Nouveau client smp 6.22 MPICH

Moderators: Site Moderators, FAHC Science Team

Doctor_Love
Posts: 6
Joined: Mon Jan 14, 2008 8:04 pm

Nouveau client smp 6.22 MPICH

Post by Doctor_Love »

Nouveau client smp 6.22 MPICH et premier EUE pour une Wu 2653
sur un total de 880 ??? bravo le nouveau client de stanford ???



--- Opening Log file [August 4 05:43:13 UTC]


# Windows SMP Console Edition #################################################
###############################################################################

Folding@Home Client Version 6.22 SMP Beta2

http://folding.stanford.edu

###############################################################################
###############################################################################

Launch directory: D:\Folding@Home - Tripack_PC3\Console_SMP
Executable: D:\Folding@Home - Tripack_PC3\Console_SMP\Folding@home-Win32-x86.exe
Arguments: -local -verbosity 9 -smp -config

[05:43:14] - Ask before connecting: No
[05:43:14] - User name: Doctor_Love (Team 35819)
[05:43:14] - User ID: 5A255EB630898DA
[05:43:14] - Machine ID: 6
[05:43:14]
[05:43:14] Configuring Folding@Home...


[05:43:17] - Ask before connecting: No
[05:43:17] - User name: Doctor_Love (Team 35819)
[05:43:18] - User ID: 5A255EB630898DA
[05:43:18] - Machine ID: 6
[05:43:18]
[05:43:18] Loaded queue successfully.
[05:43:18]
[05:43:18] - Autosending finished units... [August 4 05:43:18 UTC]
[05:43:18] + Processing work unit
[05:43:18] Trying to send all finished work units
[05:43:18] Work type a1 not eligible for variable processors
[05:43:18] + No unsent completed units remaining.
[05:43:19] Core required: FahCore_a1.exe
[05:43:19] - Autosend completed
[05:43:19] Core found.
[05:43:19] Using generic mpiexec calls
[05:43:19] Working on queue slot 01 [August 4 05:43:19 UTC]
[05:43:19] + Working ...
[05:43:19] - Calling 'mpiexec -np 4 -channel auto -host 127.0.0.1 FahCore_a1.exe -dir work/ -suffix 01 -checkpoint 15 -verbose -lifeline 2116 -version 622'

[05:43:19]
[05:43:19] *------------------------------*
[05:43:19] Folding@Home Gromacs SMP Core
[05:43:19] Version 1.74 (March 10, 2007)
[05:43:19]
[05:43:19] Preparing to commence simulation
[05:43:19] - Ensuring status. Please wait.
[05:43:36] - Looking at optimizations...
[05:43:36] - Working with standard loops on this execution.
[05:43:36] - Previous termination of core was improper.
[05:43:37] - Going to use standard loops.
[05:43:37] - Files status OK
[05:43:41] - Expanded 2432836 -> 12916733 (decompressed 530.9 percent)
[05:43:41]
[05:43:41] Project: 2653 (Run 21, Clone 34, Gen 81)
[05:43:41]
[05:43:42] Entering M.D.
[05:43:48] Calling FAH init
[05:43:48] Read topology
[05:43:48] g local files
[05:43:48] checkpoint)
[05:43:49] Read checkpoint
[05:43:49] Protein: Protein in POPC
[05:43:49] Couldn't open for writing
[05:43:49] Writing local files
[05:43:49] Extra SSE boost OK.
[05:43:50] Writing local files
[05:43:50] Completed 0 out of 500000 steps (0 percent)
[05:53:27] Writing local files
[05:53:27] Completed 5000 out of 500000 steps (1 percent)
-----------------------------------------------------------------------
[21:35:21] Writing local files
[21:35:21] Completed 495000 out of 500000 steps (99 percent)
[21:44:58] Writing local files
[21:44:58] Completed 500000 out of 500000 steps (100 percent)
[21:44:59] Writing final coordinates.
[21:44:59] Past main M.D. loop
[21:44:59] Will end MPI now
[21:45:59]
[21:45:59] Finished Work Unit:
[21:45:59] - Reading up to 3727488 from "work/wudata_01.arc": Read 3727488
[21:45:59] - Reading up to 1944828 from "work/wudata_01.xtc": Read 1944828
[21:46:00] goefile size: 0
[21:46:00] logfile size: 25606
[21:46:00] Leaving Run
[21:46:01] - Writing 5703570 bytes of core data to disk...
[21:46:01] ... Done.
[21:46:01] - Failed to delete work/wudata_01.sas
[21:46:01] - Failed to delete work/wudata_01.goe
[21:46:01] Warning: check for stray files
[21:46:01] - Shutting down core
[21:48:01]
[21:48:01] Folding@home Core Shutdown: FINISHED_UNIT
[21:48:01]
[21:48:01] Folding@home Core Shutdown: FINISHED_UNIT
[21:48:08] CoreStatus = 7B (123)
[21:48:08] Client-core communications error: ERROR 0x7b
[21:48:08] This is a sign of more serious problems, shutting down.

Entre guillemet "celle là je me la met où (dans le C..)''
7im
Posts: 10189
Joined: Thu Nov 29, 2007 4:30 pm
Hardware configuration: Intel i7-4770K @ 4.5 GHz, 16 GB DDR3-2133 Corsair Vengence (black/red), EVGA GTX 760 @ 1200 MHz, on an Asus Maximus VI Hero MB (black/red), in a blacked out Antec P280 Tower, with a Xigmatek Night Hawk (black) HSF, Seasonic 760w Platinum (black case, sleeves, wires), 4 SilenX 120mm Case fans with silicon fan gaskets and silicon mounts (all black), a 512GB Samsung SSD (black), and a 2TB Black Western Digital HD (silver/black).
Location: Arizona
Contact:

Re: Nouveau client smp 6.22 MPICH

Post by 7im »

1 erreur dans 880 unités de travail n'est pas un problème nouveau client. Ceci est probablement une mauvaise unité de travail. Bravo Stanford pour faire un bon client!!!

0x7b erreurs sont généralement de l'évolution une mise en réseau tout en pliage, ou d'overclocking trop. Ne vous inquiétez pas de problème isolé 1 à moins qu'il ne se reproduise plus. Merci.
How to provide enough information to get helpful support
Tell me and I forget. Teach me and I remember. Involve me and I learn.
Xilikon
Posts: 155
Joined: Sun Dec 02, 2007 1:34 pm

Re: Nouveau client smp 6.22 MPICH

Post by Xilikon »

7im, using a translator make a answer which make no sense. Lemme try better :

1 erreur après 880 unités sont dans les normes pour ce client, tout le monde en a des errors à l'occasion, moi inclus. Ceci est peut-être un mauvais unité.

Ce que 7im essaie de dire dans une traduction botché est que les erreurs 0x7b sont généralement causés par un overclocking excessif ou d'un problème réseau. Ne t'en fais pas avec ceci à moins que ca se reproduit.
Image
uncle_fungus
Site Admin
Posts: 1288
Joined: Fri Nov 30, 2007 9:37 am
Location: Oxfordshire, UK

Re: Nouveau client smp 6.22 MPICH

Post by uncle_fungus »

Xilikon wrote:7im, using a translator make a answer which make no sense.
Peut-être, mais il a essayé au moins.
7im
Posts: 10189
Joined: Thu Nov 29, 2007 4:30 pm
Hardware configuration: Intel i7-4770K @ 4.5 GHz, 16 GB DDR3-2133 Corsair Vengence (black/red), EVGA GTX 760 @ 1200 MHz, on an Asus Maximus VI Hero MB (black/red), in a blacked out Antec P280 Tower, with a Xigmatek Night Hawk (black) HSF, Seasonic 760w Platinum (black case, sleeves, wires), 4 SilenX 120mm Case fans with silicon fan gaskets and silicon mounts (all black), a 512GB Samsung SSD (black), and a 2TB Black Western Digital HD (silver/black).
Location: Arizona
Contact:

Re: Nouveau client smp 6.22 MPICH

Post by 7im »

I didn't make any sense before the translation, so I'm not suprised at the results. ;)
How to provide enough information to get helpful support
Tell me and I forget. Teach me and I remember. Involve me and I learn.
uncle_fungus
Site Admin
Posts: 1288
Joined: Fri Nov 30, 2007 9:37 am
Location: Oxfordshire, UK

Re: Nouveau client smp 6.22 MPICH

Post by uncle_fungus »

lol, that never helps :)
Xilikon
Posts: 155
Joined: Sun Dec 02, 2007 1:34 pm

Re: Nouveau client smp 6.22 MPICH

Post by Xilikon »

The whole thread made no sense, even the OP despite my native french language skills :?
Image
Foxery
Posts: 118
Joined: Mon Mar 03, 2008 3:11 am
Hardware configuration: Intel Core2 Quad Q9300 (Intel P35 chipset)
Radeon 3850, 512MB model (Catalyst 8.10)
Windows XP, SP2
Location: Syracuse, NY

Re: Nouveau client smp 6.22 MPICH

Post by Foxery »

My own lost French skills aside, the question here is how the cores can throw an EUE after saying the unit has completed.

[21:48:01] Folding@home Core Shutdown: FINISHED_UNIT
[21:48:08] CoreStatus = 7B (123)
[21:48:08] Client-core communications error: ERROR 0x7b

I couldn't make out his bolded statement's meaning at all, even with a translator. toTOW?
Core2 Quad/Q9300, Radeon 3850/512MB (WinXP SP2)
7im
Posts: 10189
Joined: Thu Nov 29, 2007 4:30 pm
Hardware configuration: Intel i7-4770K @ 4.5 GHz, 16 GB DDR3-2133 Corsair Vengence (black/red), EVGA GTX 760 @ 1200 MHz, on an Asus Maximus VI Hero MB (black/red), in a blacked out Antec P280 Tower, with a Xigmatek Night Hawk (black) HSF, Seasonic 760w Platinum (black case, sleeves, wires), 4 SilenX 120mm Case fans with silicon fan gaskets and silicon mounts (all black), a 512GB Samsung SSD (black), and a 2TB Black Western Digital HD (silver/black).
Location: Arizona
Contact:

Re: Nouveau client smp 6.22 MPICH

Post by 7im »

Vista tends to do this with the MPICH client. Instead of the client stopping at the time of the error, it waits for the end of the WU. Lame.
How to provide enough information to get helpful support
Tell me and I forget. Teach me and I remember. Involve me and I learn.
toTOW
Site Moderator
Posts: 6309
Joined: Sun Dec 02, 2007 10:38 am
Location: Bordeaux, France
Contact:

Re: Nouveau client smp 6.22 MPICH

Post by toTOW »

J'avoue que j'ai pas vu cette erreur souvent ... alors d'après le Wiki http://fahwiki.net/index.php/CoreStatus_codes#7B , voici une liste possible des causes :

- overclocking
- changement d'état du réseau (perte Wifi, changement d'IP, branchement d'un cable, ...) pendant le traitement de la WU
- Windows Update forçant un reboot peut aussi provoquer cette erreur.
- barettes mémoire défaillantes.

Si c'est le deuxième cas (problème réseau), l'utilisation de la version DeinoMPI du client devrait résoudre le problème, elle est plus robuste dans ce cas.

How strange it is to write in French on this forum ;)
Foxery wrote:I couldn't make out his bolded statement's meaning at all, even with a translator. toTOW?
It's better that you didn't get it :roll: ... when I'll get back home with a decent connection, I'll try to find the video which explains this (it's from a movie, where a prisoner answer "In Iraq" (pronounced very closely to "in your ass") to a question which was something like 'wher did you hide these weapons ?" ... in French version of the movie, they didn't tranlate the "In Iraq" answer, but the other one :roll: ).
Image

Folding@Home beta tester since 2002. Folding Forum moderator since July 2008.
Mactin
Posts: 222
Joined: Sun Dec 02, 2007 1:08 pm
Location: Côte-des-Neiges, Montréal, Québec

Re: Nouveau client smp 6.22 MPICH

Post by Mactin »

Juste un petit commentaire en passant :
Depuis que j'ai mis à jour mon client à version 6.22, j'ai eu des erreurs sur mes deux premiers WU (p2665 et un p3065) et ensuite deux autres sans problèmes. Les deux erreurs se sont produites en arrêtant le client avec Ctrl-C et un redémarrer, dans les deux cas, ils ont recommencé à zéro.
Avec 5.91, j'avais eu une seule erreur (p2652) en 375 WU !

Mon système : Q6600, 2Go, Vista maison (sans overclocking*).

Comment dit-on overclocking en français ?
Image
John Naylor
Posts: 357
Joined: Mon Dec 03, 2007 4:36 pm
Hardware configuration: Q9450 OC @ 3.2GHz (Win7 Home Premium) - SMP2
E7500 OC @ 3.66GHz (Windows Home Server) - SMP2
i5-3750k @ 3.8GHz (Win7 Pro) - SMP2
Location: University of Birmingham, UK

Re: Nouveau client smp 6.22 MPICH

Post by John Naylor »

toTOW wrote:How strange it is to write in French on this forum ;)
Strange but useful :D what would we do without you?
Folding whatever I'm sent since March 2006 :) Beta testing since October 2006. www.FAH-Addict.net Administrator since August 2009.
toTOW
Site Moderator
Posts: 6309
Joined: Sun Dec 02, 2007 10:38 am
Location: Bordeaux, France
Contact:

Re: Nouveau client smp 6.22 MPICH

Post by toTOW »

On ne traduit pas overclocking en français ... on dit overclocking ;)

Peut être que le délais entre ton CTRL + C et ton reboot ont été trop court, ne laissant pas le temps aux cores de s'arrêter ... ou le temps au cache d'écrire le checkpoint proprement ...
Image

Folding@Home beta tester since 2002. Folding Forum moderator since July 2008.
Mactin
Posts: 222
Joined: Sun Dec 02, 2007 1:08 pm
Location: Côte-des-Neiges, Montréal, Québec

Re: Nouveau client smp 6.22 MPICH

Post by Mactin »

toTOW wrote:On ne traduit pas overclocking en français ... on dit overclocking ;)
J'ai fait ce que j'aurais du faire en partant... j'ai été consulter Le grand dictionaire terminologique de l'Office québécois de la langue française (http://www.oqlf.gouv.qc.ca/ressources/gdt.html).

En français on doit dire : surcadençage
Image
toTOW
Site Moderator
Posts: 6309
Joined: Sun Dec 02, 2007 10:38 am
Location: Bordeaux, France
Contact:

Re: Nouveau client smp 6.22 MPICH

Post by toTOW »

Oui mais personne ne l'utilise dans le petit monde des overclockeurs ... tout comme on parle souvent de vmod, vdrop, vcore ... et on confond souvent tension (français) et voltage (anglais).

Il suffit de voir les sites français sur le sujet ... (pour les québécois, je ne sais pas, je ne connais pas de sites hardware de votre province).
Image

Folding@Home beta tester since 2002. Folding Forum moderator since July 2008.
Post Reply