Issue 1001150: hotspot profiler does not work correctly on P4 CPUs with HT (original) (raw)
This issue has been migrated to GitHub: https://github.com/python/cpython/issues/40667
classification
| Title: | hotspot profiler does not work correctly on P4 CPUs with HT | ||
|---|---|---|---|
| Type: | behavior | Stage: | |
| Components: | Extension Modules, Library (Lib) | Versions: | Python 2.6, 3rd party |
process
| Status: | closed | Resolution: | |
|---|---|---|---|
| Dependencies: | Superseder: | ||
| Assigned To: | Nosy List: | ajaksu2, complex, nnorwitz | |
| Priority: | low | Keywords: |
Created on 2004-07-31 10:50 by complex, last changed 2022-04-11 14:56 by admin. This issue is now closed.
| Messages (7) | ||
|---|---|---|
| msg60542 - (view) | Author: Viktor Ferenczi (complex) | Date: 2004-07-31 10:50 |
| Using the hotspot module produces wrong timing data on Intel P4 CPUs with HyperThreading (HT) support enabled. For example: Running tests... .................................................. ---------------------------------------------------------------------- Ran 50 tests in 1.782s OK Loading results... Printing results... 24087 function calls (23727 primitive calls) in 5333.530 CPU seconds The 50 tests run in 1.782 seconds, but the profiler accumulates 5333.530 seconds. | ||
| msg60543 - (view) | Author: Viktor Ferenczi (complex) | Date: 2004-07-31 13:25 |
| Logged In: YES user_id=142612 OS: WinXP Prof ENG SP1 Python: 2.3.4 final, EXE installer (binary) | ||
| msg60544 - (view) | Author: Neal Norwitz (nnorwitz) *  |
Date: 2004-07-31 14:56 |
| Logged In: YES user_id=33168 There have been a few changes to hotshot which could fix this problem. Can you test the current version in CVS? I'm not sure if 2.4a1 has the fixes or not, but you could also try that version. Also, what test are you using? test_hotshot only has 3 tests. | ||
| msg60545 - (view) | Author: Neal Norwitz (nnorwitz) * |
Date: 2004-07-31 18:03 |
| Logged In: YES user_id=33168 There have been a few changes to hotshot which could fix this problem. Can you test the current version in CVS? I'm not sure if 2.4a1 has the fixes or not, but you could also try that version. Also, what test are you using? test_hotshot only has 3 tests. | ||
| msg82077 - (view) | Author: Daniel Diniz (ajaksu2) *  |
Date: 2009-02-14 14:44 |
| Will close unless OP provides more feedback or someone else opposes. | ||
| msg82403 - (view) | Author: Viktor Ferenczi (complex) | Date: 2009-02-18 02:20 |
| The hotspot module is obsolate, so this bug should be closed as "wont fix". | ||
| msg82417 - (view) | Author: Daniel Diniz (ajaksu2) * |
Date: 2009-02-18 14:38 |
| Thanks Viktor! |
| History | |||
|---|---|---|---|
| Date | User | Action | Args |
| 2022-04-11 14:56:06 | admin | set | github: 40667 |
| 2009-02-18 14:38:36 | ajaksu2 | set | status: pending -> closedmessages: + |
| 2009-02-18 02:20:10 | complex | set | messages: + |
| 2009-02-18 01:51:42 | ajaksu2 | set | status: open -> pending |
| 2009-02-14 14:44:52 | ajaksu2 | set | versions: + Python 2.6, 3rd partynosy: + ajaksu2messages: + priority: normal -> lowcomponents: + Extension Modulestype: behavior |
| 2004-07-31 10:50:39 | complex | create |