September 2013 - HPDD-discuss

kernel panic when upgrading from lustre-zfs 2.3.49 -> lustre-zfs 2.4

by Nathaniel Everett Garver-Daniels

Hello, Last year around this time I set up a lustre / zfs system based on zfs 0.6.0_rc3_31chaos lustre 2.3.49.92 that I built from source. It's been chugging along merrily with a combined MGS/MDS and Three OSSs, each with one OST. For some other reasons I had to upgrade the other machines in my cluster from Redhat 6.3 to Redhat 6.4 and it seemed like a good time to try and update to a more official release. I followed the instructions on zfslinux.org for adding their repository and installed zfs 0.6.2 and lustre-2.4.0. After un-mounting all of the clients / OSTs and the MGS/MDS I restarted the system with the new lustre and zfs installed. The zfs filesystems looked OK, but when I tried to "mount -a -t lustre" it had a kernel panic. I haven't been able to get a dump off of the machine yet, but I was wondering if anyone else has run in to this type of problem when doing an upgrade with zfs osds. Also, any recommendations on trying to troubleshoot this while I leave the current system running would be appreciated. My plan is to send a zfs snapshot of the MGS/MDS to another machine and try upgrading it there. I'm wondering if I might need to do a "zpool update" before I try and mount the lustre filesystem. Thanks, -Nate Garver-Daniels Systems Administrator

8 years, 2 months

2
1
0 / 0

problem when build the source code of lustre

by Andy Joe

Hi, I followed the instruction of https://wiki.hpdd.intel.com/pages/viewpage.action?pageId=8126821 to install lustre for the source code. I built the patched kernel successfully. However, when I built the source code of lustre. The following problem appeared. +++++++++++ Problem Below +++++++++++++++++ Applying ext4 patches: rhel6.3/ext4-use-vzalloc-in-ext4_fill_flex_info.patch rhel6.3/ext4-introduce-ext4_kvmalloc-ext4_kzalloc-and-ext4_kvfree.patch rhel6.3/ext4-add-missing-kfree-on-error-return-path-in-add_new_gdb.patch rhel6.3/ext4-use-ext4_kvzalloc-ext4_kvmalloc-for-s_group_desc-and-s_group_info.patch rhel6.3/ext4-wantedi-2.6.patch rhel6.3/ext4-map_inode_page-2.6.18.patch rhel6.3/export-ext4-2.6.patch rhel6.3/ext4-remove-cond_resched-calls.patch rhel6.3/ext4-nlink-2.6.patch sles11sp1/ext4-ext_generation.patch rhel6.3/ext4-inode-version.patch rhel6.4/ext4-mmp.patch rhel6.3/ext4-lookup-dotdot.patch rhel6.3/ext4-print-inum-in-htree-warning.patch rhel6.3/ext4-xattr-no-update-ctime.patch rhel6.4/ext4-prealloc.patch rhel6.3/ext4-mballoc-extra-checks.patch rhel6.4/ext4-misc.patch rhel6.3/ext4-big-endian-check-2.6.patch rhel6.3/ext4-alloc-policy-2.6.patch rhel6.3/ext4-force_over_128tb.patch rhel6.3/ext4-pdir-fix.patch rhel6.3/ext4-add-more-error-checks-to-ext4_mkdir.patch rhel6.3/ext4-osd-iop-common.patch rhel6.3/ext4-osd-iam-exports.patch rhel6.3/ext4-dynlocks-common.patch rhel6.3/ext4-hash-indexed-dir-dotdot-update.patch rhel6.3/ext4-kill-dx_root.patch rhel6.3/ext4-extents-mount-option.patch rhel6.3/ext4-fiemap-2.6.patch rhel6.4/ext4-mballoc-pa_free-mismatch.patch rhel6.3/ext4_data_in_dirent.patch rhel6.3/ext4-large-eas.patch rhel6.3/ext4-disable-mb-cache.patch rhel6.3/ext4-back-dquot-to.patch rhel6.3/ext4-nocmtime-2.6.patch rhel6.3/ext4-journal-callback.patch rhel6.3/ext4-store-tree-generation-at-find.patch rhel6.3/ext4_pdirop.patch rhel6.4/ext4_extra_isize.patch1 out of 1 hunk FAILED -- saving rejects to file fs/ext4/inode.c.rej make[4]: *** [sources] Error 1 make[4]: Leaving directory `/home/build/lustre-release/ldiskfs/ldiskfs' make[3]: *** [all-recursive] Error 1 make[3]: Leaving directory `/home/build/lustre-release/ldiskfs' make[2]: *** [all] Error 2 make[2]: Leaving directory `/home/build/lustre-release/ldiskfs' make[1]: *** [all-recursive] Error 1 make[1]: Leaving directory `/home/build/lustre-release' make: *** [all] Error 2 +++++++++++++ END ++++++++++++++++ Any suggestions are welcome. Yizheng

8 years, 2 months

2
1
0 / 0

Failure to connect to some OST from a client machine

by Bob Ball

We are running Lustre 2.1.6 on Scientific Linux 6.4, kernel 2.6.32-358.11.1.el6.x86_64. This was an upgrade from Lustre 1.8.4 on SL5. We have had a few situations lately where a client stops talking to some subset of the OST (about 58 of these total on 8 OSS, nearly 500TB in total). I have a couple of questions. 1. "lctl dl" on the OSS shows a smaller count on the affected servers; on the client, all OSS showed UP in "lctl dl". Today, I first tried rebooting this OSS, but that did not change the situation. I ended up rebooting the client before I could get full connectivity. Is there any way from the client to get the reconnect, short of rebooting that client? 2. It used to be the case under Lustre 1.8.4 that I could run "lfs df -h" on the client, and see all OST, even those where the connection was not working, for whatever reason. That is no longer the case, now the lfs command stops at the first, non-talking OST. This seems more like a bug than a feature. Is there some other way to see a list of non-communicating OST on a client? Thanks in advance for any help offered. bob

8 years, 2 months

2
4
0 / 0

APAC LUG Save the Date - Japan Translation/Invitation

by OpenSFS Administration

Hello HPDD Discuss mailing list participants, It appears there were font issues with the previous message we distributed. If you are interested in viewing the original post with the Japanese translation for the upcoming APAC LUG event <http://www.opensfs.org/apac-lug-2013/> , you can view the original message at http://lists.lustre.org/pipermail/lustre-discuss/2013-September/017524.html We hope your Japanese colleagues or contacts will be able to attend the APAC LUG event scheduled for October, 17, 2013. Sincerely, __________________________ OpenSFS Administration 3855 SW 153rd Drive Beaverton, OR 97006 USA Phone: +1 503-619-0561 | Fax: +1 503-644-6708 Twitter: @OpenSFS Email: admin(a)opensfs.org | Website: www.opensfs.org ---------------------------------------------------------------------- Message: 1 Date: Thu, 5 Sep 2013 09:35:35 -0700 From: OpenSFS Administration < <mailto:admin@opensfs.org> admin(a)opensfs.org> To: < <mailto:discuss@lists.opensfs.org> discuss(a)lists.opensfs.org>, < <mailto:lustre-discuss@lists.lustre.org> lustre-discuss(a)lists.lustre.org>, < <mailto:hpdd-discuss@lists.01.org> hpdd-discuss(a)lists.01.org> Subject: [HPDD-discuss] Lustre????????(LUG)????????? Message-ID: < <mailto:002a01ceaa55$f35db5b0$da192110$@opensfs.org> 002a01ceaa55$f35db5b0$da192110$(a)opensfs.org> Content-Type: text/plain; charset="utf-8" The following message is a translated version of the email we distributed announcing the upcoming APAC LUG events. We encourage you to circulate the notice below to any of your Japanese colleagues or contacts. The previous English email is also attached for reference. ???????? ?? ?? ??????????? ???????? ?? ?? ??????????? ???????????? Lustre???????????????????????????????????????????????????TOP500??????????Tia nhe-2?????????????????10?15????????????????201?????????????K Computer??????????????10?17????????? ???????????? ?????Lustre????????????OpenSFS?????????????????????????????????????????????? ?????Lustra??????????????????????? Lustre????????(LUG)??????????????????????????????????????IT????????????????? ?????????????????????????? ??????????????? LUG??????Lustre????????????????????????????????????????????????????????????? ??????????????????Lustre??????????????????Lustre???????????????????????????? ???????????? ???????????????????????????????????????????????????????????????????????????? ???LUG?????????????????????????????????????? <mailto:???????????????admin@opensfs.org> ???????????????admin(a)opensfs.org????????? ?????2013?10?6???? ??????????? ??????????????????????????????????Lustre???????????????????????????????????? ?????????????????????????????????????????????admin(a)opensfs.org?????????? ???????????? OpenSFS????????????????????????????????????????????????????????????????????a dmin(a)opensfs.org????????? __________________________ OpenSFS Administration 3855 SW 153rd Drive Beaverton, OR 97006 USA Phone: +1 503-619-0561 | Fax: +1 503-644-6708 Twitter: < <https://twitter.com/opensfs> https://twitter.com/opensfs> @OpenSFS Email: < <mailto:admin@opensfs.org> mailto:admin@opensfs.org> <mailto:admin@opensfs.org> admin(a)opensfs.org | Website: < <http://www.opensfs.org> http://www.opensfs.org> <http://www.opensfs.org> www.opensfs.org -------------- next part -------------- An HTML attachment was scrubbed... URL: < <http://lists.01.org/pipermail/hpdd-discuss/attachments/20130905/6c0a1824/at tachment.html> http://lists.01.org/pipermail/hpdd-discuss/attachments/20130905/6c0a1824/att achment.html> -------------- next part -------------- An embedded message was scrubbed... From: OpenSFS Administration < <mailto:admin@opensfs.org> admin(a)opensfs.org> Subject: Save the Date - China & Japan LUG Events Date: Wed, 7 Aug 2013 14:02:56 -0700 Size: 14040 URL: < <http://lists.01.org/pipermail/hpdd-discuss/attachments/20130905/6c0a1824/at tachment.mht> http://lists.01.org/pipermail/hpdd-discuss/attachments/20130905/6c0a1824/att achment.mht> ------------------------------ _______________________________________________ HPDD-discuss mailing list <mailto:HPDD-discuss@lists.01.org> HPDD-discuss(a)lists.01.org <https://lists.01.org/mailman/listinfo/hpdd-discuss> https://lists.01.org/mailman/listinfo/hpdd-discuss End of HPDD-discuss Digest, Vol 10, Issue 2 *******************************************

8 years, 2 months

1
0
0 / 0

Lustreユーザーグループ(LUG)のイベント日程案内

by OpenSFS Administration

The following message is a translated version of the email we distributed announcing the upcoming APAC LUG events. We encourage you to circulate the notice below to any of your Japanese colleagues or contacts. The previous English email is also attached for reference. イベント日程案内中国北京２０１３年１０月１５日イベント日程案内日本東京２０１３年１０月１７日イベント日程決定のご案内 Lustreファイルシステムのデベロッパー及びユーザーと一日を過ごすイベント開催の日程が決定致しました。初日は現在TOP500のナンバーワンであるTianhe-2のホームカントリー中国にて、この秋10月15日に開催されます。そして２回目は201１年のナンバーワンであったK Computerのホームカントリー日本にて、10月17日に開催されます。このエベントは無料です。グローバルLustreコミュニティーを支持するOpenSFSは、ハイパーフォーマンスコンピューティングとビッグデータワークロードのプレミアムファイルシステムであるLustraの将来を確定するため、日々努力を重ねています。 Lustreユーザーグループ(LUG)のイベントは、世界をリードする企業やベンダー、そしてストーレージマネジャーやITディレクターが集合し、それぞれの専門知識と過去の経験を分かち合える、理想的な機会です。テクニカルセッション：演題募集 LUGイベントは、Lustreファイルシステムの使用方法についてのテクニカルプレゼンテーションが出来る格好の場です。このイベントで発表したいトピックについて、手短かな演題を提出して下さい。Lustreをどのように使用しているか、あるいはLustreから何を学んだかという主題を、３０−４０分のプレゼンテーションでまとめて下さい。プレゼンテーションの数には限りがあり、テクニカルセッションは、ごく少数の英語でのプレゼンテーションを除いては、ほぼ全てが中国語または日本語で行われます。過去のLUGイベントでのテクニカルセッションのリストをご参照の上、演題を提出して下さい。タイトル、演題、そして連絡先をadmin(a)opensfs.xn--org-u63b5cg8jwht23xyhi9n3c. 締め切りは2013年10月6日です。パネルディスカッションパネルディスカッションは、現在活躍中のデベロッパー、ベンダー、そしてLustreユーザーが、将来の推奨、今後の機能強化、そして現実的な最前の措置などについて討論できる理想の場です。パネルディスカッションのトピックについてご提案がありましたら、admin(a)opensfs.xn--org-u63b3a0exb3f0j5dx098ak7tf. スポンサーシップについて OpenSFSでは、今回のイベントにおき、北京または東京にて、あらゆるスポンサーシップパッケージを揃えています。スポンサーシップに興味のある企業機関はadmin(a)opensfs.xn--org-u63b5cg8jwht23xj6xfgewb. __________________________ OpenSFS Administration 3855 SW 153rd Drive Beaverton, OR 97006 USA Phone: +1 503-619-0561 | Fax: +1 503-644-6708 Twitter: <https://twitter.com/opensfs> @OpenSFS Email: <mailto:admin@opensfs.org> admin(a)opensfs.org | Website: <http://www.opensfs.org> www.opensfs.org

8 years, 2 months

1
0
0 / 0

��C Lustre��

by OpenSFS Administration

尊敬的Lustre用户和研发人员，您好！我们即将在TOP500中排名第一的天河2号的故乡，中国举办Lustre用户峰会（Lustre User Group），请您在日历中为此保留出一天，与世界顶尖的Lustre开发人员和Lustre用户们进行交流。会议将于2013年10月15日在北京举行，参加该会议不需要任何费用。作为世界范围Lustre社区的重要代表，OpenSFS一直以来引领着Lustre的长远规划，使其保持在高性能运算中的领先地位以及满足大数据负载。而这次由OpenSFS和Lustre的主要使用机构以及供应商共同举办的Lustre用户峰会，将会是存储和IT精英们进行经验共享和技术交流的理想机会。 * 技术研讨会（Technical Sessions）－正在征集演讲摘要 LUG将是您共享对Lustre的研究和使用经验的理想机会，我们十分期待您能提交您将演讲的主题摘要，演讲的时间长度将是30-45分钟。由于会议时间只有一天，所能接受的演讲数量有限，请您尽快提交。另外，大部分的演讲将会使用普通话，少数的将会使用英文。您可以从 <http://www.opensfs.org/> www.opensfs.org获取以往LUG演讲主题，作为您此次提交LUG演讲主题的参考。提交摘要的方式是，将摘要的中英文（双语）标题，内容以及您的个人简介和联系方法发送至 <mailto:admin@opensfs.org> admin(a)opensfs.org ，摘要提交的最后期限是2013年10月6日。 * 专题研讨会（ Panel Discussions）专题研讨会是听取顶尖Lustre研发人员、供应商以及用户对与未来的需求、发展方向、最优使用经验的最佳环节。如果您对研讨专题内容有所建议，或者希望参与研讨环节，请您发送邮件至 <mailto:admin@opensfs.org> admin(a)opensfs.org . * 赞助机会（Sponsorship Opportunities）如果您的公司或者机构希望成为赞助商，也请您联系 <mailto:admin@opensfs.org> admin(a)opensfs.org 获取详细信息，OpenSFS可以提供不同级别的赞助机会。 __________________________ OpenSFS Administration 3855 SW 153rd Drive Beaverton, OR 97006 USA Phone: +1 503-619-0561 | Fax: +1 503-644-6708 Twitter: <https://twitter.com/opensfs> @OpenSFS Email: <mailto:admin@opensfs.org> admin(a)opensfs.org | Website: <http://www.opensfs.org> www.opensfs.org

8 years, 2 months

1
0
0 / 0

Should I care about SSD lifetime?

by Arman Khalatyan

Hi, I have a lustre 2.4 with mirrored SSDs for MDT/MDS. Should I care about SSD lifetime ? Or is it better to have 15k disks instead of SSDs? My Filesystem is about 50TB but with heavy parallel IO loaded. there are about 20Mln files most of them in the range:10KB-1MB thanks, Arman.

8 years, 2 months

1
0
0 / 0

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

HPDD-discuss September 2013