Skip to main content

Reverse debugging for Python

RevPDB

A "reverse debugger" is a debugger where you can go forward and backward in time. It is an uncommon feature, at least in the open source world, but I have no idea why. I have used undodb-gdb and rr, which are reverse debuggers for C code, and I can only say that they saved me many, many days of poking around blindly in gdb.

The PyPy team is pleased to give you "RevPDB", a reverse-debugger similar to rr but for Python.

An example is worth a thousand words. Let's say your big Python program has a bug that shows up inconsistently. You have nailed it down to something like:

  • start x.py, which does stuff (maybe involving processing files, answering some web requests that you simulate from another terminal, etc.);
  • sometimes, after a few minutes, your program's state becomes inconsistent and you get a failing assert or another exception.

This is the case where RevPDB is useful.

RevPDB is available only on 64-bit Linux and OS/X right now, but should not be too hard to port to other OSes. It is very much alpha-level! (It is a debugger full of bugs. Sorry about that.) I believe it is still useful---it helped me in one real use case already.

How to get RevPDB

The following demo was done with an alpha version for 64-bit Linux, compiled for Arch Linux. I won't provide the binary; it should be easy enough to retranslate (much faster than a regular PyPy because it contains neither a JIT nor a custom GC). Grab the PyPy sources from Mercurial, and then:

hg update reverse-debugger
# or "hg update ff376ccacb36" for exactly this demo
cd pypy/goal
../../rpython/bin/rpython -O2 --revdb targetpypystandalone.py  \
                  --withoutmod-cpyext --withoutmod-micronumpy

and possibly rename the final pypy-c to pypy-revdb to avoid confusion.

Other platforms than 64-bit Linux and OS/X need some fixes before they work.

Demo

For this demo, we're going to use this x.py as the "big program":

import os

class Foo(object):
    value = 5

lst1 = [Foo() for i in range(100)]
lst1[50].value += 1
for x in lst1:
    x.value += 1

for x in lst1:
    if x.value != 6:
        print 'oops!'
        os._exit(1)

Of course, it is clear what occurs in this small example: the check fails on item 50. For this demo, the check has been written with os._exit(1), because this exits immediately the program. If it was written with an assert, then its failure would execute things in the traceback module afterwards, to print the traceback; it would be a minor mess just to find the exact point of the failing assert. (This and other issues are supposed to be fixed in the future, but for now it is alpha-level.)

Anyway, with a regular assert and a regular post-mortem pdb, we could observe that x.value is indeed 7 instead of 6 when the assert fails. Imagine that the program is much bigger: how would we find the exact chain of events that caused this value 7 to show up on this particular Foo object? This is what RevPDB is for.

First, we need for now to disable Address Space Layout Randomization (ASLR), otherwise replaying will not work. This is done once with the following command line, which changes the state until the next reboot:

echo 0 | sudo tee /proc/sys/kernel/randomize_va_space

UPDATE: the above is no longer necessary from revision ff376ccacb36.

Run x.py with RevPDB's version of PyPy instead of the regular interpreter (CPython or PyPy):

PYPYRDB=log.rdb ./pypy-revdb x.py

This pypy-revdb executable is like a slow PyPy executable, running (for now) without a JIT. This produces a file log.rdb which contains a complete log of this execution. (If the bug we are tracking occurs rarely, we need to re-run it several times until we get the failure. But once we got the failure, then we're done with this step.)

Start:

rpython/translator/revdb/revdb.py log.rdb

We get a pdb-style debugger. This revdb.py is a normal Python program, which you run with an unmodified Python; internally, it looks inside the log for the path to pypy-revdb and run it as needed (as one forking subprocess, in a special mode).

Initially, we are at the start of the program---not at the end, like we'd get in a regular debugger:

File "<builtin>/app_main.py", line 787 in setup_bootstrap_path:
(1)$

The list of commands is available with help.

Go to the end with continue (or c):

(1)$ continue
File "/tmp/x.py", line 14 in <module>:
...
  lst1 = [Foo() for i in range(100)]
  lst1[50].value += 1
  for x in lst1:
      x.value += 1

  for x in lst1:
      if x.value != 6:
          print 'oops!'
>         os._exit(1)
(19727)$

We are now at the beginning of the last executed line. The number 19727 is the "time", measured in number of lines executed. We can go backward with the bstep command (backward step, or bs), line by line, and forward again with the step command. There are also commands bnext, bcontinue and bfinish and their forward equivalents. There is also "go TIME" to jump directly to the specified time. (Right now the debugger only stops at "line start" events, not at function entry or exit, which makes some cases a bit surprising: for example, a step from the return statement of function foo() will jump directly to the caller's caller, if the caller's current line was return foo() + 2, because no "line start" event occurs in the caller after foo() returns to it.)

We can print Python expressions and statements using the p command:

(19727)$ p x
$0 = <__main__.Foo object at 0xfffffffffffeab3e>
(19727)$ p x.value
$1 = 7
(19727)$ p x.value + 1
8

The "$NUM =" prefix is only shown when we print an object that really exists in the debugged program; that's why the last line does not contain it. Once a $NUM has been printed, then we can use it in further expressions---even at a different point time. It becomes an anchor that always refers to the same object:

(19727)$ bstep

File "/tmp/x.py", line 13 in <module>:
...

  lst1 = [Foo() for i in range(100)]
  lst1[50].value += 1
  for x in lst1:
      x.value += 1

  for x in lst1:
      if x.value != 6:
>         print 'oops!'
          os._exit(1)
(19726)$ p $0.value
$1 = 7

In this case, we want to know when this value 7 was put in this attribute. This is the job of a watchpoint:

(19726)$ watch $0.value
Watchpoint 1 added
updating watchpoint value: $0.value => 7

This watchpoint means that $0.value will be evaluated at each line. When the repr() of this expression changes, the watchpoint activates and execution stops:

(19726)$ bcontinue
[searching 19629..19726]
[searching 19338..19629]

updating watchpoint value: $0.value => 6
Reverse-hit watchpoint 1: $0.value
File "/tmp/x.py", line 9 in <module>:
  import os

  class Foo(object):
      value = 5

  lst1 = [Foo() for i in range(100)]
  lst1[50].value += 1
  for x in lst1:
>     x.value += 1

  for x in lst1:
      if x.value != 6:
          print 'oops!'
          os._exit(1)
(19524)$

Note that using the $NUM syntax is essential in watchpoints. You can't say "watch x.value", because the variable x will go out of scope very soon when we move forward or backward in time. In fact the watchpoint expression is always evaluated inside an environment that contains the builtins but not the current locals and globals. But it also contains all the $NUM, which can be used to refer to known objects. It is thus common to watch $0.attribute if $0 is an object, or to watch len($1) if $1 is some list. The watch expression can also be a simple boolean: for example, "watch $2 in $3" where $3 is some dict and $2 is some object that you find now in the dict; you would use this to find out the time when $2 was put inside $3, or removed from it.

Use "info watchpoints" and "delete <watchpointnum>" to manage watchpoints.

There are also regular breakpoints, which you set with "b FUNCNAME". It breaks whenever there is a call to a function that happens to have the given name. (It might be annoying to use for a function like __init__() which has many homonyms. There is no support for breaking on a fully-qualified name or at a given line number for now.)

In our demo, we stop at the line x.value += 1, which is where the value was changed from 6 to 7. Use bcontinue again to stop at the line lst1[50].value += 1, which is where the value was changed from 5 to 6. Now we know how this value attribute ends up being 7.

(19524)$ bcontinue
[searching 19427..19524]
[searching 19136..19427]

updating watchpoint value: $0.value => 5
Reverse-hit watchpoint 1: $0.value
File "/tmp/x.py", line 7 in <module>:
  import os

  class Foo(object):
      value = 5

  lst1 = [Foo() for i in range(100)]
> lst1[50].value += 1
  for x in lst1:
      x.value += 1

  for x in lst1:
      if x.value != 6:
...
(19422)$

Try to use bcontinue yet another time. It will stop now just before $0 is created. At that point in time, $0 refers to an object that does not exist yet, so the watchpoint now evaluates to an error message (but it continues to work as before, with that error message as the string it currently evaluates to).

(19422)$ bcontinue
[searching 19325..19422]

updating watchpoint value: $0.value => RuntimeError:
               '$0' refers to an object created later in time
Reverse-hit watchpoint 1: $0.value
File "/tmp/x.py", line 6 in <module>:
  import os

  class Foo(object):
      value = 5

> lst1 = [Foo() for i in range(100)]
  lst1[50].value += 1
  for x in lst1:
      x.value += 1

  for x in lst1:
...
(19371)$

In big programs, the workflow is similar, just more complex. Usually it works this way: we find interesting points in time with some combination of watchpoints and some direct commands to move around. We write down on a piece of (real or virtual) paper these points in history, including most importantly their time, so that we can construct an ordered understanding of what is going on.

The current revdb can be annoying and sometimes even crash; but the history you reconstruct can be kept. All the times and expressions printed are still valid when you restart revdb. The only thing "lost" is the $NUM objects, which you need to print again. (Maybe instead of $0, $1, ... we should use $<big number>, where the big number identifies uniquely the object by its creation time. These numbers would continue to be valid even after revdb is restarted. They are more annoying to use than just $0 though.)

Screencast: Here's a (slightly typo-y) screencast of cfbolz using the reverse debugger:

Current issues

General issues:

  • If you are using revdb on a log that took more than a few minutes to record, then it can be painfully slow. This is because revdb needs to replay again big parts of the log for some operations.
  • The pypy-revdb is currently missing the following modules:
    • thread (implementing multithreading is possible, but not done yet);
    • cpyext (the CPython C API compatibility layer);
    • micronumpy (minor issue only);
    • _continuation (for greenlets).
  • Does not contain a JIT, and does not use our fast garbage collectors. You can expect pypy-revdb to be maybe 3 times slower than CPython.
  • Only works on Linux and OS/X. There is no fundamental reason for this restriction, but it is some work to fix.
  • Replaying a program uses a lot more memory; maybe 15x as much than during the recording. This is because it creates many forks. If you have a program that consumes 10% of your RAM or more, you will need to reduce MAX_SUBPROCESSES in process.py.

Replaying also comes with a bunch of user interface issues:

  • Attempted to do I/O or access raw memory: we get this whenever trying to print some expression that cannot be evaluated with only the GC memory---or which can, but then the __repr__() method of the result cannot. We need to reset the state with bstep + step before we can print anything else. However, if only the __repr__() crashes, you still see the $NUM = prefix, and you can use that $NUM afterwards.
  • id() is globally unique, returning a reproducible 64-bit number, so sometimes using id(x) is a workaround for when using x doesn't work because of Attempted to do I/O issues (e.g. p [id(x) for x in somelist]).
  • as explained in the demo, next/bnext/finish/bfinish might jump around a bit non-predictably.
  • similarly, breaks on watchpoints can stop at apparently unexpected places (when going backward, try to do "step" once). The issue is that it can only stop at the beginning of every line. In the extreme example, if a line is foo(somelist.pop(getindex())), then somelist is modified in the middle. Immediately before this modification occurs, we are in getindex(), and immediately afterwards we are in foo(). The watchpoint will stop the program at the end of getindex() if running backward, and at the start of foo() if running forward, but never actually on the line doing the change.
  • watchpoint expressions must not have any side-effect at all. If they do, the replaying will get out of sync and revdb.py will complain about that. Regular p expressions and statements can have side-effects; these effects are discarded as soon as you move in time again.
  • sometimes even "p import foo" will fail with Attempted to do I/O. Use instead "p import sys; foo = sys.modules['foo']".
  • use help to see all commands. backtrace can be useful. There is no up command; you have to move in time instead, e.g. using bfinish to go back to the point where the current function was called.

How RevPDB is done

If I had to pick the main advantage of PyPy over CPython, it is that we have got with the RPython translation toolchain a real place for experimentation. Every now and then, we build inside RPython some feature that gives us an optionally tweaked version of the PyPy interpreter---tweaked in a way that would be hard to do with CPython, because it would require systematic changes everywhere. The most obvious and successful examples are the GC and the JIT. But there have been many other experiments along the same lines, from the so-called stackless transformation in the early days, to the STM version of PyPy.

RevPDB works in a similar way. It is a version of PyPy in which some operations are systematically replaced with other operations.

To keep the log file at a reasonable size, we duplicate the content of all GC objects during replaying---by repeating the same actions on them, without writing anything in the log file. So that means that in the pypy-revdb binary, the operations that do arithmetic or read/write GC-managed memory are not modified. Most operations are like that. However, the other operations, the ones that involve either non-GC memory or calls to external C functions, are tweaked. Each of these operations is replaced with code that works in two modes, based on a global flag:

  • in "recording" mode, we log the result of the operation (but not the arguments);
  • in "replaying" mode, we don't really do the operation at all, but instead just fetch the result from the log.

Hopefully, all remaining unmodified operations (arithmetic and GC load/store) are completely deterministic. So during replaying, every integer or non-GC pointer variable will have exactly the same value as it had during recording. Interestingly, it means that if the recording process had a big array in non-GC memory, then in the replaying process, the array is not allocated at all; it is just represented by the same address, but there is nothing there. When we record "read item 123 from the array", we record the result of the read (but not the "123"). When we replay, we're seeing again the same "read item 123 from the array" operation. At that point, we don't read anything; we just return the result from the log. Similarly, when recording a "write" to the array, we record nothing (this write operation has no result); so that when replaying, we redo nothing.

Note how that differs from anything managed by GC memory: GC objects (including GC arrays) are really allocated, writes really occur, and reads are redone. We don't touch the log in this case.

Other reverse debuggers for Python

There are already some Python experiments about reverse debugging. This is also known as "omniscient debugging". However, I claim that the result they get to is not very useful (for the purpose presented here). How they work is typically by recording changes to some objects, like lists and dictionaries, in addition to recording the history of where your program passed through. However, the problem of Python is that lists and dictionaries are not the end of the story. There are many, many, many types of objects written in C which are mutable---in fact, the immutable ones are the exception. You can try to systematically record all changes, but it is a huge task and easy to forget a detail.

In other words it is a typical use case for tweaking the RPython translation toolchain, rather than tweaking the CPython (or PyPy) interpreter directly. The result that we get here with RevPDB is more similar to rr anyway, in that only a relatively small number of external events are recorded---not every single change to every single list and dictionary.

Some links:

For C:

Future work

As mentioned above, it is alpha-level, and only works on Linux and OS/X. So the plans for the immediate future are to fix the various issues described above, and port to more operating systems. The core of the system is in the C file and headers in rpython/translator/revdb/src-revdb.

For interested people, there is also the Duhton interpreter and its reverse-debugger branch, which is where I prototyped the RPython concept before moving to PyPy. The basics should work for any interpreter written in RPython, but they require some specific code to interface with the language; in the case of PyPy, it is in pypy/interpreter/reverse_debugging.py.

In parallel, there are various user interface improvements that people could be interested in, like a more "pdb++" experience. (And the script at rpython/translator/revdb/revdb.py should be moved out into some more "official" place, and the reverse-debugger branch should be merged back to default.)

I would certainly welcome any help!

-+- Armin

Rachmad Imam Tarecha wrote on 2016-07-08 13:57:

I think python is hard programming language, :D

mrh1997 wrote on 2016-07-09 22:59:

I am really impressed!
Especially of the fact that you did the Job within one month.

I had the idea of such a tool, too some time ago (with exactly the same approach, but in CPython instead of PyPy).
But I failed to implement it, as in CPython I had to do a lot more modifications...

Armin Rigo wrote on 2016-07-10 18:31:

Seems to work out of the box on OS/X. I've updated it in the blog post.

Ron Barak wrote on 2016-07-14 22:50:

Erratum:
RevPDB is only available only on 64-bit Linux -> RevPDB is available only on 64-bit Linux

Armin Rigo wrote on 2016-07-15 08:55:

Thanks for the typo.

PyPy2 v5.3 released - major C-extension support improvements

We have released PyPy2.7 v5.3, about six weeks after PyPy 5.1 and a week after PyPy3.3 v5.2 alpha 1, the first PyPy release targeting 3.3 compatibility. This new PyPy2.7 release includes major improvements for the C-API compatibility layer. In addition to complete support for lxml, we now pass most (more than 95%) of the upstream numpy test suite. We can build and run scipy and matplotlib as well. Most of the failures have to do with (ab) use of the C-API, for instance writing to a read-only pointer obtained from PyString_AsString().

Note that the C-API compatibility layer is significantly slower than CPython, as explained in the blog post about the new strategy for reflection of C objects into the PyPy interpreter.

We updated cffi to version 1.7 (incremental changes which provide a nicer developer experience, documented here). We would encourage developers to move their C-extension modules to cffi, but are willing to help you work through issues with existing code; come to #pypy on IRC and let us know how we can help you help us do better.

You can download the PyPy2 v5.3 release here:
We would like to thank our donors for their continued support of the PyPy project. We would also like to thank our contributors and encourage new people to join the project. PyPy has many layers and we need help with all of them: PyPy and RPython documentation improvements, tweaking popular modules to run on PyPy, or general help with making RPython’s JIT even better.

What is PyPy?

PyPy is a very compliant Python interpreter, almost a drop-in replacement for CPython 2.7. It’s fast (PyPy and CPython 2.7 performance comparison) due to its integrated tracing JIT compiler.

We also welcome developers of other dynamic languages to see what RPython can do for them.

This release supports:
  • x86 machines on most common operating systems (Linux 32/64, Mac OS X 64, Windows 32, OpenBSD, FreeBSD)
  • newer ARM hardware (ARMv6 or ARMv7, with VFPv3) running Linux
  • big- and little-endian variants of PPC64 running Linux
  • s390x running Linux

Other Highlights

(since the release of PyPy 5.1 in April, 2016)

  • New features:
    • Merge a major expansion of the C-API support in cpyext, also expand cpyext tests to allow running them after translation as well as untranslated
    • Instead of “GIL not held when a CPython C extension module calls PyXxx”, we now silently acquire/release the GIL. Helps with C extension modules that call some PyXxx() functions without holding the GIL (arguably, they are theoretically buggy).
    • Support command line -v to trace import statements
    • Revive traceviewer, a tool to use pygame to view traces

  • Numpy via our internal _numpypy module:
    • Implement ufunc.outer
    • Move PyPy-specific numpypy headers to a subdirectory (also changed the repo accordingly)
     
  • Performance improvements:
    • Use bitstrings to compress lists of descriptors that are attached to an EffectInfo
    • Remove most of the _ovf, _zer and _val operations from RPython. Kills quite some code internally, and allows the JIT to do better optimizations: for example, app-level code like x / 2 or x % 2 can now be turned into x >> 1 or x & 1, even if x is possibly negative.
    • Rework the way registers are moved/spilled in before_call()

  • Internal refactorings:
    • Refactor code to better support Python3-compatible syntax
    • Reduce the size of generated C sources during translation by eliminating many many unused struct declarations (Issue #2281)
    • Reduce the size of generated code by using the same function objects in all generated subclasses
    • Share cpyext Py* function wrappers according to the signature, shrinking the translated libpypy.so by about 10% (without the JIT)
Please update, and continue to help us make PyPy better. Cheers
The PyPy Team
Anonymous wrote on 2016-06-09 19:48:

"We can build and run scipy and matplotlib as well."

That's exciting. Are there special instructions needed to build and run spicy and matplotlib with PyPy to see how well it presently works for particular applications? Or is it not even really ready for outsiders to knock it around yet?

mattip wrote on 2016-06-09 23:26:

No special instructions, just build from source (binaries precompiled for cpython will not work) using "pypy setup.py install", and let us know how it goes. The order should be numpy, matplotlib, scipy (we have reports that pygtk works too fwiw).

There have already been some bug reports, so you might want to patch your pymem.h header in pypy/include with this changeset https://bitbucket.org/pypy/pypy/commits/68486f0f79c649514, and if you are on OSX you may need to patch numpy/distutils/fcompiler/gnu.py with this patch https://bitbucket.org/pypy/numpy/commits/50bff5807e09721acc4d778ce8ffdef86e2f4c50

Canesin wrote on 2016-06-12 17:38:

Great work as usual!

PyPy3.3 v5.2 alpha 1 released

We're pleased to announce the first alpha release of PyPy3.3 v5.2. This is the
first release of PyPy which targets Python 3.3 (3.3.5) compatibility.

We would like to thank all of the people who donated to the py3k proposal
for supporting the work that went into this and future releases.

You can download the PyPy3.3 v5.2 alpha 1 release here:

https://pypy.org/download.html#python-3-3-5-compatible-pypy3-3-v5-2

Highlights

What is PyPy?

PyPy is a very compliant Python interpreter, almost a drop-in replacement for
CPython 2.7.10 and one day 3.3.5. It's fast due to its integrated tracing JIT
compiler.

We also welcome developers of other dynamic languages to see what RPython
can do for them.

This release supports:

  • x86 machines on most common operating systems except Windows
    (Linux 32/64, Mac OS X 64, OpenBSD, FreeBSD),
  • newer ARM hardware (ARMv6 or ARMv7, with VFPv3) running Linux,
  • big- and little-endian variants of PPC64 running Linux,
  • s390x running Linux

Please try it out and let us know what you think. We welcome feedback, we know
you are using PyPy, please tell us about it!

We'd especially like to thank these people for their contributions to this
release:

Manuel Jacob, Ronan Lamy, Mark Young, Amaury Forgeot d'Arc, Philip Jenvey,
Martin Matusiak, Vasily Kuznetsov, Matti Picus, Armin Rigo and many others.

Cheers

The PyPy Team

rnbdlnch wrote on 2016-05-31 09:33:

thank you!!!

Unknown wrote on 2016-05-31 12:47:

Many, many thanks!

Unknown wrote on 2016-05-31 13:30:

As a follow-up: Did asyncio work previously? Anyway, it does now as 'yield from' is there. Beautiful!

Anonymous wrote on 2016-06-01 01:52:

Great News!!! Thank you!!!

Robert wrote on 2016-06-03 23:04:

Excited! Can't wait for the 3.4 compatibility!

Sean Vieira wrote on 2016-07-05 19:33:

Hip, hip, huzzah!

Hai Zaar wrote on 2016-07-25 14:59:

Great news guys! Did you consider skipping 3.3/3.4 support all together and going straight for 3.5 compatibility?

Armin Rigo wrote on 2016-07-31 14:22:

We'll be working next on 3.5 support.

PyPy 5.1.1 bugfix released

We have released a bugfix for PyPy 5.1, due to a regression in installing third-party packages depending on numpy (using our numpy fork available at https://bitbucket.org/pypy/numpy ).

Thanks to those who reported the issue. We also fixed a regression in translating PyPy which increased the memory required to translate. Improvement will be noticed by downstream packagers and those who translate rather than
download pre-built binaries.

What is PyPy?

PyPy is a very compliant Python interpreter, almost a drop-in replacement for CPython 2.7. It's fast (PyPy and CPython 2.7.x performance comparison) due to its integrated tracing JIT compiler.

We also welcome developers of other dynamic languages to see what RPython can do for them.

This release supports:
  • x86 machines on most common operating systems (Linux 32/64, Mac OS X 64, Windows 32, OpenBSD, FreeBSD),
  • newer ARM hardware (ARMv6 or ARMv7, with VFPv3) running Linux,
  • big- and little-endian variants of PPC64 running Linux,
  • s390x running Linux
Please update, and continue to help us make PyPy better.

Cheers

The PyPy Team
No comments.

PyPy 5.1 released

We have released PyPy 5.1, about a month after PyPy 5.0.

This release includes more improvement to warmup time and memory requirements, extending the work done on PyPy 5.0. We have seen an additional reduction of about 20% in memory requirements, and up to 30% warmup time improvement, more detail in the blog post.

We also now have full support for the IBM s390x. Since this support is in RPython, any dynamic language written using RPython, like PyPy, will automagically be supported on that architecture.

We updated cffi to 1.6 (cffi 1.6 itself will be released shortly), and continue to improve support for the wider python ecosystem using the PyPy interpreter.

You can download the PyPy 5.1 release here:
We would like to thank our donors for the continued support of the PyPy project.
We would also like to thank our contributors and encourage new people to join the project. PyPy has many layers and we need help with all of them: PyPy and RPython documentation improvements, tweaking popular modules to run on pypy, or general help with making RPython’s JIT even better.

What is PyPy?

PyPy is a very compliant Python interpreter, almost a drop-in replacement for CPython 2.7. It’s fast (PyPy and CPython 2.7.x performance comparison) due to its integrated tracing JIT compiler.

We also welcome developers of other dynamic languages to see what RPython can do for them.

This release supports:
  • x86 machines on most common operating systems (Linux 32/64, Mac OS X 64, Windows 32, OpenBSD, FreeBSD),
  • newer ARM hardware (ARMv6 or ARMv7, with VFPv3) running Linux,
  • big- and little-endian variants of PPC64 running Linux,
  • s390x running Linux

Other Highlights

(since the release of PyPy 5.0 in March, 2016


  • New features:

    • A new jit backend for the IBM s390x, which was a large effort over the past few months.
    • Add better support for PyUnicodeObject in the C-API compatibility layer
    • Support GNU/kFreeBSD Debian ports in vmprof
    • Add __pypy__._promote
    • Make attrgetter a single type for CPython compatibility

  • Bug Fixes

    • Catch exceptions raised in an exit function
    • Fix a corner case in the JIT
    • Fix edge cases in the cpyext refcounting-compatible semantics (more work on cpyext compatibility is coming in the cpyext-ext branch, but isn’t ready yet)
    • Try harder to not emit NEON instructions on ARM processors without NEON support
    • Improve the rpython posix module system interaction function calls
    • Detect a missing class function implementation instead of calling a random function
    • Check that PyTupleObjects do not contain any NULLs at the point of conversion to W_TupleObjects
    • In ctypes, fix _anonymous_ fields of instances
    • Fix JIT issue with unpack() on a Trace which contains half-written operations
    • Fix sandbox startup (a regression in 5.0)
    • Fix possible segfault for classes with mangled mro or __metaclass__
    • Fix isinstance(deque(), Hashable) on the pure python deque
    • Fix an issue with forkpty()
    • Issues reported with our previous release were resolved after reports from users on our issue tracker at https://foss.heptapod.net/pypy/pypy/-/issues or on IRC at #pypy

  • Numpy:

    • Implemented numpy.where for a single argument
    • Indexing by a numpy scalar now returns a scalar
    • Fix transpose(arg) when arg is a sequence
    • Refactor include file handling, now all numpy ndarray, ufunc, and umath functions exported from libpypy.so are declared in pypy_numpy.h, which is included only when building our fork of numpy
    • Add broadcast

  • Performance improvements:

    • Improve str.endswith([tuple]) and str.startswith([tuple]) to allow JITting
    • Merge another round of improvements to the warmup performance
    • Cleanup history rewriting in pyjitpl
    • Remove the forced minor collection that occurs when rewriting the assembler at the start of the JIT backend
    • Port the resource module to cffi
     
    • Internal refactorings:

      • Use a simpler logger to speed up translation
      • Drop vestiges of Python 2.5 support in testing
      • Update rpython functions with ones needed for py3k
    Please update, and continue to help us make PyPy better.
    Cheers
    The PyPy Team







    No comments.

    PyPy Enterprise Edition

    With the latest additions, PyPy's JIT now supports the Z architecture on Linux. The newest architecture revision (also known as s390x, or colloquially referred to as "big iron") is the 64-bit extension for IBM mainframes. Currently only Linux 64 bit is supported (not z/OS nor TPF).
    This is the fourth assembler backend supported by PyPy in addition to x86 (32 and 64), ARM (32-bit only) and PPC64 (both little- and big-endian). It might seem that we kind of get a hang of new architectures. Thanks to IBM for funding this work!

    History

    When I went to university one lecture covered the prediction of Thomas Watson in 1943. His famous quote "I think there is a world market for maybe five computers ...", turned out not to be true.

    However, even 70 years later, mainframes are used more often than you think. They back critical tasks requiring a high level of stability/security and offer high hardware and computational utilization rates by virtualization.

    With the new PyPy JIT backend we are happy to present a fast Python virtual machine for mainframes and contribute more free software running on s390x.

    Meta tracing

    Even though the JIT backend has been tested on PyPy, it is not restricted to  the Python programming language. Do you have a great idea for a DSL, or another language that should run on mainframes? Go ahead and just implement your interpreter using RPython.

    How do I get a copy?

    PyPy can be built using the usual instructions found here. As soon as the next PyPy version has been released we will provide binaries. Until then you can just grab a nightly here.We are currently busy to get the next version of PyPy ready, so an official release will be rolled out soon.

    Comparing s390x to x86

    The goal of this comparison is not to scientifically evaluate the benefits/disadvantages on s390x, but rather to see that PyPy's architecture delivers the same benefits as it does on other platforms. Similar to the comparison done for PPC I ran the benchmarks using the same setup. The first column is the speedup of the PyPy JIT VM compared to the speedup of a pure PyPy interpreter 1). Note that the s390x's OS was virtualized.

      Label               x86     s390x      s390x (run 2)

      ai                 13.7      12.4       11.9
      bm_chameleon        8.5       6.3        6.8
      bm_dulwich_log      5.1       5.0        5.1
      bm_krakatau         5.5       2.0        2.0
      bm_mako             8.4       5.8        5.9
      bm_mdp              2.0       3.8        3.8
      chaos              56.9      52.6       53.4
      crypto_pyaes       62.5      64.2       64.2
      deltablue           3.3       3.9        3.6
      django             28.8      22.6       21.7
      eparse              2.3       2.5        2.6
      fannkuch            9.1       9.9       10.1
      float              13.8      12.8       13.8
      genshi_text        16.4      10.5       10.9
      genshi_xml          8.2       7.9        8.2
      go                  6.7       6.2       11.2
      hexiom2            24.3      23.8       23.5
      html5lib            5.4       5.8        5.7
      json_bench         28.8      27.8       28.1
      meteor-contest      5.1       4.2        4.4
      nbody_modified     20.6      19.3       19.4
      pidigits            1.0      -1.1       -1.0
      pyflate-fast        9.0       8.7        8.5
      pypy_interp         3.3       4.2        4.4
      raytrace-simple    69.0     100.9       93.4
      richards           94.1      96.6       84.3
      rietveld            3.2       2.5        2.7
      slowspitfire        2.8       3.3        4.2
      spambayes           5.0       4.8        4.8
      spectral-norm      41.9      39.8       42.6
      spitfire            3.8       3.9        4.3
      spitfire_cstringio  7.6       7.9        8.2
      sympy_expand        2.9       1.8        1.8
      sympy_integrate     4.3       3.9        4.0
      sympy_str           1.5       1.3        1.3
      sympy_sum           6.2       5.8        5.9
      telco              61.2      48.5       54.8
      twisted_iteration  55.5      41.9       43.8
      twisted_names       8.2       9.3        9.7
      twisted_pb         12.1      10.4       10.2
      twisted_tcp         4.9       4.8        5.2


      Geometric mean:    9.31      9.10       9.43


    As you can see the benefits are comparable on both platforms.
    Of course this is scientifically not good enough, but it shows a tendency. s390x can achieve the same results as you can get on x86.

    Are you running your business application on a mainframe? We would love to get some feedback. Join us in IRC tell us if PyPy made your application faster!

    plan_rich & the PyPy Team

    1) PyPy revision for the benchmarks: 4b386bcfee54
    No comments.

    Warmup improvements: more efficient trace representation

    Hello everyone.

    I'm pleased to inform that we've finished another round of improvements to the warmup performance of PyPy. Before I go into details, I'll recap the achievements that we've done since we've started working on the warmup performance. I picked a random PyPy from November 2014 (which is definitely before we started the warmup work) and compared it with a recent one, after 5.0. The exact revisions are respectively ffce4c795283 and cfbb442ae368. First let's compare pure warmup benchmarks that can be found in our benchmarking suite. Out of those, pypy-graph-alloc-removal numbers should be taken with a grain of salt, since other work could have influenced the results. The rest of the benchmarks mentioned is bottlenecked purely by warmup times.

    You can see how much your program spends in warmup running PYPYLOG=jit-summary:- pypy your-program.py under "tracing" and "backend" fields (in the first three lines). An example looks like that:

    [e00c145a41] {jit-summary
    Tracing:        71      0.053645 <- time spent tracing & optimizing
    Backend:        71      0.028659 <- time spent compiling to assembler
    TOTAL:                  0.252217 <- total run time of the program
    

    The results of the benchmarks

    benchmark time - old time - new speedup JIT time - old JIT time - new
    function_call 1.86 1.42 1.3x 1.12s 0.57s
    function_call2 5.17s 2.73s 1.9x 4.2s 1.6s
    bridges 2.77s 2.07s 1.3x 1.5s 0.8s
    pypy-graph-alloc-removal 2.06s 1.65s 1.25x 1.25s 0.79s

    As we can see, the overall warmup benchmarks got up to 90% faster with JIT time dropping by up to 2.5x. We have more optimizations in the pipeline, with an idea how to transfer some of the JIT gains into more of a total program runtime by jitting earlier and more eagerly.

    Details of the last round of optimizations

    Now the nitty gritty details - what did we actually do? I covered a lot of warmup improvements in the past blog posts so I'm going to focus on the last change, the jit-leaner-frontend branch. This last change is simple, instead of using pointers to store the "operations" objects created during tracing, we use a compact list of 16-bit integers (with 16bit pointers in between). On 64bit machine the memory wins are tremendous - the new representation is 4x more efficient to use 16bit pointers than full 64bit pointers. Additionally, the smaller representation has much better cache behavior and much less pointer chasing in memory. It also has a better defined lifespan, so we don't need to bother tracking them by the GC, which also saves quite a bit of time.

    The change sounds simple, but the details in the underlaying data mean that everything in the JIT had to be changed which took quite a bit of effort :-)

    Going into the future on the JIT front, we have an exciting set of optimizations, ranging from faster loops through faster warmup to using better code generation techniques and broadening the kind of program that PyPy speeds up. Stay tuned for the updates.

    We would like to thank our commercial partners for making all of this possible. The work has been performed by baroquesoftware and would not be possible without support from people using PyPy in production. If your company uses PyPy and want it to do more or does not use PyPy but has performance problems with the Python installation, feel free to get in touch with me, trust me using PyPy ends up being a lot cheaper than rewriting everything in go :-)

    Best regards,
    Maciej Fijalkowski


    Peter wrote on 2016-04-08 08:55:

    It would be nice to compare speed with C-Python and on short benchmarks, as that is where warmup time matters the most

    Maciej Fijalkowski wrote on 2016-04-08 09:14:

    Those benchmarks are very synthetic warmup-oriented ones. It means you exec() piece of code and then run it 2000 times and then exec again. Any other short-running programs have a lot more noise where you have multiple effects taking place and it would be really hard to compare between old and new pypy. That said it's a fair requirement, we have one more branch in the pipeline and I'll try to get more real world data.

    PyPy 5.0.1 bugfix released

    PyPy 5.0.1


    We have released a bugfix for PyPy 5.0, after reports that the newly released lxml 3.6.0, which now supports PyPy 5.0 +, can crash on large files. Thanks to those who reported the crash. Please update, downloads are available at

    pypy.org/download.html

    The changes between PyPy 5.0 and 5.0.1 are only two bug fixes: one in cpyext, which fixes notably (but not only) lxml; and another for a corner case of the JIT.

    What is PyPy?


    PyPy is a very compliant Python interpreter, almost a drop-in replacement for CPython 2.7. It’s fast (PyPy and CPython 2.7.x performance comparison) due to its integrated tracing JIT compiler.
    We also welcome developers of other dynamic languages to see what RPython can do for them.
    This release supports x86 machines on most common operating systems (Linux 32/64, Mac OS X 64, Windows 32, OpenBSD, FreeBSD), newer ARM hardware (ARMv6 or ARMv7, with VFPv3) running Linux, and the big- and little-endian variants of PPC64 running Linux.

    Please update, and continue to help us make PyPy better.

    Cheers
    The PyPy Team
    Armin Rigo wrote on 2016-03-28 03:39:

    ppc64 released four days ago, and big-endian updated just now to fix an important bug. There are other big-endian bugs left which we're fixing as we go along; they will be in the next official release.

    PyPy 5.0 released

    PyPy 5.0

    We have released PyPy 5.0, about three months after PyPy 4.0.1. We encourage all users of PyPy to update to this version.

    You can download the PyPy 5.0 release here:
    We would like to thank our donors for the continued support of the PyPy project.
    We would also like to thank our contributors and encourage new people to join the project. PyPy has many layers and we need help with all of them: PyPy and RPython documentation improvements, tweaking popular modules to run on pypy, or general help with making RPython’s JIT even better.

     

    Faster and Leaner

    We continue to improve the warmup time and memory usage of JIT-related metadata. The exact effects depend vastly on the program you’re running and can range from insignificant to warmup being up to 30% faster and memory dropping by about 30%.

     

    C-API Upgrade

    We also merged a major upgrade to our C-API layer (cpyext), simplifying the interaction between c-level objects and PyPy interpreter level objects. As a result, lxml (prerelease) with its cython compiled component passes all tests on PyPy. The new cpyext is also much faster. This major refactoring will soon be followed by an expansion of our C-API compatibility.

     

    Profiling with vmprof supported on more platforms


    vmprof has been a go-to profiler for PyPy on linux for a few releases and we’re happy to announce that thanks to the cooperation with jetbrains, vmprof now works on Linux, OS X and Windows on both PyPy and CPython.

     

    CFFI

    While not applicable only to PyPy, cffi is arguably our most significant contribution to the python ecosystem. PyPy 5.0 ships with cffi-1.5.2 which now allows embedding PyPy (or CPython) in a C program.

     

    What is PyPy?


    PyPy is a very compliant Python interpreter, almost a drop-in replacement for CPython 2.7. It’s fast (pypy and cpython 2.7.x performance comparison) due to its integrated tracing JIT compiler.
    We also welcome developers of other dynamic languages to see what RPython can do for them.
    This release supports x86 machines on most common operating systems (Linux 32/64, Mac OS X 64, Windows 32, OpenBSD, freebsd), newer ARM hardware (ARMv6 or ARMv7, with VFPv3) running Linux, and 64 bit PowerPC hardware, specifically Linux running the big- and little-endian variants of ppc64.

     

    Other Highlights (since 4.0.1 released in November 2015)

    • New features:
      • Support embedding PyPy in a C-program via cffi and static callbacks in cffi.
        This deprecates the old method of embedding PyPy
      • Refactor vmprof to work cross-operating-system, deprecate using buggy
        libunwind on Linux platforms. Vmprof even works on Windows now.
      • Support more of the C-API type slots, like tp_getattro, and fix C-API
        macros, functions, and structs such as _PyLong_FromByteArray(),
        PyString_GET_SIZE, f_locals in PyFrameObject, Py_NAN, co_filename in
        PyCodeObject
      • Use a more stable approach for allocating PyObjects in cpyext. (see
        blog post). Once the PyObject corresponding to a PyPy object is created,
        it stays around at the same location until the death of the PyPy object.
        Done with a little bit of custom GC support. It allows us to kill the
        notion of “borrowing” inside cpyext, reduces 4 dictionaries down to 1, and
        significantly simplifies the whole approach (which is why it is a new
        feature while technically a refactoring) and allows PyPy to support the
        populart lxml module (as of the next release) with no PyPy specific
        patches needed
      • Make the default filesystem encoding ASCII, like CPython
      • Use hypothesis in test creation, which is great for randomizing tests
       
      • Bug Fixes
        • Backport always using os.urandom for uuid4 from cpython and fix the JIT as well
          (issue #2202)
        • More completely support datetime, optimize timedelta creation
        • Fix for issue #2185 which caused an inconsistent list of operations to be
          generated by the unroller, appeared in a complicated DJango app
        • Fix an elusive issue with stacklets on shadowstack which showed up when
          forgetting stacklets without resuming them
        • Fix entrypoint() which now acquires the GIL
        • Fix direct_ffi_call() so failure does not bail out before setting CALL_MAY_FORCE
        • Fix (de)pickling long values by simplifying the implementation
        • Fix RPython rthread so that objects stored as threadlocal do not force minor
          GC collection and are kept alive automatically. This improves perfomance of
          short-running Python callbacks and prevents resetting such object between
          calls
        • Support floats as parameters to itertools.isslice()
        • Check for the existence of CODESET, ignoring it should have prevented PyPy
          from working on FreeBSD
        • Fix for corner case (likely shown by Krakatau) for consecutive guards with
          interdependencies
        • Fix applevel bare class method comparisons which should fix pretty printing
          in IPython
        • Issues reported with our previous release were resolved after reports from users on our issue tracker at https://foss.heptapod.net/pypy/pypy/-/issues or on IRC at #pypy
         
        • Numpy:
          • Updates to numpy 1.10.2 (incompatibilities and not-implemented features
            still exist)
          • Support dtype=((‘O’, spec)) union while disallowing record arrays with
            mixed object, non-object values
          • Remove all traces of micronumpy from cpyext if –withoutmod-micronumpy option used
          • Support indexing filtering with a boolean ndarray
          • Support partition() as an app-level function, together with a cffi wrapper
            in pypy/numpy, this now provides partial support for partition()
           
          • Performance improvements:
            • Optimize global lookups
            • Improve the memory signature of numbering instances in the JIT. This should
              massively decrease the amount of memory consumed by the JIT, which is
              significant for most programs. Also compress the numberings using variable-
              size encoding
            • Optimize string concatenation
            • Use INT_LSHIFT instead of INT_MUL when possible
            • Improve struct.unpack by casting directly from the underlying buffer.
              Unpacking floats and doubles is about 15 times faster, and integer types
              about 50% faster (on 64 bit integers). This was then subsequently
              improved further in optimizeopt.py.
            • Optimize two-tuple lookups in mapdict, which improves warmup of instance
              variable access somewhat
            • Reduce all guards from int_floordiv_ovf if one of the arguments is constant
            • Identify permutations of attributes at instance creation, reducing the
              number of bridges created
            • Greatly improve re.sub() performance
             
            • Internal refactorings:
              • Refactor and improve exception analysis in the annotator
              • Remove unnecessary special handling of space.wrap().
              • Support list-resizing setslice operations in RPython
              • Tweak the trace-too-long heuristic for multiple jit drivers
              • Refactor bookkeeping (such a cool word - three double letters) in the
                annotater
              • Refactor wrappers for OS functions from rtyper to rlib and simplify them
              • Simplify backend loading instructions to only use four variants
              • Simplify GIL handling in non-jitted code
              • Refactor naming in optimizeopt
              • Change GraphAnalyzer to use a more precise way to recognize external
                functions and fix null pointer handling, generally clean up external
                function handling
              • Remove pure variants of getfield_gc_* operations from the JIT by
                determining purity while tracing
              • Refactor databasing
              • Simplify bootstrapping in cpyext
              • Refactor rtyper debug code into python.rtyper.debug
              • Seperate structmember.h from Python.h Also enhance creating api functions
                to specify which header file they appear in (previously only pypy_decl.h)
              • Fix tokenizer to enforce universal newlines, needed for Python 3 support
            Please try it out and let us know what you think. We welcome feedback, we know you are using PyPy, please tell us about it!
            Cheers
            The PyPy Team
            HelpingHand wrote on 2016-03-10 22:30:

            What is the status on finally getting a functional x64 build for windows? I am mainly interested in embedding PyPy and unless there is support for it, I will continue to avoid it.

            mathgl wrote on 2016-03-11 05:05:

            does new cpyext help for supporting numpy?

            mattip wrote on 2016-03-11 08:06:

            HelpingHand: work on x64 for windows [0] is awaiting a champion, with either the skill to do it or with the deep pockets to sponsor it. If you are interested, please come to #pypy on IRC to discuss it

            [0] https://doc.pypy.org/en/latest/windows.html#what-is-missing-for-a-full-64-bit-translation

            mattip wrote on 2016-03-11 08:09:

            mathgl: yes, we are cautiously optimistic that if we now flesh out cpyext to support enough of the C-API that vanilla numpy might just work. Stay tuned for further developments

            Martin Gfeller wrote on 2016-03-11 08:57:

            I've asked Brett Cannon, well-know Pythonista working at Microsoft about whether they could sponsor or undertake Windows 64-bit work.

            If you have a substantial use cause requiring the speed of PyPy, large address spaces and Windows, it might help.

            Unknown wrote on 2016-03-11 10:52:

            What happened to the speed graph on speed.pypy.org? The speedups for earlier versions of PyPy before 5.0 suddenly are much higher than they used to be. Compare for example against the graph of a couple of weeks ago (https://web.archive.org/web/20160228102615/https://speed.pypy.org/)

            Version 28/2 11/3
            1.5 3.18x 4.86x
            2.1 6.12x 7.50x
            2.4.0 6.22x 7.61x
            2.6.1 7.05x 8.58x

            Has the benchmark been changed, the timing method, the speed computation, hardware used, etc? More importantly, which version is "correct"?

            Maciej Fijalkowski wrote on 2016-03-11 10:56:

            Hi Paul.

            We rerun all benchmarks on old Pythons and it shows now a different subset of benchmarks. I must admit I don't know why the main site chooses some benchmarks and not others, it's certainly not deliberate. Any single number you use is not correct, a bit by definition - we suggest you look in details what the benchmarks do or even better, benchmark yourself. We'll look why it's showing a different subset

            Unknown wrote on 2016-03-11 11:07:

            Great news! Awesome!

            mattip wrote on 2016-03-11 12:40:

            Paul Melis, Maciej Fjalkowski - indeed there was a bug; I reran the old benchmarks but only ~half ran to completion. I reverted the bad run, now results are like they used to be. Thanks for pointing it out

            Unknown wrote on 2016-03-14 03:52:

            When is release of pypy3 5.0?
            I'd like also to get the profit of pypy5.0 by a condition of support of python 3.2.5.

            Armin Rigo wrote on 2016-03-17 15:07:

            lxml 3.6.0 released with support for PyPy 5.x.

            Armin Rigo wrote on 2016-03-20 11:10:

            Before trying out lxml 3.6.0, upgrade to PyPy 5.0.1: the release 5.0.0 does not reliably work with it.

            C-API Support update

            As you know, PyPy can emulate the CPython C API to some extent. In this post I will describe an important optimization that we merged to improve the performance and stability of the C-API emulation layer.

            The C-API is implemented by passing around PyObject * pointers in the C code. The problem with providing the same interface with PyPy is that objects don't natively have the same PyObject * structure at all; and additionally their memory address can change. PyPy handles the difference by maintaining two sets of objects. More precisely, starting from a PyPy object, it can allocate on demand a PyObject structure and fill it with information that points back to the original PyPy objects; and conversely, starting from a C-level object, it can allocate a PyPy-level object and fill it with information in the opposite direction.

            I have merged a rewrite of the interaction between C-API C-level objects and PyPy's interpreter level objects. This is mostly a simplification based on a small hack in our garbage collector. This hack makes the garbage collector aware of the reference-counted PyObject structures. When it considers a pair consisting of a PyPy object and a PyObject, it will always free either none or both of them at the same time. They both stay alive if either there is a regular GC reference to the PyPy object, or the reference counter in the PyObject is bigger than zero.

            This gives a more stable result. Previously, a PyPy object might grow a corresponding PyObject, loose it (when its reference counter goes to zero), and later have another corresponding PyObject re-created at a different address. Now, once a link is created, it remains alive until both objects die.

            The rewrite significantly simplifies our previous code (which used to be based on at least 4 different dictionaries), and should make using the C-API somewhat faster (though it is still slower than using pure python or cffi).

            A side effect of this work is that now PyPy actually supports the upstream lxml package---which is is one of the most popular packages on PyPI. (Specifically, you need version 3.5.0 with this pull request to remove old PyPy-specific hacks that were not really working. See details.) At this point, we no longer recommend using the cffi-lxml alternative: although it may still be faster, it might be incomplete and old.

            We are actively working on extending our C-API support, and hope to soon merge a branch to support more of the C-API functions (some numpy news coming!). Please try it out and let us know how it works for you.

            Armin Rigo and the PyPy team

            mathgl wrote on 2016-02-25 16:40:

            wow, s good news. When trying to pick up a new lib, I always check whether it supports pypy first.

            Anonymous wrote on 2016-02-26 14:57:

            Really looking forward to hearing news from the numpy front!

            Unknown wrote on 2016-02-26 18:42:

            Great. Maybe now Odoo will work with PyPy!

            Anonymous wrote on 2016-02-28 09:58:

            Great, in particular the native lxml. This is used in many large production systems that will now be even more interested in PyPy.