that you can see what has happened in
temporal order. -
Small size Austin compiles to a single binary executable of just a bunch
of KB. -
Easy to maintain Occasionally, the Python C API changes and Austin will
need to be adjusted to new releases. However, given that Austin, like CPython,
is written in C, implementing the new changes is rather straight-forward.
Examples
The following flame graph has been obtained with the command
austin -i 50 ./test.py | ./flamegraph.pl --countname=us > test.svg
where the sample test.py
script has the following content
import psutil
for i in range(1000):
list(psutil.process_iter())
To profile Apache2 WSGI application, one can attach Austin to the web server
with
austin -Cp `pgrep apache2 | head -n 1`
Any child processes will be automatically detected as they are created and
Austin will sample them too.
Austin TUI
The Python TUI that is currently included in this repository provides an
example of how to use Austin to profile Python applications. You can use
PageUp
and PageDown
to navigate the frame stack of each frame as the Python
application runs.
If you want to give it a go you can install it using pip
with
pip install git+https://github.com/P403n1x87/austin.git --upgrade
and run it with
austin-tui [OPTION...] command [ARG...]
with the same command line as Austin.
The TUI is based on
python-curses
. The version included with the standard
Windows installations of Python is broken so it won't work out of the box. A
solution is to install the the wheel of the port to Windows from
this page. Wheel files
can be installed directly withpip
, as described in the
linked
page.
Web Austin
Web Austin is yet another example of how to use Austin to make a profiling
tool. It makes use of
d3-flame-graph to display a
live flame graph in the web browser that refreshes every 3 seconds with newly
collected samples. Web Austin can also be used for remote profiling by
setting the WEBAUSTIN_HOST
and WEBAUSTIN_PORT
environment variables.
If you want to give it a go you can install it using pip
with
pip install git+https://github.com/P403n1x87/austin.git --upgrade
and run it with
austin-web [OPTION...] command [ARG...]
with the same command line as Austin. This starts a simple HTTP server that
serves on WEBAUSTIN_HOST
if set or on localhost
otherwise. The port can be
controlled with the WEBAUSTIN_PORT
environment variable. If it is not set,
Web Austin will use an ephemeral port.
Speedscope
Austin output format can be converted easily into the
Speedscope JSON format. You can find a sample utility along
with the TUI and Austin Web.
If you want to give it a go you can install it using pip
with
pip install git+https://github.com/P403n1x87/austin.git --upgrade
and run it with
austin2speedscope [-h] [--indent INDENT] [-V] input output
where input
is a file containing the output from Austin and output
is the
name of the JSON file to use to save the result of the conversion, ready to be
used on Speedscope.