From kameyama @ pccluster.org Thu Jan 20 13:40:13 2011 From: kameyama @ pccluster.org (Kameyama Toyohisa) Date: Thu, 20 Jan 2011 13:40:13 +0900 Subject: [SCore-users-jp] =?iso-2022-jp?b?RndkOiBTQ29yZTdCYXRhNSA=?= =?iso-2022-jp?b?GyRCJE5KQk5zPEI5VCRHRGQ7XyQ5JGs4PT5dJEskRCQkJEYbKEIgLSA=?= =?iso-2022-jp?b?GyRCPEFMZBsoQiAt?= Message-ID: <4D37BCAD.9060308@pccluster.org> 亀山です. すみません. 間違って削除してしまったので, 転送します. Kameyama Toyohisa -------- Original Message -------- Subject: SCore7Bata5 の並列実行で停止する現象について - 質問 - Date: Thu, 20 Jan 2011 13:20:18 +0900 (JST) From: 鈴木 陽介 To: score-users-jp @ pccluster.org CC: kameyama @ pccluster.org, howtoget_m_meg1116 @ yahoo.co.jp 亀山様 神奈川大学 鈴木陽介です。 SCore7Bata5の並列実行で停止する現象について-質問- http://www.pccluster.org/pipermail/score-users-jp/2010-October/003608.html 最新バージョンにバージョンアップすれば、この問題は 解決しますか? ただし、SCore7Bata5のバージョンで、何か修正パッチを 当てれば、改善するのであれば、その方法を教えてください。 大学側で実行した場合のログは以下のとおりです。 <うまくいった場合> [root @ server3 sc01]# scrun -nodes=4x1 ./a.out SCore (7.Beta.5) Connected SCORE{1} 4 nodes (4x1) ready. time = 22.740914 seconds, iteration = 133, performance = 440.971438 MFLOPS <失敗した場合> [root @ server3 sc01]# scrun -nodes=16x1 ./a.out SCore (7.Beta.5) Connected SCORE{1} 16 nodes (16x1) ready. ------------------------------- これ以降は、マシンがフリーズ状態のようです。 応答がありません。コントロール+Cでキャンセルした場合 は、計算ホストの一部の再起動が必要です。 なお、実行したプログラムは(P44-45 Linuxで並列処理をし よう 第2版)を使っています。 以 上 -------------------------------------- Get the new Internet Explorer 8 optimized for Yahoo! JAPAN http://pr.mail.yahoo.co.jp/ie8/ From kameyama @ pccluster.org Thu Jan 20 13:59:51 2011 From: kameyama @ pccluster.org (Kameyama Toyohisa) Date: Thu, 20 Jan 2011 13:59:51 +0900 Subject: [SCore-users-jp] =?iso-2022-jp?b?RndkOiBTQ29yZTdCYXRhNSA=?= =?iso-2022-jp?b?GyRCJE5KQk5zPEI5VCRHRGQ7XyQ5JGs4PT5dJEskRCQkJEYbKEIgLSA=?= =?iso-2022-jp?b?GyRCPEFMZBsoQiAt?= In-Reply-To: <4D37BCAD.9060308@pccluster.org> References: <4D37BCAD.9060308@pccluster.org> Message-ID: <4D37C147.1010808@pccluster.org> 亀山です. (01/20/11 13:40), Kameyama Toyohisa Wrote: > SCore7Bata5の並列実行で停止する現象について-質問- > > http://www.pccluster.org/pipermail/score-users-jp/2010-October/003608.html > > 最新バージョンにバージョンアップすれば、この問題は > 解決しますか? 多分, SCore 7.0 以降でしたら動くと思います. (前の mail の段階で修正していたのですが, 思っていた修正箇所と違っていたような...) > ただし、SCore7Bata5のバージョンで、何か修正パッチを > 当てれば、改善するのであれば、その方法を教えてください。 多分. このバグだけに限定すれば, device driver だけ変更すれば動くと思いますが... score7-src/SCore/pmx/arch/ethernet/driver/linux2_6/pmx_ethernet_main.c の patch は http://escore.cvs.sourceforge.net/viewvc/escore/score7-src/SCore/pmx/arch/ethernet/driver/ethernet/linux2_6/pmx_ethernet_main.c?r1=1.49&r2=1.45&view=patch で入手できます. Kameyama Toyohisa From kameyama @ pccluster.org Fri Jan 21 08:54:11 2011 From: kameyama @ pccluster.org (Kameyama Toyohisa) Date: Fri, 21 Jan 2011 08:54:11 +0900 Subject: [SCore-users-jp] =?iso-2022-jp?b?GyRCI1MjYyNvI3IjZSM3ISUjMCElGyhC?= =?iso-2022-jp?b?GyRCIzEkTiUkJXMlOSVIITwlaz5yN28kSyREJCQkRhsoQiAtIA==?= =?iso-2022-jp?b?GyRCPEFMZBsoQiAt?= In-Reply-To: <20110120151417.2425.qmail@web2908.mail.tnz.yahoo.co.jp> References: <20110120151417.2425.qmail@web2908.mail.tnz.yahoo.co.jp> Message-ID: <4D38CB23.3000703@pccluster.org> 亀山です. (01/21/11 00:14), 鈴木 陽介 Wrote: > Score7.0.1のインストール条件について-質問- > > CentOSのバージョンは5.5でないといけませんか? > 現状5.4 Finalです。 大丈夫だと思います. 最悪, source からコンパイルすれば確実ですが, 多分, rpm で install できると思います. Kameyama Toyohisa From yosukeys @ yahoo.co.jp Fri Jan 21 18:35:20 2011 From: yosukeys @ yahoo.co.jp (=?ISO-2022-JP?B?GyRCTmtMWhsoQiAbJEJNWzJwGyhC?=) Date: Fri, 21 Jan 2011 18:35:20 +0900 (JST) Subject: [SCore-users-jp] =?iso-2022-jp?b?GyRCJVElQyUxITwlOBsoQiBzY29yZTcu?= =?iso-2022-jp?b?QmV0YS41LWNvbW1vbi03LkJldGEuNS0xLng4Nl82NCAbJEIkKyRpGyhC?= =?iso-2022-jp?b?GyRCJE4lVSUhJSQlayRINiU5ZyQ3JEYkJCReJDkhIyFJJSglaSE8GyhC?= =?iso-2022-jp?b?GyRCJEskRCQkJEYbKEI=?= Message-ID: <20110121093520.54647.qmail@web2911.mail.tnz.yahoo.co.jp> 亀山様 神奈川大学 鈴木陽介です。 御指導いただいたとおり、以下のコマンドを実行しましたが sh ./bininstall -server ”パッケージ score7.Beta.5-common-7.Beta.5-1.x86_64 から のファイルと競合しています。”とエラーが発生して インストールが強制終了してしまいます。 ログは以下のとおりです。どうしたら、よろしいでしょうか? [root @ server3 rpm.rhel5.x86_64]# sh ./bininstall -server 準備中... ########################################### [100%] ファイル /opt/score/bin (パッケージ score7.0.0-common-7.0.0-1.x86_64 から) は、パッケージ score7.Beta.5-common-7.Beta.5-1.x86_64 からのファイルと競合しています。 ファイル /opt/score/cgi-bin (パッケージ score7.0.0-common-7.0.0-1.x86_64 から) は、パッケージ score7.Beta.5-common-7.Beta.5-1.x86_64 からのファイルと競合しています。 ファイル /opt/score/doc (パッケージ score7.0.0-common-7.0.0-1.x86_64 から) は、パッケージ score7.Beta.5-common-7.Beta.5-1.x86_64 からのファイルと競合しています。 ファイル /opt/score/etc (パッケージ score7.0.0-common-7.0.0-1.x86_64 から) は、パッケージ score7.Beta.5-common-7.Beta.5-1.x86_64 からのファイルと競合しています。 ファイル /opt/score/install (パッケージ score7.0.0-common-7.0.0-1.x86_64 から) は、パッケージ score7.Beta.5-common-7.Beta.5-1.x86_64 からのファイルと競合しています。 ファイル /opt/score/lib (パッケージ score7.0.0-common-7.0.0-1.x86_64 から) は、パッケージ score7.Beta.5-common-7.Beta.5-1.x86_64 からのファイルと競合しています。 ファイル /opt/score/libexec (パッケージ score7.0.0-common-7.0.0-1.x86_64 から) は、パッケージ score7.Beta.5-common-7.Beta.5-1.x86_64 からのファイルと競合しています。 ファイル /opt/score/modules (パッケージ score7.0.0-common-7.0.0-1.x86_64 から) は、パッケージ score7.Beta.5-common-7.Beta.5-1.x86_64 からのファイルと競合しています。 ファイル /opt/score/mpi (パッケージ score7.0.0-common-7.0.0-1.x86_64 から) は、パッケージ score7.Beta.5-common-7.Beta.5-1.x86_64 からのファイルと競合しています。 ファイル /opt/score/sbin (パッケージ score7.0.0-common-7.0.0-1.x86_64 から) は、パッケージ score7.Beta.5-common-7.Beta.5-1.x86_64 からのファイルと競合しています。 ファイル /opt/score/share (パッケージ score7.0.0-common-7.0.0-1.x86_64 から) は、パッケージ score7.Beta.5-common-7.Beta.5-1.x86_64 からのファイルと競合しています。 ファイル /opt/score/test (パッケージ score7.0.0-common-7.0.0-1.x86_64 から) は、パッケージ score7.Beta.5-common-7.Beta.5-1.x86_64 からのファイルと競合しています。 [root @ server3 rpm.rhel5.x86_64]# sh ./bininstall -server -------------------------------------- Get the new Internet Explorer 8 optimized for Yahoo! JAPAN http://pr.mail.yahoo.co.jp/ie8/ From yosukeys @ yahoo.co.jp Sat Jan 22 07:51:39 2011 From: yosukeys @ yahoo.co.jp (=?ISO-2022-JP?B?GyRCTmtMWhsoQiAbJEJNWzJwGyhC?=) Date: Sat, 22 Jan 2011 07:51:39 +0900 (JST) Subject: [SCore-users-jp] =?iso-2022-jp?b?YmluaW5zdGFsbCAbJEIlOSUvJWobKEI=?= =?iso-2022-jp?b?GyRCJVclSCROSlQ9OCRyJDckRiEiJSQlcyU5JUghPCVrJTMlXiVzGyhC?= =?iso-2022-jp?b?GyRCJUk8QjlUO34kTiUoJWkhPCFJNiU5ZyUoJWkhPCFJJHIyc0hyGyhC?= =?iso-2022-jp?b?GyRCJDkkayEjGyhC?= Message-ID: <20110121225139.62404.qmail@web2904.mail.tnz.yahoo.co.jp> 亀山様 神奈川大学 鈴木陽介です。 以下のエラーがご指導いただいた手順では、 RPM版でのSCore 7 beta5をSCore 7.0.1に に更新できませんでした。 ついては、以下の手順で更新を実行したいと思います。 ■bininstallスクリプトの編集をして、インストールコマンド 実行時のエラー”競合エラー”によってインストールができな い状況を回避する。 (1)SCore 7 beta5(CentOS 5.4(Final))をSCore 7.0.1(CentOS 5.5 ) に更新する。 CentOS 5.4(Final)の環境を yum update -yコマンドで CentOS 5.5(Final)の最新環境にバージョンアップする。 CentOS のバージョンの確認方法は cat /etc/issueで表示されます。 インストールイメージのダウンロード   http://www.pccluster.org/ja/download.html  PC クラスタコンソーシアム>ダウンロード>SCoreディスト リビューション  >SCore Cluster System Software Version 7からISOイメー ジをダウンロードする。  ISOイメージをダウンロードしたあと、DVDメディアに書き込 みインストールディスク  として作成する。 DVDをserverホストにマウントして、イメージをデスクトップ にすべてコピーする。   Score7/score/rpm.rhel5.x86_64/bininstallスクリプトを 編集する。 編集するところは1ヶ所です。 $show rpm --replacepkgs -Uvh $rpms 2>&1 を $show rpm --replacepkgs --force -Uvh $rpms 2>&1 に修正する。 --force をつける。 参考にしたURLは以下のとおりです。     http://www11.atwiki.jp/foxeye/pages/36.html 管理ホストx1、計算ホストx16台に(bininstallスクリプ トを編集した) SCore 7.0.1のインストールイメージをSCPコマンドで各デス クトップにコピーする。 手順(HowToInstall-From-RPM.txt)を実行する http://www.pccluster.org/score_doc/score-7.0.1/HowToInstall-From-RPM.txt 手順どおりに実行します。 デスクトップにコピーしたインストールイメージからコマンド を実行することです。つまり、以下のコマンドを実行するだけ とおもっています 2.1 Server Host On the server host, do the following. server$ su - Password: server# cd server# sh ./bininstall -server 2.1 Compute Host On each compute host, do the following. compNN$ su - Password: compNN# cd compNN# sh ./bininstall -comp 手順(How to SETUP Score7)を実行する  http://www.pccluster.org/score_doc/score-7.0.1/SetupSCore.txt 1. Setup ssh (or rsh) 2. Setup NFS 3. Create the Machine file 4. Reboot every compute hosts 5. Wait for booting up 6. Creating SCore database 7. Reboot 8. MPI Hello 以 上 -------------------------------------- Get the new Internet Explorer 8 optimized for Yahoo! JAPAN http://pr.mail.yahoo.co.jp/ie8/ From yosukeys @ yahoo.co.jp Sat Jan 22 14:53:28 2011 From: yosukeys @ yahoo.co.jp (=?ISO-2022-JP?B?GyRCTmtMWhsoQiAbJEJNWzJwGyhC?=) Date: Sat, 22 Jan 2011 14:53:28 +0900 (JST) Subject: [SCore-users-jp] =?iso-2022-jp?b?GyRCMEoyPCROPEI5VCVtJTAkKyRpGyhC?= =?iso-2022-jp?b?GyRCISIlKCVpITwkTjJyPkNKfUshJCwkbyQrJGwkUDY1JCgkRiQvGyhC?= =?iso-2022-jp?b?GyRCJEAkNSQkISMbKEI=?= Message-ID: <20110122055329.15561.qmail@web2901.mail.tnz.yahoo.co.jp> 亀山様 神奈川大学 鈴木陽介です。 cc:三田さん) Score7の正規版+CentOS5.5(Final)の環境にbininstallスクリ プトに--forceオプションをつけてバージョンアップした後、 以下のプログラムをコンパイル、実行しましたが エラーになってしまいます。ラプラスのプログラムです。 -質問1- Score7の正規版+CentOS5.5(Final)の環境に問題がないか切り 分けをする方法を教えてください。 -質問2- 以下の実行ログから、エラーの解消方法がわかれば教えて ください。 -質問3- PMX/EtherHXB device driverの設定手順は今回のエラー 解消には関係ありますか? 実行エラーのログ # mpicc mpi-lap.c # scrun -nodes=4x1 ./a.out SCore (7.0.0) Connected SCORE{1} 4 nodes (4x1) ready. A.OUT @ host003#3516 <><><><><<><> (no trace available) <><><><><<><> A.OUT @ host003#3516: SIGSEGV (Access violation for mapped object) A.OUT @ host002#4395 <><><><><<><> (no trace available) <><><><><<><> A.OUT @ host002#4395: SIGSEGV (Access violation for mapped object) SCAN:a.out @ host003#3517: ------ Scanning a.out#3517 ------ SCAN:a.out @ host002#4396: ------ Scanning a.out#4396 ------ SCAN:a.out @ host003#3517: [Thread debugging using libthread_db enabled] SCAN:a.out @ host002#4396: [Thread debugging using libthread_db enabled] SCAN:a.out @ host002#4396: 0x0000003e5fc0e380 in __pause_nocancel () from /lib64/libpthread.so.0 SCAN:a.out @ host002#4396: **** Inspecting address: 0x2b61239119a8 **** SCAN:a.out @ host002#4396: 0x2b6123911978 : SCAN:a.out @ host002#4396: loopne 0x2b6123911989 SCAN:a.out @ host002#4396: 0x2b612391197a : mov $0x73,%bh SCAN:a.out @ host002#4396: 0x2b612391197c : add $0x41,%al SCAN:a.out @ host002#4396: 0x2b612391197e : shr $0x10,%ecx SCAN:a.out @ host002#4396: 0x2b6123911981 : shl $0xe,%r8 SCAN:a.out @ host002#4396: 0x2b6123911985 : mov %r13d,0x358(%r14) SCAN:a.out @ host002#4396: 0x2b612391198c : movzbl %r9b,%ecx SCAN:a.out @ host002#4396: 0x2b6123911990 : and $0x1fffc000,%r8d SCAN:a.out @ host002#4396: 0x2b6123911997 : movzwl 0x2(%rbx),%r14d SCAN:a.out @ host002#4396: 0x2b612391199c : add 0x7d0(%rbp,%rcx,8),%r8 SCAN:a.out @ host002#4396: 0x2b61239119a4 : lea (%r8,%rsi,1),%rdx SCAN:a.out @ host002#4396: 0x2b61239119a8 : cmp 0x10(%rdx),%r14w SCAN:a.out @ host002#4396: 0x2b61239119ad : SCAN:a.out @ host002#4396: je 0x2b6123911da1 SCAN:a.out @ host002#4396: 0x2b61239119b3 : mov 0x220(%rbp),%rcx SCAN:a.out @ host002#4396: 0x2b61239119ba : addl $0x1,0xd38(%rbp) SCAN:a.out @ host002#4396: 0x2b61239119c1 : movzwl 0x2(%rbx),%eax SCAN:a.out @ host002#4396: 0x2b61239119c5 : mov (%rcx),%r10d SCAN:a.out @ host002#4396: 0x2b61239119c8 : mov 0x4(%rcx),%ebx SCAN:a.out @ host002#4396: 0x2b61239119cb : cmp %ebx,%r10d SCAN:a.out @ host002#4396: 0x2b61239119ce : SCAN:a.out @ host002#4396: jb 0x2b6123911b10 SCAN:a.out @ host002#4396: 0x2b61239119d4 : mov (%rcx),%r14d SCAN:a.out @ host002#4396: 0x2b61239119d7 : mov 0x4(%rcx),%r11d SCAN:a.out @ host002#4396: 0x2b61239119db : mov %r11d,%edi SCAN:a.out @ host002#4396: 0x2b61239119de : mov %r14d,%edx SCAN:a.out @ host002#4396: 0x2b61239119e1 : add $0x3ff,%rdi SCAN:a.out @ host002#4396: 0x2b61239119e8 : cmp %rdi,%rdx SCAN:a.out @ host003#3517: 0x0000003aa960e380 in __pause_nocancel () from /lib64/libpthread.so.0 SCAN:a.out @ host003#3517: **** Inspecting address: 0x2b7b06ba49a8 **** SCAN:a.out @ host003#3517: 0x2b7b06ba4978 : SCAN:a.out @ host003#3517: loopne 0x2b7b06ba4989 SCAN:a.out @ host003#3517: 0x2b7b06ba497a : mov $0x73,%bh SCAN:a.out @ host003#3517: 0x2b7b06ba497c : add $0x41,%al SCAN:a.out @ host003#3517: 0x2b7b06ba497e : shr $0x10,%ecx SCAN:a.out @ host003#3517: 0x2b7b06ba4981 : shl $0xe,%r8 SCAN:a.out @ host003#3517: 0x2b7b06ba4985 : mov %r13d,0x358(%r14) SCAN:a.out @ host003#3517: 0x2b7b06ba498c : movzbl %r9b,%ecx SCAN:a.out @ host003#3517: 0x2b7b06ba4990 : and $0x1fffc000,%r8d SCAN:a.out @ host003#3517: 0x2b7b06ba4997 : movzwl 0x2(%rbx),%r14d SCAN:a.out @ host003#3517: 0x2b7b06ba499c : add 0x7d0(%rbp,%rcx,8),%r8 SCAN:a.out @ host003#3517: 0x2b7b06ba49a4 : lea (%r8,%rsi,1),%rdx SCAN:a.out @ host003#3517: 0x2b7b06ba49a8 : cmp 0x10(%rdx),%r14w SCAN:a.out @ host003#3517: 0x2b7b06ba49ad : SCAN:a.out @ host003#3517: je 0x2b7b06ba4da1 SCAN:a.out @ host003#3517: 0x2b7b06ba49b3 : mov 0x220(%rbp),%rcx SCAN:a.out @ host003#3517: 0x2b7b06ba49ba : addl $0x1,0xd38(%rbp) SCAN:a.out @ host003#3517: 0x2b7b06ba49c1 : movzwl 0x2(%rbx),%eax SCAN:a.out @ host003#3517: 0x2b7b06ba49c5 : mov (%rcx),%r10d SCAN:a.out @ host003#3517: 0x2b7b06ba49c8 : mov 0x4(%rcx),%ebx SCAN:a.out @ host003#3517: 0x2b7b06ba49cb : cmp %ebx,%r10d SCAN:a.out @ host003#3517: 0x2b7b06ba49ce : SCAN:a.out @ host003#3517: jb 0x2b7b06ba4b10 SCAN:a.out @ host003#3517: 0x2b7b06ba49d4 : mov (%rcx),%r14d SCAN:a.out @ host003#3517: 0x2b7b06ba49d7 : mov 0x4(%rcx),%r11d SCAN:a.out @ host003#3517: 0x2b7b06ba49db : mov %r11d,%edi SCAN:a.out @ host003#3517: 0x2b7b06ba49de : mov %r14d,%edx SCAN:a.out @ host003#3517: 0x2b7b06ba49e1 : add $0x3ff,%rdi SCAN:a.out @ host003#3517: 0x2b7b06ba49e8 : cmp %rdi,%rdx SCAN:a.out @ host003#3517: **** Stack Back Trace **** SCAN:a.out @ host003#3517: SCAN:a.out @ host003#3517: Thread 1 (Thread 0x2b7b066b8670 (LWP 3517)): SCAN:a.out @ host003#3517: #0 0x0000003aa960e380 in __pause_nocancel () from /lib64/libpthread.so.0 SCAN:a.out @ host003#3517: No symbol table info available. SCAN:a.out @ host003#3517: #1 0x00002b7b062a8ad5 in __sc__attach_debugger (signal=11, SCAN:a.out @ host003#3517: ctxp=) at ../attach.c:137 SCAN:a.out @ host003#3517: pc = 47807393843624 SCAN:a.out @ host003#3517: pid_debuggee = -514 SCAN:a.out @ host003#3517: pid_debugger = SCAN:a.out @ host003#3517: #2 0x00002b7b062a8a7e in score_exception_handler (signal=11, info=0x1b819d70, SCAN:a.out @ host003#3517: ctx=0x1b819c40) at ../attach.c:210 SCAN:a.out @ host003#3517: errout = 0x3aa8d51860 SCAN:a.out @ host003#3517: #3 SCAN:a.out @ host003#3517: No symbol table info available. SCAN:a.out @ host003#3517: #4 0x00002b7b06ba49a8 in PMX_etherhxb_receive () SCAN:a.out @ host003#3517: from /opt/score/7.0.0//lib/obj.x86_64-rhel5-linux2_6/etherhxb.so SCAN:a.out @ host003#3517: No symbol table info available. SCAN:a.out @ host003#3517: #5 0x00002b7b057a6819 in comp_receive (pmc=0x2b7b066b9000, SCAN:a.out @ host003#3517: bufp=0x7fffb5a31940, sizep=0x7fffb5a31938, descp=0x7fffb5a31928) SCAN:a.out @ host003#3517: at ../composite.c:2560 SCAN:a.oSCAN:a.out @ host002#4396: **** Stack Back Trace **** SCAN:a.out @ host002#4396: SCAN:a.out @ host002#4396: Thread 1 (Thread 0x2b6123425670 (LWP 4396)): SCAN:a.out @ host002#4396: #0 0x0000003e5fc0e380 in __pause_nocancel () from /lib64/libpthread.so.0 SCAN:a.out @ host002#4396: No symbol table info available. SCAN:a.out @ host002#4396: #1 0x00002b6123015ad5 in __sc__attach_debugger (signal=11, SCAN:a.out @ host002#4396: ctxp=) at ../attach.c:137 SCAN:a.out @ host002#4396: pc = 47696208533928 SCAN:a.out @ host002#4396: pid_debuggee = -514 SCAN:a.out @ host002#4396: pid_debugger = SCAN:a.out @ host002#4396: #2 0x00002b6123015a7e in score_exception_handler (signal=11, info=0x1bcc8d70, SCAN:a.out @ host002#4396: ctx=0x1bcc8c40) at ../attach.c:210 SCAN:a.out @ host002#4396: errout = 0x3e5f351860 SCAN:a.out @ host002#4396: #3 SCAN:a.out @ host002#4396: No symbol table info available. SCAN:a.out @ host002#4396: #4 0x00002b61239119a8 in PMX_etherhxb_receive () SCAN:a.out @ host002#4396: from /opt/score/7.0.0//lib/obj.x86_64-rhel5-linux2_6/etherhxb.so SCAN:a.out @ host002#4396: No symbol table info available. SCAN:a.out @ host002#4396: #5 0x00002b6122513819 in comp_receive (pmc=0x2b6123426000, SCAN:a.out @ host002#4396: bufp=0x7fff129fead0, sizep=0x7fff129feac8, descp=0x7fff129feab8) SCAN:a.out @ host002#4396: at ../composite.c:2560 SCAN:a.out @ host002#4396: No locals. SCAN:a.out @ host002#4396: #6 pmxReceive (pmc=0x2b6123426000, bufp=0x7fff129fead0, sizep=0x7fff129feac8, SCAN:a.out @ host002#4396: descp=0x7fff129feab8) at ../composite.c:2650 SCAN:a.out @ host002#4396: err = 71 SCAN:a.out @ host002#4396: #7 0x00002b61220d08ec in MTMIT_BT_SCore_Recv () SCAN:a.out @ host002#4396: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host002#4396: No symbol table info available. SCAN:a.out @ host002#4396: #8 0x00002b61220cac36 in MTMIT_BT_Progress () SCAN:a.out @ host002#4396: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host002#4396: No symbol table info available. SCAN:a.out @ host002#4396: #9 0x00002b61220c9c55 in MTMI_WaitEvent () SCAN:a.out @ host002#4396: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host002#4396: No symbol table info available. SCAN:a.out @ host002#4396: #10 0x00002b6121e0e657 in MPID_MTMI_progress () SCAN:a.out @ host002#4396: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host002#4396: No symbol table info available. SCAN:a.out @ host002#4396: #11 0x00002b6121e0e7cc in MPID_Progress_wait () SCAN:a.out @ host002#4396: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host002#4396: No symbol table info available. SCAN:a.out @ host002#4396: #12 0x00002b6121e50e13 in PMPI_Wait () SCAN:a.out @ host002#4396: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host002#4396: No symbol table info available. SCAN:a.out @ host002#4396: #13 0x0000000000400f3e in main () SCAN:a.out @ host002#4396: No symbol table info available. ut @ host003#3517: No locals. SCAN:a.out @ host003#3517: #6 pmxReceive (pmc=0x2b7b066b9000, bufp=0x7fffb5a31940, sizep=0x7fffb5a31938, SCAN:a.out @ host003#3517: descp=0x7fffb5a31928) at ../composite.c:2650 SCAN:a.out @ host003#3517: err = 71 SCAN:a.out @ host003#3517: #7 0x00002b7b053638ec in MTMIT_BT_SCore_Recv () SCAN:a.out @ host003#3517: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host003#3517: No symbol table info available. SCAN:a.out @ host003#3517: #8 0x00002b7b0535dc36 in MTMIT_BT_Progress () SCAN:a.out @ host003#3517: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host003#3517: No symbol table info available. SCAN:a.out @ host003#3517: #9 0x00002b7b0535cc55 in MTMI_WaitEvent () SCAN:a.out @ host003#3517: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host003#3517: No symbol table info available. SCAN:a.out @ host003#3517: #10 0x00002b7b050a1657 in MPID_MTMI_progress () SCAN:a.out @ host003#3517: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host003#3517: No symbol table info available. SCAN:a.out @ host003#3517: #11 0x00002b7b050a17cc in MPID_Progress_wait () SCAN:a.out @ host003#3517: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host003#3517: No symbol table info available. SCAN:a.out @ host003#3517: #12 0x00002b7b050e3e13 in PMPI_Wait () SCAN:a.out @ host003#3517: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host003#3517: No symbol table info available. SCAN:a.out @ host003#3517: #13 0x0000000000400f3e in main () SCAN:a.out @ host003#3517: No symbol table info available. <2> SCORE: Program signaled (Segmentation fault). 以 上 -------------------------------------- Get the new Internet Explorer 8 optimized for Yahoo! JAPAN http://pr.mail.yahoo.co.jp/ie8/ From yosukeys @ yahoo.co.jp Sun Jan 23 15:57:45 2011 From: yosukeys @ yahoo.co.jp (=?ISO-2022-JP?B?GyRCTmtMWhsoQiAbJEJNWzJwGyhC?=) Date: Sun, 23 Jan 2011 15:57:45 +0900 (JST) Subject: [SCore-users-jp] =?iso-2022-jp?b?U2NvcmU3LkJhdGE1IBskQiQrJGkbKEI=?= =?iso-2022-jp?b?GyRCJE5ANTUsSEckWCROJSIlQyVXJTAlbCE8JUlKfUshJEskRCQkGyhC?= =?iso-2022-jp?b?GyRCJEYbKEI=?= Message-ID: <20110123065745.32151.qmail@web2907.mail.tnz.yahoo.co.jp> 亀山樣 神奈川大学 鈴木陽介です。 Score7.Bata5からの正規版へのアップグレード方法について 自己解決ができました。競合エラーは回避できできました。 ご指導有難うございました。残る問題は別途まとめてご連絡い たします。 >Score7.Bata5からの正規版への移行方法 yum list linstalled | grep score7* yum remove score7* マシンをリブート インストールDVDをマウントして、通常のインストール手順で バージョンアップできます。前堤のシステム設定に影響はでま せん。 http://www.pccluster.org/score_doc/score-7.0.1/HowToInstall-From-DVD.txt そのあと、通常の設定手順でセットアップできます。 前堤のシステム設定に影響はでません。 http://www.pccluster.org/score_doc/score-7.0.1/SetupSCore.txt 以 上 -------------------------------------- Get the new Internet Explorer 8 optimized for Yahoo! JAPAN http://pr.mail.yahoo.co.jp/ie8/ From yosukeys @ yahoo.co.jp Sun Jan 23 16:34:16 2011 From: yosukeys @ yahoo.co.jp (=?ISO-2022-JP?B?GyRCTmtMWhsoQiAbJEJNWzJwGyhC?=) Date: Sun, 23 Jan 2011 16:34:16 +0900 (JST) Subject: [SCore-users-jp] =?iso-2022-jp?b?UE1YL0V0aGVySFhCIGRldmljZSBkcml2?= =?iso-2022-jp?b?ZXIgGyRCJE5AX0RqSn1LISRyNjUkKCRGJC8kQCQ1JCQhIxsoQg==?= Message-ID: <20110123073416.25732.qmail@web2914.mail.tnz.yahoo.co.jp> 亀山樣 神奈川大学 鈴木陽介です。 PMX/EtherHXB device driverの設定方法を教えてください。 標準インストールでは、設定は必要ないとおもいますが ラプラスのサンプルプログラム"Liunxで並列処理をしよう弟2 版"の (P44ー45)をコンパイルして、実行したところ、ノードの通信 エラー? でないかとおもわれるエラーが表示されました。 素人ですが、ネットワーク関連の問題のような気がします。 score7は標準でRPMで設定しましたのでソースコードから のconfigureではないほうがよいのですが....... (1)ethernetのエラー [root @ server3 ~]# pmxtest -network ethernet PMXTEST.EXE @ host002#5152 <><><><><<><> (no trace available) <><><><><<><> PMXTEST.EXE @ host002[0/1:0/1]#5152: ABORT open_context() at pmx.c:65 Invalid argument SCOUT(host002): Process 5152 terminated with an exception signal (9:Killed). (2)コンパイルエラー [root @ server3 sc01]# scrun -nodes=16x1 -group=pcc ./a.out SCore (7.0.0) Connected SCORE{1} 16 nodes (16x1) ready. A.OUT @ host016#4392 <><><><><<><> (no trace available) <><><><><<><> A.OUT @ host002#3634 <><><><><<><> (no trace available) <><><><><<><> A.OUT @ host003#5710 <><><><><<><> (no trace available) <><><><><<><> SCAN:a.out @ host016#4393: ------ Scanning a.out#4393 ------ SCAN:a.out @ host003#5711: ------ Scanning a.out#5711 ------ SCAN:a.out @ host016#4393: [Thread debugging using libthread_db enabled] SCAN:a.out @ host002#3635: ------ Scanning a.out#3635 ------ SCAN:a.out @ host003#5711: [Thread debugging using libthread_db enabled] SCAN:a.out @ host016#4393: 0x0000003b8600e380 in __pause_nocancel () from /lib64/libpthread.so.0 SCAN:a.out @ host016#4393: **** Inspecting address: 0x2ba5bc6349a8 **** SCAN:a.out @ host016#4393: 0x2ba5bc634978 : SCAN:a.out @ host016#4393: loopne 0x2ba5bc634989 SCAN:a.out @ host016#4393: 0x2ba5bc63497a : mov $0x73,%bh SCAN:a.out @ host016#4393: 0x2ba5bc63497c : add $0x41,%al SCAN:a.out @ host016#4393: 0x2ba5bc63497e : shr $0x10,%ecx SCAN:a.out @ host016#4393: 0x2ba5bc634981 : shl $0xe,%r8 SCAN:a.out @ host016#4393: 0x2ba5bc634985 : mov %r13d,0x358(%r14) SCAN:a.out @ host016#4393: 0x2ba5bc63498c : movzbl %r9b,%ecx SCAN:a.out @ host016#4393: 0x2ba5bc634990 : and $0x1fffc000,%r8d SCAN:a.out @ host016#4393: 0x2ba5bc634997 : movzwl 0x2(%rbx),%r14d SCAN:a.out @ host016#4393: 0x2ba5bc63499c : add 0x7d0(%rbp,%rcx,8),%r8 SCAN:a.out @ host016#4393: 0x2ba5bc6349a4 : lea (%r8,%rsi,1),%rdx SCAN:a.out @ host016#4393: 0x2ba5bc6349a8 : cmp 0x10(%rdx),%r14w SCAN:a.out @ host016#4393: 0x2ba5bc6349ad : SCAN:a.out @ host016#4393: je 0x2ba5bc634da1 SCAN:a.out @ host016#4393: 0x2ba5bc6349b3 : mov 0x220(%rbp),%rcx SCAN:a.out @ host016#4393: 0x2ba5bc6349ba : addl $0x1,0xd38(%rbp) SCAN:a.out @ host016#4393: 0x2ba5bc6349c1 : movzwl 0x2(%rbx),%eax SCAN:a.out @ host016#4393: 0x2ba5bc6349c5 : mov (%rcx),%r10d SCAN:a.out @ host016#4393: 0x2ba5bc6349c8 : mov 0x4(%rcx),%ebx SCAN:a.out @ host016#4393: 0x2ba5bc6349cb : cmp %ebx,%r10d SCAN:a.out @ host016#4393: 0x2ba5bc6349ce : SCAN:a.out @ host016#4393: jb 0x2ba5bc634b10 SCAN:a.out @ host016#4393: 0x2ba5bc6349d4 : mov (%rcx),%r14d SCAN:a.out @ host016#4393: 0x2ba5bc6349d7 : mov 0x4(%rcx),%r11d SCAN:a.out @ host016#4393: 0x2ba5bc6349db : mov %r11d,%edi SCAN:a.out @ host016#4393: 0x2ba5bc6349de : mov %r14d,%edx SCAN:a.out @ host016#4393: 0x2ba5bc6349e1 : add $0x3ff,%rdi SCAN:a.out @ host016#4393: 0x2ba5bc6349e8 : cmp %rdi,%rdx SCAN:a.out @ host016#4393: **** Stack Back Trace **** SCAN:a.out @ host016#4393: SCAN:a.out @ host016#4393: Thread 1 (Thread 0x2ba5bc148670 (LWP 4393)): SCAN:a.out @ host016#4393: #0 0x0000003b8600e380 in __pause_nocancel () from /lib64/libpthread.so.0 SCAN:a.out @ host016#4393: No symbol table info available. SCAN:a.out @ host016#4393: #1 0x00002ba5bbd38ad5 in __sc__attach_debugger (signal=11, SCAN:a.out @ host016#4393: ctxp=) at ../attach.c:137 SCAN:a.out @ host016#4393: pc = 47990830221736 SCAN:a.out @ host016#4393: pid_debuggee = -514 SCAN:a.out @ host016#4393: pid_debugger = SCAN:a.out @ host016#4393: #2 0x00002ba5bbd38a7e in score_exception_handler (signal=11, info=0x1cbbad70, SCAN:a.out @ host016#4393: ctx=0x1cbbac40) at ../attach.c:210 SCAN:a.out @ host016#4393: errout = 0x3b85751860 SCAN:a.out @ host016#4393: #3 SCAN:a.out @ host016#4393: No symbol table info available. SCAN:a.out @ host016#4393: #4 0x00002ba5bc6349a8 in PMX_etherhxb_receive () SCAN:a.out @ host016#4393: from /opt/score/7.0.0//lib/obj.x86_64-rhel5-linux2_6/etherhxb.so SCAN:a.out @ host016#4393: No symbol table info available. SCAN:a.out @ host016#4393: #5 0x00002ba5bb236819 in comp_receive (pmc=0x2ba5bc149000, SCAN:a.out @ host016#4393: bufp=0x7fff64673640, sizep=0x7fff64673638, descp=0x7fff64673628) SCAN:a.out @ host016#4393: at ../composite.c:2560 SCAN:a.oSCAN:a.out @ host003#5711: 0x0000003aa960e380 in __pause_nocancel () from /lib64/libpthread.so.0 SCAN:a.out @ host003#5711: **** Inspecting address: 0x2b06651159a8 **** SCAN:a.out @ host003#5711: 0x2b0665115978 : SCAN:a.out @ host003#5711: loopne 0x2b0665115989 SCAN:a.out @ host003#5711: 0x2b066511597a : mov $0x73,%bh SCAN:a.out @ host003#5711: 0x2b066511597c : add $0x41,%al SCAN:a.out @ host003#5711: 0x2b066511597e : shr $0x10,%ecx SCAN:a.out @ host003#5711: 0x2b0665115981 : shl $0xe,%r8 SCAN:a.out @ host003#5711: 0x2b0665115985 : mov %r13d,0x358(%r14) SCAN:a.out @ host003#5711: 0x2b066511598c : movzbl %r9b,%ecx SCAN:a.out @ host003#5711: 0x2b0665115990 : and $0x1fffc000,%r8d SCAN:a.out @ host003#5711: 0x2b0665115997 : movzwl 0x2(%rbx),%r14d SCAN:a.out @ host003#5711: 0x2b066511599c : add 0x7d0(%rbp,%rcx,8),%r8 SCAN:a.out @ host003#5711: 0x2b06651159a4 : lea (%r8,%rsi,1),%rdx SCAN:a.out @ host003#5711: 0x2b06651159a8 : cmp 0x10(%rdx),%r14w SCAN:a.out @ host003#5711: 0x2b06651159ad : SCAN:a.out @ host003#5711: je 0x2b0665115da1 SCAN:a.out @ host003#5711: 0x2b06651159b3 : mov 0x220(%rbp),%rcx SCAN:a.out @ host003#5711: 0x2b06651159ba : addl $0x1,0xd38(%rbp) SCAN:a.out @ host003#5711: 0x2b06651159c1 : movzwl 0x2(%rbx),%eax SCAN:a.out @ host003#5711: 0x2b06651159c5 : mov (%rcx),%r10d SCAN:a.out @ host003#5711: 0x2b06651159c8 : mov 0x4(%rcx),%ebx SCAN:a.out @ host003#5711: 0x2b06651159cb : cmp %ebx,%r10d SCAN:a.out @ host003#5711: 0x2b06651159ce : SCAN:a.out @ host003#5711: jb 0x2b0665115b10 SCAN:a.out @ host003#5711: 0x2b06651159d4 : mov (%rcx),%r14d SCAN:a.out @ host003#5711: 0x2b06651159d7 : mov 0x4(%rcx),%r11d SCAN:a.out @ host003#5711: 0x2b06651159db : mov %r11d,%edi SCAN:a.out @ host003#5711: 0x2b06651159de : mov %r14d,%edx SCAN:a.out @ host003#5711: 0x2b06651159e1 : add $0x3ff,%rdi SCAN:a.out @ host003#5711: 0x2b06651159e8 : cmp %rdi,%rdx SCAN:a.out @ host003#5711: **** Stack Back Trace **** SCAN:a.out @ host003#5711: SCAN:a.out @ host003#5711: Thread 1 (Thread 0x2b0664c29670 (LWP 5711)): SCAN:a.out @ host003#5711: #0 0x0000003aa960e380 in __pause_nocancel () from /lib64/libpthread.so.0 SCAN:a.out @ host003#5711: No symbol table info available. SCAN:a.out @ host003#5711: #1 0x00002b0664819ad5 in __sc__attach_debugger (signal=11, SCAN:a.out @ host003#5711: ctxp=) at ../attach.c:137 SCAN:a.out @ host003#5711: pc = 47306465434024 SCAN:a.out @ host003#5711: pid_debuggee = -514 SCAN:a.out @ host003#5711: pid_debugger = SCAN:a.out @ host003#5711: #2 0x00002b0664819a7e in score_exception_handler (signal=11, info=0x192f2d70, SCAN:a.out @ host003#5711: ctx=0x192f2c40) at ../attach.c:210 SCAN:a.out @ host003#5711: errout = 0x3aa8d51860 SCAN:a.out @ host003#5711: #3 SCAN:a.out @ host003#5711: No symbol table info available. SCAN:a.out @ host003#5711: #4 0x00002b06651159a8 in PMX_etherhxb_receive () SCAN:a.out @ host003#5711: from /opt/score/7.0.0//lib/obj.x86_64-rhel5-linux2_6/etherhxb.so SCAN:a.out @ host003#5711: No symbol table info available. SCAN:a.out @ host003#5711: #5 0x00002b0663d17819 in comp_receive (pmc=0x2b0664c2a000, SCAN:a.out @ host003#5711: bufp=0x7fff3344cea0, sizep=0x7fff3344ce98, descp=0x7fff3344ce88) SCAN:a.out @ host003#5711: at ../composite.c:2560 SCAN:a.out @ host016#4393: No locals. SCAN:a.out @ host016#4393: #6 pmxReceive (pmc=0x2ba5bc149000, bufp=0x7fff64673640, sizep=0x7fff64673638, SCAN:a.out @ host016#4393: descp=0x7fff64673628) at ../composite.c:2650 SCAN:a.out @ host016#4393: err = 71 SCAN:a.out @ host016#4393: #7 0x00002ba5badf38ec in MTMIT_BT_SCore_Recv () SCAN:a.out @ host016#4393: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host016#4393: No symbol table info available. SCAN:a.out @ host016#4393: #8 0x00002ba5badedc36 in MTMIT_BT_Progress () SCAN:a.out @ host016#4393: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host016#4393: No symbol table info available. SCAN:a.out @ host016#4393: #9 0x00002ba5badec4cb in MTMI_TestAny () SCAN:a.out @ host016#4393: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host016#4393: No symbol table info available. SCAN:a.out @ host016#4393: #10 0x00002ba5bab31668 in MPID_MTMI_progress () SCAN:a.out @ host016#4393: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host016#4393: No symbol table info available. SCAN:a.out @ host016#4393: #11 0x00002ba5bab317cc in MPID_Progress_wait () SCAN:a.out @ host016#4393: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host016#4393: No symbol table info available. SCAN:a.out @ host016#4393: #12 0x00002ba5bab73e13 in PMPI_Wait () SCAN:a.out @ host016#4393: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host016#4393: No symbol table info available. SCAN:a.out @ host016#4393: #13 0x0000000000400f3e in main () SCAN:a.out @ host016#4393: No symbol table info available. ut @ host003#5711: No locals. SCAN:a.out @ host003#5711: #6 pmxReceive (pmc=0x2b0664c2a000, bufp=0x7fff3344cea0, sizep=0x7fff3344ce98, SCAN:a.out @ host003#5711: descp=0x7fff3344ce88) at ../composite.c:2650 SCAN:a.out @ host003#5711: err = 71 SCAN:a.out @ host003#5711: #7 0x00002b06638d48ec in MTMIT_BT_SCore_Recv () SCAN:a.out @ host003#5711: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host003#5711: No symbol table info available. SCAN:a.out @ host003#5711: #8 0x00002b06638cec36 in MTMIT_BT_Progress () SCAN:a.out @ host003#5711: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host003#5711: No symbol table info available. SCAN:a.out @ host003#5711: #9 0x00002b06638cdc55 in MTMI_WaitEvent () SCAN:a.out @ host003#5711: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host003#5711: No symbol table info available. SCAN:a.out @ host003#5711: #10 0x00002b0663612657 in MPID_MTMI_progress () SCAN:a.out @ host003#5711: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host003#5711: No symbol table info available. SCAN:a.out @ host003#5711: #11 0x00002b06636127cc in MPID_Progress_wait () SCAN:a.out @ host003#5711: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host003#5711: No symbol table info available. SCAN:a.out @ host003#5711: #12 0x00002b0663654e13 in PMPI_Wait () SCAN:a.out @ host003#5711: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host003#5711: No symbol table info available. SCAN:a.out @ host003#5711: #13 0x0000000000400f3e in main () SCAN:a.out @ host003#5711: No symbol table info available. SCAN:a.out @ host002#3635: [Thread debugging using libthread_db enabled] SCAN:a.out @ host002#3635: 0x0000003e5fc0e380 in __pause_nocancel () from /lib64/libpthread.so.0 SCAN:a.out @ host002#3635: **** Inspecting address: 0x2b1e2e0229a8 **** SCAN:a.out @ host002#3635: 0x2b1e2e022978 : SCAN:a.out @ host002#3635: loopne 0x2b1e2e022989 SCAN:a.out @ host002#3635: 0x2b1e2e02297a : mov $0x73,%bh SCAN:a.out @ host002#3635: 0x2b1e2e02297c : add $0x41,%al SCAN:a.out @ host002#3635: 0x2b1e2e02297e : shr $0x10,%ecx SCAN:a.out @ host002#3635: 0x2b1e2e022981 : shl $0xe,%r8 SCAN:a.out @ host002#3635: 0x2b1e2e022985 : mov %r13d,0x358(%r14) SCAN:a.out @ host002#3635: 0x2b1e2e02298c : movzbl %r9b,%ecx SCAN:a.out @ host002#3635: 0x2b1e2e022990 : and $0x1fffc000,%r8d SCAN:a.out @ host002#3635: 0x2b1e2e022997 : movzwl 0x2(%rbx),%r14d SCAN:a.out @ host002#3635: 0x2b1e2e02299c : add 0x7d0(%rbp,%rcx,8),%r8 SCAN:a.out @ host002#3635: 0x2b1e2e0229a4 : lea (%r8,%rsi,1),%rdx SCAN:a.out @ host002#3635: 0x2b1e2e0229a8 : cmp 0x10(%rdx),%r14w SCAN:a.out @ host002#3635: 0x2b1e2e0229ad : SCAN:a.out @ host002#3635: je 0x2b1e2e022da1 SCAN:a.out @ host002#3635: 0x2b1e2e0229b3 : mov 0x220(%rbp),%rcx SCAN:a.out @ host002#3635: 0x2b1e2e0229ba : addl $0x1,0xd38(%rbp) SCAN:a.out @ host002#3635: 0x2b1e2e0229c1 : movzwl 0x2(%rbx),%eax SCAN:a.out @ host002#3635: 0x2b1e2e0229c5 : mov (%rcx),%r10d SCAN:a.out @ host002#3635: 0x2b1e2e0229c8 : mov 0x4(%rcx),%ebx SCAN:a.out @ host002#3635: 0x2b1e2e0229cb : cmp %ebx,%r10d SCAN:a.out @ host002#3635: 0x2b1e2e0229ce : SCAN:a.out @ host002#3635: jb 0x2b1e2e022b10 SCAN:a.out @ host002#3635: 0x2b1e2e0229d4 : mov (%rcx),%r14d SCAN:a.out @ host002#3635: 0x2b1e2e0229d7 : mov 0x4(%rcx),%r11d SCAN:a.out @ host002#3635: 0x2b1e2e0229db : mov %r11d,%edi SCAN:a.out @ host002#3635: 0x2b1e2e0229de : mov %r14d,%edx SCAN:a.out @ host002#3635: 0x2b1e2e0229e1 : add $0x3ff,%rdi SCAN:a.out @ host002#3635: 0x2b1e2e0229e8 : cmp %rdi,%rdx SCAN:a.out @ host002#3635: **** Stack Back Trace **** SCAN:a.out @ host002#3635: SCAN:a.out @ host002#3635: Thread 1 (Thread 0x2b1e2db36670 (LWP 3635)): SCAN:a.out @ host002#3635: #0 0x0000003e5fc0e380 in __pause_nocancel () from /lib64/libpthread.so.0 SCAN:a.out @ host002#3635: No symbol table info available. SCAN:a.out @ host002#3635: #1 0x00002b1e2d726ad5 in __sc__attach_debugger (signal=11, SCAN:a.out @ host002#3635: ctxp=) at ../attach.c:137 SCAN:a.out @ host002#3635: pc = 47408620906920 SCAN:a.out @ host002#3635: pid_debuggee = -514 SCAN:a.out @ host002#3635: pid_debugger = SCAN:a.out @ host002#3635: #2 0x00002b1e2d726a7e in score_exception_handler (signal=11, info=0x15ca1d70, SCAN:a.out @ host002#3635: ctx=0x15ca1c40) at ../attach.c:210 SCAN:a.out @ host002#3635: errout = 0x3e5f351860 SCAN:a.out @ host002#3635: #3 SCAN:a.out @ host002#3635: No symbol table info available. SCAN:a.out @ host002#3635: #4 0x00002b1e2e0229a8 in PMX_etherhxb_receive () SCAN:a.out @ host002#3635: from /opt/score/7.0.0//lib/obj.x86_64-rhel5-linux2_6/etherhxb.so SCAN:a.out @ host002#3635: No symbol table info available. SCAN:a.out @ host002#3635: #5 0x00002b1e2cc24819 in comp_receive (pmc=0x2b1e2db37000, SCAN:a.out @ host002#3635: bufp=0x7fffa89724f0, sizep=0x7fffa89724e8, descp=0x7fffa89724d8) SCAN:a.out @ host002#3635: at ../composite.c:2560 SCAN:a.out @ host002#3635: No locals. SCAN:a.out @ host002#3635: #6 pmxReceive (pmc=0x2b1e2db37000, bufp=0x7fffa89724f0, sizep=0x7fffa89724e8, SCAN:a.out @ host002#3635: descp=0x7fffa89724d8) at ../composite.c:2650 SCAN:a.out @ host002#3635: err = 71 SCAN:a.out @ host002#3635: #7 0x00002b1e2c7e18ec in MTMIT_BT_SCore_Recv () SCAN:a.out @ host002#3635: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host002#3635: No symbol table info available. SCAN:a.out @ host002#3635: #8 0x00002b1e2c7dbc36 in MTMIT_BT_Progress () SCAN:a.out @ host002#3635: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host002#3635: No symbol table info available. SCAN:a.out @ host002#3635: #9 0x00002b1e2c7da4cb in MTMI_TestAny () SCAN:a.out @ host002#3635: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host002#3635: No symbol table info available. SCAN:a.out @ host002#3635: #10 0x00002b1e2c51f668 in MPID_MTMI_progress () SCAN:a.out @ host002#3635: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host002#3635: No symbol table info available. SCAN:a.out @ host002#3635: #11 0x00002b1e2c51f7cc in MPID_Progress_wait () SCAN:a.out @ host002#3635: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host002#3635: No symbol table info available. SCAN:a.out @ host002#3635: #12 0x00002b1e2c561e13 in PMPI_Wait () SCAN:a.out @ host002#3635: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host002#3635: No symbol table info available. SCAN:a.out @ host002#3635: #13 0x0000000000400f3e in main () SCAN:a.out @ host002#3635: No symbol table info available. <15> SCORE: Program signaled (Segmentation fault). [root @ server3 sc01]# scrun -nodes=15x1 -group=pcc ./a.out SCore (7.0.0) Connected SCORE{1} 15 nodes (15x1) ready. A.OUT @ host003#5866 <><><><><<><> (no trace available) <><><><><<><> A.OUT @ host002#3790 <><><><><<><> (no trace available) <><><><><<><> SCAN:a.out @ host003#5867: ------ Scanning a.out#5867 ------ SCAN:a.out @ host002#3791: ------ Scanning a.out#3791 ------ SCAN:a.out @ host003#5867: [Thread debugging using libthread_db enabled] SCAN:a.out @ host002#3791: [Thread debugging using libthread_db enabled] SCAN:a.out @ host003#5867: 0x0000003aa960e380 in __pause_nocancel () from /lib64/libpthread.so.0 SCAN:a.out @ host003#5867: **** Inspecting address: 0x2b9caf13f9a8 **** SCAN:a.out @ host003#5867: 0x2b9caf13f978 : SCAN:a.out @ host003#5867: loopne 0x2b9caf13f989 SCAN:a.out @ host003#5867: 0x2b9caf13f97a : mov $0x73,%bh SCAN:a.out @ host003#5867: 0x2b9caf13f97c : add $0x41,%al SCAN:a.out @ host003#5867: 0x2b9caf13f97e : shr $0x10,%ecx SCAN:a.out @ host003#5867: 0x2b9caf13f981 : shl $0xe,%r8 SCAN:a.out @ host003#5867: 0x2b9caf13f985 : mov %r13d,0x358(%r14) SCAN:a.out @ host003#5867: 0x2b9caf13f98c : movzbl %r9b,%ecx SCAN:a.out @ host003#5867: 0x2b9caf13f990 : and $0x1fffc000,%r8d SCAN:a.out @ host003#5867: 0x2b9caf13f997 : movzwl 0x2(%rbx),%r14d SCAN:a.out @ host003#5867: 0x2b9caf13f99c : add 0x7d0(%rbp,%rcx,8),%r8 SCAN:a.out @ host003#5867: 0x2b9caf13f9a4 : lea (%r8,%rsi,1),%rdx SCAN:a.out @ host003#5867: 0x2b9caf13f9a8 : cmp 0x10(%rdx),%r14w SCAN:a.out @ host003#5867: 0x2b9caf13f9ad : SCAN:a.out @ host003#5867: je 0x2b9caf13fda1 SCAN:a.out @ host003#5867: 0x2b9caf13f9b3 : mov 0x220(%rbp),%rcx SCAN:a.out @ host003#5867: 0x2b9caf13f9ba : addl $0x1,0xd38(%rbp) SCAN:a.out @ host003#5867: 0x2b9caf13f9c1 : movzwl 0x2(%rbx),%eax SCAN:a.out @ host003#5867: 0x2b9caf13f9c5 : mov (%rcx),%r10d SCAN:a.out @ host003#5867: 0x2b9caf13f9c8 : mov 0x4(%rcx),%ebx SCAN:a.out @ host003#5867: 0x2b9caf13f9cb : cmp %ebx,%r10d SCAN:a.out @ host003#5867: 0x2b9caf13f9ce : SCAN:a.out @ host003#5867: jb 0x2b9caf13fb10 SCAN:a.out @ host003#5867: 0x2b9caf13f9d4 : mov (%rcx),%r14d SCAN:a.out @ host003#5867: 0x2b9caf13f9d7 : mov 0x4(%rcx),%r11d SCAN:a.out @ host003#5867: 0x2b9caf13f9db : mov %r11d,%edi SCAN:a.out @ host003#5867: 0x2b9caf13f9de : mov %r14d,%edx SCAN:a.out @ host003#5867: 0x2b9caf13f9e1 : add $0x3ff,%rdi SCAN:a.out @ host003#5867: 0x2b9caf13f9e8 : cmp %rdi,%rdx SCAN:a.out @ host003#5867: **** Stack Back Trace **** SCAN:a.out @ host003#5867: SCAN:a.out @ host003#5867: Thread 1 (Thread 0x2b9caec53670 (LWP 5867)): SCAN:a.out @ host003#5867: #0 0x0000003aa960e380 in __pause_nocancel () from /lib64/libpthread.so.0 SCAN:a.out @ host003#5867: No symbol table info available. SCAN:a.out @ host003#5867: #1 0x00002b9cae843ad5 in __sc__attach_debugger (signal=11, SCAN:a.out @ host003#5867: ctxp=) at ../attach.c:137 SCAN:a.out @ host003#5867: pc = 47951952214440 SCAN:a.out @ host003#5867: pid_debuggee = -514 SCAN:a.out @ host003#5867: pid_debugger = SCAN:a.out @ host003#5867: #2 0x00002b9cae843a7e in score_exception_handler (signal=11, info=0x174e7d70, SCAN:a.out @ host003#5867: ctx=0x174e7c40) at ../attach.c:210 SCAN:a.out @ host003#5867: errout = 0x3aa8d51860 SCAN:a.out @ host003#5867: #3 SCAN:a.out @ host003#5867: No symbol table info available. SCAN:a.out @ host003#5867: #4 0x00002b9caf13f9a8 in PMX_etherhxb_receive () SCAN:a.out @ host003#5867: from /opt/score/7.0.0//lib/obj.x86_64-rhel5-linux2_6/etherhxb.so SCAN:a.out @ host003#5867: No symbol table info available. SCAN:a.out @ host003#5867: #5 0x00002b9cadd41819 in comp_receive (pmc=0x2b9caec54000, SCAN:a.out @ host003#5867: bufp=0x7fff12f01500, sizep=0x7fff12f014f8, descp=0x7fff12f014e8) SCAN:a.out @ host003#5867: at ../composite.c:2560 SCAN:a.oSCAN:a.out @ host002#3791: 0x0000003e5fc0e380 in __pause_nocancel () from /lib64/libpthread.so.0 SCAN:a.out @ host002#3791: **** Inspecting address: 0x2b194f3d39a8 **** SCAN:a.out @ host002#3791: 0x2b194f3d3978 : SCAN:a.out @ host002#3791: loopne 0x2b194f3d3989 SCAN:a.out @ host002#3791: 0x2b194f3d397a : mov $0x73,%bh SCAN:a.out @ host002#3791: 0x2b194f3d397c : add $0x41,%al SCAN:a.out @ host002#3791: 0x2b194f3d397e : shr $0x10,%ecx SCAN:a.out @ host002#3791: 0x2b194f3d3981 : shl $0xe,%r8 SCAN:a.out @ host002#3791: 0x2b194f3d3985 : mov %r13d,0x358(%r14) SCAN:a.out @ host002#3791: 0x2b194f3d398c : movzbl %r9b,%ecx SCAN:a.out @ host002#3791: 0x2b194f3d3990 : and $0x1fffc000,%r8d SCAN:a.out @ host002#3791: 0x2b194f3d3997 : movzwl 0x2(%rbx),%r14d SCAN:a.out @ host002#3791: 0x2b194f3d399c : add 0x7d0(%rbp,%rcx,8),%r8 SCAN:a.out @ host002#3791: 0x2b194f3d39a4 : lea (%r8,%rsi,1),%rdx SCAN:a.out @ host002#3791: 0x2b194f3d39a8 : cmp 0x10(%rdx),%r14w SCAN:a.out @ host002#3791: 0x2b194f3d39ad : SCAN:a.out @ host002#3791: je 0x2b194f3d3da1 SCAN:a.out @ host002#3791: 0x2b194f3d39b3 : mov 0x220(%rbp),%rcx SCAN:a.out @ host002#3791: 0x2b194f3d39ba : addl $0x1,0xd38(%rbp) SCAN:a.out @ host002#3791: 0x2b194f3d39c1 : movzwl 0x2(%rbx),%eax SCAN:a.out @ host002#3791: 0x2b194f3d39c5 : mov (%rcx),%r10d SCAN:a.out @ host002#3791: 0x2b194f3d39c8 : mov 0x4(%rcx),%ebx SCAN:a.out @ host002#3791: 0x2b194f3d39cb : cmp %ebx,%r10d SCAN:a.out @ host002#3791: 0x2b194f3d39ce : SCAN:a.out @ host002#3791: jb 0x2b194f3d3b10 SCAN:a.out @ host002#3791: 0x2b194f3d39d4 : mov (%rcx),%r14d SCAN:a.out @ host002#3791: 0x2b194f3d39d7 : mov 0x4(%rcx),%r11d SCAN:a.out @ host002#3791: 0x2b194f3d39db : mov %r11d,%edi SCAN:a.out @ host002#3791: 0x2b194f3d39de : mov %r14d,%edx SCAN:a.out @ host002#3791: 0x2b194f3d39e1 : add $0x3ff,%rdi SCAN:a.out @ host002#3791: 0x2b194f3d39e8 : cmp %rdi,%rdx SCAN:a.out @ host002#3791: **** Stack Back Trace **** SCAN:a.out @ host002#3791: SCAN:a.out @ host002#3791: Thread 1 (Thread 0x2b194eee7670 (LWP 3791)): SCAN:a.out @ host002#3791: #0 0x0000003e5fc0e380 in __pause_nocancel () from /lib64/libpthread.so.0 SCAN:a.out @ host002#3791: No symbol table info available. SCAN:a.out @ host002#3791: #1 0x00002b194ead7ad5 in __sc__attach_debugger (signal=11, SCAN:a.out @ host002#3791: ctxp=) at ../attach.c:137 SCAN:a.out @ host002#3791: pc = 47387703589288 SCAN:a.out @ host002#3791: pid_debuggee = -514 SCAN:a.out @ host002#3791: pid_debugger = SCAN:a.out @ host002#3791: #2 0x00002b194ead7a7e in score_exception_handler (signal=11, info=0x190fdd70, SCAN:a.out @ host002#3791: ctx=0x190fdc40) at ../attach.c:210 SCAN:a.out @ host002#3791: errout = 0x3e5f351860 SCAN:a.out @ host002#3791: #3 SCAN:a.out @ host002#3791: No symbol table info available. SCAN:a.out @ host002#3791: #4 0x00002b194f3d39a8 in PMX_etherhxb_receive () SCAN:a.out @ host002#3791: from /opt/score/7.0.0//lib/obj.x86_64-rhel5-linux2_6/etherhxb.so SCAN:a.out @ host002#3791: No symbol table info available. SCAN:a.out @ host002#3791: #5 0x00002b194dfd5819 in comp_receive (pmc=0x2b194eee8000, SCAN:a.out @ host002#3791: bufp=0x7fff27dd1160, sizep=0x7fff27dd1158, descp=0x7fff27dd1148) SCAN:a.out @ host002#3791: at ../composite.c:2560 SCAN:a.out @ host003#5867: No locals. SCAN:a.out @ host003#5867: #6 pmxReceive (pmc=0x2b9caec54000, bufp=0x7fff12f01500, sizep=0x7fff12f014f8, SCAN:a.out @ host003#5867: descp=0x7fff12f014e8) at ../composite.c:2650 SCAN:a.out @ host003#5867: err = 71 SCAN:a.out @ host003#5867: #7 0x00002b9cad8fe8ec in MTMIT_BT_SCore_Recv () SCAN:a.out @ host003#5867: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host003#5867: No symbol table info available. SCAN:a.out @ host003#5867: #8 0x00002b9cad8f8c36 in MTMIT_BT_Progress () SCAN:a.out @ host003#5867: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host003#5867: No symbol table info available. SCAN:a.out @ host003#5867: #9 0x00002b9cad8f7c55 in MTMI_WaitEvent () SCAN:a.out @ host003#5867: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host003#5867: No symbol table info available. SCAN:a.out @ host003#5867: #10 0x00002b9cad63c657 in MPID_MTMI_progress () SCAN:a.out @ host003#5867: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host003#5867: No symbol table info available. SCAN:a.out @ host003#5867: #11 0x00002b9cad63c7cc in MPID_Progress_wait () SCAN:a.out @ host003#5867: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host003#5867: No symbol table info available. SCAN:a.out @ host003#5867: #12 0x00002b9cad67ee13 in PMPI_Wait () SCAN:a.out @ host003#5867: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host003#5867: No symbol table info available. SCAN:a.out @ host003#5867: #13 0x0000000000400f3e in main () SCAN:a.out @ host003#5867: No symbol table info available. ut @ host002#3791: No locals. SCAN:a.out @ host002#3791: #6 pmxReceive (pmc=0x2b194eee8000, bufp=0x7fff27dd1160, sizep=0x7fff27dd1158, SCAN:a.out @ host002#3791: descp=0x7fff27dd1148) at ../composite.c:2650 SCAN:a.out @ host002#3791: err = 71 SCAN:a.out @ host002#3791: #7 0x00002b194db928ec in MTMIT_BT_SCore_Recv () SCAN:a.out @ host002#3791: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host002#3791: No symbol table info available. SCAN:a.out @ host002#3791: #8 0x00002b194db8cc36 in MTMIT_BT_Progress () SCAN:a.out @ host002#3791: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host002#3791: No symbol table info available. SCAN:a.out @ host002#3791: #9 0x00002b194db8b4cb in MTMI_TestAny () SCAN:a.out @ host002#3791: from /opt/score/7.0.0/mpi/libmtmi/obj.x86_64-rhel5-linux2_6/lib/libmtmi.so.1 SCAN:a.out @ host002#3791: No symbol table info available. SCAN:a.out @ host002#3791: #10 0x00002b194d8d0668 in MPID_MTMI_progress () SCAN:a.out @ host002#3791: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host002#3791: No symbol table info available. SCAN:a.out @ host002#3791: #11 0x00002b194d8d07cc in MPID_Progress_wait () SCAN:a.out @ host002#3791: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host002#3791: No symbol table info available. SCAN:a.out @ host002#3791: #12 0x00002b194d912e13 in PMPI_Wait () SCAN:a.out @ host002#3791: from /opt/score/7.0.0/mpi/mpich2/x86_64-rhel5-linux2_6/1.2.1-ch_score-gnu/lib/libmpich.so.1.2 SCAN:a.out @ host002#3791: No symbol table info available. SCAN:a.out @ host002#3791: #13 0x0000000000400f3e in main () SCAN:a.out @ host002#3791: No symbol table info available. <2> SCORE: Program signaled (Segmentation fault). (3)正常に処理された場合、(ただし1台のみでの実行) ********************************** ***1台に対して行った場合は正常*** ********************************** [root @ server3 sc01]# scrun -nodes=1x1 -group=pcc ./a.out SCore (7.0.0) Connected SCORE{1} One node ready. time = 42.535520 seconds, iteration = 133, performance = 235.758105 MFLOPS [root @ server3 sc01]# scrun -nodes=1x2 -group=pcc ./a.out SCore (7.0.0) Connected SCORE{1} 2 nodes (1x2) ready. time = 31.004537 seconds, iteration = 133, performance = 323.439552 MFLOPS [root @ server3 sc01]# scrun -nodes=1x3 -group=pcc ./a.out SCore (7.0.0) Connected SCORE{1} 3 nodes (1x3) ready. time = 64.379530 seconds, iteration = 133, performance = 155.765250 MFLOPS [root @ server3 sc01]# scrun -nodes=1x4 -group=pcc ./a.out SCore (7.0.0) Connected SCORE{1} 4 nodes (1x4) ready. time = 74.913215 seconds, iteration = 133, performance = 151.415352 MFLOPS 以 上 -------------------------------------- Get the new Internet Explorer 8 optimized for Yahoo! JAPAN http://pr.mail.yahoo.co.jp/ie8/ From kameyama @ pccluster.org Mon Jan 24 10:45:48 2011 From: kameyama @ pccluster.org (Kameyama Toyohisa) Date: Mon, 24 Jan 2011 10:45:48 +0900 Subject: [SCore-users-jp] =?iso-2022-jp?b?UE1YL0V0aGVySFhCIGRldmljZSBkcml2?= =?iso-2022-jp?b?ZXIgGyRCJE5AX0RqSn1LISRyNjUkKCRGJC8kQCQ1JCQhIxsoQg==?= In-Reply-To: <20110123073416.25732.qmail@web2914.mail.tnz.yahoo.co.jp> References: <20110123073416.25732.qmail@web2914.mail.tnz.yahoo.co.jp> Message-ID: <4D3CD9CC.5060101@pccluster.org> 亀山です. (01/23/11 16:34), 鈴木 陽介 Wrote: > PMX/EtherHXB device driverの設定方法を教えてください。 確かもとの http://www.pccluster.org/pipermail/score-users-jp/2010-October/003608.html は PMX/Ethernet の問題でしたが, (直したのも PMX/Ethernet のほうです.) 使いたいのは PMX/EtherHXB ですか? device driver は特別な設定は不要ですが, EtherHXB の場合は NIC も変更する 必要があります. 多分, 今回の場合はそこは通っているようですが... > (1)ethernetのエラー > > [root @ server3 ~]# pmxtest -network ethernet > PMXTEST.EXE @ host002#5152<><><><><<><> (no trace > available)<><><><><<><> > PMXTEST.EXE @ host002[0/1:0/1]#5152: ABORT open_context() at > pmx.c:65 Invalid argument > SCOUT(host002): Process 5152 terminated with an exception > signal (9:Killed). これでエラーが出るということはなんらかの network の 設定をしているのでしょうか? 環境変数 SCORE_MESSAGE を ALL:2 に設定することで もう少し詳しいエラーがわかると思います. ちなみに, etherhxb のテストをしたい場合は pmxtest -network etherhxb のはずですが... 2)コンパイルエラー コンパイルは通っているので実行エラーでは? > [root @ server3 sc01]# scrun -nodes=16x1 -group=pcc ./a.out > SCore (7.0.0) Connected 前の mail では 7.0.1 を install しようとしていたように思えましたが, 何故か 7.0.0 が起動されていますね... こちらも SCORE_MESSAGE を設定することで, もう少し詳しい情報が 得られると思います. Kameyama Toyohisa