[SCore-users-jp] Re: [SCore-users] (no subject)

[Shinji Sumimoto]

Hi.

From: neural_shock ＠ e-mail.ru
Subject: Re: [SCore-users] (no subject)
Date: Mon, 29 Jul 2002 11:56:20 +0400
Message-ID: <3d44f524.5f33.0 ＠ e-mail.ru>

neural_shock> >Hi.
neural_shock> >
neural_shock> >Sorry for late response.
neural_shock> >
neural_shock> >From: neural_shock ＠ e-mail.ru
neural_shock> >Subject: [SCore-users] (no subject)
neural_shock> >Date: Wed, 24 Jul 2002 11:18:39 +0400
neural_shock> >Message-ID: <3d3e54cf.7f1.0 ＠ e-mail.ru>
neural_shock> >
neural_shock> >neural_shock> hello.
neural_shock> >neural_shock> 
neural_shock> >neural_shock> here are some logs of checpointing failure in english. see messages
neural_shock> on Jul 24
neural_shock> >neural_shock> in "messages" file in attached tar ball. there are also "gdbout2"
neural_shock> file, there
neural_shock> >neural_shock> are some debug information from kgdb. 
neural_shock> >neural_shock> 
neural_shock> >neural_shock> with respect, mike.
neural_shock> >
neural_shock> >Could you give us more information.
neural_shock> >
neural_shock> >1) Is the program (LU class A) working fine without check pointing?
neural_shock> >
neural_shock> >2)  How about class W of LU.
neural_shock> >
neural_shock> >Shinji.
neural_shock> >-----
neural_shock> >Shinji Sumimoto
neural_shock> hello.
neural_shock> 
neural_shock> 1. yes it works fine.
neural_shock> 2. i did not run lu class w. there are too few memory on my test machines even
neural_shock> for class b of this programm ( as far as i think. SCore's FEP does not print
neural_shock> "memory could be exhausted" but nodes begins swap pages too heavy when i run
neural_shock> lu.B.2 ).
neural_shock> 
neural_shock> with respect, mike. 

Are these true?

Class W is smaller than Class A.

Class S < W < A < B

Shinji.

------
Shinji Sumimoto, Fujitsu Labs
_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users