From nrcb ＠ streamline-computing.com  Mon Jul  1 07:18:34 2002
From: nrcb ＠ streamline-computing.com (Nick Birkett)
Date: Sun, 30 Jun 2002 23:18:34 +0100
Subject: [SCore-users-jp] [SCore-users] SCore and RH 7.3 kernel.
Message-ID: <200206302218.g5UMIYw23292@pecan.comlab.ox.ac.uk>

I see RedHat have put some shared memory enhancements (?) into their
kernel 2.4.18-3. 

As the shared memory performance fro 2.4 kernels is not good I had a go at applying
the SCore kernel patches, but had no success so far:

/linux-2.4.18-3/lib/lib.a /raid1/src/linux-2.4.18-3/arch/i386/lib/lib.a --end-group -o .tmp_vmlinux1
kernel/kernel.o(.kstrtab+0x1dd5): multiple definition of `__kstrtab_kmap_pte'
arch/i386/kernel/kernel.o(.kstrtab+0x922): first defined here
kernel/kernel.o(__ksymtab+0x760): multiple definition of `__ksymtab_kmap_prot'
arch/i386/kernel/kernel.o(__ksymtab+0x268): first defined here
kernel/kernel.o(__ksymtab+0x768): multiple definition of `__ksymtab_kmap_pte'
arch/i386/kernel/kernel.o(__ksymtab+0x260): first defined here
kernel/kernel.o(.kstrtab+0x1dbd): multiple definition of `__kstrtab_kmap_prot'
arch/i386/kernel/kernel.o(.kstrtab+0x939): first defined here
kernel/kernel.o(__ksymtab+0x1368): multiple definition of `__ksymtab_empty_zero_page'
arch/i386/kernel/kernel.o(__ksymtab+0xb0): first defined here
kernel/kernel.o(.kstrtab+0x4e81): multiple definition of `__kstrtab_empty_zero_page'
arch/i386/kernel/kernel.o(.kstrtab+0x270): first defined here
make[1]: *** [kallsyms] Error 1

Anyone else tried this ?

Nick
_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From kameyama ＠ pccluster.org  Mon Jul  1 11:27:35 2002
From: kameyama ＠ pccluster.org (=?iso-2022-jp?b?a2FtZXlhbWEgGyRCIXcbKEIgcGNjbHVzdGVyLm9yZw==?=)
Date: Mon, 01 Jul 2002 11:27:35 +0900
Subject: [SCore-users-jp] Re: [SCore-users] SCore and RH 7.3 kernel.
In-Reply-To: Your message of "Sun, 30 Jun 2002 23:18:34 JST."
             <200206302218.g5UMIYw23292@pecan.comlab.ox.ac.uk>
Message-ID: <200207010227.g612RZv22783@yl-dhcp18.is.s.u-tokyo.ac.jp>

In article <200206302218.g5UMIYw23292 ＠ pecan.comlab.ox.ac.uk> Nick Birkett <nrcb ＠ streamline-computing.com> wrotes:
> As the shared memory performance fro 2.4 kernels is not good I had a go at ap
> plying
> the SCore kernel patches, but had no success so far:
> 
> /linux-2.4.18-3/lib/lib.a /raid1/src/linux-2.4.18-3/arch/i386/lib/lib.a --end
> -group -o .tmp_vmlinux1
> kernel/kernel.o(.kstrtab+0x1dd5): multiple definition of `__kstrtab_kmap_pte'
> arch/i386/kernel/kernel.o(.kstrtab+0x922): first defined here
> kernel/kernel.o(__ksymtab+0x760): multiple definition of `__ksymtab_kmap_prot
> '
> arch/i386/kernel/kernel.o(__ksymtab+0x268): first defined here
> kernel/kernel.o(__ksymtab+0x768): multiple definition of `__ksymtab_kmap_pte'
> arch/i386/kernel/kernel.o(__ksymtab+0x260): first defined here
> kernel/kernel.o(.kstrtab+0x1dbd): multiple definition of `__kstrtab_kmap_prot
> '

kmap_pte and kmap_prot export symbol:
    when CONFIG_HIGHMEM is true in kernel/ksyms.c on redhat 7.3 kerenel.
    when CONFIG_PM_MEMORY is true in arch/i386/kernel/i386_ksyms.c on SCore patch.

> arch/i386/kernel/kernel.o(.kstrtab+0x939): first defined here
> kernel/kernel.o(__ksymtab+0x1368): multiple definition of `__ksymtab_empty_ze
> ro_page'
> arch/i386/kernel/kernel.o(__ksymtab+0xb0): first defined here
> kernel/kernel.o(.kstrtab+0x4e81): multiple definition of `__kstrtab_empty_zer
> o_page'
> arch/i386/kernel/kernel.o(.kstrtab+0x270): first defined here

empty_zero_page export symbol:
    always true in arch/i386/kernel/i386_ksyms.c on redhat 7.3 kerenel.
    when CONFIG_PM_MEMORY is true in  kernel/ksyms.c on SCore patch.


Please delete these lines:
  In kernel/ksyms.c
     EXPORT_SYMBOL(empty_zero_page);
  in arch/i386/kernel/i386_ksyms.c
     EXPORT_SYMBOL(kmap_pte);
     EXPORT_SYMBOL(kmap_prot);

                       from Kameyama Toyohisa
_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From neural_shock ＠ e-mail.ru  Fri Jul  5 19:13:19 2002
From: neural_shock ＠ e-mail.ru (=?iso-2022-jp?b?bmV1cmFsX3Nob2NrIBskQiF3GyhCIGUtbWFpbC5ydQ==?=)
Date: Fri, 5 Jul 2002 14:13:19 +0400
Subject: [SCore-users-jp] [SCore-users] (no subject)
Message-ID: <3d25713f.6ef3.0@e-mail.ru>

hello people. I am novic at using the Score cluster software. and i would like
to know more about it. in particular about pm2 library. especisally about its
abilities to store context of process.

my questions are simple, i think. here they are.

1. if there are in ( pm2 lib ) such capability ( to save task context ).
2. if the answer on 1st question is 'yes', how may i save it?
 
http://www.e-mail.ru

---
??????? ????? ?? DVD ?? ???? ?? 250?. ???????, ??????????? ??????????.
?????????? DVD ?????? ?? http://www.auction.ru/v2/Catalogue/Catalogue.asp?RID=73

_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From s-sumi ＠ bd6.so-net.ne.jp  Sun Jul  7 14:23:15 2002
From: s-sumi ＠ bd6.so-net.ne.jp (Shinji Sumimoto)
Date: Sun, 07 Jul 2002 14:23:15 +0900 (JST)
Subject: [SCore-users-jp] [SCore-users] (no subject)
In-Reply-To: <3d25713f.6ef3.0@e-mail.ru>
References: <3d25713f.6ef3.0@e-mail.ru>
Message-ID: <20020707.142315.730552295.s-sumi@bd6.so-net.ne.jp>

Hi.

From: neural_shock ＠ e-mail.ru
Subject: [SCore-users-jp] [SCore-users] (no subject)
Date: Fri, 5 Jul 2002 14:13:19 +0400
Message-ID: <3d25713f.6ef3.0 ＠ e-mail.ru>

neural_shock> hello people. I am novic at using the Score cluster software. and i would like
neural_shock> to know more about it. in particular about pm2 library. especisally about its
neural_shock> abilities to store context of process.
neural_shock> 
neural_shock> my questions are simple, i think. here they are.
neural_shock> 
neural_shock> 1. if there are in ( pm2 lib ) such capability ( to save task context ).
neural_shock> 2. if the answer on 1st question is 'yes', how may i save it?
neural_shock>  

PM supports only network contexts, but does not support process(task)
context. SCore supports checkpointing function in the combination of
PM network context store function and task context store function
provided by SCore-D originally. 

About PM network context function. Please refer the "PM 2.1 API": 

http://www.pccluster.org/score/dist/score/html/en/man/man3/PM.html

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


From kameyama ＠ pccluster.org  Mon Jul  8 22:14:28 2002
From: kameyama ＠ pccluster.org (=?iso-2022-jp?b?a2FtZXlhbWEgGyRCIXcbKEIgcGNjbHVzdGVyLm9yZw==?=)
Date: Mon, 08 Jul 2002 22:14:28 +0900
Subject: [SCore-users-jp] [SCore-users] (no subject)
In-Reply-To: Your message of "Wed, 01 Jan 1997 00:58:13 JST."
             <32C97055.1020708@e-mail.ru>
Message-ID: <200207081314.g68DESv15411@yl-dhcp18.is.s.u-tokyo.ac.jp>

In article <32C97055.1020708 ＠ e-mail.ru> neural_shock <neural_shock ＠ e-mail.ru> wrotes:
> but i still wish to know how SCore checkpoints tasks( memory, network 
> contexts, etc ). where can i find the description of checkpointing 
> process? and, please, do not refer to source code, may be i am stupid, 
> but i had not saw it( the scheme of checkpointing ) when looked through 
> the SCored's sources( there are too little comments :-(, and i have too 
> little experience in "reverse engineering" )

In source code, checkpoint execute in:
    score-src/SCore/scoredlib/user/ckpt*.[ch]
checkpoint test source programs are under:
    score-src/SCore/scored/test/mpc++/ckpt/

                       from Kameyama Toyohisa
_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From suga ＠ sse.co.jp  Tue Jul  9 13:32:04 2002
From: suga ＠ sse.co.jp (Sugano, Mitsukuni)
Date: Tue, 09 Jul 2002 13:32:04 +0900
Subject: [SCore-users-jp] MPICH/Compiler
Message-ID: <3D2A6744.48F6B374@sse.co.jp>

住商エレクトロニクスの菅野と申します。


SCoreのMPICHのデフォルトコンパイラは、GNUですが、
Intel等他のコンパイラを使用する際の手順に関して
質問させていただきたくメールさせていただきました。

以下、ご回答いただければ幸いです。

−−−

MPICHでintelコンパイラを使用したい場合の設定は、
概要として、以下の手順だと思うのですが、わから
無い部分がございますので、教えていただけますで
しょうか。

今回は、EITですべてのノードを設定しているという
前提です。

また、EITの場合とそれ以外の場合で、コンパイラ
を追加する方法は異なりますでしょうか？

さらに、はじめから、異なるコンパイラを使用する
ことがわかっている場合、EITやbinRPMを使用する
より、スクラッチからソースでインストールした
方が良いのでしょうか？


＊　MPICHでintelコンパイラを使うための手順

「/opt/score/etc/compilers/site」に、「intel」
　の行を追加
（GNUも入れる必要がありますか？）

ソースをリコンパイル

	# cd /opt/score

ここで、MPICHに必要なtarファイルは、mpi以外にどれに
なりますでしょうか？おそらく、mpiだけでは、configure
等不足するファイルがあると思います。

	# for tarfile in /mnt/cdrom/source.source/*.tar.gz
	# do
	# tar xzf $tarfile
	# done

	# cd score-src
	# ./configure --option=site
	# make

makeの後に以下は必要ありますか？
          # /opt/score/install/setup -score_server

また、計算ノードでも、リコンパイルする必要がありますか？

−−−

以上、よろしくお願いいたします。


From kameyama ＠ pccluster.org  Tue Jul  9 13:55:09 2002
From: kameyama ＠ pccluster.org (=?iso-2022-jp?b?a2FtZXlhbWEgGyRCIXcbKEIgcGNjbHVzdGVyLm9yZw==?=)
Date: Tue, 09 Jul 2002 13:55:09 +0900
Subject: [SCore-users-jp] MPICH/Compiler
In-Reply-To: Your message of "Tue, 09 Jul 2002 13:32:04 JST."
             <3D2A6744.48F6B374@sse.co.jp>
Message-ID: <200207090455.g694t9v19551@yl-dhcp18.is.s.u-tokyo.ac.jp>

亀山です.

In article <3D2A6744.48F6B374 ＠ sse.co.jp> "Sugano, Mitsukuni" <suga ＠ sse.co.jp> wrotes:
> また、EITの場合とそれ以外の場合で、コンパイラ
> を追加する方法は異なりますでしょうか？

基本的には変わりません.

> さらに、はじめから、異なるコンパイラを使用する
> ことがわかっている場合、EITやbinRPMを使用する
> より、スクラッチからソースでインストールした
> 方が良いのでしょうか？

多分, EIT で install してからのほうが楽だと思います.

> 「/opt/score/etc/compilers/site」に、「intel」
> 　の行を追加
> （GNUも入れる必要がありますか？）

GNU は不要です.

> ソースをリコンパイル
> 
> 	# cd /opt/score
> 
> ここで、MPICHに必要なtarファイルは、mpi以外にどれに
> なりますでしょうか？おそらく、mpiだけでは、configure
> 等不足するファイルがあると思います。

    http://www.pccluster.org/score/dist/score/html/ja/installation/download-source.html
の基本コンポーネントと moi で良いと思います.

> 
> 	# for tarfile in /mnt/cdrom/source.source/*.tar.gz
> 	# do
> 	# tar xzf $tarfile
> 	# done
> 
> 	# cd score-src
> 	# ./configure --option=site

標準で使用するのでしたら, --option=site は不要です.

> makeの後に以下は必要ありますか？
>           # /opt/score/install/setup -score_server
> 
> また、計算ノードでも、リコンパイルする必要がありますか？

EIT でインストールしていることを前提とするのでしたら不要です.

もう少し簡単には, site ファイルを編集したあと mpi だけを展開して
    # cd //opt/score/score-src/runtime/mpi
    # smake
    # smake install
でインストールできると思います.

                       from Kameyama Toyohisa


From suga ＠ sse.co.jp  Tue Jul  9 19:04:17 2002
From: suga ＠ sse.co.jp (Sugano, Mitsukuni)
Date: Tue, 09 Jul 2002 19:04:17 +0900
Subject: [SCore-users-jp] MPICH/Compiler
References: <200207090455.g694t9v19551@yl-dhcp18.is.s.u-tokyo.ac.jp>
Message-ID: <3D2AB521.C66B2A0E@sse.co.jp>

亀山様：

菅野です。
ご回答ありがとうございました。
今後ともよろしくお願いします。

kameyama ＠ pccluster.org wrote:
> 
> 亀山です.
> 
> In article <3D2A6744.48F6B374 ＠ sse.co.jp> "Sugano, Mitsukuni" <suga ＠ sse.co.jp> wrotes:
> > また、EITの場合とそれ以外の場合で、コンパイラ
> > を追加する方法は異なりますでしょうか？
> 
> 基本的には変わりません.
> 
> > さらに、はじめから、異なるコンパイラを使用する
> > ことがわかっている場合、EITやbinRPMを使用する
> > より、スクラッチからソースでインストールした
> > 方が良いのでしょうか？
> 
> 多分, EIT で install してからのほうが楽だと思います.
> 
> > 「/opt/score/etc/compilers/site」に、「intel」
> > 　の行を追加
> > （GNUも入れる必要がありますか？）
> 
> GNU は不要です.
> 
> > ソースをリコンパイル
> >
> >       # cd /opt/score
> >
> > ここで、MPICHに必要なtarファイルは、mpi以外にどれに
> > なりますでしょうか？おそらく、mpiだけでは、configure
> > 等不足するファイルがあると思います。
> 
>     http://www.pccluster.org/score/dist/score/html/ja/installation/download-source.html
> の基本コンポーネントと moi で良いと思います.
> 
> >
> >       # for tarfile in /mnt/cdrom/source.source/*.tar.gz
> >       # do
> >       # tar xzf $tarfile
> >       # done
> >
> >       # cd score-src
> >       # ./configure --option=site
> 
> 標準で使用するのでしたら, --option=site は不要です.
> 
> > makeの後に以下は必要ありますか？
> >           # /opt/score/install/setup -score_server
> >
> > また、計算ノードでも、リコンパイルする必要がありますか？
> 
> EIT でインストールしていることを前提とするのでしたら不要です.
> 
> もう少し簡単には, site ファイルを編集したあと mpi だけを展開して
>     # cd //opt/score/score-src/runtime/mpi
>     # smake
>     # smake install
> でインストールできると思います.
> 
>                        from Kameyama Toyohisa
> _______________________________________________
> SCore-users-jp mailing list
> SCore-users-jp ＠ pccluster.org
> http://www.pccluster.org/mailman/listinfo/score-users-jp


From iriya ＠ crc.co.jp  Tue Jul  9 20:46:30 2002
From: iriya ＠ crc.co.jp (=?ISO-2022-JP?B?GyRCRn5DKxsoQg==?=
 =?ISO-2022-JP?B?IBskQjJCMGwbKEI=?=)
Date: Tue, 09 Jul 2002 20:46:30 +0900
Subject: [SCore-users-jp] OpenMP-MPI
Message-ID: <200207091146.AA00205@crcpc79.crc.co.jp>

初めて投稿します入谷と申します.

本日ようやくSCore5.0.1のインストールに成功しました.
早速,FORTRAN で MPI と OpenMP の混合プログラムを作ったのですが
コンパイル方法がわかりません.
ドキュメント等ポインタだけでもかまいませんので
どなたか御教示いただけないでしょうか.

インストール状況：
EITで失敗したため,RPMパッケージにより手動インストールしました.
手順は,概ねインストールガイド通りです.
コンパイラは gcc, OpenMP は Omni OpenMP 


----------------------------------------
入谷 佳一 (Iriya Yoshikazu)
  (株)CRCソリューションズ  
   エネルギー技術部  システム安全チーム
   Tel.  03-5634-5803  Fax.03-5634-7338


From msato ＠ is.tsukuba.ac.jp  Wed Jul 10 00:25:24 2002
From: msato ＠ is.tsukuba.ac.jp (Mitsuhisa Sato)
Date: Wed, 10 Jul 2002 00:25:24 +0900
Subject: [SCore-users-jp] OpenMP-MPI
In-Reply-To: <200207091146.AA00205@crcpc79.crc.co.jp>
References: <200207091146.AA00205@crcpc79.crc.co.jp>
Message-ID: <20020710002524H.msato@is.tsukuba.ac.jp>

From: iriya ＠ crc.co.jp (入谷 佳一)
Subject: [SCore-users-jp] OpenMP-MPI
Date: Tue, 09 Jul 2002 20:46:30 +0900

> 初めて投稿します入谷と申します.
> 
> 本日ようやくSCore5.0.1のインストールに成功しました.
> 早速,FORTRAN で MPI と OpenMP の混合プログラムを作ったのですが
> コンパイル方法がわかりません.
> ドキュメント等ポインタだけでもかまいませんので
> どなたか御教示いただけないでしょうか.
> 
> インストール状況：
> EITで失敗したため,RPMパッケージにより手動インストールしました.
> 手順は,概ねインストールガイド通りです.
> コンパイラは gcc, OpenMP は Omni OpenMP 

Omni OpenMP担当者です。
まだ、omni OpenMPはmpichのドライバに組み込んだことはないので、わかりま
せんが、まずは、mpicc -v でリンクするパスをしらべて、omccでコンパイル、
必要なライブラリをリンクすればできるとおもいます。

いま、出張なので、詳しくはあとで。とりいそぎ。
さとう。


From iriya ＠ crc.co.jp  Wed Jul 10 09:56:57 2002
From: iriya ＠ crc.co.jp (=?ISO-2022-JP?B?GyRCRn5DKxsoQg==?=
 =?ISO-2022-JP?B?IBskQjJCMGwbKEI=?=)
Date: Wed, 10 Jul 2002 09:56:57 +0900
Subject: [SCore-users-jp] OpenMP-MPI
In-Reply-To: <20020710002524H.msato@is.tsukuba.ac.jp>
References: <20020710002524H.msato@is.tsukuba.ac.jp>
Message-ID: <200207100056.AA00206@crcpc79.crc.co.jp>

入谷です．

おせわになります．
>
>Omni OpenMP担当者です。
>まだ、omni OpenMPはmpichのドライバに組み込んだことはないので、わかりま
>せんが、まずは、mpicc -v でリンクするパスをしらべて、omccでコンパイル、
>必要なライブラリをリンクすればできるとおもいます。
>
>いま、出張なので、詳しくはあとで。とりいそぎ。
>さとう。

ありがとう御座います.早速試してみます.

----------------------------------------
入谷 佳一 (Iriya Yoshikazu)
  (株)CRCソリューションズ  
   エネルギー技術部  システム安全チーム
   Tel.  03-5634-5803  Fax.03-5634-7338


From iriya ＠ crc.co.jp  Wed Jul 10 14:38:43 2002
From: iriya ＠ crc.co.jp (=?ISO-2022-JP?B?GyRCRn5DKxsoQg==?=
 =?ISO-2022-JP?B?IBskQjJCMGwbKEI=?=)
Date: Wed, 10 Jul 2002 14:38:43 +0900
Subject: [SCore-users-jp] OpenMP-MPI
In-Reply-To: <20020710002524H.msato@is.tsukuba.ac.jp>
References: <20020710002524H.msato@is.tsukuba.ac.jp>
Message-ID: <200207100538.AA00207@crcpc79.crc.co.jp>

入谷です．

おせわになります．
>まずは、mpicc -v でリンクするパスをしらべて、omccでコンパイル、
>必要なライブラリをリンクすればできるとおもいます。
mpif77 -v で出てきたリストから,mpiのライブラリをリンクすると
以下のようになり,リンクに失敗してしまいました.
 
ompf77 -o a.out a.f  -static -fconserve-space \
  -L/opt/score5.0.0/mpi/mpich-1.2.0/i386-redhat7-linux2_4/lib \
  -lmpich -lmpichf

Compiling 'a.f'...
  MAIN a:
a.o: In function `__Omni_FortranEntryPoint':
a.o(.text+0xb0): undefined reference to `mpi_init_'
a.o(.text+0xcd): undefined reference to `mpi_comm_rank_'
a.o(.text+0xea): undefined reference to `mpi_comm_size_'
a.o(.text+0x155): undefined reference to `mpi_wtime_'
a.o(.text+0x17d): undefined reference to `mpi_barrier_'
a.o(.text+0x18a): undefined reference to `mpi_finalize_'
collect2: ld returned 1 exit status
Error 1

そこで,
nm libmpich.a |grep -i MPI_Init
などとしてlibmpich.a,libmpichf.aの mpi_initのシンボルを
見ると,どちらも

         U MPI_Init
00000000 W mpi_init__
00000000 T pmpi_init__

となっていました.
なにか指定方法が違うのでしょうか?

よろしくお願いいたします.

----------------------------------------
入谷 佳一 (Iriya Yoshikazu)
  (株)CRCソリューションズ  
   エネルギー技術部  システム安全チーム
   Tel.  03-5634-5803  Fax.03-5634-7338


From kameyama ＠ pccluster.org  Wed Jul 10 14:54:52 2002
From: kameyama ＠ pccluster.org (=?iso-2022-jp?b?a2FtZXlhbWEgGyRCIXcbKEIgcGNjbHVzdGVyLm9yZw==?=)
Date: Wed, 10 Jul 2002 14:54:52 +0900
Subject: [SCore-users-jp] OpenMP-MPI
In-Reply-To: Your message of "Wed, 10 Jul 2002 14:38:43 JST."
             <200207100538.AA00207@crcpc79.crc.co.jp>
Message-ID: <200207100554.g6A5srv25970@yl-dhcp18.is.s.u-tokyo.ac.jp>

亀山です.

本格的には Omni を optional compiler として
mpi を作り直す必要があるのですが...

In article <200207100538.AA00207 ＠ crcpc79.crc.co.jp> iriya ＠ crc.co.jp (入谷 佳一) wrotes:
> >まずは、mpicc -v でリンクするパスをしらべて、omccでコンパイル、
> >必要なライブラリをリンクすればできるとおもいます。
> mpif77 -v で出てきたリストから,mpiのライブラリをリンクすると
> 以下のようになり,リンクに失敗してしまいました.
>  
> ompf77 -o a.out a.f  -static -fconserve-space \
>   -L/opt/score5.0.0/mpi/mpich-1.2.0/i386-redhat7-linux2_4/lib \
>   -lmpich -lmpichf
> 
> Compiling 'a.f'...
>   MAIN a:
> a.o: In function `__Omni_FortranEntryPoint':
> a.o(.text+0xb0): undefined reference to `mpi_init_'
> a.o(.text+0xcd): undefined reference to `mpi_comm_rank_'
> a.o(.text+0xea): undefined reference to `mpi_comm_size_'
> a.o(.text+0x155): undefined reference to `mpi_wtime_'
> a.o(.text+0x17d): undefined reference to `mpi_barrier_'
> a.o(.text+0x18a): undefined reference to `mpi_finalize_'
> collect2: ld returned 1 exit status
> Error 1

Omni の Fortran compiler は Fortran の呼び出しに _ を使用するようです.

>          U MPI_Init
> 00000000 W mpi_init__
> 00000000 T pmpi_init__

これに対して, default の gcc の mpi は Fortran の呼び出しに __ を
使用します.

この件に関しましては
    /opt/score5.0.0/mpi/mpich-1.2.0/i386-redhat7-linux2_4/lib
の代わりに
    /opt/score5.0.0/mpi/mpich-1.2.0/i386-redhat7-linux2_4_gnu1ul/lib
(g77 で -second-underscore option をつけたときの環境です.)
を使用すればクリアできると思います.

更に SCore 関連の library
    -L/opt/score5.0.0/lib/i386-redhat7-linux2_4 -lscoreusr -lscorecommon -lpm -lscwrap
も指定する必要があります.

                       from Kameyama Toyohisa


From iriya ＠ crc.co.jp  Wed Jul 10 16:19:13 2002
From: iriya ＠ crc.co.jp (=?ISO-2022-JP?B?GyRCRn5DKxsoQg==?=
 =?ISO-2022-JP?B?IBskQjJCMGwbKEI=?=)
Date: Wed, 10 Jul 2002 16:19:13 +0900
Subject: [SCore-users-jp] OpenMP-MPI
In-Reply-To: <200207100554.g6A5srv25970@yl-dhcp18.is.s.u-tokyo.ac.jp>
References: <200207100554.g6A5srv25970@yl-dhcp18.is.s.u-tokyo.ac.jp>
Message-ID: <200207100719.AA00208@crcpc79.crc.co.jp>

入谷です．

ありがとう御座います.少し賢くなりました.

>Omni の Fortran compiler は Fortran の呼び出しに _ を使用するようです.
>これに対して, default の gcc の mpi は Fortran の呼び出しに __ を
>使用します.
>
>この件に関しましては
>    /opt/score5.0.0/mpi/mpich-1.2.0/i386-redhat7-linux2_4/lib
>の代わりに
>    /opt/score5.0.0/mpi/mpich-1.2.0/i386-redhat7-linux2_4_gnu1ul/lib
>(g77 で -second-underscore option をつけたときの環境です.)
>を使用すればクリアできると思います.

ところが

/opt/score5.0.0/mpi/mpich-1.2.0/i386-redhat7-linux2_4_gnu1ul/lib
を指定しても変化がありませんでした.
試しに i386-redhat7-linux2_4_gnu1ul/lib の libmpi.a のシンボルを nm で
調べるとi386-redhat7-linux2_4/lib と同じシンボルでした.
2つのライブラリの rm の結果をファイルにとって diff をかけると
以下の1行しか違っていませんでした.
2477c2477
< 000001e0 r .LC14
---
> 00000220 r .LC14

ライブラリを作り直さなくてはならないのでしょうか...

----------------------------------------
入谷 佳一 (Iriya Yoshikazu)
  (株)CRCソリューションズ  
   エネルギー技術部  システム安全チーム
   Tel.  03-5634-5803  Fax.03-5634-7338


From kameyama ＠ pccluster.org  Wed Jul 10 16:37:19 2002
From: kameyama ＠ pccluster.org (=?iso-2022-jp?b?a2FtZXlhbWEgGyRCIXcbKEIgcGNjbHVzdGVyLm9yZw==?=)
Date: Wed, 10 Jul 2002 16:37:19 +0900
Subject: [SCore-users-jp] OpenMP-MPI
In-Reply-To: Your message of "Wed, 10 Jul 2002 16:19:13 JST."
             <200207100719.AA00208@crcpc79.crc.co.jp>
Message-ID: <200207100737.g6A7bJv26350@yl-dhcp18.is.s.u-tokyo.ac.jp>

亀山です.

In article <200207100719.AA00208 ＠ crcpc79.crc.co.jp> iriya ＠ crc.co.jp (入谷 佳一) wrotes:
> ところが
> 
> /opt/score5.0.0/mpi/mpich-1.2.0/i386-redhat7-linux2_4_gnu1ul/lib
> を指定しても変化がありませんでした.
> 試しに i386-redhat7-linux2_4_gnu1ul/lib の libmpi.a のシンボルを nm で
> 調べるとi386-redhat7-linux2_4/lib と同じシンボルでした.

すみません.
そのようですね.

> ライブラリを作り直さなくてはならないのでしょうか...

そのようです.
以下の手順で mpi を作り直してください.
(基本的には MPICH/Compiler で説明したのと変わりません.)
1. mpi のソースを入手して /opt/score のしたで展開する.
2. /opt/score/etc/compilers/site に omni を追加する.
   多分
       omni  /opt/omni/bin/omcc  - /opt/omni/bin/omf77
   となると思います.
3. mpi をコンパイル
    # cd //opt/score/score-src/runtime/mpi
    # smake 2>&1 | tee make.log
    # smake install 2>&1 tee makeinstall.log

omni 版 mpi は
    /opt/score/score-src/runtime/mpi/mpich-1.2.0/build.i386-redhat7-linux2_4_omni
でコンパイルされます.
mpi のコンパイルは omcc/omf77 ではなく, scorecc/scoref77 でコンパイルする
ことになります.
もし, mpi のコンパイルに失敗してしまったら log を送ってください.

うまく install できtれば mpicc/mpif77 に -compiler omni をつけることにより
コンパイルできます.
    % mpif77 -compiler omni foo.f
のようになります.

よろしくお願いします.

                       from Kameyama Toyohisa


From kameyama ＠ pccluster.org  Wed Jul 10 20:54:25 2002
From: kameyama ＠ pccluster.org (=?iso-2022-jp?b?a2FtZXlhbWEgGyRCIXcbKEIgcGNjbHVzdGVyLm9yZw==?=)
Date: Wed, 10 Jul 2002 20:54:25 +0900
Subject: [SCore-users-jp] Re: =?ISO-2022-JP?B?bXBpGyRCJTMlcyVRJSQlazw6R1QbKEI=?=
In-Reply-To: Your message of "Wed, 10 Jul 2002 17:53:47 JST."
             <200207100853.AA00209@crcpc79.crc.co.jp>
Message-ID: <200207101154.g6ABsPv27276@yl-dhcp18.is.s.u-tokyo.ac.jp>

亀山です.

In article <200207100853.AA00209 ＠ crcpc79.crc.co.jp> iriya ＠ crc.co.jp (入谷 佳一) wrotes:
>     # smake 2>&1 | tee make.log
> で失敗してしまいました.
> お手数ですが,よろしくお願いいたします.

いくつか問題がありました.
1. omni では当然 pthread を使用するのですが, SCore 環境では checkpoint のため,
   特別の pthread を使用する必要があります.
   これを使用するには pthread のあとに -lscwrap を指定する必要があります,
   とりあえず, link するためには
       /opt/omni/lib/openmp/gcc/lib/openmp/libexec/omniDriver
   の genSystemLibrary() の最後の
       sysLibs="-lpthread";;
   を
      sysLibs="-lpthread -lscwrap";;
   に変更する必要があります.
   (但し, これを行うと, 通常の環境での Omni が使用できなくなります.

2. source を full path で指定したとき, object file が current directory に
   できない.
       % omf77 -c /tmp/a.f
   とすると a.o は current directory にできずに /tmp/a.o ができます.
   これは mpi のコンパイル環境の仮定とは違うため, うまく library などが
   できません.
   とりあえず, 以下を実行してください.
   (directory 以外はやっていることは変わりません.)
       # /opt/score/score-src/runtime/mpi/mpich-1.2.0/src
       # ./configure -arch=LINUX -device=ch_score -mpe \
	 -cc=/opt/score5.0.0/bin/scorecc -fc=/opt/score5.0.0/bin/scoref77 \
	 -optcc=-O4 -optf77=-O -cflags=-compiler=omni -fflags=-compiler=omni \
	 -nof90 -noc++ \
	 -prefix=/opt/score5.0.0/mpi/mpich-1.2.0/i386-redhat7-linux2_4_omni \
	 -comm=zerocopy
       # make
       # make install
   (Fortran のサンプルプログラムのコンパイルに失敗しますが, とりあえず
   無視してください. 3. を参照してください.)

3. Fortran の include path の指定が -I ではできない.
   2. のコンパイルの仮定でコンパイルされる Fortran サンプルプログラムには
	include 'mpif.h'
   の指定があるのですが, これをみつけてくれません.
   Fortran を使用するときは compile する current directory に
       /opt/score5.0.0/mpi/mpich-1.2.0/i386-redhat7-linux2_4_omni/include/mpif.h  をコピーしてください.

すべて一時しのぎばかりで申し訳ありません.

                       from Kameyama Toyohisa


From s-sumi ＠ bd6.so-net.ne.jp  Wed Jul 10 23:15:23 2002
From: s-sumi ＠ bd6.so-net.ne.jp (Shinji Sumimoto)
Date: Wed, 10 Jul 2002 23:15:23 +0900 (JST)
Subject: [SCore-users-jp] [SCore-users] (no subject)
In-Reply-To: <32C97055.1020708@e-mail.ru>
References: <32C97055.1020708@e-mail.ru>
Message-ID: <20020710.231523.730553170.s-sumi@bd6.so-net.ne.jp>

Hi.

From: neural_shock <neural_shock ＠ e-mail.ru>
Subject: [SCore-users-jp] [SCore-users] (no subject)
Date: Wed, 01 Jan 1997 00:58:13 +0500
Message-ID: <32C97055.1020708 ＠ e-mail.ru>
neural_shock> thanks, Shinji.
neural_shock> 
neural_shock> but i still wish to know how SCore checkpoints tasks( memory, network 
neural_shock> contexts, etc ). where can i find the description of checkpointing 
neural_shock> process? and, please, do not refer to source code, may be i am stupid, 
neural_shock> but i had not saw it( the scheme of checkpointing ) when looked through 
neural_shock> the SCored's sources( there are too little comments :-(, and i have too 
neural_shock> little experience in "reverse engineering" )
neural_shock> 
neural_shock> with hope on answer, mike.

Sorry, mike..

But there is no documents (descriptions) about details of
checkpointing except source codes.  The idea is not difficult, but
implementation is too complicate to describe on E-mail.

The node is score-src/SCore/scoredlib/usr/ckpt*.[ch].

Shinji.
-----
E-Mail: s-sumi ＠ bd6.so-net.ne.jp
_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From hori ＠ swimmy-soft.com  Thu Jul 11 10:32:14 2002
From: hori ＠ swimmy-soft.com (Atsushi HORI)
Date: Thu, 11 Jul 2002 10:32:14 +0900
Subject: [SCore-users-jp] [SCore-users] Re: checkpointing
In-Reply-To: <32C97055.1020708@e-mail.ru>
References: <32C97055.1020708@e-mail.ru>
Message-ID: <3109228334.hori0001@mail.bestsystems.co.jp>

Hi, Mike,

#subject is changed.

I am Atsushi Hori and I designed and wrote (still writing) SCore-D 
staff.

>but i still wish to know how SCore checkpoints tasks( memory, network 
>contexts, etc ). where can i find the description of checkpointing 
>process? and, please, do not refer to source code, may be i am stupid, 
>but i had not saw it( the scheme of checkpointing ) when looked through 
>the SCored's sources( there are too little comments :-(, and i have too 
>little experience in "reverse engineering" )
>
>with hope on answer, mike.

Well, SCore-D is very complicated and I am sure nobody else can 
understand :-)

The basic idea of SCore-D checkpointing comes from Network 
Preemption. This idea is applied to gang scheduling and checkpointing 
in SCore-D.

In the current OSes, communication is thought to be not so frequent 
and everytime user wants to communicate it must issue system call. We 
thought the frequency of communication in parallel computation is 
much higher than that of distributed computing, and we designed to 
allow user processes to access network interface without any 
systemcalls, but when user processes are switched the network context 
is saved and restored. The network context includes the status of 
network interface hardware (NIC) and the messages in a network.

Well, in checkpointing, the 'whole context' of user's parallel 
process (a set of processes derived from the same program) consists 
of contexts of Unix (Linux) processes and the network context. Once 
network preemption is implemented, then the process contexts and 
network contexts are saved into disks, and restored when a user 
parallel process is restarted from the checkpoint.

The saving and restoring of the process context is not a new but a 
well-known technique and I am sure you can find some papers via web 
search engines.

I attached the paper presented in SC98 on the network preemption.

----
Atsushi HORI
Swimmy Software, Inc.

-------------- next part --------------
テキスト形式以外の添付ファイルを保管しました...
ファイル名: HORI98.PDF
型:         application/octet-stream
サイズ:     300411 バイト
説明:       無し
URL:        <http://new1.pccluster.org/pipermail/score-users-jp/attachments/20020711/5570615c/attachment.obj>

From iriya ＠ crc.co.jp  Thu Jul 11 10:42:16 2002
From: iriya ＠ crc.co.jp (=?ISO-2022-JP?B?GyRCRn5DKxsoQg==?=
 =?ISO-2022-JP?B?IBskQjJCMGwbKEI=?=)
Date: Thu, 11 Jul 2002 10:42:16 +0900
Subject: [SCore-users-jp] Re: =?ISO-2022-JP?B?bXBpGyRCJTMlcyVRJSQlazw6R1QbKEI=?=
In-Reply-To: <200207101154.g6ABsPv27276@yl-dhcp18.is.s.u-tokyo.ac.jp>
References: <200207101154.g6ABsPv27276@yl-dhcp18.is.s.u-tokyo.ac.jp>
Message-ID: <200207110142.AA00210@crcpc79.crc.co.jp>

入谷です．

MPI＋omni OpenMPの件,お教えいただいた方法で
コンパイル・実行できました.
大変御世話になりました.
ありがとう御座いました.

>いくつか問題がありました.
>1. omni では当然 pthread を使用するのですが, SCore 環境では checkpoint のため,
>   特別の pthread を使用する必要があります.
>   これを使用するには pthread のあとに -lscwrap を指定する必要があります,
>   とりあえず, link するためには
>       /opt/omni/lib/openmp/gcc/lib/openmp/libexec/omniDriver
>   の genSystemLibrary() の最後の
>       sysLibs="-lpthread";;
>   を
>      sysLibs="-lpthread -lscwrap";;
>   に変更する必要があります.
>   (但し, これを行うと, 通常の環境での Omni が使用できなくなります.
>
>2. source を full path で指定したとき, object file が current directory に
>   できない.
>       % omf77 -c /tmp/a.f
>   とすると a.o は current directory にできずに /tmp/a.o ができます.
>   これは mpi のコンパイル環境の仮定とは違うため, うまく library などが
>   できません.
>   とりあえず, 以下を実行してください.
>   (directory 以外はやっていることは変わりません.)
>       # /opt/score/score-src/runtime/mpi/mpich-1.2.0/src
>       # ./configure -arch=LINUX -device=ch_score -mpe \
>	 -cc=/opt/score5.0.0/bin/scorecc -fc=/opt/score5.0.0/bin/scoref77 \
>	 -optcc=-O4 -optf77=-O -cflags=-compiler=omni -fflags=-compiler=omni \
>	 -nof90 -noc++ \
>	 -prefix=/opt/score5.0.0/mpi/mpich-1.2.0/i386-redhat7-linux2_4_omni \
>	 -comm=zerocopy
>       # make
>       # make install
>   (Fortran のサンプルプログラムのコンパイルに失敗しますが, とりあえず
>   無視してください. 3. を参照してください.)
>
>3. Fortran の include path の指定が -I ではできない.
>   2. のコンパイルの仮定でコンパイルされる Fortran サンプルプログラムには
>	include 'mpif.h'
>   の指定があるのですが, これをみつけてくれません.
>   Fortran を使用するときは compile する current directory に
>       /opt/score5.0.0/mpi/mpich-1.2.0/i386-redhat7-linux2_4_omni/include/mpif.h  をコピーしてください.
>
>すべて一時しのぎばかりで申し訳ありません.
>
>                       from Kameyama Toyohisa

----------------------------------------
入谷 佳一 (Iriya Yoshikazu)
  (株)CRCソリューションズ  
   エネルギー技術部  システム安全チーム
   Tel.  03-5634-5803  Fax.03-5634-7338


From iriya ＠ crc.co.jp  Thu Jul 11 12:10:13 2002
From: iriya ＠ crc.co.jp (=?ISO-2022-JP?B?GyRCRn5DKxsoQg==?=
 =?ISO-2022-JP?B?IBskQjJCMGwbKEI=?=)
Date: Thu, 11 Jul 2002 12:10:13 +0900
Subject: [SCore-users-jp] =?ISO-2022-JP?B?U0NvcmU1LjAuMRskQiUkJXMlOSVIITwlazUtGyhK?=
 =?ISO-2022-JP?B?GyRCTz8bKEI=?=
Message-ID: <200207110310.AA00211@crcpc79.crc.co.jp>

入谷です．

Scoreインストールの記録です.
手動インストールの主要な問題点はMLの過去ログに
載っているので新しい情報はありませんが,ご報告まで.

----------------------------
環境：
  ノーザンライツ(株) NL1200 x3
  チップセット：ServerWorks ServerSetIII 
  LANチップ：Intel 82559
  CPU：PentiumIII 933MHz x2
  Memory:1GB
  OS:RedHatLinux7.2

PC Cluster Consortium のサイトから
SCore5.0.1のISO9660イメージを取得し,インストールCDROMを作成

EITインストール：失敗
  「Cluster Setup」でcompute host機にFDを挿入して
  bootするとcompute hostではイメージを展開した後
  画面がクリアされ,何も表示されない.
  「Cluster Setup」にmac address等の情報が表示されない

手動インストール：
「SCore Cluster System Software インストールガイド」の
「RPMファイルによるインストール」にそってインストール

インストールガイド通りでなかった点は以下のとおり

 1.SCore Linux Kernel のインストレーション
   ・/etc/lilo.confのカーネルイメージ名
       *-2.4.18-2SCOREsmp
       *-2.4.18-2SCORE
 2.SCoreシステムインストール
   ・./bininstall は続けて2回実行しないと
     全てのファイルがコピーされなかった.
   ・scorehosts.dbのサンプルファイルの位置
     doc/html/installation/ -> doc/html/en/installation/
   ・ msgbserb 始動後 /var/log/msgbserb.out ファイルが存在しない
   ・pm-ethernet.confの作成
      # /opt/score/deploy/mkpmethernetconf -speed 100 pm-udp.conf
      Usage: mkpmethernetconf [options] -g group [output_file]
          or mkpmethernetconf [options] host_list_file [output_file]
     となるので
      # /opt/score/deploy/mkpmethernetconf -speed 100 -g pcc
     で作成した.
3.その他
  ・server host と compute host を兼用させるには
    server host に ./bininstall -compute から始めて,すべての
    compute host の設定を実施しなければならない.


  


----------------------------------------
入谷 佳一 (Iriya Yoshikazu)
  (株)CRCソリューションズ  
   エネルギー技術部  システム安全チーム
   Tel.  03-5634-5803  Fax.03-5634-7338


From hori ＠ swimmy-soft.com  Thu Jul 11 12:50:53 2002
From: hori ＠ swimmy-soft.com (Atsushi HORI)
Date: Thu, 11 Jul 2002 12:50:53 +0900
Subject: [SCore-users-jp] =?ISO-2022-JP?B?U0NvcmU1LjAuMRskQiUkJXMlOSVIITwlazUtTz8bKEo=?=
In-Reply-To: <200207110310.AA00211@crcpc79.crc.co.jp>
References: <200207110310.AA00211@crcpc79.crc.co.jp>
Message-ID: <3109236653.hori0000@mail.bestsystems.co.jp>

堀@スイミー・ソフトウェアです．

>EITインストール：失敗
>  「Cluster Setup」でcompute host機にFDを挿入して
>  bootするとcompute hostではイメージを展開した後
>  画面がクリアされ,何も表示されない.
>  「Cluster Setup」にmac address等の情報が表示されない

私も RedHat 7.2 で EIT が失敗（DHCP もどき（？）がうまく動いていない？
）という報告を受けています．RedHat 7.3 だと動いたそうです．

----
堀 敦史（ほり あつし）
スイミー・ソフトウェア株式会社



From ishikawa ＠ is.s.u-tokyo.ac.jp  Thu Jul 11 13:07:28 2002
From: ishikawa ＠ is.s.u-tokyo.ac.jp (Yutaka Ishikawa)
Date: Thu, 11 Jul 2002 13:07:28 +0900 (JST)
Subject: [SCore-users-jp] Re: [SCore-users-jp]
 =?iso-2022-jp?B?U0NvcmU1LjAuMRskQiUkJXMlOSVIITwlazUtTz8bKEI=?=
In-Reply-To: <3109236653.hori0000@mail.bestsystems.co.jp>
References: <200207110310.AA00211@crcpc79.crc.co.jp>
	<3109236653.hori0000@mail.bestsystems.co.jp>
Message-ID: <20020711.130728.884014539.ishikawa@is.s.u-tokyo.ac.jp>

入谷様、堀様、

サーバマシンにネットワークが2枚刺さっていて、クラスタ側にはeth1でつながっ
ているというような状況ではないでしょうか？

＃でも、RedHat 7.3では動くというのはちょっと違うような。

石川
From: Atsushi HORI <hori ＠ swimmy-soft.com>
Subject: Re: [SCore-users-jp] SCore5.0.1インストール記録
Date: Thu, 11 Jul 2002 12:50:53 +0900

> 堀@スイミー・ソフトウェアです．
> 
> >EITインストール：失敗
> >  「Cluster Setup」でcompute host機にFDを挿入して
> >  bootするとcompute hostではイメージを展開した後
> >  画面がクリアされ,何も表示されない.
> >  「Cluster Setup」にmac address等の情報が表示されない
> 
> 私も RedHat 7.2 で EIT が失敗（DHCP もどき（？）がうまく動いていない？
> ）という報告を受けています．RedHat 7.3 だと動いたそうです．
> 
> ----
> 堀 敦史（ほり あつし）
> スイミー・ソフトウェア株式会社
> 
> _______________________________________________
> SCore-users-jp mailing list
> SCore-users-jp ＠ pccluster.org
> http://www.pccluster.org/mailman/listinfo/score-users-jp


From iriya ＠ crc.co.jp  Thu Jul 11 13:29:54 2002
From: iriya ＠ crc.co.jp (=?ISO-2022-JP?B?GyRCRn5DKxsoQg==?=
 =?ISO-2022-JP?B?IBskQjJCMGwbKEI=?=)
Date: Thu, 11 Jul 2002 13:29:54 +0900
Subject: [SCore-users-jp] =?ISO-2022-JP?B?U0NvcmU1LjAuMRskQiUkGyhK?=
 =?ISO-2022-JP?B?GyRCJXMlOSVIITwlazUtTz8bKEI=?=
In-Reply-To: <20020711.130728.884014539.ishikawa@is.s.u-tokyo.ac.jp>
References: <20020711.130728.884014539.ishikawa@is.s.u-tokyo.ac.jp>
Message-ID: <200207110429.AA00213@crcpc79.crc.co.jp>

入谷です．

>サーバマシンにネットワークが2枚刺さっていて、クラスタ側にはeth1でつながっ
>ているというような状況ではないでしょうか？
LANはオンボードで2つですが,使用しているのは全てのマシンでeth0のみです.

>> 
>> 私も RedHat 7.2 で EIT が失敗（DHCP もどき（？）がうまく動いていない？
>> ）という報告を受けています．RedHat 7.3 だと動いたそうです．

東清システム・インテグレーションズの土屋様からも,FDが使うDHCPが
うまく動いていないのではないかと指摘されました.その際には,
/etc/hosts に,このDHCPが使うアドレスを設定するよう御教示いただき
dhcp0という名前を追加したのですが,改善しませんでした.

----------------------------------------
入谷 佳一 (Iriya Yoshikazu)
  (株)CRCソリューションズ  
   エネルギー技術部  システム安全チーム
   Tel.  03-5634-5803  Fax.03-5634-7338


From hori ＠ swimmy-soft.com  Thu Jul 11 15:46:54 2002
From: hori ＠ swimmy-soft.com (Atsushi HORI)
Date: Thu, 11 Jul 2002 15:46:54 +0900
Subject: [SCore-users-jp] Re: [SCore-users-jp]=?ISO-2022-JP?B?U0NvcmU1LjAuMRskQiUkJXMlOSVIITwlazUtTz8bKEo=?=
In-Reply-To: <20020711.130728.884014539.ishikawa@is.s.u-tokyo.ac.jp>
References: <200207110310.AA00211@crcpc79.crc.co.jp>
Message-ID: <3109247214.hori0001@mail.bestsystems.co.jp>

堀@スイミー・ソフトウェアです．

>サーバマシンにネットワークが2枚刺さっていて、クラスタ側にはeth1でつながっ
>ているというような状況ではないでしょうか？

多分そうだと思います（未確認）．4.2.1 でもサーバに２枚刺さっていると片
方を ifdown しないとうまく動きませんでした（関係あるか？）．

>＃でも、RedHat 7.3では動くというのはちょっと違うような。

これも未確認情報です．

----
堀 敦史（ほり あつし）
スイミー・ソフトウェア株式会社



From ishikawa ＠ is.s.u-tokyo.ac.jp  Thu Jul 11 19:40:34 2002
From: ishikawa ＠ is.s.u-tokyo.ac.jp (Yutaka Ishikawa)
Date: Thu, 11 Jul 2002 19:40:34 +0900 (JST)
Subject: [SCore-users-jp] Re: [SCore-users-jp]
 =?iso-2022-jp?B?U0NvcmU1LjAuMRskQiUkJXMlOSVIITwlazUtTz8bKEI=?=
In-Reply-To: <200207110429.AA00213@crcpc79.crc.co.jp>
References: <20020711.130728.884014539.ishikawa@is.s.u-tokyo.ac.jp>
	<200207110429.AA00213@crcpc79.crc.co.jp>
Message-ID: <20020711.194034.1025211521.ishikawa@is.s.u-tokyo.ac.jp>

入谷様、堀様、score-usersの皆様、

> 東清システム・インテグレーションズの土屋様からも,FDが使うDHCPが
> うまく動いていないのではないかと指摘されました.その際には,
> /etc/hosts に,このDHCPが使うアドレスを設定するよう御教示いただき
> dhcp0という名前を追加したのですが,改善しませんでした.

SCore 5.0から仕組みを変えていますので、これは意味をなしていません。
eitのCluster Setup画面で Show Log というボタンがあります。
今度、うまくいかなかった時に、Show Logボタンをクリックして、ログを
送って頂けると幸いです。

石川


From iriya ＠ crc.co.jp  Fri Jul 12 18:22:17 2002
From: iriya ＠ crc.co.jp (=?ISO-2022-JP?B?GyRCRn5DKxsoQg==?=
 =?ISO-2022-JP?B?IBskQjJCMGwbKEI=?=)
Date: Fri, 12 Jul 2002 18:22:17 +0900
Subject: [SCore-users-jp] =?ISO-2022-JP?B?b21uaRskQiROQCk4QhsoQj8=?=
Message-ID: <200207120922.AA00214@crcpc79.crc.co.jp>

入谷と申します．

Score環境でMPI-OpenMPでのプログラムをつくるために
昨日からomni Fortran コンパイラを使い始めました.
気がついた点を報告します. 

ところで,こうした情報はどこかで見られるのでしょうか?
webやscoreのMLの過去ログを探しましたが見つけられませんでした.


1. open文のファイル名の指定の時点で文字列を結合できない

    open(io, file=head//'.out')
  とすると
    open: illegal unit number
    apparent state: internal I/O
    lately writing direct unformatted external IO
    <0> SCORE: Program signaled (SIGABRT).
  となる.
    fname = head//'.out'
    open(io, file=fname)
  で対応.

2.サブルーチンで大きな配列をローカルに取れない
      program main
      call sub1()
      stop
      end

      subroutine sub1()
      integer ii(600000)
      ii(1) = 1
      return
      end

  は Segmentation fault となる.
      integer ii(600000)
      save ii
  のようにsaveが必要.
  -static や -fno-automatic は効かなかった.

3. !によるコメント
  7カラム以降から始まる!によるコメントだけの行は parse error となる.
  実行文の後ろの!によるコメントはOK

4. 乱数
  なにもライブラリを指定しないと rand() 等の関数が呼べなくなりました.




----------------------------------------
入谷 佳一 (Iriya Yoshikazu)
  (株)CRCソリューションズ  
   エネルギー技術部  システム安全チーム
   Tel.  03-5634-5803  Fax.03-5634-7338


From msato ＠ is.tsukuba.ac.jp  Sat Jul 13 03:07:25 2002
From: msato ＠ is.tsukuba.ac.jp (Mitsuhisa Sato)
Date: Sat, 13 Jul 2002 03:07:25 +0900
Subject: [SCore-users-jp] =?iso-2022-jp?B?b21uaRskQiROQCk4QhsoQj8=?=
In-Reply-To: <200207120922.AA00214@crcpc79.crc.co.jp>
References: <200207120922.AA00214@crcpc79.crc.co.jp>
Message-ID: <20020713030725Y.msato@is.tsukuba.ac.jp>

入谷 様、

From: iriya ＠ crc.co.jp (入谷 佳一)
Subject: [SCore-users-jp] omniの制限?
Date: Fri, 12 Jul 2002 18:22:17 +0900

> 入谷と申します．
> 
> Score環境でMPI-OpenMPでのプログラムをつくるために
> 昨日からomni Fortran コンパイラを使い始めました.
> 気がついた点を報告します. 

Feed backありがとうございます。

> ところで,こうした情報はどこかで見られるのでしょうか?
> webやscoreのMLの過去ログを探しましたが見つけられませんでした.

レポートされたバグに関してはできるだけ対応するつもりですので、よろしく
お願いします。

> 1. open文のファイル名の指定の時点で文字列を結合できない
> 
>     open(io, file=head//'.out')
>   とすると
>     open: illegal unit number
>     apparent state: internal I/O
>     lately writing direct unformatted external IO
>     <0> SCORE: Program signaled (SIGABRT).
>   となる.
>     fname = head//'.out'
>     open(io, file=fname)
>   で対応.

これについては、BUGとおもわれますのでfixして、currentに反映します。

> 2.サブルーチンで大きな配列をローカルに取れない
>       program main
>       call sub1()
>       stop
>       end
> 
>       subroutine sub1()
>       integer ii(600000)
>       ii(1) = 1
>       return
>       end
> 
>   は Segmentation fault となる.
>       integer ii(600000)
>       save ii
>   のようにsaveが必要.
>   -static や -fno-automatic は効かなかった.

OpenMPでは、基本的にすべてのlocal変数がstack上にとられることになります。
つまり、スレッドごとにローカル変数をとるためです。

ですので、saveで指定することになりますが、threadによって共有されること
に注意する必要があります。

もしも、大きい配列をstack上に取る場合には、threadあたりのスタックサイ
ズを設定する環境変数がありますが、thread libraryやOSによってはこの機能
がサポートされていない場合があります。

> 3. !によるコメント
>   7カラム以降から始まる!によるコメントだけの行は parse error となる.
>   実行文の後ろの!によるコメントはOK

これもbugかとおもいますので、なおします。

> 4. 乱数
>   なにもライブラリを指定しないと rand() 等の関数が呼べなくなりました.

？？？これはどういうことでしょうか？

さとう。





From iriya ＠ crc.co.jp  Mon Jul 15 14:03:19 2002
From: iriya ＠ crc.co.jp (=?ISO-2022-JP?B?GyRCRn5DKxsoQg==?=
 =?ISO-2022-JP?B?IBskQjJCMGwbKEI=?=)
Date: Mon, 15 Jul 2002 14:03:19 +0900
Subject: [SCore-users-jp] omni Fortran =?ISO-2022-JP?B?GyRCJWwlXSE8JUgbKEI=?=
Message-ID: <200207150503.AA00215@crcpc79.crc.co.jp>

入谷です．

omni Fortran を使用して以下の現象に
遭遇したので,ご報告します.

read(io,format, end=999)
でEOF処理をすると,次にreadが呼ばれると
readから処理が戻ってきません.
topで見るとCPUは消費しています.

       open (11, file = 'data1.dat')
       do while(.true.)
          read(11,*,end=999) i
       end if
   999 continue
       close(11)
       open (12, file = 'data2.dat')
       read(12,*, end=999) i  <-------
       ...

read(io,format, iostat=iost)
ではiostに常に0が入りeofに達すると
最後の行を読み込みます.
そのため下のリストは無限ループになります.

       open (11, file = 'data1.dat')
       do while(.true.)
          read(11,*,iostat=iost) i
          if(iost.eq.0) exit
       end if
       close(11)

----------------------------------------
入谷 佳一 (Iriya Yoshikazu)
  (株)CRCソリューションズ  
   エネルギー技術部  システム安全チーム
   Tel.  03-5634-5803  Fax.03-5634-7338


From kameyama ＠ pccluster.org  Mon Jul 15 14:15:41 2002
From: kameyama ＠ pccluster.org (=?iso-2022-jp?b?a2FtZXlhbWEgGyRCIXcbKEIgcGNjbHVzdGVyLm9yZw==?=)
Date: Mon, 15 Jul 2002 14:15:41 +0900
Subject: [SCore-users-jp] =?ISO-2022-JP?B?b21uaRskQiROQCk4QhsoQj8=?=
In-Reply-To: Your message of "Sat, 13 Jul 2002 03:07:25 JST."
             <20020713030725Y.msato@is.tsukuba.ac.jp>
Message-ID: <200207150515.g6F5Ffv32353@yl-dhcp18.is.s.u-tokyo.ac.jp>

亀山です.

In article <20020713030725Y.msato ＠ is.tsukuba.ac.jp> Mitsuhisa Sato <msato ＠ is.tsukuba.ac.jp> wrotes:
> > 4. 乱数
> >   なにもライブラリを指定しないと rand() 等の関数が呼べなくなりました.
> 
> ？？？これはどういうことでしょうか？

g77 では乱数発生のための関数 rand/srand などは libg2c.a に入っていて
ライブラリ指定無しで使用できます.
(gcc のソースでは libU77 のしたになります.)
しかし, Omni にはこの関数は libf2c.a には含まれていませんので,
rand() などが使用できない, ということだと思います.

                       from Kameyama Toyohisa


From neural_shock ＠ e-mail.ru  Mon Jul 15 15:28:36 2002
From: neural_shock ＠ e-mail.ru (=?iso-2022-jp?b?bmV1cmFsX3Nob2NrIBskQiF3GyhCIGUtbWFpbC5ydQ==?=)
Date: Mon, 15 Jul 2002 10:28:36 +0400
Subject: [SCore-users-jp] [SCore-users] (no subject)
Message-ID: <3d326b94.3a61.0@e-mail.ru>

hi, it is me again, mike. i have two questions.

1st. if there some ability to use SCore's checkpointing with other cluster schedulers,
for example with pbs, with pure pbs, i mean, without tss and groups?

2st. i have put to the trial checkpointing mechanism. here is situation i liked
it to handle. i have two computing hosts ( PIII 800MHz/128Mb ), say comp1 and
comp2. comp1 is scored server in group pcc and it is beeing rebooted by cron
every ten minutes to simulate system failure. on these hosts LU class A benchmark
from MPB is running. 

and i have observed the following behavior of system. when comp1 node starts
the rebooting in the middle of checkpointing process some kernel error takes
place, according to eip and System.map in function __free_pages_ok. several
times this error does not lead to "system crash" ( node reboots normally and
computation restarts from normally finished checkpoint ), but later node cannot
complete the "going down" process( not linux's process, i use this term to name
actions which system carries out before rebooting itself ), and halts.

may be it is some kind of bug, may be i have done something wrong. and if somebody
wish to look at details i can post debug messages log.

with respect, mike.
http://www.e-mail.ru

---
??????? ????? ?? DVD ?? ???? ?? 250?. ???????, ??????????? ??????????.
?????????? DVD ?????? ?? http://www.auction.ru/v2/Catalogue/Catalogue.asp?RID=73

_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From m-hirano ＠ aist.go.jp  Mon Jul 15 18:09:55 2002
From: m-hirano ＠ aist.go.jp (Motonori Heita Hirano)
Date: Mon, 15 Jul 2002 18:09:55 +0900
Subject: [SCore-users-jp] Re: omni Fortran =?ISO-2022-JP?B?GyRCJWwlXSE8JUgbKEI=?=
In-Reply-To: Your message of "Mon, 15 Jul 2002 14:03:19 JST."
             <200207150503.AA00215@crcpc79.crc.co.jp>
Message-ID: <200207150909.g6F99tA28978@eldorado.a02.aist.go.jp>

  $B$4Js9p$"$j$,$H$&$4$6$$$^$9!#(B

%% In article <200207150503.AA00215 ＠ crcpc79.crc.co.jp>,
iriya ＠ crc.co.jp (=?ISO-2022-JP?B?GyRCRn5DKxsoQg==?=

>> read(io,format, end=999)
>> $B$G(BEOF$B=hM}$r$9$k$H(B,$B<!$K(Bread$B$,8F$P$l$k$H(B
>> read$B$+$i=hM}$,La$C$F$-$^$;$s(B.
>> top$B$G8+$k$H(BCPU$B$O>CHq$7$F$$$^$9(B.

>>        open (11, file = 'data1.dat')
>>        do while(.true.)
>>           read(11,*,end=999) i
>>        end if
>>    999 continue
>>        close(11)
>>        open (12, file = 'data2.dat')
>>        read(12,*, end=999) i  <-------
>>        ...

  $B%W%m%0%i%`$,$=$N$h$&$K$+$+$l$F$$$k$+$i$@$H;W$$$^$9!#(Bdata1.dat $B$G(B eof 
$B$r6t$C$?>l9g!"(B999 $B9T$K@)8f$,0\$j$^$9!#<!$K(B data2.dat $B$G(B eof $B$r6t$C$?>l(B
$B9g$K$b!"(B999 $B9T$K@)8f$,0\$j$^$9$+$i!"(Bdata2.dat $B$r$R$?$9$i(B open() $B$7$^$9!#(B
CPU $B$r>CHq$9$k$N$O$=$N$?$a$@$H9M$($^$9!#(B

>> read(io,format, iostat=iost)
>> $B$G$O(Biost$B$K>o$K(B0$B$,F~$j(Beof$B$KC#$9$k$H(B
>> $B:G8e$N9T$rFI$_9~$_$^$9(B.
>> $B$=$N$?$a2<$N%j%9%H$OL58B%k!<%W$K$J$j$^$9(B.

>>        open (11, file = 'data1.dat')
>>        do while(.true.)
>>           read(11,*,iostat=iost) i
>>           if(iost.eq.0) exit
>>        end if
>>        close(11)

  $B$3$A$i$G$O$=$l$,:F8=$G$-$^$;$s$G$7$?!#(Bexit $B$H$$$&M=Ls8l$O(B f77 $B$K$O$J(B
$B$$$?$a!"DL>o$N(B fortran 77 $B%3%s%Q%$%i$G$O!">e5-%3!<%I$,%3%s%Q%$%k$G$-$^(B
$B$;$s!#0J2<$N$h$&$K=$@5$7$F$b!"F1CM$@$H2r<a$7!"(BGNU Fortran 77 $B%3%s%Q%$(B
$B%i(B g77, SUN Fortran 77 $B%3%s%Q%$%i!"(BOmni omf77 $B$G3NG'$7$^$7$?!#(B

      program main

      open (11, file = 'data1.dat')
      do while (.true.)
         read (11, *, iostat=iost) i
         write(*, *) i
         if (iost.eq.0) then
            goto 111
         end if
      end do
 111  continue
      close(11)

      end

  $B>e5-$9$Y$F$N%3%s%Q%$%i$K$*$$$F!"(Bdata1.dat $B$h$j!":G=i$N(B 1 $B9T$r(B 
integer $B$H$7$F(B i $B$K(B read $B$7$?;~E@$G%W%m%0%i%`$O ＠ 5>o=*N;$7$^$9!#(B

  $B$^$?!">e5-%3!<%I$G$NJQ?t(B iost $B$H(B 0 $B$H$NHf3S$G$9$,!"(B1 $B$HHf3S$9$k$h$&(B
$B$K=$@5$9$k$H!"$*$C$7$c$k$h$&$K:G8e$N9T$rFI$_$D$E$1$^$9!#$,!"$3$l$b!"A0(B
$B=R$N(B omf77 $B0J30$N%3%s%Q%$%i$HF1MM$NF0:n$G$9!#(B

---
m-hirano


From alambert ＠ scl.ameslab.gov  Tue Jul 16 00:36:41 2002
From: alambert ＠ scl.ameslab.gov (Alex Lambert)
Date: Mon, 15 Jul 2002 10:36:41 -0500
Subject: [SCore-users-jp] [SCore-users] Hint re installing SCore (or any Linux) on Asus P4B motherboards
Message-ID: <200207151536.g6FFahw02770@grasshopper.scl.ameslab.gov>

All,

I've had a difficult time installing the SCore client software/bootdisk onto 
a machine I have with an Asus motherboard (P4B). I attempted to replace the 
floppy drive and tried several different disks, to no avail. I spent a week 
working on this and finally found out what was wrong.

The BIOS for the P4B series appears to be badly broken -- it won't boot Linux 
disks at all. Everything I tried was met with "Boot failed", but 98 bootdisks 
worked fine. By luck, I stumbled upon an update to fix this.

The 1010 BIOS available from ASUS's website 
(ftp://ftp.asus.com/pub/ASUS/mb/sock478/p4b/1010.zip) fixes this issue. Be 
forewarned that you'll need a DOS boot floppy and the AFLASH.EXE utility 
(ftp://ftp.asus.com/pub/ASUS/mb/flash/aflash.exe).

Hope this helps someone out there. I look forward to testing SCore.



Regards,

Alex Lambert
Scalable Computing Laboratory
_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From klaas ＠ ccrl-nece.de  Tue Jul 16 00:56:48 2002
From: klaas ＠ ccrl-nece.de (Jens Klaas)
Date: Mon, 15 Jul 2002 17:56:48 +0200 (MESZ)
Subject: [SCore-users-jp] [SCore-users] pbs & multiuser env
Message-ID: <200207151556.RAA66362@einstein.ccrl-nece.technopark.gmd.de>

Dear all,
I installed score and the PBS scheduler. Anything is working fine
within the Score single-user environment. 
I would like to use the features of the multiuser environment
(chekpointing/restart) together with PBS.

Who can I submit a job with PBS inside the multiuser environment?

cu
    Jens

------------------------------------------------------------------------------
Jens Klaas
NEC Europe Ltd.
C&C Research Laboratories
Rathausallee 10
D-53757 Sankt Augustin

Phone:                         
02241/9252-0                  
02241/9252-72                 
                             
Fax:                          
02241/9252-99                  

eMail:
klaas ＠ ccrl-nece.de
www.ccrl-nece.de/klaas
------------------------------------------------------------------------------
In sharks we trust. 
------------------------------------------------------------------------------



-------------- next part --------------
テキスト形式以外の添付ファイルを保管しました...
ファイル名: 無し
型:         text/x-vcard
サイズ:     238 バイト
説明:       vCard
URL:        <http://new1.pccluster.org/pipermail/score-users-jp/attachments/20020715/d4d191e3/attachment.vcf>

From hori ＠ swimmy-soft.com  Tue Jul 16 09:14:38 2002
From: hori ＠ swimmy-soft.com (Atsushi HORI)
Date: Tue, 16 Jul 2002 09:14:38 +0900
Subject: [SCore-users-jp] Re: [SCore-users] pbs & multiuser env
In-Reply-To: <200207151556.RAA66362@einstein.ccrl-nece.technopark.gmd.de>
References: <200207151556.RAA66362@einstein.ccrl-nece.technopark.gmd.de>
Message-ID: <3109655678.hori0000@mail.bestsystems.co.jp>

Hi, Jens,

>I installed score and the PBS scheduler. Anything is working fine
>within the Score single-user environment. 

Good.

>I would like to use the features of the multiuser environment
>(chekpointing/restart) together with PBS.
>
>Who can I submit a job with PBS inside the multiuser environment?

Well, currently SCore checkpoint/restart only works in multi-user 
mode and PBS submit single-user mode jobs.

In the next release, hoepfully in this fall, checkpoint/restart will 
work in single-user mode too. However, at this moment, I am not sure 
the checkpoint/restart works with PBS or not.

----
Atsushi HORI
Swimmy Software, Inc.

_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From s-sumi ＠ flab.fujitsu.co.jp  Tue Jul 16 10:31:13 2002
From: s-sumi ＠ flab.fujitsu.co.jp (Shinji Sumimoto)
Date: Tue, 16 Jul 2002 10:31:13 +0900 (JST)
Subject: [SCore-users-jp] Re: [SCore-users] Hint re installing SCore (or any Linux) on Asus
 P4B motherboards
In-Reply-To: <200207151536.g6FFahw02770@grasshopper.scl.ameslab.gov>
References: <200207151536.g6FFahw02770@grasshopper.scl.ameslab.gov>
Message-ID: <20020716.103113.707908250.s-sumi@flab.fujitsu.co.jp>

Hi.

Thank you for your informative message. 

Is it possible to boot some other media, such as CD-ROM?  If so, there
is a way to write score client boot image to CD-R in order to install
SCore.

The boot disk image of SCore clients is /opt/score/ndboot/images/boot.img.

So, to create bootable CD-ROM
================================================================================
Ex:

Using mkisofs
 
/tmp# mkisofs -b /opt/score/ndboot/images/boot.img -c boot.catalog -o /tmp/score-boot.iso -J -r -T 

and cdrecord.

or using xcdroast 
================================================================================

Shinji.

From: Alex Lambert <alambert ＠ scl.ameslab.gov>
Subject: [SCore-users] Hint re installing SCore (or any Linux) on Asus P4B motherboards
Date: Mon, 15 Jul 2002 10:36:41 -0500
Message-ID: <200207151536.g6FFahw02770 ＠ grasshopper.scl.ameslab.gov>

alambert> All,
alambert> 
alambert> I've had a difficult time installing the SCore client software/bootdisk onto 
alambert> a machine I have with an Asus motherboard (P4B). I attempted to replace the 
alambert> floppy drive and tried several different disks, to no avail. I spent a week 
alambert> working on this and finally found out what was wrong.
alambert> 
alambert> The BIOS for the P4B series appears to be badly broken -- it won't boot Linux 
alambert> disks at all. Everything I tried was met with "Boot failed", but 98 bootdisks 
alambert> worked fine. By luck, I stumbled upon an update to fix this.
alambert> 
alambert> The 1010 BIOS available from ASUS's website 
alambert> (ftp://ftp.asus.com/pub/ASUS/mb/sock478/p4b/1010.zip) fixes this issue. Be 
alambert> forewarned that you'll need a DOS boot floppy and the AFLASH.EXE utility 
alambert> (ftp://ftp.asus.com/pub/ASUS/mb/flash/aflash.exe).
alambert> 
alambert> Hope this helps someone out there. I look forward to testing SCore.
alambert> 
alambert> 
alambert> 
alambert> Regards,
alambert> 
alambert> Alex Lambert
alambert> Scalable Computing Laboratory
alambert> _______________________________________________
alambert> SCore-users mailing list
alambert> SCore-users ＠ pccluster.org
alambert> http://www.pccluster.org/mailman/listinfo/score-users
alambert> 
alambert> 
------
Shinji Sumimoto, Fujitsu Labs
_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From iriya ＠ crc.co.jp  Tue Jul 16 11:13:44 2002
From: iriya ＠ crc.co.jp (=?ISO-2022-JP?B?GyRCRn5DKxsoQg==?=
 =?ISO-2022-JP?B?IBskQjJCMGwbKEI=?=)
Date: Tue, 16 Jul 2002 11:13:44 +0900
Subject: [SCore-users-jp] Re: omni Fortran
 =?ISO-2022-JP?B?GyRCJWwlXSE8JUgbKEI=?=
In-Reply-To: <200207150909.g6F99tA28978@eldorado.a02.aist.go.jp>
References: <200207150909.g6F99tA28978@eldorado.a02.aist.go.jp>
Message-ID: <200207160213.AA00220@crcpc79.crc.co.jp>

入谷です．

おせわになります．
申し訳ありません.報告用にメーラ上でプログラムを書いて
間違えてしまいました.

もう一度,確認いたしましたので,実行したプログラムを
記載します.
環境はRedHat7.2,Score5.0.1で,omniコンパイラが使えるようmpiを
再構築してあります.

お手数をおかけして申し訳ありませんがもう一度確認いただけますでしょうか

間違えた情報で貴重なお時間を使わせてしまい申し訳ありませんでした.
以後,気をつけます.今後ともよろしくお願いいたします.
--------------------
1. EOFをreadの"end="で検知する場合

プログラム：
      program main
      integer ii
      open(11, file='data1.dat')
      do while(.true.)
          read(11, *, end = 100) ii
          write(*,*) ii
      end do
  100 continue
      open(12, file='data2.dat')
      do while(.true.)
          write(*,*) 'bf 2nd read'
          read(12, *, end = 110) ii
          write(*,*) 'aft 2nd read' ! この行に実行が移りません
          write(*,*) ii
      end do
  110 continue

       stop
       end

実行状況：
# mpif77 -compiler omni -Wall a.f
!Compiling 'a.f'...
  MAIN main:
# cat data1.dat
123
1234
# cat data2.dat
234
2345
23456
#./a.out
 123
 1234
 bf 2nd read
ここで戻ってこなくなります.

# g77 d.f
# ./a.out
 123
 1234
 bf 2nd read
 aft 2nd read
 234
 bf 2nd read
 aft 2nd read
 2345
 bf 2nd read
 aft 2nd read
 23456
 bf 2nd read
#

2.EOFをread文のiostatで判定する場合

      program main
      integer i

      open (11, file = 'data1.dat')
      do while (.true.)
         read (11, *, iostat=iost) i
         write(*,*) 'iostat=',iost
         if (iost.ne.0) then  !前回mailで誤って.eq.で判定するよう書いていました.
            goto 111
         end if
         write(*, *) i
      end do
 111  continue
      close(11)
      stop
      end


# mpif77 -compiler omni -Wall  a.f
Compiling 'a.f'...
  MAIN main:
# ./a.out
 iostat= 0
 123
 iostat= 0
 1234
 iostat= 0
 1234
 iostat= 0
 1234
 iostat= 0
 1234
 iostat= 0
となり,iostatに正常EOFの値(負の整数値)が入ってきません

# g77 a.f
# ./a.out
 iostat= 0
 123
 iostat= 0
 1234
 iostat= -1

--------
>      program main
>
>      open (11, file = 'data1.dat')
>      do while (.true.)
>         read (11, *, iostat=iost) i
>         write(*, *) i
>         if (iost.eq.0) then
            goto 111
>         end if
>      end do
> 111  continue
>      close(11)
>
>      end
>
> 上記すべてのコンパイラにおいて、data1.dat より、最初の 1 行を 
>integer として i に read した時点でプログラムは正常終了します。
正常に読めたらループを抜けるので文法どおりの動作です
>
>  また、上記コードでの変数 iost と 0 との比較ですが、1 と比較するよう
>に修正すると、おっしゃるように最後の行を読みつづけます。が、これも、前
>述の omf77 以外のコンパイラと同様の動作です。
READエラーが起こるまで無限ループであるので文法どおりの動作だと思います.

----------------------------------------
入谷 佳一 (Iriya Yoshikazu)
  (株)CRCソリューションズ  
   エネルギー技術部  システム安全チーム
   Tel.  03-5634-5803  Fax.03-5634-7338


From neural_shock ＠ e-mail.ru  Tue Jul 16 14:36:51 2002
From: neural_shock ＠ e-mail.ru (=?iso-2022-jp?b?bmV1cmFsX3Nob2NrIBskQiF3GyhCIGUtbWFpbC5ydQ==?=)
Date: Tue, 16 Jul 2002 09:36:51 +0400
Subject: [SCore-users-jp] [SCore-users] (no subject)
Message-ID: <3d33b0f3.7d39.0@e-mail.ru>

oops! i forgot to ask second question. i hope you have read my previous post,
so here is it without preamble. what has happened? was it some kind of bug or
my mistake? 

yours faithfully, mike.
http://www.e-mail.ru

---
??????? ????? ?? DVD ?? ???? ?? 250?. ???????, ??????????? ??????????.
?????????? DVD ?????? ?? http://www.auction.ru/v2/Catalogue/Catalogue.asp?RID=73

_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From kameyama ＠ pccluster.org  Tue Jul 16 18:02:29 2002
From: kameyama ＠ pccluster.org (=?iso-2022-jp?b?a2FtZXlhbWEgGyRCIXcbKEIgcGNjbHVzdGVyLm9yZw==?=)
Date: Tue, 16 Jul 2002 18:02:29 +0900
Subject: [SCore-users-jp] Re: =?ISO-2022-JP?B?U0NvcmUbJEI+ZSRHJE4bKEJBYnNvZnQ=?= ProFortran
 for =?ISO-2022-JP?B?TGludXgbJEIkTjE/TVE8QkBTJEskRCQkJEYbKEI=?=
In-Reply-To: Your message of "Tue, 16 Jul 2002 17:09:37 JST."
             <20020716170930.82B6.SOFT.SUPPORT@hulinks.co.jp>
Message-ID: <200207160902.g6G92Tv06772@yl-dhcp18.is.s.u-tokyo.ac.jp>

亀山です.

score-info は obsolate です.
日本語の問い合わせは score-users-jp を使用してください.

In article <20020716170930.82B6.SOFT.SUPPORT ＠ hulinks.co.jp> soft.support ＠ hulinks.co.jp (HULINKS GROUP SUPPORT) wrotes:
> SCoreはクラスタ環境を提供するツールであると認識しておりますが、
> これまでに、弊社取り扱いソフトAbsoft ProFortran for LinuxをSCore上で用いて、
> 並列処理された実績の有無について、お伺いしたくメールをお送りしたしだいです。

一応, 2000 年 4 月ごろ absoft Fortran で簡単な mpi program を
動かしたことはあります.
使用したのはそのときの Trial Version です.
(すみません, 正確な version は不明です.)
そのときのコンパイラの設定は SCore 3.1 以降のソースに含めています.

しかし, それ以降は動かしていませんので, 現在の SCore 5.0.1/現在のバージョンの
Absoft Fortran で動くかどうかは分かりません.

                       from Kameyama Toyohisa


From ken-fujita ＠ sa.uno.ne.jp  Wed Jul 17 13:32:21 2002
From: ken-fujita ＠ sa.uno.ne.jp (Ken Fujita)
Date: Wed, 17 Jul 2002 13:32:21 +0900
Subject: [SCore-users-jp] =?ISO-2022-JP?B?GyRCJSQlcyU5JUghPCVrO34kSyUoJWkhPBsoQg==?=
 =?ISO-2022-JP?B?GyRCJCxAOCQ4JF4kOSEjGyhC?=
Message-ID: <20020717131445.20A2.KEN-FUJITA@sa.uno.ne.jp>

はじめまして、藤田と申します。

Score5.0.1をRedHatLinux7.2に入れているところです。計算ノードにインストー
ルするときにエラーが発生して困っています。
状況としましては、計算ノードをフロッピでブートさせた後、MacアドレスとIP
アドレスが表示された後、Nextを選択してファイルの転送が始まります。しかし、
2つか3つのファイルが転送されると以下のメッセージが出て、転送が止まってし
まいます。

information

The file
mnt/source2/RedHat/RPMS/パッケージ名
cannnot be opend. This is due to a missing file, a bad
package, or bad media. Press <return> to try again.

※パッケージ名はそのときによって変わります。

ここで、すぐにOKを押しても同じメッセージが表示されます。2,3分経ってから
OKを選択すると、次へ進みますがまた2つか3つのファイルが転送されると止まっ
てしまいます。それが何度か繰り返されるとインストールも止まってしまいます。
ハブ、ネットワークカード、ネットワークケーブル等変えて試してみましたが、
どれも同様の状況になってしまいます。

なお、ハードウェアの構成は
CPU:Celeron350MHz
MEM:128MB
HDD:サーバ  30GB
    クライアント  4.2GB
で構成しています。

また、この構成でDebianGNU/LinuxとLAM、及びMPICHを動作させていた際は正常
に動作していました。

どうぞよろしくお願いします。

■■■■■■■■■■■■■■■■■■■■■■■■■
   岐阜工業高等専門学校建設工学専攻1年  藤田 憲
         k1413 ＠ mail.archi.gifu-nct.ac.jp 
■■■■■■■■■■■■■■■■■■■■■■■■■



From ishikawa ＠ is.s.u-tokyo.ac.jp  Wed Jul 17 14:01:52 2002
From: ishikawa ＠ is.s.u-tokyo.ac.jp (Yutaka Ishikawa)
Date: Wed, 17 Jul 2002 14:01:52 +0900 (JST)
Subject: [SCore-users-jp] Re: [SCore-users-jp]
 =?iso-2022-jp?B?GyRCJSQlcyU5JUghPCVrO34kSyUoJWkhPCQsQDgkOCReJDkhIxsoQg==?=
In-Reply-To: <20020717131445.20A2.KEN-FUJITA@sa.uno.ne.jp>
References: <20020717131445.20A2.KEN-FUJITA@sa.uno.ne.jp>
Message-ID: <20020717.140152.730553979.ishikawa@is.s.u-tokyo.ac.jp>

From: Ken Fujita <ken-fujita ＠ sa.uno.ne.jp>
> information
> The file
> mnt/source2/RedHat/RPMS/パッケージ名
> cannnot be opend. This is due to a missing file, a bad
> package, or bad media. Press <return> to try again.

同様の症状を昨日体験したばかりです。
それで、これは、メッセージにかいてある通りなのですが、どうもCD-ROMから読
めてないのではないかと疑っています。
> ハブ、ネットワークカード、ネットワークケーブル等変えて試してみましたが、
> どれも同様の状況になってしまいます。
それで、
とのことなので、CD-ROMイメージをディスクにコピーして頂き、そこをmount point
にして実行してみて下さい。
もし、.isoイメージのファイルがあれば、CD-ROMには何も入れずに、次のように
するというのも手です。以下の例では、/root/score-5.0.1.isoというファイルを
想定します。
	# mount -o loop /root/score-5.0.1.iso /mnt/cdrom
こんな感じで、やってみて下さい。

石川


From s-sumi ＠ flab.fujitsu.co.jp  Wed Jul 17 12:40:11 2002
From: s-sumi ＠ flab.fujitsu.co.jp (Shinji Sumimoto)
Date: Wed, 17 Jul 2002 12:40:11 +0900 (JST)
Subject: [SCore-users-jp] Re: [SCore-users] (no subject)
In-Reply-To: <3d33b0f3.7d39.0@e-mail.ru>
References: <3d33b0f3.7d39.0@e-mail.ru>
Message-ID: <20020717.124011.984922857.s-sumi@flab.fujitsu.co.jp>

Hi. 

From: neural_shock ＠ e-mail.ru
Subject: [SCore-users] (no subject)
Date: Tue, 16 Jul 2002 09:36:51 +0400
Message-ID: <3d33b0f3.7d39.0 ＠ e-mail.ru>

neural_shock> oops! i forgot to ask second question. i hope you have read my previous post,
neural_shock> so here is it without preamble. what has happened? was it some kind of bug or
neural_shock> my mistake? 

Could you send more detail log messages for the problems? 

Shinji.

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


From neural_shock ＠ e-mail.ru  Wed Jul 17 17:00:59 2002
From: neural_shock ＠ e-mail.ru (=?iso-2022-jp?b?bmV1cmFsX3Nob2NrIBskQiF3GyhCIGUtbWFpbC5ydQ==?=)
Date: Wed, 17 Jul 2002 12:00:59 +0400
Subject: [SCore-users-jp] Re: [SCore-users] (no subject)
Message-ID: <3d35243b.3457.0@e-mail.ru>

>Hi. 
>
>From: neural_shock ＠ e-mail.ru
>Subject: [SCore-users] (no subject)
>Date: Tue, 16 Jul 2002 09:36:51 +0400
>Message-ID: <3d33b0f3.7d39.0 ＠ e-mail.ru>
>
>neural_shock> oops! i forgot to ask second question. i hope you have read my
previous post,
>neural_shock> so here is it without preamble. what has happened? was it some
kind of bug or
>neural_shock> my mistake? 
>
>Could you send more detail log messages for the problems? 
>
>Shinji.
>
>neural_shock> yours faithfully, mike.
>------
>Shinji Sumimoto, Fujitsu Labs
>_______________________________________________
>SCore-users mailing list
>SCore-users ＠ pccluster.org
>http://www.pccluster.org/mailman/listinfo/score-users

hello. the message log is attached. system failed to restart at jul 16 19:13:04.


WARNING! the log is koi8-r encoded ( of course, all PM debug messages are in
english and therefore are readable )

with respect, mike.
http://www.e-mail.ru

---
??????? ????? ?? DVD ?? ???? ?? 250?. ???????, ??????????? ??????????.
?????????? DVD ?????? ?? http://www.auction.ru/v2/Catalogue/Catalogue.asp?RID=73

_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From m-hirano ＠ aist.go.jp  Wed Jul 17 17:33:26 2002
From: m-hirano ＠ aist.go.jp (Motonori Heita Hirano)
Date: Wed, 17 Jul 2002 17:33:26 +0900
Subject: [SCore-users-jp] Re: omni Fortran
       =?ISO-2022-JP?B?GyRCJWwlXSE8JUgbKEI=?=
In-Reply-To: Your message of "Tue, 16 Jul 2002 11:13:44 JST."
             <200207160213.AA00220@crcpc79.crc.co.jp>
Message-ID: <200207170833.g6H8XQA07936@eldorado.a02.aist.go.jp>

%% iriya ＠ crc.co.jp (=?ISO-2022-JP?B?GyRCRn5DKxsoQg==?=
=?ISO-2022-JP?B?IBskQjJCMGwbKEI=?=) writes:

	:
>> $B4V0c$($?>pJs$G5.=E$J$*;~4V$r;H$o$;$F$7$^$$?=$7Lu$"$j$^$;$s$G$7$?(B.
>> $B0J8e(B,$B5$$r$D$1$^$9(B.

  $B$$$($$$((B :) $B$*5$$K$J$5$i$J$$$G$/$@$5$$!#(B

>> 1. EOF$B$r(Bread$B$N(B"end="$B$G8!CN$9$k>l9g(B
	:

  $B>u67!"3NG'$G$-$^$7$?!#(BEOF $B$r6t$C$?>l9g$N(B jump $B%3!<%I$N ＠ 8@.$,4V0c$C$F(B
$B$$$F!"(BMT safe I/O $B$N$?$a$NGSB>@)8fMQ(B lock $B$r$O$:$7K:$l$F$$$^$7$?!#C`<!(B
$B%W%m%0%i%`$H$7$FF0:n$5$;$k>l9g(B(omf77 -omp $B$H$7$F%3%s%Q%$%i$r5/F0$9$k(B)
$B$K$O!"$3$NLdBj$O5/$-$^$;$s!#$,!"B?J,!"F~C+$5$s$N$*;H$$$K$J$j$?$$$N$O(B 
OpenMP(SCore-MPI and/or SCASH) $B$@$H;W$$$^$9$N$G!"8=>u!"2sHr:v$O$"$j$^(B
$B$;$s!#(B

>> 2.EOF$B$r(Bread$BJ8$N(Biostat$B$GH=Dj$9$k>l9g(B
	:

  $B$3$A$i$b3NG'$G$-$^$7$?!#$3$l$b%3!<%I ＠ 8@.$N8m$j$G$7$?!#(B

  1, 2 $B$H$b$G$-$k$+$.$jAa5^$KBP1~$7$^$9!#(B

  $B$4Js9p$"$j$,$H$&$4$6$$$^$7$?!#(B
---
m-hirano


From neural_shock ＠ e-mail.ru  Wed Jul 17 18:03:51 2002
From: neural_shock ＠ e-mail.ru (=?iso-2022-jp?b?bmV1cmFsX3Nob2NrIBskQiF3GyhCIGUtbWFpbC5ydQ==?=)
Date: Wed, 17 Jul 2002 13:03:51 +0400
Subject: [SCore-users-jp] [SCore-users] (no subject)
Message-ID: <3d3532f7.12ab.0@e-mail.ru>

i have recieved my previous post. it was without attachment... strange. so resend
You message log.
http://www.e-mail.ru

-------------- next part --------------
テキスト形式以外の添付ファイルを保管しました...
ファイル名: messages.bz2
型:         application/octet-stream
サイズ:     23635 バイト
説明:       無し
URL:        <http://new1.pccluster.org/pipermail/score-users-jp/attachments/20020717/6c07dba1/attachment.obj>

From ishikawa ＠ is.s.u-tokyo.ac.jp  Wed Jul 17 18:11:00 2002
From: ishikawa ＠ is.s.u-tokyo.ac.jp (Yutaka Ishikawa)
Date: Wed, 17 Jul 2002 18:11:00 +0900 (JST)
Subject: [SCore-users-jp] Re: [SCore-users-jp]
 =?iso-2022-jp?B?GyRCJSQlcyU5JUghPCVrO34kSyUoJWkhPCQsQDgkOCReJDkhIxsoQg==?=
In-Reply-To: <20020717164424.C3FC.KEN-FUJITA@sa.uno.ne.jp>
References: <20020717131445.20A2.KEN-FUJITA@sa.uno.ne.jp>
	<20020717.140152.730553979.ishikawa@is.s.u-tokyo.ac.jp>
	<20020717164424.C3FC.KEN-FUJITA@sa.uno.ne.jp>
Message-ID: <20020717.181100.607959253.ishikawa@is.s.u-tokyo.ac.jp>

藤田様、

状況をscore-users-jpの皆様にも知って欲しいので、replyもscore-users-jp宛で
お願いします。

From: Ken Fujita <ken-fujita ＠ sa.uno.ne.jp>
> おっしゃるとおりにisoイメージを作成して、マウントして、やってみました。
> でも同じところで止まってしまいます。途中まで進んだということは、isoイメー
> ジ、マウント共に出来ているという事だと思います。また、CD-ROMのほうは出し
> て試してみましたのでCD-ROMから読んでいるという事もないと思います。

そうすると、NFSがおかしくなっているんですね。
とりあえずの対処方法です。
昨日は、このような状況になった計算ホスト上で以下のことをしました。
なお、以下のようなメッセージが出たとします。
    > The file
    > mnt/source2/RedHat/RPMS/パッケージ名
    > cannnot be opend. This is due to a missing file, a bad
    > package, or bad media. Press <return> to try again.

１）Alt + F2を押すとshell画面に切り替わります。
２）ここで、
	# cd /mnt/scoure2/RedHat/RPMS/
	# ls -l パッケージ名
３）その後、サーバホスト上で、エラーメッセージダイアログのOKボタンをクリック。

手間がかかりますが、これで対応のほどお願いします。

それから、もし、可能でしたら、上記状態になった時に、計算ホスト上で
Alt + F3画面でNFS回りのエラーが出ていないか見て頂けると幸いです。

よろしくお願い致します。

石川






From s-sumi ＠ flab.fujitsu.co.jp  Wed Jul 17 19:36:41 2002
From: s-sumi ＠ flab.fujitsu.co.jp (Shinji Sumimoto)
Date: Wed, 17 Jul 2002 19:36:41 +0900 (JST)
Subject: [SCore-users-jp] Fault on checkpointng Re: [SCore-users] (no subject)
In-Reply-To: <3d3532f7.12ab.0@e-mail.ru>
References: <3d3532f7.12ab.0@e-mail.ru>
Message-ID: <20020717.193641.951455000.s-sumi@flab.fujitsu.co.jp>

Hi. 

Kernel faults are occurred on your cluster.

How are you implementing your checkpointing mechanizm?
Or, is this a log when SCore checkpointing function? 

Shinji.
 
=====================================================================================
Jul 16 17:57:29 rscu_21 kernel: EIP:    0010:[pm_ethernet_devioctl+707/17712]    Not tainted
Jul 16 17:57:29 rscu_21 kernel: EIP:    0010:[<c01a2f23>]    Not tainted
Jul 16 17:57:29 rscu_21 kernel: EFLAGS: 00010296
Jul 16 17:57:29 rscu_21 kernel: eax: 0000005c   ebx: c7f403d4   ecx: 0000000c   edx: 00000000
Jul 16 17:57:29 rscu_21 kernel: esi: c7f44184   edi: 00014680   ebp: c17d7f94   esp: c17d7950
Jul 16 17:57:29 rscu_21 kernel: ds: 0018   es: 0018   ss: 0018
Jul 16 17:57:29 rscu_21 kernel: Process lu.A.2.1 (pid: 740, stackpage=c17d7000)
Jul 16 17:57:29 rscu_21 kernel: Stack: 00000000 00000145 c17d7984 c01b464b c7fbc800 00000086 00000000 c4a5c900 
Jul 16 17:57:29 rscu_21 kernel:        00000005 0000d000 0000222b 00000000 c1e86140 c17d79b0 c019db76 c1e86140 
Jul 16 17:57:29 rscu_21 kernel:        00000293 c1e86140 00000020 00000293 c7fbc800 00000000 00000000 00000000 
Jul 16 17:57:29 rscu_21 kernel: Call Trace: [boomerang_start_xmit+507/656] [pm_ethernet_xmitskb+358/416] [boomerang_start_xmit+507/656] [pm_ethernet_loop+1178/1200] [pm_ethernet_xmitskb+358/416] 
Jul 16 17:57:29 rscu_21 kernel: Call Trace: [<c01b464b>] [<c019db76>] [<c01b464b>] [<c019e80a>] [<c019db76>] 
Jul 16 17:57:29 rscu_21 kernel:    [pm_ethernet_loop+1178/1200] [kfree_skbmem+13/96] [kfree_skbmem+13/96] [pm_ethernet_loop+1178/1200] [ide_set_handler+87/112] [pm_ethernet_loop+1178/1200] 
Jul 16 17:57:29 rscu_21 kernel:    [<c019e80a>] [<c01d076d>] [<c01d076d>] [<c019e80a>] [<c01b7037>] [<c019e80a>] 
鯊フ 16 17:57:29 rscu_21 sshd: sshd -TERM succeeded
Jul 16 17:57:29 rscu_21 kernel:    [kfree_skbmem+13/96] [__kfree_skb+212/224] [pm_ethernet_netif_rx+1903/9168] [do_schedule+801/848] [kfree_skbmem+13/96] [__kfree_skb+212/224] 
Jul 16 17:57:30 rscu_21 kernel:    [<c01d076d>] [<c01d0894>] [<c019fe0f>] [<c01105d1>] [<c01d076d>] [<c01d0894>] 
Jul 16 17:57:30 rscu_21 kernel:    [tcp_clean_rtx_queue+425/800] [tcp_clean_rtx_queue+352/800] [__alloc_pages+207/400] [kmem_cache_grow+227/544] [boomerang_start_xmit+507/656] [kmalloc+242/288] 
Jul 16 17:57:30 rscu_21 sshd[516]: Received signal 15; terminating.
Jul 16 17:57:30 rscu_21 kernel:    [<c01eb949>] [<c01eb900>] [<c01296df>] [<c0127483>] [<c01b464b>] [<c0127782>] 
Jul 16 17:57:30 rscu_21 kernel:    [boomerang_start_xmit+507/656] [boomerang_start_xmit+507/656] [pm_ethernet_xmitskb+358/416] [pm_ethernet_sendctl+472/768] [pm_ethernet_loop+1178/1200] [kfree_skbmem+13/96] 
=====================================================================================


From: neural_shock ＠ e-mail.ru
Subject: [SCore-users] (no subject)
Date: Wed, 17 Jul 2002 13:03:51 +0400
Message-ID: <3d3532f7.12ab.0 ＠ e-mail.ru>

neural_shock> i have recieved my previous post. it was without attachment... strange. so resend
------
Shinji Sumimoto, Fujitsu Labs
_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From neural_shock ＠ e-mail.ru  Wed Jul 17 20:00:44 2002
From: neural_shock ＠ e-mail.ru (=?iso-2022-jp?b?bmV1cmFsX3Nob2NrIBskQiF3GyhCIGUtbWFpbC5ydQ==?=)
Date: Wed, 17 Jul 2002 15:00:44 +0400
Subject: [SCore-users-jp] [SCore-users] checkpointing failure
Message-ID: <3d354e5c.342d.0@e-mail.ru>

>Hi. 

>Kernel faults are occurred on your cluster.

>How are you implementing your checkpointing mechanizm?
>Or, is this a log when SCore checkpointing function? 

>Shinji.

>..... here must be log.

hi.

the part of log which you have posted corresponds to the moment when SCore is
doing checkpointing, and the system starts to reboot.

later i will repeat this "exepriment" on machine without localization in order
to "generate" logs in pure english. 

rscu_21 is comp1 in my previous description of situation.

with respect, mike.
http://www.e-mail.ru

---
??????? ????? ?? DVD ?? ???? ?? 250?. ???????, ??????????? ??????????.
?????????? DVD ?????? ?? http://www.auction.ru/v2/Catalogue/Catalogue.asp?RID=73

_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From ken-fujita ＠ sa.uno.ne.jp  Wed Jul 17 20:06:40 2002
From: ken-fujita ＠ sa.uno.ne.jp (Ken Fujita)
Date: Wed, 17 Jul 2002 20:06:40 +0900
Subject: [SCore-users-jp] Re: [SCore-users-jp]
 =?ISO-2022-JP?B?GyRCJSQlcyU5JUghPCVrO34kSyUoJWkhPBsoQg==?=
 =?ISO-2022-JP?B?GyRCJCxAOCQ4JF4kOSEjGyhC?=
In-Reply-To: <20020717.181100.607959253.ishikawa@is.s.u-tokyo.ac.jp>
References: <20020717164424.C3FC.KEN-FUJITA@sa.uno.ne.jp> <20020717.181100.607959253.ishikawa@is.s.u-tokyo.ac.jp>
Message-ID: <20020717200310.C3FE.KEN-FUJITA@sa.uno.ne.jp>

藤田です。あわてていて返信先を直すのを忘れてました。申し訳ありません。そ
れで、先ほどの内容をもう一度送信します。

藤田です。早速のお返事ありがとうございます。早速試してみましたがうまくい
きませんでした。

>とのことなので、CD-ROMイメージをディスクにコピーして頂き、そこをmount point
>にして実行してみて下さい。
>もし、.isoイメージのファイルがあれば、CD-ROMには何も入れずに、次のように
>するというのも手です。以下の例では、/root/score-5.0.1.isoというファイルを
>想定します。
>	# mount -o loop /root/score-5.0.1.iso /mnt/cdrom
>こんな感じで、やってみて下さい。

おっしゃるとおりにisoイメージを作成して、マウントして、やってみました。
でも同じところで止まってしまいます。途中まで進んだということは、isoイメー
ジ、マウント共に出来ているという事だと思います。また、CD-ROMのほうは出し
て試してみましたのでCD-ROMから読んでいるという事もないと思います。

よろしくお願いします。

>１）Alt + F2を押すとshell画面に切り替わります。
>２）ここで、
>	# cd /mnt/scoure2/RedHat/RPMS/
>	# ls -l パッケージ名
>３）その後、サーバホスト上で、エラーメッセージダイアログのOKボタンをクリック。
>
>手間がかかりますが、これで対応のほどお願いします。
>
>それから、もし、可能でしたら、上記状態になった時に、計算ホスト上で
>Alt + F3画面でNFS回りのエラーが出ていないか見て頂けると幸いです。

分かりました。早速やってみたいと思いますが、今日はもう出来ないので、明日
の朝試してみたいと思います。ありがとうございます。

■■■■■■■■■■■■■■■■■■■■■■■■■
   岐阜工業高等専門学校建設工学専攻1年  藤田 憲
        k1413 ＠ mail.archi.gifu-nct.ac.jp 
■■■■■■■■■■■■■■■■■■■■■■■■■



From ken-fujita ＠ sa.uno.ne.jp  Thu Jul 18 10:54:39 2002
From: ken-fujita ＠ sa.uno.ne.jp (Ken Fujita)
Date: Thu, 18 Jul 2002 10:54:39 +0900
Subject: [SCore-users-jp] Re: [SCore-users-jp]
 =?ISO-2022-JP?B?GyRCJSQlcyU5JUghPCVrO34kSyUoJWkhPBsoQg==?=
 =?ISO-2022-JP?B?GyRCJCxAOCQ4JF4kOSEjGyhC?=
In-Reply-To: <20020717.181100.607959253.ishikawa@is.s.u-tokyo.ac.jp>
References: <20020717164424.C3FC.KEN-FUJITA@sa.uno.ne.jp> <20020717.181100.607959253.ishikawa@is.s.u-tokyo.ac.jp>
Message-ID: <20020718101233.C405.KEN-FUJITA@sa.uno.ne.jp>

藤田です。

さっそく試してみました。やはりNFS関連のエラーのようです。

>１）Alt + F2を押すとshell画面に切り替わります。
>２）ここで、
>	# cd /mnt/scoure2/RedHat/RPMS/
>	# ls -l パッケージ名
>３）その後、サーバホスト上で、エラーメッセージダイアログのOKボタンをクリック。

ls: パッケージ名: State NFS file handle
このようなメッセージが出ます。

>それから、もし、可能でしたら、上記状態になった時に、計算ホスト上で
>Alt + F3画面でNFS回りのエラーが出ていないか見て頂けると幸いです。

* WARNING: not all package in hdlist had order tag
このエラーが表示されています。

わたしはNFS関連があまり分からないので、対処方法があまり分かりません。
よろしくお願い致します。

■■■■■■■■■■■■■■■■■■■■■■■■■
   岐阜工業高等専門学校建設工学専攻1年  藤田 憲
       k1413 ＠ mail.archi.gifu-nct.ac.jp 
■■■■■■■■■■■■■■■■■■■■■■■■■



From ishikawa ＠ is.s.u-tokyo.ac.jp  Thu Jul 18 11:38:56 2002
From: ishikawa ＠ is.s.u-tokyo.ac.jp (Yutaka Ishikawa)
Date: Thu, 18 Jul 2002 11:38:56 +0900 (JST)
Subject: [SCore-users-jp] Re: [SCore-users-jp]
 =?iso-2022-jp?B?GyRCJSQlcyU5JUghPCVrO34kSyUoJWkhPCQsQDgkOCReJDkhIxsoQg==?=
In-Reply-To: <20020718101233.C405.KEN-FUJITA@sa.uno.ne.jp>
References: <20020717164424.C3FC.KEN-FUJITA@sa.uno.ne.jp>
	<20020717.181100.607959253.ishikawa@is.s.u-tokyo.ac.jp>
	<20020718101233.C405.KEN-FUJITA@sa.uno.ne.jp>
Message-ID: <20020718.113856.27781438.ishikawa@is.s.u-tokyo.ac.jp>

藤田様、

From: Ken Fujita <ken-fujita ＠ sa.uno.ne.jp>
> ls: パッケージ名: State NFS file handle
> このようなメッセージが出ます。

なぜ、State NFS file handleになるのか良く分からないので、
lsの結果が出てくるまで、これを何回か試すしか手がないです。

> * WARNING: not all package in hdlist had order tag
> このエラーが表示されています。

これについてはとりあえずはきにしなくても大丈夫です。

それで、何台かの計算ホストはインストール成功されているのでしょうか？

石川


From ken-fujita ＠ sa.uno.ne.jp  Thu Jul 18 17:01:05 2002
From: ken-fujita ＠ sa.uno.ne.jp (Ken Fujita)
Date: Thu, 18 Jul 2002 17:01:05 +0900
Subject: [SCore-users-jp] Re: [SCore-users-jp]
 =?ISO-2022-JP?B?GyRCJSQlcyU5JUghPCVrO34kSyUoJWkhPBsoQg==?=
 =?ISO-2022-JP?B?GyRCJCxAOCQ4JF4kOSEjGyhC?=
In-Reply-To: <20020718.113856.27781438.ishikawa@is.s.u-tokyo.ac.jp>
References: <20020718101233.C405.KEN-FUJITA@sa.uno.ne.jp> <20020718.113856.27781438.ishikawa@is.s.u-tokyo.ac.jp>
Message-ID: <20020718165610.30AC.KEN-FUJITA@sa.uno.ne.jp>

藤田です。

>なぜ、State NFS file handleになるのか良く分からないので、
>lsの結果が出てくるまで、これを何回か試すしか手がないです。

何回か試してやってみたところ最後までいけました。ありがとうございます。

>それで、何台かの計算ホストはインストール成功されているのでしょうか？

とりあえず一台目でこの状況になったので、まだ他の計算ホストへのインストー
ルはこれからです。とりあえず計算ホスト4台構成のクラスタを考えているので、
あと3台のインストールをこれから行なうつもりです。ありがとうございました。

■■■■■■■■■■■■■■■■■■■■■■■■■
   岐阜工業高等専門学校建設工学専攻1年  藤田 憲
       k1413 ＠ mail.archi.gifu-nct.ac.jp 
■■■■■■■■■■■■■■■■■■■■■■■■■



From alambert ＠ scl.ameslab.gov  Sat Jul 20 04:47:40 2002
From: alambert ＠ scl.ameslab.gov (Alex Lambert)
Date: Fri, 19 Jul 2002 14:47:40 -0500
Subject: [SCore-users-jp] [SCore-users] Error: mpich-1.2.0 device score2 is not installed
Message-ID: <200207191947.g6JJlmB18960@grasshopper.ge1>

Greetings,

I'm trying to test the performance of MPICH-SCore 2.0 as opposed to the 1.0 
that is used by default. When I try to specify it explicitly when compiling, 
I receive an error saying that the device is not installed.

How would I go about enabling the 2.0 version? I've attempted to recompile 
per the directions, but mangled my install horribly (oops).




Thanks,


Alex Lambert
Scalable Computing Lab

alambert ＠ grasshopper:~$ echo $PATH
/opt/score/bin:/opt/score/sbin:/opt/score/deploy:/usr/local/bin:/usr/local/sbin:/scl/bin:/usr/bin:/usr/sbin:/usr/bin/X11:/bin:/sbin:/etc:/usr/etc:/usr/etc/fore/etc:/usr/java/jdk1.3.1/bin:/usr/kerberos/bin
alambert ＠ grasshopper:~$ ls -alR 
/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4
/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4:
total 44
drwxrwxr-x   11 root     root         4096 Jul 12 08:43 .
drwxr-xr-x    4 root     root         4096 Jul 12 08:43 ..
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 bin
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 doc
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 examples
drwxrwxr-x    3 root     root         4096 Jul 12 08:43 include
drwxrwxr-x    3 root     root         4096 Jul 12 08:43 lib
drwxrwxr-x    5 root     root         4096 Jul 12 08:43 man
drwxrwxr-x    3 root     root         4096 Jul 12 08:43 MPI-2-C++
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 sbin
drwxrwxr-x    5 root     root         4096 Jul 12 08:43 share

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/bin:
total 560
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
drwxrwxr-x   11 root     root         4096 Jul 12 08:43 ..
-rwxrwxr-x    1 root     root         9516 Apr  2 20:43 clog2alog
-rwxrwxr-x    1 root     root       206476 Apr  2 20:43 clog2slog
-rwxrwxr-x    1 root     root         6284 Apr  2 20:43 clog_print
-rwxrwxr-x    1 root     root         4158 Apr  2 20:43 execer
-rwxrwxr-x    1 root     root         3521 Apr  2 20:43 logviewer
-rwxrwxr-x    1 root     root         1988 Apr  2 20:43 mpereconfig
-rwxrwxr-x    1 root     root        12920 Apr  2 20:43 mpereconfig.dat
lrwxrwxrwx    1 root     root            5 Jul 12 08:43 mpic++ -> mpiCC
-rwxrwxr-x    1 root     root         8875 Apr  2 20:43 mpicc
-rwxrwxr-x    1 root     root         7709 Apr  2 20:43 mpiCC
-rwxrwxr-x    1 root     root         8073 Apr  2 20:43 mpif77
-rwxrwxr-x    1 root     root         8468 Apr  2 20:43 mpif90
-rwxrwxr-x    1 root     root         1015 Apr  2 20:43 mpiman
-rwxrwxr-x    1 root     root         2855 Apr  2 20:43 mpireconfig
-rwxrwxr-x    1 root     root        24349 Apr  2 20:43 mpireconfig.dat
-rwxrwxr-x    1 root     root         3928 Apr  2 20:43 mpirun
-rwxrwxr-x    1 root     root        21686 Apr  2 20:43 mpirun.args
-rwxrwxr-x    1 root     root         3968 Apr  2 20:43 mpirun.ch_score
-rwxrwxr-x    1 root     root          154 Apr  2 20:43 mpirun.ch_score.args
-rwxrwxr-x    1 root     root       172844 Apr  2 20:43 slog_print
-rwxrwxr-x    1 root     root         3403 Apr  2 20:43 tarch
-rwxrwxr-x    1 root     root          834 Apr  2 20:43 tdevice

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/doc:
total 416
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
drwxrwxr-x   11 root     root         4096 Jul 12 08:43 ..
-rw-rw-r--    1 root     root       251022 Apr  2 20:43 guide.ps.gz
-rw-rw-r--    1 root     root       151934 Apr  2 20:43 install.ps.gz

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/examples:
total 52
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
drwxrwxr-x   11 root     root         4096 Jul 12 08:43 ..
-rw-rw-r--    1 root     root         1614 Apr  2 20:43 cpi.c
-rw-rw-r--    1 root     root         1937 Apr  2 20:43 cpilog.c
-rw-rw-r--    1 root     root         1623 Apr  2 20:43 cpip.c
-rw-rw-r--    1 root     root         1470 Apr  2 20:43 hello++.cc
-rw-r--r--    1 root     root         3116 Apr  2 20:43 Makefile
-rw-rw-r--    1 root     root         2652 Apr  2 20:43 Makefile.in
lrwxrwxrwx    1 root     root           13 Jul 12 08:43 mpirun -> 
../bin/mpirun
-rw-rw-r--    1 root     root         2335 Apr  2 20:43 pi3.f
-rw-rw-r--    1 root     root         2209 Apr  2 20:43 pi3f90.f90
-rw-rw-r--    1 root     root         2341 Apr  2 20:43 pi3p.f
-rw-rw-r--    1 root     root          993 Apr  2 20:43 README
-rw-rw-r--    1 root     root         2311 Apr  2 20:43 simpleio.c

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/include:
total 140
drwxrwxr-x    3 root     root         4096 Jul 12 08:43 .
drwxrwxr-x   11 root     root         4096 Jul 12 08:43 ..
-rw-rw-r--    1 root     root         6226 Apr  2 20:37 basex11.h
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 c++
-rw-rw-r--    1 root     root          739 Apr  2 20:37 mpeexten.h
-rw-rw-r--    1 root     root         5643 Apr  2 20:37 mpe_graphics.h
-rw-rw-r--    1 root     root         1812 Apr  2 20:37 mpe.h
-rw-rw-r--    1 root     root         5849 Apr  2 20:37 mpe_log.h
-rw-rw-r--    1 root     root          611 Apr  2 20:37 mpetools.h
-rw-rw-r--    1 root     root         5644 Apr  2 20:43 mpichconf.h
-rw-rw-r--    1 root     root          469 Apr  2 20:43 mpidefs.h
-rw-rw-r--    1 root     root         3550 Apr  2 20:43 mpi_errno.h
-rw-rw-r--    1 root     root         9368 Apr  2 20:43 mpif.h
-rw-rw-r--    1 root     root        33923 Apr  2 20:43 mpi.h
-rw-rw-r--    1 root     root         1191 Apr  2 20:43 mpiof.h
-rw-rw-r--    1 root     root        17495 Apr  2 20:43 mpio.h
-rw-rw-r--    1 root     root         1982 Apr  2 20:37 protofix.h

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/include/c++:
total 268
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
drwxrwxr-x    3 root     root         4096 Jul 12 08:43 ..
-rw-rw-r--    1 root     root        11202 Apr  2 20:43 comm.h
-rw-rw-r--    1 root     root        13116 Apr  2 20:43 comm_inln.h
-rw-rw-r--    1 root     root         7929 Apr  2 20:43 constants.h
-rw-rw-r--    1 root     root         4682 Apr  2 20:43 datatype.h
-rw-rw-r--    1 root     root         4694 Apr  2 20:43 datatype_inln.h
-rw-rw-r--    1 root     root         4122 Apr  2 20:43 errhandler.h
-rw-rw-r--    1 root     root         1761 Apr  2 20:43 errhandler_inln.h
-rw-rw-r--    1 root     root         1992 Apr  2 20:43 exception.h
-rw-rw-r--    1 root     root         2175 Apr  2 20:43 functions.h
-rw-rw-r--    1 root     root         3128 Apr  2 20:43 functions_inln.h
-rw-rw-r--    1 root     root         3999 Apr  2 20:43 group.h
-rw-rw-r--    1 root     root         3474 Apr  2 20:43 group_inln.h
-rw-rw-r--    1 root     root         1188 Apr  2 20:43 header.h
-rw-rw-r--    1 root     root         3034 Apr  2 20:43 intercomm.h
-rw-rw-r--    1 root     root         2282 Apr  2 20:43 intercomm_inln.h
-rw-rw-r--    1 root     root         6431 Apr  2 20:43 intracomm.h
-rw-rw-r--    1 root     root         8112 Apr  2 20:43 intracomm_inln.h
-rw-rw-r--    1 root     root         1425 Apr  2 20:43 list.h
-rw-rw-r--    1 root     root         1812 Apr  2 20:43 map.h
-rw-rw-r--    1 root     root         3454 Apr  2 20:43 mpi2c++_config.h
-rw-rw-r--    1 root     root         4432 Apr  2 20:43 mpi++.h
-rw-rw-r--    1 root     root         2194 Apr  2 20:43 op.h
-rw-rw-r--    1 root     root         3238 Apr  2 20:43 op_inln.h
-rw-rw-r--    1 root     root         8652 Apr  2 20:43 pcomm.h
-rw-rw-r--    1 root     root         3473 Apr  2 20:43 pdatatype.h
-rw-rw-r--    1 root     root         2506 Apr  2 20:43 perrhandler.h
-rw-rw-r--    1 root     root         1727 Apr  2 20:43 pexception.h
-rw-rw-r--    1 root     root         2883 Apr  2 20:43 pgroup.h
-rw-rw-r--    1 root     root         1191 Apr  2 20:43 pgroup_inln.h
-rw-rw-r--    1 root     root         1715 Apr  2 20:43 pintercomm.h
-rw-rw-r--    1 root     root         4673 Apr  2 20:43 pintracomm.h
-rw-rw-r--    1 root     root         2149 Apr  2 20:43 pmpi++.h
-rw-rw-r--    1 root     root         1941 Apr  2 20:43 pop.h
-rw-rw-r--    1 root     root         1849 Apr  2 20:43 pop_inln.h
-rw-rw-r--    1 root     root         3583 Apr  2 20:43 prequest.h
-rw-rw-r--    1 root     root         1189 Apr  2 20:43 prequest_inln.h
-rw-rw-r--    1 root     root         2503 Apr  2 20:43 pstatus.h
-rw-rw-r--    1 root     root         1188 Apr  2 20:43 pstatus_inln.h
-rw-rw-r--    1 root     root         3192 Apr  2 20:43 ptopology.h
-rw-rw-r--    1 root     root         5504 Apr  2 20:43 request.h
-rw-rw-r--    1 root     root         9217 Apr  2 20:43 request_inln.h
-rw-rw-r--    1 root     root         3186 Apr  2 20:43 status.h
-rw-rw-r--    1 root     root         2442 Apr  2 20:43 status_inln.h
-rw-rw-r--    1 root     root         5223 Apr  2 20:43 topology.h
-rw-rw-r--    1 root     root         5995 Apr  2 20:43 topology_inln.h

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/lib:
total 2464
drwxrwxr-x    3 root     root         4096 Jul 12 08:43 .
drwxrwxr-x   11 root     root         4096 Jul 12 08:43 ..
-rw-rw-r--    1 root     root        12594 Apr  2 20:37 libampe.a
-rw-rw-r--    1 root     root       181172 Apr  2 20:37 libfmpich.a
-rw-rw-r--    1 root     root        88842 Apr  2 20:37 liblmpe.a
-rw-rw-r--    1 root     root       389336 Apr  2 20:37 libmpe.a
-rw-rw-r--    1 root     root        35368 Apr  2 20:37 libmpe_nompi.a
-rw-rw-r--    1 root     root      1129816 Apr  2 20:38 libmpich.a
-rw-rw-r--    1 root     root       555326 Apr  2 20:38 libmpich++.a
-rw-rw-r--    1 root     root         2974 Apr  2 20:36 libmpichf.a
-rw-rw-r--    1 root     root         2974 Apr  2 20:39 libmpichfarg.a
-rw-rw-r--    1 root     root        60692 Apr  2 20:37 libtmpe.a
-rw-rw-r--    1 root     root         7152 Apr  2 20:37 mpe_prof.o
drwxrwxr-x    2 root     root         4096 Apr  2 20:43 shared

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/lib/shared:
total 8
drwxrwxr-x    2 root     root         4096 Apr  2 20:43 .
drwxrwxr-x    3 root     root         4096 Jul 12 08:43 ..

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/man:
total 24
drwxrwxr-x    5 root     root         4096 Jul 12 08:43 .
drwxrwxr-x   11 root     root         4096 Jul 12 08:43 ..
drwxrwxr-x    2 root     root         4096 Apr  2 20:43 man1
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 man3
drwxrwxr-x    2 root     root         4096 Apr  2 20:43 man4
-rw-rw-r--    1 root     root           72 Apr  2 20:43 mandesc

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/man/man1:
total 8
drwxrwxr-x    2 root     root         4096 Apr  2 20:43 .
drwxrwxr-x    5 root     root         4096 Jul 12 08:43 ..

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/man/man3:
total 288
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
drwxrwxr-x    5 root     root         4096 Jul 12 08:43 ..
-rw-rw-r--    1 root     root          312 Apr  2 20:43 MPI_File_c2f.3
-rw-rw-r--    1 root     root          656 Apr  2 20:43 MPI_File_close.3
-rw-rw-r--    1 root     root          742 Apr  2 20:43 MPI_File_delete.3
-rw-rw-r--    1 root     root          312 Apr  2 20:43 MPI_File_f2c.3
-rw-rw-r--    1 root     root          766 Apr  2 20:43 MPI_File_get_amode.3
-rw-rw-r--    1 root     root          807 Apr  2 20:43 
MPI_File_get_atomicity.3
-rw-rw-r--    1 root     root          980 Apr  2 20:43 
MPI_File_get_byte_offset.3
-rw-rw-r--    1 root     root          810 Apr  2 20:43 MPI_File_get_group.3
-rw-rw-r--    1 root     root          811 Apr  2 20:43 MPI_File_get_info.3
-rw-rw-r--    1 root     root          895 Apr  2 20:43 
MPI_File_get_position.3
-rw-rw-r--    1 root     root          908 Apr  2 20:43 
MPI_File_get_position_shared.3
-rw-rw-r--    1 root     root          787 Apr  2 20:43 MPI_File_get_size.3
-rw-rw-r--    1 root     root          930 Apr  2 20:43 
MPI_File_get_type_extent.3
-rw-rw-r--    1 root     root         1002 Apr  2 20:43 MPI_File_get_view.3
-rw-rw-r--    1 root     root         1065 Apr  2 20:43 MPI_File_iread.3
-rw-rw-r--    1 root     root         1172 Apr  2 20:43 MPI_File_iread_at.3
-rw-rw-r--    1 root     root         1088 Apr  2 20:43 
MPI_File_iread_shared.3
-rw-rw-r--    1 root     root         1070 Apr  2 20:43 MPI_File_iwrite.3
-rw-rw-r--    1 root     root         1178 Apr  2 20:43 MPI_File_iwrite_at.3
-rw-rw-r--    1 root     root         1089 Apr  2 20:43 
MPI_File_iwrite_shared.3
-rw-rw-r--    1 root     root          963 Apr  2 20:43 MPI_File_open.3
-rw-rw-r--    1 root     root          782 Apr  2 20:43 MPI_File_preallocate.3
-rw-rw-r--    1 root     root         1044 Apr  2 20:43 MPI_File_read.3
-rw-rw-r--    1 root     root         1071 Apr  2 20:43 MPI_File_read_all.3
-rw-rw-r--    1 root     root         1037 Apr  2 20:43 
MPI_File_read_all_begin.3
-rw-rw-r--    1 root     root          892 Apr  2 20:43 
MPI_File_read_all_end.3
-rw-rw-r--    1 root     root         1113 Apr  2 20:43 MPI_File_read_at.3
-rw-rw-r--    1 root     root         1181 Apr  2 20:43 MPI_File_read_at_all.3
-rw-rw-r--    1 root     root         1115 Apr  2 20:43 
MPI_File_read_at_all_begin.3
-rw-rw-r--    1 root     root          892 Apr  2 20:43 
MPI_File_read_at_all_end.3
-rw-rw-r--    1 root     root         1082 Apr  2 20:43 
MPI_File_read_ordered.3
-rw-rw-r--    1 root     root         1020 Apr  2 20:43 
MPI_File_read_ordered_begin.3
-rw-rw-r--    1 root     root          900 Apr  2 20:43 
MPI_File_read_ordered_end.3
-rw-rw-r--    1 root     root         1060 Apr  2 20:43 MPI_File_read_shared.3
-rw-rw-r--    1 root     root          805 Apr  2 20:43 MPI_File_seek.3
-rw-rw-r--    1 root     root          822 Apr  2 20:43 MPI_File_seek_shared.3
-rw-rw-r--    1 root     root          788 Apr  2 20:43 
MPI_File_set_atomicity.3
-rw-rw-r--    1 root     root          765 Apr  2 20:43 MPI_File_set_info.3
-rw-rw-r--    1 root     root          767 Apr  2 20:43 MPI_File_set_size.3
-rw-rw-r--    1 root     root         1036 Apr  2 20:43 MPI_File_set_view.3
-rw-rw-r--    1 root     root          704 Apr  2 20:43 MPI_File_sync.3
-rw-rw-r--    1 root     root         1049 Apr  2 20:43 MPI_File_write.3
-rw-rw-r--    1 root     root         1076 Apr  2 20:43 MPI_File_write_all.3
-rw-rw-r--    1 root     root         1018 Apr  2 20:43 
MPI_File_write_all_begin.3
-rw-rw-r--    1 root     root          896 Apr  2 20:43 
MPI_File_write_all_end.3
-rw-rw-r--    1 root     root         1156 Apr  2 20:43 MPI_File_write_at.3
-rw-rw-r--    1 root     root         1187 Apr  2 20:43 
MPI_File_write_at_all.3
-rw-rw-r--    1 root     root         1096 Apr  2 20:43 
MPI_File_write_at_all_begin.3
-rw-rw-r--    1 root     root          896 Apr  2 20:43 
MPI_File_write_at_all_end.3
-rw-rw-r--    1 root     root         1066 Apr  2 20:43 
MPI_File_write_ordered.3
-rw-rw-r--    1 root     root         1025 Apr  2 20:43 
MPI_File_write_ordered_begin.3
-rw-rw-r--    1 root     root          904 Apr  2 20:43 
MPI_File_write_ordered_end.3
-rw-rw-r--    1 root     root         1072 Apr  2 20:43 
MPI_File_write_shared.3
-rw-rw-r--    1 root     root          298 Apr  2 20:43 MPI_Info_c2f.3
-rw-rw-r--    1 root     root          659 Apr  2 20:43 MPI_Info_create.3
-rw-rw-r--    1 root     root          717 Apr  2 20:43 MPI_Info_delete.3
-rw-rw-r--    1 root     root          766 Apr  2 20:43 MPI_Info_dup.3
-rw-rw-r--    1 root     root          298 Apr  2 20:43 MPI_Info_f2c.3
-rw-rw-r--    1 root     root          646 Apr  2 20:43 MPI_Info_free.3
-rw-rw-r--    1 root     root          954 Apr  2 20:43 MPI_Info_get.3
-rw-rw-r--    1 root     root          788 Apr  2 20:43 MPI_Info_get_nkeys.3
-rw-rw-r--    1 root     root          804 Apr  2 20:43 MPI_Info_get_nthkey.3
-rw-rw-r--    1 root     root          940 Apr  2 20:43 
MPI_Info_get_valuelen.3
-rw-rw-r--    1 root     root          759 Apr  2 20:43 MPI_Info_set.3
-rw-rw-r--    1 root     root          367 Apr  2 20:43 MPIO_Request_c2f.3
-rw-rw-r--    1 root     root          367 Apr  2 20:43 MPIO_Request_f2c.3
-rw-rw-r--    1 root     root          865 Apr  2 20:43 MPIO_Test.3
-rw-rw-r--    1 root     root          794 Apr  2 20:43 MPIO_Wait.3
-rw-rw-r--    1 root     root         1848 Apr  2 20:43 
MPI_Type_create_darray.3
-rw-rw-r--    1 root     root         1566 Apr  2 20:43 
MPI_Type_create_subarray.3

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/man/man4:
total 8
drwxrwxr-x    2 root     root         4096 Apr  2 20:43 .
drwxrwxr-x    5 root     root         4096 Jul 12 08:43 ..

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/MPI-2-C++:
total 12
drwxrwxr-x    3 root     root         4096 Jul 12 08:43 .
drwxrwxr-x   11 root     root         4096 Jul 12 08:43 ..
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 examples

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/MPI-2-C++/examples:
total 44
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
drwxrwxr-x    3 root     root         4096 Jul 12 08:43 ..
-rw-rw-r--    1 root     root         1790 Apr  2 20:43 chapter_10_mpi2.cc
-rw-rw-r--    1 root     root         1477 Apr  2 20:43 hello_world.cc
-rw-r--r--    1 root     root         1183 Apr  2 20:43 Makefile
-rw-rw-r--    1 root     root         1035 Apr  2 20:43 Makefile.in
lrwxrwxrwx    1 root     root           16 Jul 12 08:43 mpirun -> 
../../bin/mpirun
-rw-rw-r--    1 root     root         2163 Apr  2 20:43 pi.cc
-rw-rw-r--    1 root     root         1724 Apr  2 20:43 README
-rw-rw-r--    1 root     root         2141 Apr  2 20:43 ring.cc
-rw-rw-r--    1 root     root         3673 Apr  2 20:43 topology.cc
-rw-rw-r--    1 root     root         2805 Apr  2 20:43 user_bcast.cc

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/sbin:
total 44
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
drwxrwxr-x   11 root     root         4096 Jul 12 08:43 ..
-rwxrwxr-x    1 root     root         1155 Apr  2 20:43 cleanipcs
-rwxr-xr-x    1 root     root        31025 Apr  2 20:43 mpiuninstall

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share:
total 24
drwxrwxr-x    5 root     root         4096 Jul 12 08:43 .
drwxrwxr-x   11 root     root         4096 Jul 12 08:43 ..
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 examples
drwxrwxr-x    7 root     root         4096 Jul 12 08:43 jumpshot-3
-rw-rw-r--    1 root     root         3116 Apr  2 20:43 Makefile.sample
drwxrwxr-x    6 root     root         4096 Jul 12 08:43 upshot

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/examples:
total 32
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
drwxrwxr-x    5 root     root         4096 Jul 12 08:43 ..
-rw-rw-r--    1 root     root         1638 Jun  7  2001 cpi.c
-rw-rw-r--    1 root     root         2733 Jun  7  2001 cpilog.c
-rw-rw-r--    1 root     root         4180 Dec 22  1999 fpi.f
-rw-rw-r--    1 root     root         3985 Jun  7  2001 Makefile.in
lrwxrwxrwx    1 root     root           64 Jul 12 08:43 mpirun -> 
/opt/score5.0.0/mpi/mpich-1.2.0/i386-redhat7-linux2_4/bin/mpirun
-rw-rw-r--    1 root     root         1487 Jun  7  2001 srtest.c

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/jumpshot-3:
total 60
drwxrwxr-x    7 root     root         4096 Jul 12 08:43 .
drwxrwxr-x    5 root     root         4096 Jul 12 08:43 ..
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 bin
drwxrwxr-x    3 root     root         4096 Jul 12 08:43 doc
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 lib
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 logfiles
-rw-rw-r--    1 root     root         1610 Jun  7  2001 README
-rw-rw-r--    1 root     root         2854 Jun  7  2001 README.slog
drwxrwxr-x    2 root     root         4096 Apr  2 20:43 sbin
-rw-rw-r--    1 root     root        17951 Jun  7  2001 TourStepByStep.txt
-rw-rw-r--    1 root     root         3487 Jun  7  2001 UserGuide.txt

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/jumpshot-3/bin:
total 16
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
drwxrwxr-x    7 root     root         4096 Jul 12 08:43 ..
-rwxrwxr-x    1 root     root         1683 Apr  2 20:43 jumpshot
-rwxrwxr-x    1 root     root          754 Apr  2 20:43 slog_print

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/jumpshot-3/doc:
total 1032
drwxrwxr-x    3 root     root         4096 Jul 12 08:43 .
drwxrwxr-x    7 root     root         4096 Jul 12 08:43 ..
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 html
-rw-rw-r--    1 root     root        10196 Jun  7  2001 jumpshot.def
-rw-rw-r--    1 root     root      1026872 Jun  7  2001 TourStepByStep.pdf

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/jumpshot-3/doc/html:
total 588
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
drwxrwxr-x    3 root     root         4096 Jul 12 08:43 ..
-rw-rw-r--    1 root     root         2569 Jun  7  2001 footnode.html
-rw-rw-r--    1 root     root            8 Jun  7  2001 images.aux
-rw-rw-r--    1 root     root         4137 Jun  7  2001 images.log
-rw-rw-r--    1 root     root         3897 Jun  7  2001 images.pl
-rw-rw-r--    1 root     root         6421 Jun  7  2001 images.tex
-rw-rw-r--    1 root     root        39322 Jun  7  2001 img10.gif
-rw-rw-r--    1 root     root        14179 Jun  7  2001 img11.gif
-rw-rw-r--    1 root     root        24365 Jun  7  2001 img12.gif
-rw-rw-r--    1 root     root        21421 Jun  7  2001 img13.gif
-rw-rw-r--    1 root     root        12735 Jun  7  2001 img1.gif
-rw-rw-r--    1 root     root        62084 Jun  7  2001 img2.gif
-rw-rw-r--    1 root     root        65594 Jun  7  2001 img3.gif
-rw-rw-r--    1 root     root        18473 Jun  7  2001 img4.gif
-rw-rw-r--    1 root     root        59650 Jun  7  2001 img5.gif
-rw-rw-r--    1 root     root        20848 Jun  7  2001 img6.gif
-rw-rw-r--    1 root     root        13782 Jun  7  2001 img7.gif
-rw-rw-r--    1 root     root         4579 Jun  7  2001 img8.gif
-rw-rw-r--    1 root     root        55575 Jun  7  2001 img9.gif
-rw-rw-r--    1 root     root         2817 Jun  7  2001 index.html
-rw-rw-r--    1 root     root         1376 Jun  7  2001 internals.pl
-rw-rw-r--    1 root     root         2617 Jun  7  2001 labels.pl
-rw-rw-r--    1 root     root          172 Jun  7  2001 next_g.gif
-rw-rw-r--    1 root     root          172 Jun  7  2001 next.gif
-rw-rw-r--    1 root     root         2344 Jun  7  2001 node1.html
-rw-rw-r--    1 root     root         4239 Jun  7  2001 node2.html
-rw-rw-r--    1 root     root        11190 Jun  7  2001 node3.html
-rw-rw-r--    1 root     root         5240 Jun  7  2001 node4.html
-rw-rw-r--    1 root     root        10579 Jun  7  2001 node5.html
-rw-rw-r--    1 root     root         2192 Jun  7  2001 node6.html
-rw-rw-r--    1 root     root         2388 Jun  7  2001 node7.html
-rw-rw-r--    1 root     root          220 Jun  7  2001 prev_g.gif
-rw-rw-r--    1 root     root          220 Jun  7  2001 prev.gif
-rw-rw-r--    1 root     root          891 Jun  7  2001 TourStepByStep.css
-rw-rw-r--    1 root     root         2817 Jun  7  2001 TourStepByStep.html
-rw-rw-r--    1 root     root          145 Jun  7  2001 up_g.gif
-rw-rw-r--    1 root     root          145 Jun  7  2001 up.gif
-rw-rw-r--    1 root     root           44 Jun  7  2001 WARNINGS

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/jumpshot-3/lib:
total 268
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
drwxrwxr-x    7 root     root         4096 Jul 12 08:43 ..
-rw-rw-r--    1 root     root         6383 Jun  7  2001 images.jar
-rw-rw-r--    1 root     root        17162 Jun  7  2001 jumpshot.colors
-rw-rw-r--    1 root     root       137699 Apr  2 20:37 jumpshot.jar
-rw-rw-r--    1 root     root          109 Jun  7  2001 jumpshot.setup
-rw-rw-r--    1 root     root        23370 Apr  2 20:37 preview.jar
-rw-rw-r--    1 root     root        34002 Apr  2 20:37 slog.jar
-rw-rw-r--    1 root     root         1252 Apr  2 20:37 slog_print.class
-rw-rw-r--    1 root     root        22174 Apr  2 20:37 statsviewer.jar

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/jumpshot-3/logfiles:
total 1688
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
drwxrwxr-x    7 root     root         4096 Jul 12 08:43 ..
-rw-rw-r--    1 root     root       685546 Jun  7  2001 invalid.slog
-rw-rw-r--    1 root     root        11692 Jun  7  2001 sample.slog
-rw-rw-r--    1 root     root       985187 Jun  7  2001 sppm_ic2a.slog
-rw-rw-r--    1 root     root         6654 Jun  7  2001 sppm.stats.0301
-rw-rw-r--    1 root     root         3956 Jun  7  2001 stats0204.txt
-rw-rw-r--    1 root     root         1633 Jun  7  2001 stats3.txt
-rw-rw-r--    1 root     root         7106 Jun  7  2001 thread1.stats

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/jumpshot-3/sbin:
total 8
drwxrwxr-x    2 root     root         4096 Apr  2 20:43 .
drwxrwxr-x    7 root     root         4096 Jul 12 08:43 ..

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/upshot:
total 24
drwxrwxr-x    6 root     root         4096 Jul 12 08:43 .
drwxrwxr-x    5 root     root         4096 Jul 12 08:43 ..
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 bin
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 bitmaps
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 logfiles
drwxrwxr-x    2 root     root         4096 Apr  2 20:43 sbin

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/upshot/bin:
total 124
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
drwxrwxr-x    6 root     root         4096 Jul 12 08:43 ..
-rwxrwxr-x    1 root     root       114299 Apr  2 20:43 upshot

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/upshot/bitmaps:
total 84
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
drwxrwxr-x    6 root     root         4096 Jul 12 08:43 ..
-rw-rw-r--    1 root     root           96 Jun  7  2001 2x2
-rw-rw-r--    1 root     root          278 Jun  7  2001 black
-rw-rw-r--    1 root     root          126 Jun  7  2001 boxes
-rw-rw-r--    1 root     root          284 Jun  7  2001 dimple3
-rw-rw-r--    1 root     root          198 Jun  7  2001 dllines3
-rw-rw-r--    1 root     root          111 Jun  7  2001 dllines4
-rw-rw-r--    1 root     root          195 Jun  7  2001 drlines3
-rw-rw-r--    1 root     root          111 Jun  7  2001 drlines4
-rw-rw-r--    1 root     root           87 Jun  7  2001 gray
-rw-rw-r--    1 root     root          105 Jun  7  2001 gray2
-rw-rw-r--    1 root     root          102 Jun  7  2001 gray3
-rw-rw-r--    1 root     root          284 Jun  7  2001 hlines2
-rw-rw-r--    1 root     root          272 Jun  7  2001 hlines3
-rw-rw-r--    1 root     root          284 Jun  7  2001 hlines4
-rw-rw-r--    1 root     root          105 Jun  7  2001 light_gray
-rw-rw-r--    1 root     root          108 Jun  7  2001 vlines2
-rw-rw-r--    1 root     root           90 Jun  7  2001 vlines3
-rw-rw-r--    1 root     root          108 Jun  7  2001 vlines4
-rw-rw-r--    1 root     root           90 Jun  7  2001 white

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/upshot/logfiles:
total 36
drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
drwxrwxr-x    6 root     root         4096 Jul 12 08:43 ..
-rw-rw-r--    1 root     root        11762 Jun  7  2001 fft.trf
-rw-rw-r--    1 root     root        15017 Jun  7  2001 sam_hyp.16.log

/opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/upshot/sbin:
total 8
drwxrwxr-x    2 root     root         4096 Apr  2 20:43 .
drwxrwxr-x    6 root     root         4096 Jul 12 08:43 ..
alambert ＠ grasshopper:~$ which mpicc
/opt/score/bin/mpicc
alambert ＠ grasshopper:~$ mpicc -device ch_score2 -o hello hello.cc
mpicc: mpich-1.2.0 device score2 is not installed
alambert ＠ grasshopper:~$ mpicc -device ch_score2 -O2 -o alltoall alltoall.c
mpicc: mpich-1.2.0 device score2 is not installed
alambert ＠ grasshopper:~$


from 'make' (after extracting source and attempting recompile):

+ DIST=
+ /opt/score/bin/mkwrapper /opt/score/bin bin .exe
+ cd /opt/score/bin
++ basename mpi_rtt.exe .exe
+ g=mpi_rtt
+ rm -f mpi_rtt
+ ln -s .wrapper mpi_rtt
++ basename mpi_bw.exe .exe
+ g=mpi_bw
+ rm -f mpi_bw
+ ln -s .wrapper mpi_bw
++ basename mpi_bw2.exe .exe
+ g=mpi_bw2
+ rm -f mpi_bw2
+ ln -s .wrapper mpi_bw2
++ basename mpitest.exe .exe
+ g=mpitest
+ rm -f mpitest
+ ln -s .wrapper mpitest
+ set +x
make[3]: Leaving directory 
`/opt/score5.0.0/work/score-src/program/bench/mpi/obj.i386-redhat7-linux2_4'
make[2]: Leaving directory `/opt/score5.0.0/work/score-src/program/bench/mpi'
make[1]: Leaving directory `/opt/score5.0.0/work/score-src/program/bench'
make: *** [all] Error 1
[root ＠ grasshopper score-src]#

_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From s-sumi ＠ bd6.so-net.ne.jp  Sat Jul 20 10:44:57 2002
From: s-sumi ＠ bd6.so-net.ne.jp (Shinji Sumimoto)
Date: Sat, 20 Jul 2002 10:44:57 +0900 (JST)
Subject: [SCore-users-jp] [SCore-users] Error: mpich-1.2.0 device
 score2 is not installed
In-Reply-To: <200207191947.g6JJlmB18960@grasshopper.ge1>
References: <200207191947.g6JJlmB18960@grasshopper.ge1>
Message-ID: <20020720.104457.730552396.s-sumi@bd6.so-net.ne.jp>

Hi.

From: Alex Lambert <alambert ＠ scl.ameslab.gov>
Subject: [SCore-users-jp] [SCore-users] Error: mpich-1.2.0 device score2 is not installed
Date: Fri, 19 Jul 2002 14:47:40 -0500
Message-ID: <200207191947.g6JJlmB18960 ＠ grasshopper.ge1>

alambert> Greetings,
alambert> 
alambert> I'm trying to test the performance of MPICH-SCore 2.0 as opposed to the 1.0 
alambert> that is used by default. When I try to specify it explicitly when compiling, 
alambert> I receive an error saying that the device is not installed.
alambert> 
alambert> How would I go about enabling the 2.0 version? I've attempted to recompile 
alambert> per the directions, but mangled my install horribly (oops).

MPICH-SCore 2.0 is not installed now. You have to re-compile SCore
from source. 

See: 
 http://www.pccluster.org/score/dist/score/html/en/installation/index.html

After installing sources.
% cd /opt/score/score-src/runtime/mpi/mpich-1.2.0
% ./mpi_make.sh -device ch_score2 build
% ./mpi_make.sh -device ch_score2 install

Notes:
	MPICH-SCore 2.0 is not supported now.
	We are now preparing new version of MPI library (Next year?). 

When you want to test MPICH/SCore2 on Myrinet2000.  Please let us
know. A patch is needed to realize zero-copy communication on
PM/Myrinet2k.
 
Shinji.

alambert> Thanks,
alambert> 
alambert> 
alambert> Alex Lambert
alambert> Scalable Computing Lab
alambert> 
alambert> alambert ＠ grasshopper:~$ echo $PATH
alambert> /opt/score/bin:/opt/score/sbin:/opt/score/deploy:/usr/local/bin:/usr/local/sbin:/scl/bin:/usr/bin:/usr/sbin:/usr/bin/X11:/bin:/sbin:/etc:/usr/etc:/usr/etc/fore/etc:/usr/java/jdk1.3.1/bin:/usr/kerberos/bin
alambert> alambert ＠ grasshopper:~$ ls -alR 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4:
alambert> total 44
alambert> drwxrwxr-x   11 root     root         4096 Jul 12 08:43 .
alambert> drwxr-xr-x    4 root     root         4096 Jul 12 08:43 ..
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 bin
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 doc
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 examples
alambert> drwxrwxr-x    3 root     root         4096 Jul 12 08:43 include
alambert> drwxrwxr-x    3 root     root         4096 Jul 12 08:43 lib
alambert> drwxrwxr-x    5 root     root         4096 Jul 12 08:43 man
alambert> drwxrwxr-x    3 root     root         4096 Jul 12 08:43 MPI-2-C++
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 sbin
alambert> drwxrwxr-x    5 root     root         4096 Jul 12 08:43 share
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/bin:
alambert> total 560
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x   11 root     root         4096 Jul 12 08:43 ..
alambert> -rwxrwxr-x    1 root     root         9516 Apr  2 20:43 clog2alog
alambert> -rwxrwxr-x    1 root     root       206476 Apr  2 20:43 clog2slog
alambert> -rwxrwxr-x    1 root     root         6284 Apr  2 20:43 clog_print
alambert> -rwxrwxr-x    1 root     root         4158 Apr  2 20:43 execer
alambert> -rwxrwxr-x    1 root     root         3521 Apr  2 20:43 logviewer
alambert> -rwxrwxr-x    1 root     root         1988 Apr  2 20:43 mpereconfig
alambert> -rwxrwxr-x    1 root     root        12920 Apr  2 20:43 mpereconfig.dat
alambert> lrwxrwxrwx    1 root     root            5 Jul 12 08:43 mpic++ -> mpiCC
alambert> -rwxrwxr-x    1 root     root         8875 Apr  2 20:43 mpicc
alambert> -rwxrwxr-x    1 root     root         7709 Apr  2 20:43 mpiCC
alambert> -rwxrwxr-x    1 root     root         8073 Apr  2 20:43 mpif77
alambert> -rwxrwxr-x    1 root     root         8468 Apr  2 20:43 mpif90
alambert> -rwxrwxr-x    1 root     root         1015 Apr  2 20:43 mpiman
alambert> -rwxrwxr-x    1 root     root         2855 Apr  2 20:43 mpireconfig
alambert> -rwxrwxr-x    1 root     root        24349 Apr  2 20:43 mpireconfig.dat
alambert> -rwxrwxr-x    1 root     root         3928 Apr  2 20:43 mpirun
alambert> -rwxrwxr-x    1 root     root        21686 Apr  2 20:43 mpirun.args
alambert> -rwxrwxr-x    1 root     root         3968 Apr  2 20:43 mpirun.ch_score
alambert> -rwxrwxr-x    1 root     root          154 Apr  2 20:43 mpirun.ch_score.args
alambert> -rwxrwxr-x    1 root     root       172844 Apr  2 20:43 slog_print
alambert> -rwxrwxr-x    1 root     root         3403 Apr  2 20:43 tarch
alambert> -rwxrwxr-x    1 root     root          834 Apr  2 20:43 tdevice
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/doc:
alambert> total 416
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x   11 root     root         4096 Jul 12 08:43 ..
alambert> -rw-rw-r--    1 root     root       251022 Apr  2 20:43 guide.ps.gz
alambert> -rw-rw-r--    1 root     root       151934 Apr  2 20:43 install.ps.gz
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/examples:
alambert> total 52
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x   11 root     root         4096 Jul 12 08:43 ..
alambert> -rw-rw-r--    1 root     root         1614 Apr  2 20:43 cpi.c
alambert> -rw-rw-r--    1 root     root         1937 Apr  2 20:43 cpilog.c
alambert> -rw-rw-r--    1 root     root         1623 Apr  2 20:43 cpip.c
alambert> -rw-rw-r--    1 root     root         1470 Apr  2 20:43 hello++.cc
alambert> -rw-r--r--    1 root     root         3116 Apr  2 20:43 Makefile
alambert> -rw-rw-r--    1 root     root         2652 Apr  2 20:43 Makefile.in
alambert> lrwxrwxrwx    1 root     root           13 Jul 12 08:43 mpirun -> 
alambert> ../bin/mpirun
alambert> -rw-rw-r--    1 root     root         2335 Apr  2 20:43 pi3.f
alambert> -rw-rw-r--    1 root     root         2209 Apr  2 20:43 pi3f90.f90
alambert> -rw-rw-r--    1 root     root         2341 Apr  2 20:43 pi3p.f
alambert> -rw-rw-r--    1 root     root          993 Apr  2 20:43 README
alambert> -rw-rw-r--    1 root     root         2311 Apr  2 20:43 simpleio.c
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/include:
alambert> total 140
alambert> drwxrwxr-x    3 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x   11 root     root         4096 Jul 12 08:43 ..
alambert> -rw-rw-r--    1 root     root         6226 Apr  2 20:37 basex11.h
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 c++
alambert> -rw-rw-r--    1 root     root          739 Apr  2 20:37 mpeexten.h
alambert> -rw-rw-r--    1 root     root         5643 Apr  2 20:37 mpe_graphics.h
alambert> -rw-rw-r--    1 root     root         1812 Apr  2 20:37 mpe.h
alambert> -rw-rw-r--    1 root     root         5849 Apr  2 20:37 mpe_log.h
alambert> -rw-rw-r--    1 root     root          611 Apr  2 20:37 mpetools.h
alambert> -rw-rw-r--    1 root     root         5644 Apr  2 20:43 mpichconf.h
alambert> -rw-rw-r--    1 root     root          469 Apr  2 20:43 mpidefs.h
alambert> -rw-rw-r--    1 root     root         3550 Apr  2 20:43 mpi_errno.h
alambert> -rw-rw-r--    1 root     root         9368 Apr  2 20:43 mpif.h
alambert> -rw-rw-r--    1 root     root        33923 Apr  2 20:43 mpi.h
alambert> -rw-rw-r--    1 root     root         1191 Apr  2 20:43 mpiof.h
alambert> -rw-rw-r--    1 root     root        17495 Apr  2 20:43 mpio.h
alambert> -rw-rw-r--    1 root     root         1982 Apr  2 20:37 protofix.h
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/include/c++:
alambert> total 268
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x    3 root     root         4096 Jul 12 08:43 ..
alambert> -rw-rw-r--    1 root     root        11202 Apr  2 20:43 comm.h
alambert> -rw-rw-r--    1 root     root        13116 Apr  2 20:43 comm_inln.h
alambert> -rw-rw-r--    1 root     root         7929 Apr  2 20:43 constants.h
alambert> -rw-rw-r--    1 root     root         4682 Apr  2 20:43 datatype.h
alambert> -rw-rw-r--    1 root     root         4694 Apr  2 20:43 datatype_inln.h
alambert> -rw-rw-r--    1 root     root         4122 Apr  2 20:43 errhandler.h
alambert> -rw-rw-r--    1 root     root         1761 Apr  2 20:43 errhandler_inln.h
alambert> -rw-rw-r--    1 root     root         1992 Apr  2 20:43 exception.h
alambert> -rw-rw-r--    1 root     root         2175 Apr  2 20:43 functions.h
alambert> -rw-rw-r--    1 root     root         3128 Apr  2 20:43 functions_inln.h
alambert> -rw-rw-r--    1 root     root         3999 Apr  2 20:43 group.h
alambert> -rw-rw-r--    1 root     root         3474 Apr  2 20:43 group_inln.h
alambert> -rw-rw-r--    1 root     root         1188 Apr  2 20:43 header.h
alambert> -rw-rw-r--    1 root     root         3034 Apr  2 20:43 intercomm.h
alambert> -rw-rw-r--    1 root     root         2282 Apr  2 20:43 intercomm_inln.h
alambert> -rw-rw-r--    1 root     root         6431 Apr  2 20:43 intracomm.h
alambert> -rw-rw-r--    1 root     root         8112 Apr  2 20:43 intracomm_inln.h
alambert> -rw-rw-r--    1 root     root         1425 Apr  2 20:43 list.h
alambert> -rw-rw-r--    1 root     root         1812 Apr  2 20:43 map.h
alambert> -rw-rw-r--    1 root     root         3454 Apr  2 20:43 mpi2c++_config.h
alambert> -rw-rw-r--    1 root     root         4432 Apr  2 20:43 mpi++.h
alambert> -rw-rw-r--    1 root     root         2194 Apr  2 20:43 op.h
alambert> -rw-rw-r--    1 root     root         3238 Apr  2 20:43 op_inln.h
alambert> -rw-rw-r--    1 root     root         8652 Apr  2 20:43 pcomm.h
alambert> -rw-rw-r--    1 root     root         3473 Apr  2 20:43 pdatatype.h
alambert> -rw-rw-r--    1 root     root         2506 Apr  2 20:43 perrhandler.h
alambert> -rw-rw-r--    1 root     root         1727 Apr  2 20:43 pexception.h
alambert> -rw-rw-r--    1 root     root         2883 Apr  2 20:43 pgroup.h
alambert> -rw-rw-r--    1 root     root         1191 Apr  2 20:43 pgroup_inln.h
alambert> -rw-rw-r--    1 root     root         1715 Apr  2 20:43 pintercomm.h
alambert> -rw-rw-r--    1 root     root         4673 Apr  2 20:43 pintracomm.h
alambert> -rw-rw-r--    1 root     root         2149 Apr  2 20:43 pmpi++.h
alambert> -rw-rw-r--    1 root     root         1941 Apr  2 20:43 pop.h
alambert> -rw-rw-r--    1 root     root         1849 Apr  2 20:43 pop_inln.h
alambert> -rw-rw-r--    1 root     root         3583 Apr  2 20:43 prequest.h
alambert> -rw-rw-r--    1 root     root         1189 Apr  2 20:43 prequest_inln.h
alambert> -rw-rw-r--    1 root     root         2503 Apr  2 20:43 pstatus.h
alambert> -rw-rw-r--    1 root     root         1188 Apr  2 20:43 pstatus_inln.h
alambert> -rw-rw-r--    1 root     root         3192 Apr  2 20:43 ptopology.h
alambert> -rw-rw-r--    1 root     root         5504 Apr  2 20:43 request.h
alambert> -rw-rw-r--    1 root     root         9217 Apr  2 20:43 request_inln.h
alambert> -rw-rw-r--    1 root     root         3186 Apr  2 20:43 status.h
alambert> -rw-rw-r--    1 root     root         2442 Apr  2 20:43 status_inln.h
alambert> -rw-rw-r--    1 root     root         5223 Apr  2 20:43 topology.h
alambert> -rw-rw-r--    1 root     root         5995 Apr  2 20:43 topology_inln.h
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/lib:
alambert> total 2464
alambert> drwxrwxr-x    3 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x   11 root     root         4096 Jul 12 08:43 ..
alambert> -rw-rw-r--    1 root     root        12594 Apr  2 20:37 libampe.a
alambert> -rw-rw-r--    1 root     root       181172 Apr  2 20:37 libfmpich.a
alambert> -rw-rw-r--    1 root     root        88842 Apr  2 20:37 liblmpe.a
alambert> -rw-rw-r--    1 root     root       389336 Apr  2 20:37 libmpe.a
alambert> -rw-rw-r--    1 root     root        35368 Apr  2 20:37 libmpe_nompi.a
alambert> -rw-rw-r--    1 root     root      1129816 Apr  2 20:38 libmpich.a
alambert> -rw-rw-r--    1 root     root       555326 Apr  2 20:38 libmpich++.a
alambert> -rw-rw-r--    1 root     root         2974 Apr  2 20:36 libmpichf.a
alambert> -rw-rw-r--    1 root     root         2974 Apr  2 20:39 libmpichfarg.a
alambert> -rw-rw-r--    1 root     root        60692 Apr  2 20:37 libtmpe.a
alambert> -rw-rw-r--    1 root     root         7152 Apr  2 20:37 mpe_prof.o
alambert> drwxrwxr-x    2 root     root         4096 Apr  2 20:43 shared
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/lib/shared:
alambert> total 8
alambert> drwxrwxr-x    2 root     root         4096 Apr  2 20:43 .
alambert> drwxrwxr-x    3 root     root         4096 Jul 12 08:43 ..
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/man:
alambert> total 24
alambert> drwxrwxr-x    5 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x   11 root     root         4096 Jul 12 08:43 ..
alambert> drwxrwxr-x    2 root     root         4096 Apr  2 20:43 man1
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 man3
alambert> drwxrwxr-x    2 root     root         4096 Apr  2 20:43 man4
alambert> -rw-rw-r--    1 root     root           72 Apr  2 20:43 mandesc
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/man/man1:
alambert> total 8
alambert> drwxrwxr-x    2 root     root         4096 Apr  2 20:43 .
alambert> drwxrwxr-x    5 root     root         4096 Jul 12 08:43 ..
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/man/man3:
alambert> total 288
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x    5 root     root         4096 Jul 12 08:43 ..
alambert> -rw-rw-r--    1 root     root          312 Apr  2 20:43 MPI_File_c2f.3
alambert> -rw-rw-r--    1 root     root          656 Apr  2 20:43 MPI_File_close.3
alambert> -rw-rw-r--    1 root     root          742 Apr  2 20:43 MPI_File_delete.3
alambert> -rw-rw-r--    1 root     root          312 Apr  2 20:43 MPI_File_f2c.3
alambert> -rw-rw-r--    1 root     root          766 Apr  2 20:43 MPI_File_get_amode.3
alambert> -rw-rw-r--    1 root     root          807 Apr  2 20:43 
alambert> MPI_File_get_atomicity.3
alambert> -rw-rw-r--    1 root     root          980 Apr  2 20:43 
alambert> MPI_File_get_byte_offset.3
alambert> -rw-rw-r--    1 root     root          810 Apr  2 20:43 MPI_File_get_group.3
alambert> -rw-rw-r--    1 root     root          811 Apr  2 20:43 MPI_File_get_info.3
alambert> -rw-rw-r--    1 root     root          895 Apr  2 20:43 
alambert> MPI_File_get_position.3
alambert> -rw-rw-r--    1 root     root          908 Apr  2 20:43 
alambert> MPI_File_get_position_shared.3
alambert> -rw-rw-r--    1 root     root          787 Apr  2 20:43 MPI_File_get_size.3
alambert> -rw-rw-r--    1 root     root          930 Apr  2 20:43 
alambert> MPI_File_get_type_extent.3
alambert> -rw-rw-r--    1 root     root         1002 Apr  2 20:43 MPI_File_get_view.3
alambert> -rw-rw-r--    1 root     root         1065 Apr  2 20:43 MPI_File_iread.3
alambert> -rw-rw-r--    1 root     root         1172 Apr  2 20:43 MPI_File_iread_at.3
alambert> -rw-rw-r--    1 root     root         1088 Apr  2 20:43 
alambert> MPI_File_iread_shared.3
alambert> -rw-rw-r--    1 root     root         1070 Apr  2 20:43 MPI_File_iwrite.3
alambert> -rw-rw-r--    1 root     root         1178 Apr  2 20:43 MPI_File_iwrite_at.3
alambert> -rw-rw-r--    1 root     root         1089 Apr  2 20:43 
alambert> MPI_File_iwrite_shared.3
alambert> -rw-rw-r--    1 root     root          963 Apr  2 20:43 MPI_File_open.3
alambert> -rw-rw-r--    1 root     root          782 Apr  2 20:43 MPI_File_preallocate.3
alambert> -rw-rw-r--    1 root     root         1044 Apr  2 20:43 MPI_File_read.3
alambert> -rw-rw-r--    1 root     root         1071 Apr  2 20:43 MPI_File_read_all.3
alambert> -rw-rw-r--    1 root     root         1037 Apr  2 20:43 
alambert> MPI_File_read_all_begin.3
alambert> -rw-rw-r--    1 root     root          892 Apr  2 20:43 
alambert> MPI_File_read_all_end.3
alambert> -rw-rw-r--    1 root     root         1113 Apr  2 20:43 MPI_File_read_at.3
alambert> -rw-rw-r--    1 root     root         1181 Apr  2 20:43 MPI_File_read_at_all.3
alambert> -rw-rw-r--    1 root     root         1115 Apr  2 20:43 
alambert> MPI_File_read_at_all_begin.3
alambert> -rw-rw-r--    1 root     root          892 Apr  2 20:43 
alambert> MPI_File_read_at_all_end.3
alambert> -rw-rw-r--    1 root     root         1082 Apr  2 20:43 
alambert> MPI_File_read_ordered.3
alambert> -rw-rw-r--    1 root     root         1020 Apr  2 20:43 
alambert> MPI_File_read_ordered_begin.3
alambert> -rw-rw-r--    1 root     root          900 Apr  2 20:43 
alambert> MPI_File_read_ordered_end.3
alambert> -rw-rw-r--    1 root     root         1060 Apr  2 20:43 MPI_File_read_shared.3
alambert> -rw-rw-r--    1 root     root          805 Apr  2 20:43 MPI_File_seek.3
alambert> -rw-rw-r--    1 root     root          822 Apr  2 20:43 MPI_File_seek_shared.3
alambert> -rw-rw-r--    1 root     root          788 Apr  2 20:43 
alambert> MPI_File_set_atomicity.3
alambert> -rw-rw-r--    1 root     root          765 Apr  2 20:43 MPI_File_set_info.3
alambert> -rw-rw-r--    1 root     root          767 Apr  2 20:43 MPI_File_set_size.3
alambert> -rw-rw-r--    1 root     root         1036 Apr  2 20:43 MPI_File_set_view.3
alambert> -rw-rw-r--    1 root     root          704 Apr  2 20:43 MPI_File_sync.3
alambert> -rw-rw-r--    1 root     root         1049 Apr  2 20:43 MPI_File_write.3
alambert> -rw-rw-r--    1 root     root         1076 Apr  2 20:43 MPI_File_write_all.3
alambert> -rw-rw-r--    1 root     root         1018 Apr  2 20:43 
alambert> MPI_File_write_all_begin.3
alambert> -rw-rw-r--    1 root     root          896 Apr  2 20:43 
alambert> MPI_File_write_all_end.3
alambert> -rw-rw-r--    1 root     root         1156 Apr  2 20:43 MPI_File_write_at.3
alambert> -rw-rw-r--    1 root     root         1187 Apr  2 20:43 
alambert> MPI_File_write_at_all.3
alambert> -rw-rw-r--    1 root     root         1096 Apr  2 20:43 
alambert> MPI_File_write_at_all_begin.3
alambert> -rw-rw-r--    1 root     root          896 Apr  2 20:43 
alambert> MPI_File_write_at_all_end.3
alambert> -rw-rw-r--    1 root     root         1066 Apr  2 20:43 
alambert> MPI_File_write_ordered.3
alambert> -rw-rw-r--    1 root     root         1025 Apr  2 20:43 
alambert> MPI_File_write_ordered_begin.3
alambert> -rw-rw-r--    1 root     root          904 Apr  2 20:43 
alambert> MPI_File_write_ordered_end.3
alambert> -rw-rw-r--    1 root     root         1072 Apr  2 20:43 
alambert> MPI_File_write_shared.3
alambert> -rw-rw-r--    1 root     root          298 Apr  2 20:43 MPI_Info_c2f.3
alambert> -rw-rw-r--    1 root     root          659 Apr  2 20:43 MPI_Info_create.3
alambert> -rw-rw-r--    1 root     root          717 Apr  2 20:43 MPI_Info_delete.3
alambert> -rw-rw-r--    1 root     root          766 Apr  2 20:43 MPI_Info_dup.3
alambert> -rw-rw-r--    1 root     root          298 Apr  2 20:43 MPI_Info_f2c.3
alambert> -rw-rw-r--    1 root     root          646 Apr  2 20:43 MPI_Info_free.3
alambert> -rw-rw-r--    1 root     root          954 Apr  2 20:43 MPI_Info_get.3
alambert> -rw-rw-r--    1 root     root          788 Apr  2 20:43 MPI_Info_get_nkeys.3
alambert> -rw-rw-r--    1 root     root          804 Apr  2 20:43 MPI_Info_get_nthkey.3
alambert> -rw-rw-r--    1 root     root          940 Apr  2 20:43 
alambert> MPI_Info_get_valuelen.3
alambert> -rw-rw-r--    1 root     root          759 Apr  2 20:43 MPI_Info_set.3
alambert> -rw-rw-r--    1 root     root          367 Apr  2 20:43 MPIO_Request_c2f.3
alambert> -rw-rw-r--    1 root     root          367 Apr  2 20:43 MPIO_Request_f2c.3
alambert> -rw-rw-r--    1 root     root          865 Apr  2 20:43 MPIO_Test.3
alambert> -rw-rw-r--    1 root     root          794 Apr  2 20:43 MPIO_Wait.3
alambert> -rw-rw-r--    1 root     root         1848 Apr  2 20:43 
alambert> MPI_Type_create_darray.3
alambert> -rw-rw-r--    1 root     root         1566 Apr  2 20:43 
alambert> MPI_Type_create_subarray.3
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/man/man4:
alambert> total 8
alambert> drwxrwxr-x    2 root     root         4096 Apr  2 20:43 .
alambert> drwxrwxr-x    5 root     root         4096 Jul 12 08:43 ..
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/MPI-2-C++:
alambert> total 12
alambert> drwxrwxr-x    3 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x   11 root     root         4096 Jul 12 08:43 ..
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 examples
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/MPI-2-C++/examples:
alambert> total 44
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x    3 root     root         4096 Jul 12 08:43 ..
alambert> -rw-rw-r--    1 root     root         1790 Apr  2 20:43 chapter_10_mpi2.cc
alambert> -rw-rw-r--    1 root     root         1477 Apr  2 20:43 hello_world.cc
alambert> -rw-r--r--    1 root     root         1183 Apr  2 20:43 Makefile
alambert> -rw-rw-r--    1 root     root         1035 Apr  2 20:43 Makefile.in
alambert> lrwxrwxrwx    1 root     root           16 Jul 12 08:43 mpirun -> 
alambert> ../../bin/mpirun
alambert> -rw-rw-r--    1 root     root         2163 Apr  2 20:43 pi.cc
alambert> -rw-rw-r--    1 root     root         1724 Apr  2 20:43 README
alambert> -rw-rw-r--    1 root     root         2141 Apr  2 20:43 ring.cc
alambert> -rw-rw-r--    1 root     root         3673 Apr  2 20:43 topology.cc
alambert> -rw-rw-r--    1 root     root         2805 Apr  2 20:43 user_bcast.cc
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/sbin:
alambert> total 44
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x   11 root     root         4096 Jul 12 08:43 ..
alambert> -rwxrwxr-x    1 root     root         1155 Apr  2 20:43 cleanipcs
alambert> -rwxr-xr-x    1 root     root        31025 Apr  2 20:43 mpiuninstall
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share:
alambert> total 24
alambert> drwxrwxr-x    5 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x   11 root     root         4096 Jul 12 08:43 ..
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 examples
alambert> drwxrwxr-x    7 root     root         4096 Jul 12 08:43 jumpshot-3
alambert> -rw-rw-r--    1 root     root         3116 Apr  2 20:43 Makefile.sample
alambert> drwxrwxr-x    6 root     root         4096 Jul 12 08:43 upshot
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/examples:
alambert> total 32
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x    5 root     root         4096 Jul 12 08:43 ..
alambert> -rw-rw-r--    1 root     root         1638 Jun  7  2001 cpi.c
alambert> -rw-rw-r--    1 root     root         2733 Jun  7  2001 cpilog.c
alambert> -rw-rw-r--    1 root     root         4180 Dec 22  1999 fpi.f
alambert> -rw-rw-r--    1 root     root         3985 Jun  7  2001 Makefile.in
alambert> lrwxrwxrwx    1 root     root           64 Jul 12 08:43 mpirun -> 
alambert> /opt/score5.0.0/mpi/mpich-1.2.0/i386-redhat7-linux2_4/bin/mpirun
alambert> -rw-rw-r--    1 root     root         1487 Jun  7  2001 srtest.c
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/jumpshot-3:
alambert> total 60
alambert> drwxrwxr-x    7 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x    5 root     root         4096 Jul 12 08:43 ..
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 bin
alambert> drwxrwxr-x    3 root     root         4096 Jul 12 08:43 doc
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 lib
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 logfiles
alambert> -rw-rw-r--    1 root     root         1610 Jun  7  2001 README
alambert> -rw-rw-r--    1 root     root         2854 Jun  7  2001 README.slog
alambert> drwxrwxr-x    2 root     root         4096 Apr  2 20:43 sbin
alambert> -rw-rw-r--    1 root     root        17951 Jun  7  2001 TourStepByStep.txt
alambert> -rw-rw-r--    1 root     root         3487 Jun  7  2001 UserGuide.txt
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/jumpshot-3/bin:
alambert> total 16
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x    7 root     root         4096 Jul 12 08:43 ..
alambert> -rwxrwxr-x    1 root     root         1683 Apr  2 20:43 jumpshot
alambert> -rwxrwxr-x    1 root     root          754 Apr  2 20:43 slog_print
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/jumpshot-3/doc:
alambert> total 1032
alambert> drwxrwxr-x    3 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x    7 root     root         4096 Jul 12 08:43 ..
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 html
alambert> -rw-rw-r--    1 root     root        10196 Jun  7  2001 jumpshot.def
alambert> -rw-rw-r--    1 root     root      1026872 Jun  7  2001 TourStepByStep.pdf
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/jumpshot-3/doc/html:
alambert> total 588
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x    3 root     root         4096 Jul 12 08:43 ..
alambert> -rw-rw-r--    1 root     root         2569 Jun  7  2001 footnode.html
alambert> -rw-rw-r--    1 root     root            8 Jun  7  2001 images.aux
alambert> -rw-rw-r--    1 root     root         4137 Jun  7  2001 images.log
alambert> -rw-rw-r--    1 root     root         3897 Jun  7  2001 images.pl
alambert> -rw-rw-r--    1 root     root         6421 Jun  7  2001 images.tex
alambert> -rw-rw-r--    1 root     root        39322 Jun  7  2001 img10.gif
alambert> -rw-rw-r--    1 root     root        14179 Jun  7  2001 img11.gif
alambert> -rw-rw-r--    1 root     root        24365 Jun  7  2001 img12.gif
alambert> -rw-rw-r--    1 root     root        21421 Jun  7  2001 img13.gif
alambert> -rw-rw-r--    1 root     root        12735 Jun  7  2001 img1.gif
alambert> -rw-rw-r--    1 root     root        62084 Jun  7  2001 img2.gif
alambert> -rw-rw-r--    1 root     root        65594 Jun  7  2001 img3.gif
alambert> -rw-rw-r--    1 root     root        18473 Jun  7  2001 img4.gif
alambert> -rw-rw-r--    1 root     root        59650 Jun  7  2001 img5.gif
alambert> -rw-rw-r--    1 root     root        20848 Jun  7  2001 img6.gif
alambert> -rw-rw-r--    1 root     root        13782 Jun  7  2001 img7.gif
alambert> -rw-rw-r--    1 root     root         4579 Jun  7  2001 img8.gif
alambert> -rw-rw-r--    1 root     root        55575 Jun  7  2001 img9.gif
alambert> -rw-rw-r--    1 root     root         2817 Jun  7  2001 index.html
alambert> -rw-rw-r--    1 root     root         1376 Jun  7  2001 internals.pl
alambert> -rw-rw-r--    1 root     root         2617 Jun  7  2001 labels.pl
alambert> -rw-rw-r--    1 root     root          172 Jun  7  2001 next_g.gif
alambert> -rw-rw-r--    1 root     root          172 Jun  7  2001 next.gif
alambert> -rw-rw-r--    1 root     root         2344 Jun  7  2001 node1.html
alambert> -rw-rw-r--    1 root     root         4239 Jun  7  2001 node2.html
alambert> -rw-rw-r--    1 root     root        11190 Jun  7  2001 node3.html
alambert> -rw-rw-r--    1 root     root         5240 Jun  7  2001 node4.html
alambert> -rw-rw-r--    1 root     root        10579 Jun  7  2001 node5.html
alambert> -rw-rw-r--    1 root     root         2192 Jun  7  2001 node6.html
alambert> -rw-rw-r--    1 root     root         2388 Jun  7  2001 node7.html
alambert> -rw-rw-r--    1 root     root          220 Jun  7  2001 prev_g.gif
alambert> -rw-rw-r--    1 root     root          220 Jun  7  2001 prev.gif
alambert> -rw-rw-r--    1 root     root          891 Jun  7  2001 TourStepByStep.css
alambert> -rw-rw-r--    1 root     root         2817 Jun  7  2001 TourStepByStep.html
alambert> -rw-rw-r--    1 root     root          145 Jun  7  2001 up_g.gif
alambert> -rw-rw-r--    1 root     root          145 Jun  7  2001 up.gif
alambert> -rw-rw-r--    1 root     root           44 Jun  7  2001 WARNINGS
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/jumpshot-3/lib:
alambert> total 268
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x    7 root     root         4096 Jul 12 08:43 ..
alambert> -rw-rw-r--    1 root     root         6383 Jun  7  2001 images.jar
alambert> -rw-rw-r--    1 root     root        17162 Jun  7  2001 jumpshot.colors
alambert> -rw-rw-r--    1 root     root       137699 Apr  2 20:37 jumpshot.jar
alambert> -rw-rw-r--    1 root     root          109 Jun  7  2001 jumpshot.setup
alambert> -rw-rw-r--    1 root     root        23370 Apr  2 20:37 preview.jar
alambert> -rw-rw-r--    1 root     root        34002 Apr  2 20:37 slog.jar
alambert> -rw-rw-r--    1 root     root         1252 Apr  2 20:37 slog_print.class
alambert> -rw-rw-r--    1 root     root        22174 Apr  2 20:37 statsviewer.jar
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/jumpshot-3/logfiles:
alambert> total 1688
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x    7 root     root         4096 Jul 12 08:43 ..
alambert> -rw-rw-r--    1 root     root       685546 Jun  7  2001 invalid.slog
alambert> -rw-rw-r--    1 root     root        11692 Jun  7  2001 sample.slog
alambert> -rw-rw-r--    1 root     root       985187 Jun  7  2001 sppm_ic2a.slog
alambert> -rw-rw-r--    1 root     root         6654 Jun  7  2001 sppm.stats.0301
alambert> -rw-rw-r--    1 root     root         3956 Jun  7  2001 stats0204.txt
alambert> -rw-rw-r--    1 root     root         1633 Jun  7  2001 stats3.txt
alambert> -rw-rw-r--    1 root     root         7106 Jun  7  2001 thread1.stats
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/jumpshot-3/sbin:
alambert> total 8
alambert> drwxrwxr-x    2 root     root         4096 Apr  2 20:43 .
alambert> drwxrwxr-x    7 root     root         4096 Jul 12 08:43 ..
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/upshot:
alambert> total 24
alambert> drwxrwxr-x    6 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x    5 root     root         4096 Jul 12 08:43 ..
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 bin
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 bitmaps
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 logfiles
alambert> drwxrwxr-x    2 root     root         4096 Apr  2 20:43 sbin
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/upshot/bin:
alambert> total 124
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x    6 root     root         4096 Jul 12 08:43 ..
alambert> -rwxrwxr-x    1 root     root       114299 Apr  2 20:43 upshot
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/upshot/bitmaps:
alambert> total 84
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x    6 root     root         4096 Jul 12 08:43 ..
alambert> -rw-rw-r--    1 root     root           96 Jun  7  2001 2x2
alambert> -rw-rw-r--    1 root     root          278 Jun  7  2001 black
alambert> -rw-rw-r--    1 root     root          126 Jun  7  2001 boxes
alambert> -rw-rw-r--    1 root     root          284 Jun  7  2001 dimple3
alambert> -rw-rw-r--    1 root     root          198 Jun  7  2001 dllines3
alambert> -rw-rw-r--    1 root     root          111 Jun  7  2001 dllines4
alambert> -rw-rw-r--    1 root     root          195 Jun  7  2001 drlines3
alambert> -rw-rw-r--    1 root     root          111 Jun  7  2001 drlines4
alambert> -rw-rw-r--    1 root     root           87 Jun  7  2001 gray
alambert> -rw-rw-r--    1 root     root          105 Jun  7  2001 gray2
alambert> -rw-rw-r--    1 root     root          102 Jun  7  2001 gray3
alambert> -rw-rw-r--    1 root     root          284 Jun  7  2001 hlines2
alambert> -rw-rw-r--    1 root     root          272 Jun  7  2001 hlines3
alambert> -rw-rw-r--    1 root     root          284 Jun  7  2001 hlines4
alambert> -rw-rw-r--    1 root     root          105 Jun  7  2001 light_gray
alambert> -rw-rw-r--    1 root     root          108 Jun  7  2001 vlines2
alambert> -rw-rw-r--    1 root     root           90 Jun  7  2001 vlines3
alambert> -rw-rw-r--    1 root     root          108 Jun  7  2001 vlines4
alambert> -rw-rw-r--    1 root     root           90 Jun  7  2001 white
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/upshot/logfiles:
alambert> total 36
alambert> drwxrwxr-x    2 root     root         4096 Jul 12 08:43 .
alambert> drwxrwxr-x    6 root     root         4096 Jul 12 08:43 ..
alambert> -rw-rw-r--    1 root     root        11762 Jun  7  2001 fft.trf
alambert> -rw-rw-r--    1 root     root        15017 Jun  7  2001 sam_hyp.16.log
alambert> 
alambert> /opt/score/mpi/mpich-1.2.0/i386-redhat7-linux2_4/share/upshot/sbin:
alambert> total 8
alambert> drwxrwxr-x    2 root     root         4096 Apr  2 20:43 .
alambert> drwxrwxr-x    6 root     root         4096 Jul 12 08:43 ..
alambert> alambert ＠ grasshopper:~$ which mpicc
alambert> /opt/score/bin/mpicc
alambert> alambert ＠ grasshopper:~$ mpicc -device ch_score2 -o hello hello.cc
alambert> mpicc: mpich-1.2.0 device score2 is not installed
alambert> alambert ＠ grasshopper:~$ mpicc -device ch_score2 -O2 -o alltoall alltoall.c
alambert> mpicc: mpich-1.2.0 device score2 is not installed
alambert> alambert ＠ grasshopper:~$
alambert> 
alambert> 
alambert> from 'make' (after extracting source and attempting recompile):
alambert> 
alambert> + DIST=
alambert> + /opt/score/bin/mkwrapper /opt/score/bin bin .exe
alambert> + cd /opt/score/bin
alambert> ++ basename mpi_rtt.exe .exe
alambert> + g=mpi_rtt
alambert> + rm -f mpi_rtt
alambert> + ln -s .wrapper mpi_rtt
alambert> ++ basename mpi_bw.exe .exe
alambert> + g=mpi_bw
alambert> + rm -f mpi_bw
alambert> + ln -s .wrapper mpi_bw
alambert> ++ basename mpi_bw2.exe .exe
alambert> + g=mpi_bw2
alambert> + rm -f mpi_bw2
alambert> + ln -s .wrapper mpi_bw2
alambert> ++ basename mpitest.exe .exe
alambert> + g=mpitest
alambert> + rm -f mpitest
alambert> + ln -s .wrapper mpitest
alambert> + set +x
alambert> make[3]: Leaving directory 
alambert> `/opt/score5.0.0/work/score-src/program/bench/mpi/obj.i386-redhat7-linux2_4'
alambert> make[2]: Leaving directory `/opt/score5.0.0/work/score-src/program/bench/mpi'
alambert> make[1]: Leaving directory `/opt/score5.0.0/work/score-src/program/bench'
alambert> make: *** [all] Error 1
alambert> [root ＠ grasshopper score-src]#
alambert> 
alambert> _______________________________________________
alambert> SCore-users mailing list
alambert> SCore-users ＠ pccluster.org
alambert> http://www.pccluster.org/mailman/listinfo/score-users
alambert> _______________________________________________
alambert> SCore-users-jp mailing list
alambert> SCore-users-jp ＠ pccluster.org
alambert> http://www.pccluster.org/mailman/listinfo/score-users-jp
alambert> 
-----
Shinji Sumimoto    Fujitsu Labs.
_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From kameyama ＠ pccluster.org  Mon Jul 22 09:45:17 2002
From: kameyama ＠ pccluster.org (=?iso-2022-jp?b?a2FtZXlhbWEgGyRCIXcbKEIgcGNjbHVzdGVyLm9yZw==?=)
Date: Mon, 22 Jul 2002 09:45:17 +0900
Subject: [SCore-users-jp] [SCore-users] Error: mpich-1.2.0 device score2 is not installed
In-Reply-To: Your message of "Sat, 20 Jul 2002 10:44:57 JST."
             <20020720.104457.730552396.s-sumi@bd6.so-net.ne.jp>
Message-ID: <200207220045.g6M0jHv17715@yl-dhcp18.is.s.u-tokyo.ac.jp>

In article <20020720.104457.730552396.s-sumi ＠ bd6.so-net.ne.jp> Shinji Sumimoto <s-sumi ＠ bd6.so-net.ne.jp> wrotes:
> MPICH-SCore 2.0 is not installed now. You have to re-compile SCore
> from source. 
> 
> See: 
>  http://www.pccluster.org/score/dist/score/html/en/installation/index.html

Because MPICH/SCore2 used PM/ethernet internal header file,
You must extract score module (score-5.0.0.score.tar.gz).

And please edit Makefile.in
     /opt/score/score-src/runtime/mpi/mpich-1.2.0/src/mpid/ch_score2/Makefile.in
to correct PM/Ethernet include path,  from
    -I$(top_srcdir)/../../../pm2/arch/ethernet/include \
to
    -I/opt/score/score-src/SCore/pm2/arch/ethernet/include \

Then, build MPICH/SCore version 2:

> After installing sources.
> % cd /opt/score/score-src/runtime/mpi/mpich-1.2.0
> % ./mpi_make.sh -device ch_score2 build
> % ./mpi_make.sh -device ch_score2 install

                       from Kameyama Toyohisa
_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From emile.carcamo ＠ nec.fr  Mon Jul 22 17:57:11 2002
From: emile.carcamo ＠ nec.fr (Emile CARCAMO)
Date: Mon, 22 Jul 2002 10:57:11 +0200
Subject: [SCore-users-jp] [SCore-users] Experience with Express5800's running SCore
Message-ID: <200207220857.g6M8vBD03828@emilepc.ess.nec.fr>

Dear list members,

	I'm experiencing some problems in deployment of kernel version
	2.4.18-1SCORE on NEC Express5800 rack mounted PC's (120RB1 model,
	processor is PIII 1266MHz).

	Running EIT from the master and remote-installation via kickstart
	works PERFECTLY. The main problem is booting 2.4.18 from the hard
	drive (machine hangs during linux load just after displaying few
	dots). I also tried a cold install of RedHat 7.3 but same trouble
	occured (booting from a 3.5' floppy is always okay, but NOT from
	the hard drive!).

	Does anybody out there have experience in SCore v5.00 deployment
	with same kind of hardware ? If so I'll be glad to hear from him
	or her :-)

	Thanks in advance for your help, and sorry if my post is not that
	much 100% ?Score related?. Best regards,

-- 
Emile_CARCAMO           NEC European            http://www.ess.nec.de
System Engineer         Supercomputer           mailto:emile.carcamo ＠ nec.fr
                        Systems France      GSM mailto:emile.carcamo ＠ orange.fr
(+33)1-3930-6601   FAX
(+33)1-3930-6613  PHONE  / Your mouse has moved. Windows NT must be restarted \
(+33)6-8063-7003   GSM   \ for the change to take effect. Reboot now?  [ OK ] /



_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From kameyama ＠ pccluster.org  Tue Jul 23 10:35:32 2002
From: kameyama ＠ pccluster.org (=?iso-2022-jp?b?a2FtZXlhbWEgGyRCIXcbKEIgcGNjbHVzdGVyLm9yZw==?=)
Date: Tue, 23 Jul 2002 10:35:32 +0900
Subject: [SCore-users-jp] [SCore-users] Experience with Express5800's running SCore
In-Reply-To: Your message of "Mon, 22 Jul 2002 10:57:11 JST."
             <200207220857.g6M8vBD03828@emilepc.ess.nec.fr>
Message-ID: <200207230135.g6N1ZWv24247@yl-dhcp18.is.s.u-tokyo.ac.jp>

In article <200207220857.g6M8vBD03828 ＠ emilepc.ess.nec.fr> Emile CARCAMO <emile.carcamo ＠ nec.fr> wrotes:
> 	I'm experiencing some problems in deployment of kernel version
> 	2.4.18-1SCORE on NEC Express5800 rack mounted PC's (120RB1 model,
> 	processor is PIII 1266MHz).
> 
> 	Running EIT from the master and remote-installation via kickstart
> 	works PERFECTLY. The main problem is booting 2.4.18 from the hard
> 	drive (machine hangs during linux load just after displaying few
> 	dots). I also tried a cold install of RedHat 7.3 but same trouble
> 	occured (booting from a 3.5' floppy is always okay, but NOT from
> 	the hard drive!).

How many root partition size do you set?
If you seting large root partition (over 1024 cylinder),
boot loader may not access kernel code.

                       from Kameyama Toyohisa
_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From hirose ＠ bq.jp.nec.com  Tue Jul 23 10:49:44 2002
From: hirose ＠ bq.jp.nec.com (Tetsuya Hirose)
Date: Tue, 23 Jul 2002 10:49:44 +0900 (JST)
Subject: [SCore-users-jp] [SCore-users] Experience with Express5800's
 running SCore
In-Reply-To: <200207220857.g6M8vBD03828@emilepc.ess.nec.fr>
References: <200207220857.g6M8vBD03828@emilepc.ess.nec.fr>
Message-ID: <20020723.104944.74755093.hirose@bq.jp.nec.com>

Dear Emile,

I'm Tetsuya Hirose, NEC.
I understand, there are no problems to use 120Rb-1 with SCore5.0.
Kameyama-san(PCCC) has tested at his site.
But I don't have 120Rb-1..., sorry.

Let me know, more information about your state.
?Error messages
?Disk partision (Yes, Kameyama-san's advice)
?Do you have RAID controller?

Best regards,
-- 
Tetsuya Hirose 
NEC HPC Enginnering Center
hirose ＠ bq.jp.nec.com


From: Emile CARCAMO <emile.carcamo ＠ nec.fr>
Subject: [SCore-users-jp] [SCore-users] Experience with Express5800's running SCore
Date: Mon, 22 Jul 2002 10:57:11 +0200

> 
> Dear list members,
> 
> 	I'm experiencing some problems in deployment of kernel version
> 	2.4.18-1SCORE on NEC Express5800 rack mounted PC's (120RB1 model,
> 	processor is PIII 1266MHz).
> 
> 	Running EIT from the master and remote-installation via kickstart
> 	works PERFECTLY. The main problem is booting 2.4.18 from the hard
> 	drive (machine hangs during linux load just after displaying few
> 	dots). I also tried a cold install of RedHat 7.3 but same trouble
> 	occured (booting from a 3.5' floppy is always okay, but NOT from
> 	the hard drive!).
> 
> 	Does anybody out there have experience in SCore v5.00 deployment
> 	with same kind of hardware ? If so I'll be glad to hear from him
> 	or her :-)
> 
> 	Thanks in advance for your help, and sorry if my post is not that
> 	much 100% ?Score related?. Best regards,
> 
> -- 
> Emile_CARCAMO           NEC European            http://www.ess.nec.de
> System Engineer         Supercomputer           mailto:emile.carcamo ＠ nec.fr
>                         Systems France      GSM mailto:emile.carcamo ＠ orange.fr
> (+33)1-3930-6601   FAX
> (+33)1-3930-6613  PHONE  / Your mouse has moved. Windows NT must be restarted \
> (+33)6-8063-7003   GSM   \ for the change to take effect. Reboot now?  [ OK ] /
> 
> 
> 
> _______________________________________________
> SCore-users mailing list
> SCore-users ＠ pccluster.org
> http://www.pccluster.org/mailman/listinfo/score-users
> _______________________________________________
> SCore-users-jp mailing list
> SCore-users-jp ＠ pccluster.org
> http://www.pccluster.org/mailman/listinfo/score-users-jp
_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From emile.carcamo ＠ nec.fr  Tue Jul 23 15:15:20 2002
From: emile.carcamo ＠ nec.fr (Emile CARCAMO)
Date: Tue, 23 Jul 2002 08:15:20 +0200
Subject: [SCore-users-jp] [SCore-users] Experience with Express5800's 
 running SCore
In-Reply-To: Your message of "Tue, 23 Jul 2002 10:49:44 +0900."
             <20020723.104944.74755093.hirose@bq.jp.nec.com> 
Message-ID: <200207230615.g6N6FKW02355@emilepc.ess.nec.fr>

> Dear Emile,
> 
> I'm Tetsuya Hirose, NEC.
> I understand, there are no problems to use 120Rb-1 with SCore5.0.
> Kameyama-san(PCCC) has tested at his site.
> But I don't have 120Rb-1..., sorry.
> 
> Let me know, more information about your state.
> Error messages
> Disk partision (Yes, Kameyama-san's advice)
> Do you have RAID controller?
> 

Dear Tetsuya and list members,

	For your information, I've enclosed a script file describing
	both "df -H" output as well as a dmesg trace. Yes I've a RAID
	controller (DAC960) to monitor several physical devices ...

	Note that "uname -a" shows 2.4.7 because I was only capable
	to boot from a RH-7.2 mkbootdisk floppy. Booting from hard
	disk drive still hangs at the very first beginning (linux is
	being loaded at that time).

	Thanks in advance for your help, and best regards.

-- 
Emile_CARCAMO           NEC European            http://www.ess.nec.de
System Engineer         Supercomputer           mailto:emile.carcamo ＠ nec.fr
                        Systems France      GSM mailto:emile.carcamo ＠ orange.fr
(+33)1-3930-6601   FAX
(+33)1-3930-6613  PHONE  / Your mouse has moved. Windows NT must be restarted \
(+33)6-8063-7003   GSM   \ for the change to take effect. Reboot now?  [ OK ] /



-------------- next part --------------
文字コード指定の無い添付文書を保管しました...
名前: score
URL:  <http://new1.pccluster.org/pipermail/score-users-jp/attachments/20020723/4896cd55/attachment.ksh>

From kameyama ＠ pccluster.org  Tue Jul 23 16:06:09 2002
From: kameyama ＠ pccluster.org (=?iso-2022-jp?b?a2FtZXlhbWEgGyRCIXcbKEIgcGNjbHVzdGVyLm9yZw==?=)
Date: Tue, 23 Jul 2002 16:06:09 +0900
Subject: [SCore-users-jp] [SCore-users] Experience with Express5800's running SCore
In-Reply-To: Your message of "Tue, 23 Jul 2002 08:15:20 JST."
             <200207230615.g6N6FKW02355@emilepc.ess.nec.fr>
Message-ID: <200207230706.g6N769v25582@yl-dhcp18.is.s.u-tokyo.ac.jp>

In article <200207230615.g6N6FKW02355 ＠ emilepc.ess.nec.fr> Emile CARCAMO <emile.carcamo ＠ nec.fr> wrotes:
> 	For your information, I've enclosed a script file describing
> 	both "df -H" output as well as a dmesg trace. Yes I've a RAID
> 	controller (DAC960) to monitor several physical devices ...
> 
> 	Note that "uname -a" shows 2.4.7 because I was only capable
> 	to boot from a RH-7.2 mkbootdisk floppy. Booting from hard
> 	disk drive still hangs at the very first beginning (linux is
> 	being loaded at that time).

I think probary initrd file is broken.
Please try below.

Pleaase check:
    /etc/modules.conf
This file must be following line:
    alias scsi_hostadapter DAC960
or
    alias scsi_hostadapter2 DAC960

And Please issu following command to make initrd disk:
    # /sbin/mkinitrd  /boot/initrd-2.4.18-1SCOREsmp.img 2.4.18-1SCOREsmp
    # /sbin/mkinitrd  /boot/initrd-2.4.18-1SCORE.img 2.4.18-1SCORE
Please check:
     /etc/lilo.conf
image file version and initrd file version must be much.
And re-install lilo, and reboot.
    # /sbin/lilo
    # reboot

If reboot is fail, you need to rebuild kernel with statically linked DAC960
driver.

                       from Kameyama Toyohisa
_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From kameyama ＠ pccluster.org  Tue Jul 23 16:50:41 2002
From: kameyama ＠ pccluster.org (=?iso-2022-jp?b?a2FtZXlhbWEgGyRCIXcbKEIgcGNjbHVzdGVyLm9yZw==?=)
Date: Tue, 23 Jul 2002 16:50:41 +0900
Subject: [SCore-users-jp] Re: [score-info-jp] =?ISO-2022-JP?B?U0NvcmUbJEIlLyVpJTklPzk9GyhC?=
 =?ISO-2022-JP?B?GyRCQ1slNSVdITwlSCROJCo0aiQkGyhC?=
In-Reply-To: Your message of "Mon, 22 Jul 2002 16:06:32 JST."
             <000001c2314e$520d2b00$c500a8c0@0292hayashi>
Message-ID: <200207230750.g6N7ofv25767@yl-dhcp18.is.s.u-tokyo.ac.jp>

亀山です.

scoe-info-jp は obsolate ですので, 問い合わせなどは
score-users-jp を使用してください.
なお, score-users-jp メイリングリストは
    http://www.pccluster.org/mailman/listinfo/score-users-jp
で subscribe できます.

In article <000001c2314e$520d2b00$c500a8c0 ＠ 0292hayashi> "林 敬三" <k-hayashi at sogo-eng.co.jp> wrotes:
> ５．そのあと、クラスタシステムが正常に機能するかどうかを、確認しようと、
> webに記載されているSCOUTテストを試みましたが、各種のコマンドが動きません。
> 　scorehosts、sceptic、msgbなどのコマンドが、見つからないといって
> 怒られてしまい、先へ進むことができません。
> 　念のため、/optディレクトリを、ls  -Rlして、コマンド名でgrepしてみました
> が、
> コマンド自体が、存在しないようです。

念のためですが, serveer host で実行しようとしていますよね?
scorehosts などのコマンドは server host のみに
install されますので, compute host に該当するコマンドはありません.
これらは server host の
    /opt/score/bin
にあるはずで, server host で login し直せばこの path を探してくれる
はずなのですが...

                       from Kameyama Toyohisa


From kameyama ＠ pccluster.org  Tue Jul 23 17:15:01 2002
From: kameyama ＠ pccluster.org (=?iso-2022-jp?b?a2FtZXlhbWEgGyRCIXcbKEIgcGNjbHVzdGVyLm9yZw==?=)
Date: Tue, 23 Jul 2002 17:15:01 +0900
Subject: [SCore-users-jp] Re: [score-info-jp] =?ISO-2022-JP?B?U0NvcmUbJEIlLyVpJTklPzk9GyhC?=
 =?ISO-2022-JP?B?GyRCQ1skSzRYJDkkazxBTGQkTiQqNGokJBsoQg==?=
In-Reply-To: Your message of "Tue, 23 Jul 2002 10:51:10 JST."
             <001101c231eb$6caabe80$c500a8c0@0292hayashi>
Message-ID: <200207230815.g6N8F1v25881@yl-dhcp18.is.s.u-tokyo.ac.jp>

亀山です.
scoe-info-jp は obsolate ですので, 問い合わせなどは
score-users-jp を使用してください.
なお, score-users-jp メイリングリストは
    http://www.pccluster.org/mailman/listinfo/score-users-jp
で subscribe できます.

In article <001101c231eb$6caabe80$c500a8c0 ＠ 0292hayashi> "林 敬三" <k-hayashi at sogo-eng.co.jp> wrotes:
> 現在、御社webサイトを拝見し、さらに2002年07月15日付で共立出版から
> 出版された、『Linuxで並列処理をしよう』という、CD-ROM付きの書籍を購入し、
> 試行させていただいています。
>
> これまでの情報で、クラスとを組むマシン達は、同一アーキテクチャーでない
> といけないとありましたが、これは、パーツレベルまで統一しなければならない
> のでしょうか。

# 少なくてもこの本には書いていないと思いますが...
統一しなくても動作に問題はありません.
(この本の 64 ページの例ではいろいろなものが混在していますし...)
但し,
  1. SCore 5.0.1 では x86 アーキテクチャしかサポートしていません.
  2. EIT では cpugen 及び speed の値は一定に設定しています.
このため, EIT で作成した cluster はすべての compute host の CPU を
同一とみなすことになります.
(CPU の数と network の種類で "クラスタ化" されることはありますが...)

> なお、インストールに当たっては、書籍付録CD-ROMを用い、
> 問題なく最後までインストールを完了しましたが、msgbはうまく動作しているように
> 見えるものの、scoutを受け付けてくれません。
> No such fike or Directoryと応答され、先へ進めません。

できれば, このときの log を送っていただけないでしょうか?
scout 自体がみつからないのか, scout から呼び出されるコマンドが
見付からないのかあたりが問題になりそうな気がします.

                       from Kameyama Toyohisa


From hirose ＠ bq.jp.nec.com  Tue Jul 23 19:32:19 2002
From: hirose ＠ bq.jp.nec.com (Tetsuya Hirose)
Date: Tue, 23 Jul 2002 19:32:19 +0900 (JST)
Subject: [SCore-users-jp] [SCore-users] Experience with Express5800's
 running SCore
In-Reply-To: <200207230615.g6N6FKW02355@emilepc.ess.nec.fr>
References: <20020723.104944.74755093.hirose@bq.jp.nec.com>
	<200207230615.g6N6FKW02355@emilepc.ess.nec.fr>
Message-ID: <20020723.193219.112626933.hirose@bq.jp.nec.com>

Dear Emile and all,

> 	dots). I also tried a cold install of RedHat 7.3 but same trouble
> 	occured (booting from a 3.5' floppy is always okay, but NOT from

This is just FYI.
There is kernel bug with DAC960 RAID controller.
Please refer here
http://rhn.redhat.com/errata/RHBA-2002-110.html
and here.
http://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=65207

I tested RH7.3 kernel-2.4.18-3smp(not SCore kernel)& Grub
on Ra-1(previous model of Rb-1) and reproduced.
Here is message at that time.
"kernel panic: No init found Try init= option to kernel"
Is this same with your state?

As bugzilla information, the problem resolved with lilo.
But I understand SCore compute nodes use lilo...
Also they said RH7.2 is no problem.

I'll try SCore kernel.
Best regards,
-- 
Tetsuya Hirose 
NEC HPC Enginnering Center
hirose ＠ bq.jp.nec.com
_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From hirose ＠ bq.jp.nec.com  Tue Jul 23 20:50:14 2002
From: hirose ＠ bq.jp.nec.com (Tetsuya Hirose)
Date: Tue, 23 Jul 2002 20:50:14 +0900 (JST)
Subject: [SCore-users-jp] [SCore-users] Experience with Express5800's
 running SCore
In-Reply-To: <20020723.193219.112626933.hirose@bq.jp.nec.com>
References: <20020723.104944.74755093.hirose@bq.jp.nec.com>
	<200207230615.g6N6FKW02355@emilepc.ess.nec.fr>
	<20020723.193219.112626933.hirose@bq.jp.nec.com>
Message-ID: <20020723.205014.18308225.hirose@bq.jp.nec.com>

Dear Emile and all,

> I tested RH7.3 kernel-2.4.18-3smp(not SCore kernel)& Grub
> on Ra-1(previous model of Rb-1) and reproduced.
> Here is message at that time.
> "kernel panic: No init found Try init= option to kernel"

> I'll try SCore kernel.

I installed RH7.2 afresh and tested.
kernel 2.4.7-10smp with Grub -- OK 
kernel 2.4.7-10smp with lilo -- OK 
kernel 2.4.18-2SCOREsmp with Grub -- Don't boot same with RH7.3.
kernel 2.4.18-2SCOREsmp with lilo -- OK

Do you use Grub boot loader? 
Is your state differ from this?

Best regards,
-- 
Tetsuya Hirose 
NEC HPC Enginnering Center
hirose ＠ bq.jp.nec.com


_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From Enomoto.Hiroshi ＠ wrc.melco.co.jp  Wed Jul 24 10:40:29 2002
From: Enomoto.Hiroshi ＠ wrc.melco.co.jp (Hiroshi Enomoto)
Date: Wed, 24 Jul 2002 10:40:29 +0900
Subject: [SCore-users-jp] =?iso-2022-jp?B?GyRCREw/Ljt+NFYkTkIsRGpKfUshJEskRCQkJEYkTjxBTGQbKEI=?=
Message-ID: <043f01c232b3$17d6c0c0$c0cc8c0a@ENOMOTO>

三菱電機の榎本です。
いつもお世話になっております。

現在pmSend とpmWrite の通信時間について調べております。
これらの通信時間の測定は、pmbench で行えると思っているのですが、
正しいでしょうか？

?pmSend に対しては、
% pmbench -network myrinet2k -host ホスト名 
?pmWrite に対しては、
% pmbench -network myrinet2k -host ホスト名　-zerocopy=vwrite

を試しました。使用したMyrinetのH/Wは以下のものです。
M3F-PCI64C-2, M3F-SW8M

結果は以下のようになりました。
?の場合は、ラウンドトリップタイムなので、2で割ったものをpmSend
の通信時間と考えました。
Byte                 us              pmSend (us)
  4                 16.51    ->       8.255
  8                 16.52    ->       8.26
 12                16.66    ->       8.33
 16                16.73    ->       8.365
 24                19.65    ->       9.825   

?の場合は、値はMB/s で表示されるので、
1/value × Bytes (us) で計算し、pmWriteの通信時間と考えました。
Byte              MB/s            pmWrite (us)
  4                 0.479    ->       8.351
  8                 0.955    ->       8.377
 12                1.424    ->       8.427
 16                1.898    ->       8.430
 24                2.830    ->       8.481

この測定結果をpmSend,pmWriteの通信時間と考えてよろしいのでしょうか？
データ数が小さければメッセージ通信の方が速いと聞いていましたが
あまり差がないのでおかしいのではと思っています。
もし誤りでしたら、測定方法を教えていただけないでしょうか？
（コードを書かずにpmライブラリを使ってできればその方がよいです）

以上よろしくお願いします。

 =============================================
  三菱電機株式会社　先端技術総合研究所
　　電力システム技術部　配電システムグループ
　　　　　　  　榎本　博
  TEL：  06-6497-7631
  FAX ： 06-6497-7727
  E-mail： Enomoto.Hiroshi ＠ wrc.melco.co.jp
 =============================================
   




From chen ＠ mdl.ipc.pku.edu.cn  Wed Jul 24 14:07:19 2002
From: chen ＠ mdl.ipc.pku.edu.cn (Chen Hao)
Date: Wed, 24 Jul 2002 13:07:19 +0800 (CST)
Subject: [SCore-users-jp] [SCore-users] How to do performance analysis?
Message-ID: <Pine.LNX.4.33.0207241300180.22461-100000@mdl.ipc.pku.edu.cn>

Dear all:
  I wanted to do some performance analysis of MPI based program in SCORE 
platform. For example, I hoped to obtain the number of times every MPI 
function was invoked and the average time spent in the function. But when 
I just compile with -pg option, it didn't work. What should I do? Need 
other tools or recompile the SCORE-MPICH with -pg option?
                                                              Chen Hao

_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From kameyama ＠ pccluster.org  Wed Jul 24 16:24:31 2002
From: kameyama ＠ pccluster.org (=?iso-2022-jp?b?a2FtZXlhbWEgGyRCIXcbKEIgcGNjbHVzdGVyLm9yZw==?=)
Date: Wed, 24 Jul 2002 16:24:31 +0900
Subject: [SCore-users-jp] Re: [SCore-users] How to do performance analysis?
In-Reply-To: Your message of "Wed, 24 Jul 2002 13:07:19 JST."
             <Pine.LNX.4.33.0207241300180.22461-100000@mdl.ipc.pku.edu.cn>
Message-ID: <200207240724.g6O7OVv31997@yl-dhcp18.is.s.u-tokyo.ac.jp>

In article <Pine.LNX.4.33.0207241300180.22461-100000 ＠ mdl.ipc.pku.edu.cn> Chen Hao <chen ＠ mdl.ipc.pku.edu.cn> wrotes:
>   I wanted to do some performance analysis of MPI based program in SCORE 
> platform. For example, I hoped to obtain the number of times every MPI 
> function was invoked and the average time spent in the function. But when 
> I just compile with -pg option, it didn't work. What should I do? Need 
> other tools or recompile the SCORE-MPICH with -pg option?

You can use profiling library in MPE.
In MPICH/SCore, you can use upshot and Jumpshot 3 log viewer.
For example, you want to use Jumpshot 3:
1. Compile and link mpi program with -mpilog option.
   % mpicc -mpilog foo.c -o foo
2. Set PE_LOG_FORMAT environment varibable to SLOG
   % setenv PE_LOG_FORMAT SLOHG
3. Execute the program.
   % scrun ./foo
   This program is createed "program_name.slog".
4. viewing log file by logviewer.
   % logviewer foo.log

To use Jumpshot3, please see:
    /opt/score/doc/mpi/jumpshot/index.html
For more dateil for MPE profile library, please see also MPE user guide:
    http://www-unix.mcs.anl.gov/mpi/mpich/docs/mpeman/mpeman.htm

                       from Kameyama Toyohisa
_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From neural_shock ＠ e-mail.ru  Wed Jul 24 16:18:39 2002
From: neural_shock ＠ e-mail.ru (=?iso-2022-jp?b?bmV1cmFsX3Nob2NrIBskQiF3GyhCIGUtbWFpbC5ydQ==?=)
Date: Wed, 24 Jul 2002 11:18:39 +0400
Subject: [SCore-users-jp] [SCore-users] (no subject)
Message-ID: <3d3e54cf.7f1.0@e-mail.ru>

hello.

here are some logs of checpointing failure in english. see messages on Jul 24
in "messages" file in attached tar ball. there are also "gdbout2" file, there
are some debug information from kgdb. 

with respect, mike.
http://www.e-mail.ru

-------------- next part --------------
テキスト形式以外の添付ファイルを保管しました...
ファイル名: log.tar.bz2
型:         application/x-bzip2
サイズ:     47066 バイト
説明:       無し
URL:        <http://new1.pccluster.org/pipermail/score-users-jp/attachments/20020724/129abcf1/attachment.bz2>

From s-sumi ＠ flab.fujitsu.co.jp  Wed Jul 24 17:21:16 2002
From: s-sumi ＠ flab.fujitsu.co.jp (Shinji Sumimoto)
Date: Wed, 24 Jul 2002 17:21:16 +0900 (JST)
Subject: [SCore-users-jp] Re: [SCore-users-jp]
 =?iso-2022-jp?B?GyRCREw/Ljt+NFYkTkIsRGpKfUshJEskRCQkJEYkTjxBTGQbKEI=?=
In-Reply-To: <043f01c232b3$17d6c0c0$c0cc8c0a@ENOMOTO>
References: <043f01c232b3$17d6c0c0$c0cc8c0a@ENOMOTO>
Message-ID: <20020724.172116.195746124.s-sumi@flab.fujitsu.co.jp>

住元です。

From: "Hiroshi Enomoto" <Enomoto.Hiroshi ＠ wrc.melco.co.jp>
Subject: [SCore-users-jp] 通信時間の測定方法についての質問
Date: Wed, 24 Jul 2002 10:40:29 +0900
Message-ID: <043f01c232b3$17d6c0c0$c0cc8c0a ＠ ENOMOTO>

Enomoto.Hiroshi> 三菱電機の榎本です。
Enomoto.Hiroshi> いつもお世話になっております。
Enomoto.Hiroshi> 
Enomoto.Hiroshi> 現在pmSend とpmWrite の通信時間について調べております。
Enomoto.Hiroshi> これらの通信時間の測定は、pmbench で行えると思っているのですが、
Enomoto.Hiroshi> 正しいでしょうか？

Enomoto.Hiroshi> ?pmSend に対しては、
Enomoto.Hiroshi> % pmbench -network myrinet2k -host ホスト名 
Enomoto.Hiroshi> ?pmWrite に対しては、
Enomoto.Hiroshi> % pmbench -network myrinet2k -host ホスト名　-zerocopy=vwrite

2つを比較するのは正しくありません。メッセージの測定はping-pongの双方向
に対してvwriteはping-pingの片方向だからです。

比較するとすれば、

% pmbench -network myrinet2k -host ホスト名 -burst 

もしくは、メッセージがping-pongするという意味で vreadと比較すべきです。

Enomoto.Hiroshi> 
Enomoto.Hiroshi> を試しました。使用したMyrinetのH/Wは以下のものです。
Enomoto.Hiroshi> M3F-PCI64C-2, M3F-SW8M
Enomoto.Hiroshi> 
Enomoto.Hiroshi> 結果は以下のようになりました。
Enomoto.Hiroshi> ?の場合は、ラウンドトリップタイムなので、2で割ったものをpmSend
Enomoto.Hiroshi> の通信時間と考えました。
Enomoto.Hiroshi> Byte                 us              pmSend (us)
Enomoto.Hiroshi>   4                 16.51    ->       8.255
Enomoto.Hiroshi>   8                 16.52    ->       8.26
Enomoto.Hiroshi>  12                16.66    ->       8.33
Enomoto.Hiroshi>  16                16.73    ->       8.365
Enomoto.Hiroshi>  24                19.65    ->       9.825   
Enomoto.Hiroshi> 
Enomoto.Hiroshi> ?の場合は、値はMB/s で表示されるので、
Enomoto.Hiroshi> 1/value × Bytes (us) で計算し、pmWriteの通信時間と考えました。
Enomoto.Hiroshi> Byte              MB/s            pmWrite (us)
Enomoto.Hiroshi>   4                 0.479    ->       8.351
Enomoto.Hiroshi>   8                 0.955    ->       8.377
Enomoto.Hiroshi>  12                1.424    ->       8.427
Enomoto.Hiroshi>  16                1.898    ->       8.430
Enomoto.Hiroshi>  24                2.830    ->       8.481
Enomoto.Hiroshi> 
Enomoto.Hiroshi> この測定結果をpmSend,pmWriteの通信時間と考えてよろしいのでしょうか？
Enomoto.Hiroshi> データ数が小さければメッセージ通信の方が速いと聞いていましたが
Enomoto.Hiroshi> あまり差がないのでおかしいのではと思っています。
Enomoto.Hiroshi> もし誤りでしたら、測定方法を教えていただけないでしょうか？
Enomoto.Hiroshi> （コードを書かずにpmライブラリを使ってできればその方がよいです）
Enomoto.Hiroshi> 
Enomoto.Hiroshi> 以上よろしくお願いします。
Enomoto.Hiroshi> 
Enomoto.Hiroshi>  =============================================
Enomoto.Hiroshi>   三菱電機株式会社　先端技術総合研究所
Enomoto.Hiroshi> 　　電力システム技術部　配電システムグループ
Enomoto.Hiroshi> 　　　　　　  　榎本　博
Enomoto.Hiroshi>   TEL：  06-6497-7631
Enomoto.Hiroshi>   FAX ： 06-6497-7727
Enomoto.Hiroshi>   E-mail： Enomoto.Hiroshi ＠ wrc.melco.co.jp
Enomoto.Hiroshi>  =============================================
Enomoto.Hiroshi>    
Enomoto.Hiroshi> 
Enomoto.Hiroshi> 
Enomoto.Hiroshi> _______________________________________________
Enomoto.Hiroshi> SCore-users-jp mailing list
Enomoto.Hiroshi> SCore-users-jp ＠ pccluster.org
Enomoto.Hiroshi> http://www.pccluster.org/mailman/listinfo/score-users-jp
Enomoto.Hiroshi> 
Enomoto.Hiroshi> 
------
Shinji Sumimoto, Fujitsu Labs


From motoki ＠ phys.aoyama.ac.jp  Sat Jul 27 12:17:08 2002
From: motoki ＠ phys.aoyama.ac.jp (Motoki Tsutsui)
Date: Sat, 27 Jul 2002 12:17:08 +0900
Subject: [SCore-users-jp] (no subject)
Message-ID: <20020727031658.284729382@cosmos.phys.aoyama.ac.jp>



From s-sumi ＠ bd6.so-net.ne.jp  Sun Jul 28 13:16:23 2002
From: s-sumi ＠ bd6.so-net.ne.jp (Shinji Sumimoto)
Date: Sun, 28 Jul 2002 13:16:23 +0900 (JST)
Subject: [SCore-users-jp] Re: [SCore-users] (no subject)
In-Reply-To: <3d3e54cf.7f1.0@e-mail.ru>
References: <3d3e54cf.7f1.0@e-mail.ru>
Message-ID: <20020728.131623.730572796.s-sumi@bd6.so-net.ne.jp>

Hi.

Sorry for late response.

From: neural_shock ＠ e-mail.ru
Subject: [SCore-users] (no subject)
Date: Wed, 24 Jul 2002 11:18:39 +0400
Message-ID: <3d3e54cf.7f1.0 ＠ e-mail.ru>

neural_shock> hello.
neural_shock> 
neural_shock> here are some logs of checpointing failure in english. see messages on Jul 24
neural_shock> in "messages" file in attached tar ball. there are also "gdbout2" file, there
neural_shock> are some debug information from kgdb. 
neural_shock> 
neural_shock> with respect, mike.

Could you give us more information.

1) Is the program (LU class A) working fine without check pointing?

2)  How about class W of LU.

Shinji.
-----
Shinji Sumimoto

_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From neural_shock ＠ e-mail.ru  Mon Jul 29 16:56:20 2002
From: neural_shock ＠ e-mail.ru (=?iso-2022-jp?b?bmV1cmFsX3Nob2NrIBskQiF3GyhCIGUtbWFpbC5ydQ==?=)
Date: Mon, 29 Jul 2002 11:56:20 +0400
Subject: [SCore-users-jp] Re: [SCore-users] (no subject)
Message-ID: <3d44f524.5f33.0@e-mail.ru>

>Hi.
>
>Sorry for late response.
>
>From: neural_shock ＠ e-mail.ru
>Subject: [SCore-users] (no subject)
>Date: Wed, 24 Jul 2002 11:18:39 +0400
>Message-ID: <3d3e54cf.7f1.0 ＠ e-mail.ru>
>
>neural_shock> hello.
>neural_shock> 
>neural_shock> here are some logs of checpointing failure in english. see messages
on Jul 24
>neural_shock> in "messages" file in attached tar ball. there are also "gdbout2"
file, there
>neural_shock> are some debug information from kgdb. 
>neural_shock> 
>neural_shock> with respect, mike.
>
>Could you give us more information.
>
>1) Is the program (LU class A) working fine without check pointing?
>
>2)  How about class W of LU.
>
>Shinji.
>-----
>Shinji Sumimoto
hello.

1. yes it works fine.
2. i did not run lu class w. there are too few memory on my test machines even
for class b of this programm ( as far as i think. SCore's FEP does not print
"memory could be exhausted" but nodes begins swap pages too heavy when i run
lu.B.2 ).

with respect, mike. 

http://www.e-mail.ru

---

---
http://www.E-mail.ru  - ?????????? ?????????? ???????? ??????.
????? 100 ??/?, SMTP/POP3, SMS, ????????????, ?????? ?? ????? ? ???????, ?????????????, ????????, ????????, ????? ? ?????? ??????.
_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From s-sumi ＠ flab.fujitsu.co.jp  Mon Jul 29 17:22:19 2002
From: s-sumi ＠ flab.fujitsu.co.jp (Shinji Sumimoto)
Date: Mon, 29 Jul 2002 17:22:19 +0900 (JST)
Subject: [SCore-users-jp] Re: [SCore-users] (no subject)
In-Reply-To: <3d44f524.5f33.0@e-mail.ru>
References: <3d44f524.5f33.0@e-mail.ru>
Message-ID: <20020729.172219.576037228.s-sumi@flab.fujitsu.co.jp>

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


From neural_shock ＠ e-mail.ru  Mon Jul 29 17:34:01 2002
From: neural_shock ＠ e-mail.ru (=?iso-2022-jp?b?bmV1cmFsX3Nob2NrIBskQiF3GyhCIGUtbWFpbC5ydQ==?=)
Date: Mon, 29 Jul 2002 12:34:01 +0400
Subject: [SCore-users-jp] Re: [SCore-users] (no subject)
Message-ID: <3d44fdf9.1a32.0@e-mail.ru>

>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

??s. you are right i was wrong. and i have tested it already. results are the
same.
http://www.e-mail.ru

---

---
http://www.E-mail.ru  - ?????????? ?????????? ???????? ??????.
????? 100 ??/?, SMTP/POP3, SMS, ????????????, ?????? ?? ????? ? ???????, ?????????????, ????????, ????????, ????? ? ?????? ??????.
_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From s-sumi ＠ flab.fujitsu.co.jp  Mon Jul 29 17:46:05 2002
From: s-sumi ＠ flab.fujitsu.co.jp (Shinji Sumimoto)
Date: Mon, 29 Jul 2002 17:46:05 +0900 (JST)
Subject: [SCore-users-jp] Re: [SCore-users] (no subject)
In-Reply-To: <3d44fdf9.1a32.0@e-mail.ru>
References: <3d44fdf9.1a32.0@e-mail.ru>
Message-ID: <20020729.174605.596533022.s-sumi@flab.fujitsu.co.jp>

From: neural_shock ＠ e-mail.ru
Subject: Re: [SCore-users] (no subject)
Date: Mon, 29 Jul 2002 12:34:01 +0400
Message-ID: <3d44fdf9.1a32.0 ＠ e-mail.ru>

neural_shock> >Hi.
neural_shock> >
neural_shock> >From: neural_shock ＠ e-mail.ru
neural_shock> >Subject: Re: [SCore-users] (no subject)
neural_shock> >Date: Mon, 29 Jul 2002 11:56:20 +0400
neural_shock> >Message-ID: <3d44f524.5f33.0 ＠ e-mail.ru>
neural_shock> >
neural_shock> >neural_shock> >Hi.
neural_shock> >neural_shock> >
neural_shock> >neural_shock> >Sorry for late response.
neural_shock> >neural_shock> >
neural_shock> >neural_shock> >From: neural_shock ＠ e-mail.ru
neural_shock> >neural_shock> >Subject: [SCore-users] (no subject)
neural_shock> >neural_shock> >Date: Wed, 24 Jul 2002 11:18:39 +0400
neural_shock> >neural_shock> >Message-ID: <3d3e54cf.7f1.0 ＠ e-mail.ru>
neural_shock> >neural_shock> >
neural_shock> >neural_shock> >neural_shock> hello.
neural_shock> >neural_shock> >neural_shock> 
neural_shock> >neural_shock> >neural_shock> here are some logs of checpointing failure in
neural_shock> english. see messages
neural_shock> >neural_shock> on Jul 24
neural_shock> >neural_shock> >neural_shock> in "messages" file in attached tar ball. there
neural_shock> are also "gdbout2"
neural_shock> >neural_shock> file, there
neural_shock> >neural_shock> >neural_shock> are some debug information from kgdb. 
neural_shock> >neural_shock> >neural_shock> 
neural_shock> >neural_shock> >neural_shock> with respect, mike.
neural_shock> >neural_shock> >
neural_shock> >neural_shock> >Could you give us more information.
neural_shock> >neural_shock> >
neural_shock> >neural_shock> >1) Is the program (LU class A) working fine without check pointing?
neural_shock> 
neural_shock> >neural_shock> >
neural_shock> >neural_shock> >2)  How about class W of LU.
neural_shock> >neural_shock> >
neural_shock> >neural_shock> >Shinji.
neural_shock> >neural_shock> >-----
neural_shock> >neural_shock> >Shinji Sumimoto
neural_shock> >neural_shock> hello.
neural_shock> >neural_shock> 
neural_shock> >neural_shock> 1. yes it works fine.
neural_shock> >neural_shock> 2. i did not run lu class w. there are too few memory on my test
neural_shock> machines even
neural_shock> >neural_shock> for class b of this programm ( as far as i think. SCore's FEP
neural_shock> does not print
neural_shock> >neural_shock> "memory could be exhausted" but nodes begins swap pages too heavy
neural_shock> when i run
neural_shock> >neural_shock> lu.B.2 ).
neural_shock> >neural_shock> 
neural_shock> >neural_shock> with respect, mike. 
neural_shock> >
neural_shock> >Are these true?
neural_shock> >
neural_shock> >Class W is smaller than Class A.
neural_shock> >
neural_shock> >Class S < W < A < B
neural_shock> >
neural_shock> 
neural_shock> 嫖s. you are right i was wrong. and i have tested it already. results are the
neural_shock> same.

So, how about class S?

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


From neural_shock ＠ e-mail.ru  Mon Jul 29 18:04:18 2002
From: neural_shock ＠ e-mail.ru (=?iso-2022-jp?b?bmV1cmFsX3Nob2NrIBskQiF3GyhCIGUtbWFpbC5ydQ==?=)
Date: Mon, 29 Jul 2002 13:04:18 +0400
Subject: [SCore-users-jp] Re: [SCore-users] (no subject)
Message-ID: <3d450512.44db.0@e-mail.ru>

>From: neural_shock ＠ e-mail.ru
>Subject: Re: [SCore-users] (no subject)
>Date: Mon, 29 Jul 2002 12:34:01 +0400
>Message-ID: <3d44fdf9.1a32.0 ＠ e-mail.ru>
>
>neural_shock> >Hi.
>neural_shock> >
>neural_shock> >From: neural_shock ＠ e-mail.ru
>neural_shock> >Subject: Re: [SCore-users] (no subject)
>neural_shock> >Date: Mon, 29 Jul 2002 11:56:20 +0400
>neural_shock> >Message-ID: <3d44f524.5f33.0 ＠ e-mail.ru>
>neural_shock> >
>neural_shock> >neural_shock> >Hi.
>neural_shock> >neural_shock> >
>neural_shock> >neural_shock> >Sorry for late response.
>neural_shock> >neural_shock> >
>neural_shock> >neural_shock> >From: neural_shock ＠ e-mail.ru
>neural_shock> >neural_shock> >Subject: [SCore-users] (no subject)
>neural_shock> >neural_shock> >Date: Wed, 24 Jul 2002 11:18:39 +0400
>neural_shock> >neural_shock> >Message-ID: <3d3e54cf.7f1.0 ＠ e-mail.ru>
>neural_shock> >neural_shock> >
>neural_shock> >neural_shock> >neural_shock> hello.
>neural_shock> >neural_shock> >neural_shock> 
>neural_shock> >neural_shock> >neural_shock> here are some logs of checpointing
failure in
>neural_shock> english. see messages
>neural_shock> >neural_shock> on Jul 24
>neural_shock> >neural_shock> >neural_shock> in "messages" file in attached
tar ball. there
>neural_shock> are also "gdbout2"
>neural_shock> >neural_shock> file, there
>neural_shock> >neural_shock> >neural_shock> are some debug information from
kgdb. 
>neural_shock> >neural_shock> >neural_shock> 
>neural_shock> >neural_shock> >neural_shock> with respect, mike.
>neural_shock> >neural_shock> >
>neural_shock> >neural_shock> >Could you give us more information.
>neural_shock> >neural_shock> >
>neural_shock> >neural_shock> >1) Is the program (LU class A) working fine without
check pointing?
>neural_shock> 
>neural_shock> >neural_shock> >
>neural_shock> >neural_shock> >2)  How about class W of LU.
>neural_shock> >neural_shock> >
>neural_shock> >neural_shock> >Shinji.
>neural_shock> >neural_shock> >-----
>neural_shock> >neural_shock> >Shinji Sumimoto
>neural_shock> >neural_shock> hello.
>neural_shock> >neural_shock> 
>neural_shock> >neural_shock> 1. yes it works fine.
>neural_shock> >neural_shock> 2. i did not run lu class w. there are too few
memory on my test
>neural_shock> machines even
>neural_shock> >neural_shock> for class b of this programm ( as far as i think.
SCore's FEP
>neural_shock> does not print
>neural_shock> >neural_shock> "memory could be exhausted" but nodes begins swap
pages too heavy
>neural_shock> when i run
>neural_shock> >neural_shock> lu.B.2 ).
>neural_shock> >neural_shock> 
>neural_shock> >neural_shock> with respect, mike. 
>neural_shock> >
>neural_shock> >Are these true?
>neural_shock> >
>neural_shock> >Class W is smaller than Class A.
>neural_shock> >
>neural_shock> >Class S < W < A < B
>neural_shock> >
>neural_shock> 
>neural_shock> $BUE(Bs. you are right i was wrong. and i have tested it already. results are the
>neural_shock> same.
>
>So, how about class S?
>
>Shinji.
>------
>Shinji Sumimoto, Fujitsu Labs

S is too small. there are no rpoblems. but as i think it is simply because checkpointing is already done when system shuts down scored.

mike.
http://www.e-mail.ru

---

---
http://www.E-mail.ru  - ?????????? ?????????? ???????? ??????.
????? 100 ??/?, SMTP/POP3, SMS, ????????????, ?????? ?? ????? ? ???????, ?????????????, ????????, ????????, ????? ? ?????? ??????.
_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From s-sumi ＠ flab.fujitsu.co.jp  Mon Jul 29 18:29:08 2002
From: s-sumi ＠ flab.fujitsu.co.jp (Shinji Sumimoto)
Date: Mon, 29 Jul 2002 18:29:08 +0900 (JST)
Subject: [SCore-users-jp] Re: [SCore-users] (no subject)
In-Reply-To: <3d450512.44db.0@e-mail.ru>
References: <3d450512.44db.0@e-mail.ru>
Message-ID: <20020729.182908.1025218771.s-sumi@flab.fujitsu.co.jp>

From: neural_shock ＠ e-mail.ru
Subject: Re: [SCore-users] (no subject)
Date: Mon, 29 Jul 2002 13:04:18 +0400
Message-ID: <3d450512.44db.0 ＠ e-mail.ru>

neural_shock> >neural_shock> >neural_shock> hello.
neural_shock> >neural_shock> >neural_shock> 
neural_shock> >neural_shock> >neural_shock> 1. yes it works fine.
neural_shock> >neural_shock> >neural_shock> 2. i did not run lu class w. there are too few
neural_shock> memory on my test
neural_shock> >neural_shock> machines even
neural_shock> >neural_shock> >neural_shock> for class b of this programm ( as far as i think.
neural_shock> SCore's FEP
neural_shock> >neural_shock> does not print
neural_shock> >neural_shock> >neural_shock> "memory could be exhausted" but nodes begins swap
neural_shock> pages too heavy
neural_shock> >neural_shock> when i run
neural_shock> >neural_shock> >neural_shock> lu.B.2 ).
neural_shock> >neural_shock> >neural_shock> 
neural_shock> >neural_shock> >neural_shock> with respect, mike. 
neural_shock> >neural_shock> >
neural_shock> >neural_shock> >Are these true?
neural_shock> >neural_shock> >
neural_shock> >neural_shock> >Class W is smaller than Class A.
neural_shock> >neural_shock> >
neural_shock> >neural_shock> >Class S < W < A < B
neural_shock> >neural_shock> >
neural_shock> >neural_shock> 
neural_shock> >neural_shock> 嫖s. you are right i was wrong. and i have tested it already. results are the
neural_shock> >neural_shock> same.
neural_shock> >
neural_shock> >So, how about class S?
neural_shock> >
neural_shock> >Shinji.
neural_shock> >------
neural_shock> >Shinji Sumimoto, Fujitsu Labs
neural_shock> 
neural_shock> S is too small. there are no rpoblems. but as i think it is simply because checkpointing is already done when system shuts down scored.

Sorry. 

How many memory do your nodes have?
Maybe 10MB free memory is needed for lu.W.2.

In my environment, lu.A.2 and lu.W.2 works fine.

====================================================
[s-sumi bin]$ scrun -nodes=2,checkpoint=5s,scored=server  ./lu.A.2  
SCore-D 5.0.0 connected (jid=2).
<0:0> SCORE: 2 nodes (2x1) ready.


 NAS Parallel Benchmarks 2.2 -- LU Benchmark

 Size:  64x 64x 64
 Iterations: 250
 Number of processes:     2

 Time step    1

SCORE: Checkpointing ... done.

SCORE: Checkpointing ... done.

SCORE: Checkpointing ... done.

SCORE: Checkpointing ... done.

SCORE: Checkpointing ... done.

SCORE: Checkpointing ... done.
 Time step   20

SCORE: Checkpointing ... FEP:WARNING SCore-D unexpectedly terminated.
FEP: [29/Jul/2002 18:31:19] Waiting for SCore-D restarted ...
FEP: [29/Jul/2002 18:31:24] SCore-D restarted.
SCore-D 5.0.0 connected (jid=2).
SCORE: Execution restarted from checkpoint.
 Time step   20

SCORE: Checkpointing ... done.

SCORE: Checkpointing ... done.

SCORE: Checkpointing ... done.

SCORE: Checkpointing ... done.

====================================================

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


From nrcb ＠ streamline-computing.com  Wed Jul 31 16:25:50 2002
From: nrcb ＠ streamline-computing.com (Nick Birkett)
Date: Wed, 31 Jul 2002 08:25:50 +0100
Subject: [SCore-users-jp] [SCore-users] 2 swiches, one server.
Message-ID: <200207310725.g6V7Ppf02906@zeralda.streamline.com>

Hi we would like to set up 2 SCore Myrinet clusters using a single front end server.
 Both sets of cluster hosts are on the same ether subnet (192.168.1.0/16), but have separate Myrinet switches (not connected).

The main cluster is already up and running SCore use the batch scheduling.
We have 4-8 more compute hosts, and a separate Myrinet switch. We would like to 
run Score multi-user on the second cluster.

My understanding is that this is possible if I include 2 pm-myrinet.confs 

pm-myrinet.conf for the main cluster
pm-myrinet2.conf for the second cluster

eg in scorehosts.db :

/* PM/Myrinet */
myrinet2k       type=myrinet2k \
                -firmware:file=/opt/score/share/lanai/lanaiM2k.mcp \
                -config:file=/opt/score/etc/pm-myrinet.conf
myrinet2k-2       type=myrinet2k \
                -firmware:file=/opt/score/share/lanai/lanaiM2k.mcp \
                -config:file=/opt/score/etc/pm-myrinet.2conf
.....
.....

#define MSGBSERV        msgbserv=(zeralda.streamline.com:8764)
/* 128 hosts - Main cluster */
comp000.streamline     HOST_0 network=myrinet2k,ethernet,shmem0,shmem1 group=_scoreall_,MYRI,ETHER,SHMEM smp=2 MSGBSERV
comp001.streamline     HOST_1 network=myrinet2k,ethernet,shmem0,shmem1 group=_scoreall_,MYRI,ETHER,SHMEM smp=2 MSGBSERV
.......
.......
comp127.streamline     HOST_127 network=myrinet2k,ethernet,shmem0,shmem1 group=_scoreall_,MYRI,ETHER,SHMEM smp=2 MSGBSERV

/* 4 hosts - development cluster */
comp128.streamline     HOST_128 network=myrinet2k-2,ethernet,shmem0,shmem1 group=_scoreall_,MYRI,ETHER,SHMEM smp=2 MSGBSERV
comp129.streamline     HOST_129 network=myrinet2k-2,ethernet,shmem0,shmem1 group=_scoreall_,MYRI,ETHER,SHMEM smp=2 MSGBSERV
comp130.streamline     HOST_130 network=myrinet2k-2,ethernet,shmem0,shmem1 group=_scoreall_,MYRI,ETHER,SHMEM smp=2 MSGBSERV
comp131.streamline     HOST_131 network=myrinet2k-2,ethernet,shmem0,shmem1 group=_scoreall_,MYRI,ETHER,SHMEM smp=2 MSGBSERV



pm-myrinet.conf is the standard conf for a 128 port switch and pm-myrinet.2conf is a conf for 8 port switch.

Is this correct I wonder ? 

Thanks,


Nick
_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users


From kameyama ＠ pccluster.org  Wed Jul 31 16:57:58 2002
From: kameyama ＠ pccluster.org (=?iso-2022-jp?b?a2FtZXlhbWEgGyRCIXcbKEIgcGNjbHVzdGVyLm9yZw==?=)
Date: Wed, 31 Jul 2002 16:57:58 +0900
Subject: [SCore-users-jp] Re: [SCore-users] 2 swiches, one server.
In-Reply-To: Your message of "Wed, 31 Jul 2002 08:25:50 JST."
             <200207310725.g6V7Ppf02906@zeralda.streamline.com>
Message-ID: <200207310757.g6V7vwv18078@yl-dhcp18.is.s.u-tokyo.ac.jp>

In article <200207310725.g6V7Ppf02906 ＠ zeralda.streamline.com> Nick Birkett <nrcb ＠ streamline-computing.com> wrotes:
> comp001.streamline     HOST_1 network=myrinet2k,ethernet,shmem0,shmem1 group=
> _scoreall_,MYRI,ETHER,SHMEM smp=2 MSGBSERV
> .......
> .......
> comp127.streamline     HOST_127 network=myrinet2k,ethernet,shmem0,shmem1 grou
> p=_scoreall_,MYRI,ETHER,SHMEM smp=2 MSGBSERV
> 
> /* 4 hosts - development cluster */
> comp128.streamline     HOST_128 network=myrinet2k-2,ethernet,shmem0,shmem1 gr
> oup=_scoreall_,MYRI,ETHER,SHMEM smp=2 MSGBSERV
> comp129.streamline     HOST_129 network=myrinet2k-2,ethernet,shmem0,shmem1 gr
> oup=_scoreall_,MYRI,ETHER,SHMEM smp=2 MSGBSERV
> comp130.streamline     HOST_130 network=myrinet2k-2,ethernet,shmem0,shmem1 gr
> oup=_scoreall_,MYRI,ETHER,SHMEM smp=2 MSGBSERV
> comp131.streamline     HOST_131 network=myrinet2k-2,ethernet,shmem0,shmem1 gr
> oup=_scoreall_,MYRI,ETHER,SHMEM smp=2 MSGBSERV
>
> pm-myrinet.conf is the standard conf for a 128 port switch and pm-myrinet.2co
> nf is a conf for 8 port switch.
> 
> Is this correct I wonder ? 

Yes, this is correct.
Please forget restart scoreboard and msgbserv.

I recommended to create different group name for comp128-comp131.

If you want to run scored on this 4 hosts,
you need to specify the hosts to run scout or scored.
If group name is not created, you must run:
    # scout -g comp128+comp129+comp130+compcomp131
    # scored
or
    # sc_watcfh -g comp128+comp129+comp130+compcomp131 ...

If you create group for comp128-comp131 (for example develop), you can run:
    # scout -g develop
    # scored
or
    # sc_watcfh -g develop ...

if you plan to add second cluster hosts, you may run separate msgbserv.
You can run multiple msgbserv one one hosts (with different port number),
then you want to add hosts in develop cluster, you must restart scoreboard
and msgbserv for development cluster.
You don't need to restart msgbserv for main cluster in this case.

                       from Kameyama Toyohisa
_______________________________________________
SCore-users mailing list
SCore-users ＠ pccluster.org
http://www.pccluster.org/mailman/listinfo/score-users