git/list[1] front-page[2] threads[3] people[4] search[5] about
 

Re: GIT get corrupted on lustre

From
ECEric Chamberland <eric.chamberland@giref.ulaval.ca>
Date
Jan 18, 2013, 17:50 UTC
Message-ID
<50F98B53.9080109@giref.ulaval.ca>
In-Reply-To
<871B6C10EBEFE342A772D1159D1320853A044B42@umechphj.easf.csd.disa.mil>
Good idea!
I did a strace and here is the output with the error:
http://www.giref.ulaval.ca/~ericc/strace_git_error.txt
Hope it will be insightful!
Eric
On 01/17/2013 12:17 PM, Pyeron, Jason J CTR (US) wrote:
Show 56 quoted lines
> Sorry, I am in cygwin mode, and I had crossed wires in my head. s/ProcessMon/strace/
>
>> -----Original Message-----
>> From: git-owner@vger.kernel.org [mailto:git-owner@vger.kernel.org] On
>> Behalf Of Maxime Boissonneault
>> Sent: Thursday, January 17, 2013 11:41 AM
>> To: Pyeron, Jason J CTR (US)
>> Cc: Eric Chamberland; Philippe Vaucher; git@vger.kernel.org; Sébastien
>> Boisvert
>> Subject: Re: GIT get corrupted on lustre
>>
>> I don't know of any lustre filesystem that is used on Windows. Barely
>> anybody uses Windows in the HPC industry.
>> This is a Linux cluster.
>>
>> Maxime Boissonneault
>>
>> Le 2013-01-17 11:40, Pyeron, Jason J CTR (US) a écrit :
>>>> -----Original Message-----
>>>> From: Eric Chamberland
>>>> Sent: Thursday, January 17, 2013 11:31 AM
>>>>
>>>> On 01/17/2013 09:23 AM, Philippe Vaucher wrote:
>>>>>> Anyone has a new idea?
>>>>> Did you try Jeff King's code to confirm his idea?
>>>>>
>>>>> Philippe
>>>>>
>>>> Yes I did, but it was running without any problem....
>>>>
>>>> I find that my test case is "simple" (fresh git clone then "git gc"
>> in
>>>> a
>>>> crontab), I bet anyone who has access to a Lustre filesystem can
>>>> reproduce the problem...  The problem is to have such a filesystem
>> to
>>>> do
>>>> the tests....
>>> Stabbing in the dark, but can you log the details with ProcessMon?
>>>
>>> http://technet.microsoft.com/en-us/sysinternals/bb896645
>>>
>>>> But I am available to do it...
>>> -Jason
>>
>>
>> --
>> ---------------------------------
>> Maxime Boissonneault
>> Analyste de calcul - Calcul Québec, Université Laval
>> Ph. D. en physique
>>
>> --
>> To unsubscribe from this list: send the line "unsubscribe git" in
>> the body of a message to majordomo@vger.kernel.org
>> More majordomo info at  http://vger.kernel.org/majordomo-info.html
Previous: Pyeron, Jason J CTR (US)Next: Erik Faye-Lund
Message 12 of 36 in “GIT get corrupted on lustre”
  1. Eric ChamberlandDec 24, 2012
  2. Andreas SchwabDec 24, 2012
  3. Brian J. MurrellDec 24, 2012
  4. Eric ChamberlandJan 8, 2013
  5. Eric ChamberlandJan 9, 2013
  6. Eric ChamberlandJan 17, 2013
  7. Philippe VaucherJan 17, 2013
  8. Eric ChamberlandJan 17, 2013
  9. Pyeron, Jason J CTR (US)Jan 17, 2013
  10. Maxime BoissonneaultJan 17, 2013
  11. Pyeron, Jason J CTR (US)Jan 17, 2013
  12. Eric ChamberlandJan 18, 2013
  13. Erik Faye-LundJan 21, 2013
  14. Thomas RastJan 21, 2013
  15. Maxime BoissonneaultJan 21, 2013
  16. Thomas RastJan 21, 2013
  17. Brian J. MurrellJan 21, 2013
  18. Thomas RastJan 21, 2013
  19. Eric ChamberlandJan 22, 2013
  20. Junio C HamanoJan 22, 2013
  21. Thomas RastJan 22, 2013
  22. Eric ChamberlandJan 22, 2013
  23. Sébastien BoisvertJan 23, 2013
  24. Sébastien BoisvertJan 23, 2013
  25. Erik Faye-LundJan 23, 2013
  26. Thomas RastJan 23, 2013
  27. Erik Faye-LundJan 23, 2013
  28. Thomas RastJan 23, 2013
  29. Erik Faye-LundJan 23, 2013
  30. Jonathan NiederJan 23, 2013
  31. Sébastien BoisvertJan 23, 2013
  32. Eric ChamberlandFeb 4, 2013
  33. Eric ChamberlandJan 21, 2013
  34. Eric ChamberlandJan 21, 2013
  35. Greg TroxelDec 25, 2012
  36. Jeff KingDec 26, 2012

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.