[issue8299] Improve GIL in 2.7

Kristján Valur Jónsson report at bugs.python.org
Sun Apr 11 14:21:18 CEST 2010


Kristján Valur Jónsson <kristjan at ccpgames.com> added the comment:

Fyi, here is the output using the unmodified Windows GIL, i.e. without my patch being active:
C:\pydev\python\trunk\PCbuild>python.exe ..\Tools\ccbench\ccbench.py -t -y
== CPython 2.7a4+.0 (trunk) ==
== AMD64 Windows on 'Intel64 Family 6 Model 23 Stepping 6, GenuineIntel' ==

--- Throughput ---

Pi calculation (Python)

threads= 1:   623 iterations/s. balance
threads= 2:   489 ( 78%)        0.0289
threads= 3:   461 ( 74%)        0.0369
threads= 4:   460 ( 73%)        0.0426

regular expression (C)

threads= 1:   515 iterations/s. balance
threads= 2:   548 (106%)        0.0771
threads= 3:   532 (103%)        0.0556
threads= 4:   523 (101%)        0.1132

SHA1 hashing (C)

threads= 1:  1188 iterations/s. balance
threads= 2:  1212 (102%)        0.0232
threads= 3:  1198 (100%)        0.0250
threads= 4:  1215 (102%)        0.0163

You see results virtually identical to the ROUNDROBIN_GIL implementation.  This is just do demonstrate that Windows has had the ROUNDROBIN_GIL behaviour all along.

----------

_______________________________________
Python tracker <report at bugs.python.org>
<http://bugs.python.org/issue8299>
_______________________________________


More information about the Python-bugs-list mailing list