From committee at io500.org Wed Apr 3 16:53:59 2024 From: committee at io500.org (IO500 Committee) Date: Wed, 03 Apr 2024 09:53:59 -0600 Subject: [gpfsug-discuss] IO500 CFS ISC 2024 Message-ID: Call for Submission Stabilization Period: Monday, April 1st - Friday, April 15th, 2024 Submission Deadline: Tuesday, May 3rd, 2024 AoE The IO500 is now accepting and encouraging submissions for the upcoming 14th semi-annual IO500 Production and Research lists, in conjunction with ISC24. Once again, we are also accepting submissions to both the Production and Research 10 Client Node Challenges to encourage the submission of small scale results. View the requirements for submitting to each list on the IO500 Webpage. The new ranked lists will be announced at the BoF [1]. We hope to see many new results. Background Following the success of the Top500 in collecting and analyzing historical trends in supercomputer technology and evolution, the IO500 was created in 2017, published its first list at SC17, and has grown continually since then. The benchmarks represent community accepted standards, including being used in Request for Proposals for new HPC platforms. The benchmarks showcase the IO access pattern extremes giving a full picture of storage system potential performance. The list is about much more than just the raw rank; all submissions help the community by collecting and publishing a wider corpus of data. The multi-fold goals of the benchmark suite are as follows: - Represent naive and optimized access patterns for the execution of a rich variety of HPC applications, their achievable performance and the documentation of how the numbers are achieved. - Support small to extreme-scale Research and Production HPC systems using flexible storage APIs - Maximizing simplicity in running the benchmark suite while offering tunable parameters Specifically, the benchmark suite includes a hero-run of both IOR and mdtest configured however possible to maximize performance and establish an upper-bound for performance. It also includes runs with highly prescribed parameters in an attempt to determine a lower performance bound. Finally, it includes a namespace search as this has been determined to be a highly sought-after feature in HPC storage systems that has historically not been well-measured. Supported Storage APIs are those that are part of IOR and mdtest. Extending these tools with a public pull request can be done to enable new storage APIs. The goals of the community are also multi-fold: 1. Gather historical data for the sake of analysis and to aid predictions of storage futures 2. Collect tuning information to share valuable performance optimizations across the community 3. Encourage vendors and designers to optimize for workloads beyond "hero runs" 4. Establish bounded expectations for users, procurers, and administrators 5. Understand and be able to reproduce performance on storage systems Using the IO500 Reproducibility guidelines, each submission is labeled according to the breadth of details provided and the access to the deployed storage software that enables the community to reproduce the results and study system design changes over time. The IO500 follows a two-staged approach. First, there will be a two-week stabilization period during which we encourage the community to verify that the benchmark runs properly on a variety of storage systems. During this period the benchmark may be updated based upon feedback from the community. The final benchmark will then be released. We expect that runs compliant with the rules made during the stabilization period will be valid as a final submission unless a significant defect is found. 10 Client Node I/O Challenge The 10 Client Node Challenge is conducted using the regular IO500 benchmark, however, with the rule that exactly 10 client nodes must be used to run the benchmark. You may use any shared storage with any number of servers. We will announce the results in the Production and Research lists as well as in separate derived lists. Birds-of-a-Feather We encourage you to submit [2] to join our community, and to attend the ISC?24 BoF [1] on Tuesday, May 12, 2024 at 10:05am - 11:05am CEST, where we will announce the new IO500 Production and Research lists and their 10 Client Node counterparts. Be Part of the Community Submissions of all sizes are welcome; the webpage has customizable sorting, so it is possible to submit on a small system and still get a very good per-client score, for example. We will also highlight new and interesting results with invited talk(s) at the BoF. [1] https://io500.org/pages/bof-isc24 [2] https://io500.org/submission [3] https://io500.org/rules-submission From Walter.Sklenka at EDV-Design.at Tue Apr 9 12:25:33 2024 From: Walter.Sklenka at EDV-Design.at (Walter Sklenka) Date: Tue, 9 Apr 2024 11:25:33 +0000 Subject: [gpfsug-discuss] gpfs userquota : can df represent the users space used Message-ID: Hi! A collegue/customer asked me theses days why on the quota enabled filesystem a "df ." in the home dir does not show his used and free space , representing the quotas I have to admit I never checked this before . On an other gpfs cluster he says it does When using mmlsquota as normal user this works xy at lxx:~$ /usr/lpp/mmfs/bin/mmlsquota --block-size auto Block Limits | File Limits Filesystem Fileset type blocks quota limit in_doubt grace | files quota limit in_doubt grace Remarks mulfs home USR 29.31G 4.785T 5T 0 none | 208821 0 0 0 none mulfs scratch USR 16K 0 0 0 none | 79 0 0 0 none My silly question is, should "df" do the same and if not what could be the reasons? Have a nice day! Mit freundlichen Gr??en Walter Sklenka Technical Consultant EDV-Design Informationstechnologie GmbH Giefinggasse 6/1/2, A-1210 Wien Tel: +43 1 29 22 165-31 Fax: +43 1 29 22 165-90 E-Mail: sklenka at edv-design.at Internet: www.edv-design.at -------------- next part -------------- An HTML attachment was scrubbed... URL: From jonathan.buzzard at strath.ac.uk Tue Apr 9 12:50:14 2024 From: jonathan.buzzard at strath.ac.uk (Jonathan Buzzard) Date: Tue, 9 Apr 2024 12:50:14 +0100 Subject: [gpfsug-discuss] gpfs userquota : can df represent the users space used In-Reply-To: References: Message-ID: On 09/04/2024 12:25, Walter Sklenka wrote: > CAUTION: This email originated outside the University. Check before > clicking links or attachments. > > Hi! > > A collegue/customer asked me theses days why on the quota enabled > filesystem a ?df .? in the home dir ??does not show his used and free > space , representing the quotas > > I have to admit I never checked this before . On an other gpfs cluster > he says it does > > When using mmlsquota as normal user this works > > xy at lxx:~$ /usr/lpp/mmfs/bin/mmlsquota --block-size auto > > Block Limits?????????????????????????????????????????????? |???? File Limits > > Filesystem Fileset??? type???????? blocks????? quota????? limit > in_doubt??? grace |??? files?? quota??? limit in_doubt??? grace? Remarks > > mulfs????? home?????? USR????????? 29.31G???? 4.785T???????? 5T > 0???? none |?? 208821?????? 0??????? 0??????? 0???? none > > mulfs????? scratch??? USR???????????? 16K????????? 0????????? 0 > 0???? none |?????? 79?????? 0??????? 0??????? 0???? none > > My silly question is, should ?df? do the same and if not what could be > the reasons? > Sounds like the home directory might be a fileset and filesetdf might be set for the file system where df is reporting the home directory quota numbers for mmdf. In general mmdf behaves like df so you get a "device free" report not a quota report. I wrote a small utility that I call mmdiskusage that reports a users home directory quota if it exists. It also skips the in_doubt number because that confuses users. We have it called automatically when they log on, start a terminal etc. Output looks like this Block Limits | File Limits Usage Quota Limit Grace | Files Quota Limit Grace 55.7G 350G 1T n/a | 37109 1000000 2000000 n/a I could post the source if people are interested. It's about 100 lines of clean C plus comments Apache license. It was a development of the mmdfree command I wrote back in the day for Samba. JAB. -- Jonathan A. Buzzard Tel: +44141-5483420 HPC System Administrator, ARCHIE-WeSt. University of Strathclyde, John Anderson Building, Glasgow. G4 0NG From Walter.Sklenka at EDV-Design.at Tue Apr 9 13:40:49 2024 From: Walter.Sklenka at EDV-Design.at (Walter Sklenka) Date: Tue, 9 Apr 2024 12:40:49 +0000 Subject: [gpfsug-discuss] gpfs userquota : can df represent the users space used In-Reply-To: References: Message-ID: <79988442e4ac4beabd9d81c744a57bc6@Mail.EDVDesign.cloudia> Hello Jonathan! Yes you are right: home is a fileset and filesetdf is set So do I understand right: a df always shows a "device free" report ( independent from being a fileset or not) Yes, I would be very interested in the utility ? Thank you very much ! Best wishes Mit freundlichen Gr??en Walter Sklenka Technical Consultant EDV-Design Informationstechnologie GmbH Giefinggasse 6/1/2, A-1210 Wien Tel: +43 1 29 22 165-31 Fax: +43 1 29 22 165-90 E-Mail: sklenka at edv-design.at Internet: www.edv-design.at -----Original Message----- From: gpfsug-discuss On Behalf Of Jonathan Buzzard Sent: Dienstag, 9. April 2024 13:50 To: gpfsug-discuss at gpfsug.org Subject: Re: [gpfsug-discuss] gpfs userquota : can df represent the users space used On 09/04/2024 12:25, Walter Sklenka wrote: > CAUTION: This email originated outside the University. Check before > clicking links or attachments. > > Hi! > > A collegue/customer asked me theses days why on the quota enabled > filesystem a ?df .? in the home dir does not show his used and free > space , representing the quotas > > I have to admit I never checked this before . On an other gpfs cluster > he says it does > > When using mmlsquota as normal user this works > > xy at lxx:~$ /usr/lpp/mmfs/bin/mmlsquota --block-size auto > > Block Limits | File > Limits > > Filesystem Fileset type blocks quota limit > in_doubt grace | files quota limit in_doubt grace > Remarks > > mulfs home USR 29.31G 4.785T 5T > 0 none | 208821 0 0 0 none > > mulfs scratch USR 16K 0 0 > 0 none | 79 0 0 0 none > > My silly question is, should ?df? do the same and if not what could be > the reasons? > Sounds like the home directory might be a fileset and filesetdf might be set for the file system where df is reporting the home directory quota numbers for mmdf. In general mmdf behaves like df so you get a "device free" report not a quota report. I wrote a small utility that I call mmdiskusage that reports a users home directory quota if it exists. It also skips the in_doubt number because that confuses users. We have it called automatically when they log on, start a terminal etc. Output looks like this Block Limits | File Limits Usage Quota Limit Grace | Files Quota Limit Grace 55.7G 350G 1T n/a | 37109 1000000 2000000 n/a I could post the source if people are interested. It's about 100 lines of clean C plus comments Apache license. It was a development of the mmdfree command I wrote back in the day for Samba. JAB. -- Jonathan A. Buzzard Tel: +44141-5483420 HPC System Administrator, ARCHIE-WeSt. University of Strathclyde, John Anderson Building, Glasgow. G4 0NG _______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at gpfsug.org http://gpfsug.org/mailman/listinfo/gpfsug-discuss_gpfsug.org -------------- next part -------------- An HTML attachment was scrubbed... URL: From jpr9c at virginia.edu Wed Apr 10 16:42:52 2024 From: jpr9c at virginia.edu (Ruffner, Scott (jpr9c)) Date: Wed, 10 Apr 2024 15:42:52 +0000 Subject: [gpfsug-discuss] TEE/SGX and GPFS Encryption Message-ID: Dear GPFSUG - I'm wondering if anyone has experience with using GPFS encryption along with Trusted Execution Environments in Edge devices (in this case, DMZ compute environments). I'd be interested in chatting about TEE memory protection for the decrypted storage off line. Best, Scott Ruffner From scottg at emailhosting.com Thu Apr 11 20:36:16 2024 From: scottg at emailhosting.com (scottg at emailhosting.com) Date: Thu, 11 Apr 2024 15:36:16 -0400 Subject: [gpfsug-discuss] US/NYC user group meeting? Message-ID: <019c01da8c47$858c9300$90a5b900$@emailhosting.com> Hi all, Will there be a User group meeting in NYC this year? If so, is there a date? Thanks Scott -------------- next part -------------- An HTML attachment was scrubbed... URL: From richard.rupp at us.ibm.com Thu Apr 11 20:56:29 2024 From: richard.rupp at us.ibm.com (Richard Rupp) Date: Thu, 11 Apr 2024 19:56:29 +0000 Subject: [gpfsug-discuss] US/NYC user group meeting? In-Reply-To: <019c01da8c47$858c9300$90a5b900$@emailhosting.com> References: <019c01da8c47$858c9300$90a5b900$@emailhosting.com> Message-ID: Yes. But we don?t have a date yet. Regards, Richard Rupp Senior Storage Technical Specialist, IBM Technology, US Public Market Cell: 347-510-6746 Webex: https://ibm.webex.com/join/richard.rupp From: gpfsug-discuss On Behalf Of scottg at emailhosting.com Sent: Thursday, April 11, 2024 3:36 PM To: gpfsug-discuss at gpfsug.org Subject: [EXTERNAL] [gpfsug-discuss] US/NYC user group meeting? Hi all, Will there be a User group meeting in NYC this year? If so, is there a date? Thanks Scott ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ZjQcmQRYFpfptBannerStart This Message Is From an Untrusted Sender You have not previously corresponded with this sender. Report Suspicious ? ZjQcmQRYFpfptBannerEnd Hi all, Will there be a User group meeting in NYC this year? If so, is there a date? Thanks Scott -------------- next part -------------- An HTML attachment was scrubbed... URL: From novosirj at rutgers.edu Thu Apr 11 21:01:57 2024 From: novosirj at rutgers.edu (Ryan Novosielski) Date: Thu, 11 Apr 2024 20:01:57 +0000 Subject: [gpfsug-discuss] US/NYC user group meeting? In-Reply-To: References: <019c01da8c47$858c9300$90a5b900$@emailhosting.com> Message-ID: A remote option would be most appreciated. Happy to sign an NDA or whatever might be necessary. -- #BlackLivesMatter ____ || \\UTGERS, |---------------------------*O*--------------------------- ||_// the State | Ryan Novosielski - novosirj at rutgers.edu || \\ University | Sr. Technologist - 973/972.0922 (2x0922) ~*~ RBHS Campus || \\ of NJ | Office of Advanced Research Computing - MSB A555B, Newark `' On Apr 11, 2024, at 15:56, Richard Rupp wrote: Yes. But we don?t have a date yet. Regards, Richard Rupp Senior Storage Technical Specialist, IBM Technology, US Public Market Cell: 347-510-6746 Webex: https://ibm.webex.com/join/richard.rupp From: gpfsug-discuss > On Behalf Of scottg at emailhosting.com Sent: Thursday, April 11, 2024 3:36 PM To: gpfsug-discuss at gpfsug.org Subject: [EXTERNAL] [gpfsug-discuss] US/NYC user group meeting? Hi all, Will there be a User group meeting in NYC this year? If so, is there a date? Thanks Scott ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? Hi all, Will there be a User group meeting in NYC this year? If so, is there a date? Thanks Scott _______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at gpfsug.org http://gpfsug.org/mailman/listinfo/gpfsug-discuss_gpfsug.org -------------- next part -------------- An HTML attachment was scrubbed... URL: From scottg at emailhosting.com Thu Apr 11 23:52:02 2024 From: scottg at emailhosting.com (scottg) Date: Thu, 11 Apr 2024 18:52:02 -0400 Subject: [gpfsug-discuss] US/NYC user group meeting? In-Reply-To: Message-ID: Ok. Thanks.Sent from my T-Mobile 5G Device -------- Original message --------From: Richard Rupp Date: 4/11/24 4:01 PM (GMT-05:00) To: gpfsug main discussion list Subject: Re: [gpfsug-discuss] US/NYC user group meeting? Yes. But we don?t have a date yet. ? Regards, ? Richard Rupp Senior Storage Technical Specialist, IBM Technology, US Public Market Cell: 347-510-6746? Webex: https://ibm.webex.com/join/richard.rupp ? From: gpfsug-discuss On Behalf Of scottg at emailhosting.com Sent: Thursday, April 11, 2024 3:36 PM To: gpfsug-discuss at gpfsug.org Subject: [EXTERNAL] [gpfsug-discuss] US/NYC user group meeting? ? Hi all, Will there be a User group meeting in NYC this year? If so, is there a date? Thanks Scott ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? ? Hi all, Will there be a User group meeting in NYC this year? If so, is there a date? ? Thanks Scott -------------- next part -------------- An HTML attachment was scrubbed... URL: From techie879 at gmail.com Fri Apr 12 09:06:21 2024 From: techie879 at gmail.com (Imam Toufique) Date: Fri, 12 Apr 2024 01:06:21 -0700 Subject: [gpfsug-discuss] accessing REST API endpoint details Message-ID: Hello, I am looking to access the REST API endpoints , this link , https://www.ibm.com/docs/en/storage-scale/5.1.5?topic=ssma-accessing-spectrum-scale-rest-api-endpoint-details-through-swagger-api-explorer#bl1adm_accessingAPIdetails__title__2 , explains about a process accessing this via some GPFS GUI server. I am not sure what that means. I have never used any GUI server for any GPFS related setup or config or management. Does anyone know a CLI method of accessing the REST API endpoint details. Thanks in advance. --IT -------------- next part -------------- An HTML attachment was scrubbed... URL: From daniel.kidger at hpe.com Fri Apr 12 09:50:36 2024 From: daniel.kidger at hpe.com (Kidger, Daniel) Date: Fri, 12 Apr 2024 08:50:36 +0000 Subject: [gpfsug-discuss] accessing REST API endpoint details In-Reply-To: References: Message-ID: Imran, Perhaps the confusion is between the GUI itself and the Gui server? The RestAPI can be fully accessed from the command line of any machine that can reach the URL of the GUI server. I do this regularly using small Python scripts. ie The GUI server provides *both* the web based GUI and the RestAPI What the link you posted below (using Swagger) does is provide a way to explore and learn the RestAPI from completely inside a web browser. Definitely recommended as a teaching aid until you feel comfortable just using say ?curl? from the Linux command line or a short piece of Python. To use the RestAPI, you will need the GUI server process to be running. Also remember it uses the same username/passwords for accessing both. You can create these using /usr/lpp/mmfs/gui/cli/mkuser I strongly recommend creating a user that only has monitoring permissions for use with the RestAPI. That way you are guaranteed not to break anything from a RestAPI call. Daniel Daniel Kidger HPC Storage Solutions Architect, EMEA daniel.kidger at hpe.com +44 (0)7818 522266 hpe.com [cid:image001.png at 01DA8CBD.7C8F88E0] From: gpfsug-discuss On Behalf Of Imam Toufique Sent: Friday, April 12, 2024 9:06 AM To: gpfsug-discuss at spectrumscale.org Subject: [gpfsug-discuss] accessing REST API endpoint details Hello, I am looking to access the REST API endpoints , this link , https://www.ibm.com/docs/en/storage-scale/5.1.5?topic=ssma-accessing-spectrum-scale-rest-api-endpoint-details-through-swagger-api-explorer#bl1adm_accessingAPIdetails__title__2 , explains about a process accessing this via some GPFS GUI server. I am not sure what that means. I have never used any GUI server for any GPFS related setup or config or management. Does anyone know a CLI method of accessing the REST API endpoint details. Thanks in advance. --IT -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: image001.png Type: image/png Size: 2541 bytes Desc: image001.png URL: From daniel.kidger at hpe.com Fri Apr 12 09:50:36 2024 From: daniel.kidger at hpe.com (Kidger, Daniel) Date: Fri, 12 Apr 2024 08:50:36 +0000 Subject: [gpfsug-discuss] accessing REST API endpoint details In-Reply-To: References: Message-ID: Imran, Perhaps the confusion is between the GUI itself and the Gui server? The RestAPI can be fully accessed from the command line of any machine that can reach the URL of the GUI server. I do this regularly using small Python scripts. ie The GUI server provides *both* the web based GUI and the RestAPI What the link you posted below (using Swagger) does is provide a way to explore and learn the RestAPI from completely inside a web browser. Definitely recommended as a teaching aid until you feel comfortable just using say ?curl? from the Linux command line or a short piece of Python. To use the RestAPI, you will need the GUI server process to be running. Also remember it uses the same username/passwords for accessing both. You can create these using /usr/lpp/mmfs/gui/cli/mkuser I strongly recommend creating a user that only has monitoring permissions for use with the RestAPI. That way you are guaranteed not to break anything from a RestAPI call. Daniel Daniel Kidger HPC Storage Solutions Architect, EMEA daniel.kidger at hpe.com +44 (0)7818 522266 hpe.com [cid:image001.png at 01DA8CBD.7C8F88E0] From: gpfsug-discuss On Behalf Of Imam Toufique Sent: Friday, April 12, 2024 9:06 AM To: gpfsug-discuss at spectrumscale.org Subject: [gpfsug-discuss] accessing REST API endpoint details Hello, I am looking to access the REST API endpoints , this link , https://www.ibm.com/docs/en/storage-scale/5.1.5?topic=ssma-accessing-spectrum-scale-rest-api-endpoint-details-through-swagger-api-explorer#bl1adm_accessingAPIdetails__title__2 , explains about a process accessing this via some GPFS GUI server. I am not sure what that means. I have never used any GUI server for any GPFS related setup or config or management. Does anyone know a CLI method of accessing the REST API endpoint details. Thanks in advance. --IT -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: image001.png Type: image/png Size: 2541 bytes Desc: image001.png URL: From paul.musset at brain.mpg.de Fri Apr 12 14:33:54 2024 From: paul.musset at brain.mpg.de (Paul Musset) Date: Fri, 12 Apr 2024 15:33:54 +0200 Subject: [gpfsug-discuss] upgrading cluster with toolkit: precheck fails with "'scale_nfs_url' is undefined" Message-ID: Hello, I am working for the Max Planck Institute for Brain Research where we have a 4 nodes-3PB cluster. The cluster was installed manually but I am trying to use the toolkit to upgrade. During the precheck phase, launched with ./spectrumscale upgrade precheck, there is an error on all 4 nodes saying FAILED! => {"msg": "The task includes an option with an undefined variable. The error was: 'scale_nfs_url' is undefined\n\nThe error appears to be in '/usr/lpp/mmfs/5.1.9.2/ansible-toolkit/ansible/upgrade_sample/playbook_repo_create.yml': line 455, column 11, but may\nbe elsewhere in the file depending on the exact syntax problem.\n\nThe offending line appears to be:\n\n\n ???????- name: upgrade | configure nfs YUM repository\n ? ^ here\n"} Has anyone seen something like that before and/or knows where it could come from ? Thanks in advance Paul From paul.musset at brain.mpg.de Fri Apr 12 15:33:23 2024 From: paul.musset at brain.mpg.de (Paul Musset) Date: Fri, 12 Apr 2024 16:33:23 +0200 Subject: [gpfsug-discuss] upgrading cluster with toolkit: precheck fails with "'scale_nfs_url' is undefined" In-Reply-To: References: Message-ID: Hello, I think I found part of the cause of the problem. I am using scientific linux 7 so maybe its too different from RHEL7 so? the following part of the ansible code doesn't find the correct version ?????? - name: upgrade | nfs path ?????????set_fact: scale_nfs_url: 'ganesha_rpms/rhel7/' ?????????when: ansible_distribution in scale_rhel_distribution and ansible_distribution_major_version == '7' would there be a way for the precheck command to understand that it is an os similar to rhel 7 ? For exemple, running that `LINUX_DISTRIBUTION=REDHAT_AS_LINUX ?mmbuildgpl` worked previously for mmbuildgpl Best regards Paul On 12/04/2024 15.33, Paul Musset wrote: > Hello, > > I am working for the Max Planck Institute for Brain Research where we > have a 4 nodes-3PB cluster. > > The cluster was installed manually but I am trying to use the toolkit > to upgrade. > During the precheck phase, launched with ./spectrumscale upgrade > precheck, there is an error on all 4 nodes saying > > FAILED! => {"msg": "The task includes an option with an undefined > variable. The error was: 'scale_nfs_url' is undefined\n\nThe error > appears to be in > '/usr/lpp/mmfs/5.1.9.2/ansible-toolkit/ansible/upgrade_sample/playbook_repo_create.yml': > line 455, column 11, but may\nbe elsewhere in the file depending on > the exact syntax problem.\n\nThe offending line appears to be:\n\n\n > ???????- name: upgrade | configure nfs YUM repository\n ? ^ here\n"} > > Has anyone seen something like that before and/or knows where it could > come from ? > > Thanks in advance > > Paul > > _______________________________________________ > gpfsug-discuss mailing list > gpfsug-discuss at gpfsug.org > http://gpfsug.org/mailman/listinfo/gpfsug-discuss_gpfsug.org From scottg at emailhosting.com Fri Apr 12 15:48:49 2024 From: scottg at emailhosting.com (scottg at emailhosting.com) Date: Fri, 12 Apr 2024 10:48:49 -0400 Subject: [gpfsug-discuss] upgrading cluster with toolkit: precheck fails with "'scale_nfs_url' is undefined" In-Reply-To: References: Message-ID: <02c401da8ce8$88527ea0$98f77be0$@emailhosting.com> I would think that if you export LINUX_DISTRIBUTION=REDHAT_AS_LINUX before you run the precheck, it might work -----Original Message----- From: gpfsug-discuss On Behalf Of Paul Musset Sent: Friday, April 12, 2024 10:33 AM To: gpfsug-discuss at gpfsug.org Subject: Re: [gpfsug-discuss] upgrading cluster with toolkit: precheck fails with "'scale_nfs_url' is undefined" Hello, I think I found part of the cause of the problem. I am using scientific linux 7 so maybe its too different from RHEL7 so the following part of the ansible code doesn't find the correct version - name: upgrade | nfs path set_fact: scale_nfs_url: 'ganesha_rpms/rhel7/' when: ansible_distribution in scale_rhel_distribution and ansible_distribution_major_version == '7' would there be a way for the precheck command to understand that it is an os similar to rhel 7 ? For exemple, running that `LINUX_DISTRIBUTION=REDHAT_AS_LINUX mmbuildgpl` worked previously for mmbuildgpl Best regards Paul On 12/04/2024 15.33, Paul Musset wrote: > Hello, > > I am working for the Max Planck Institute for Brain Research where we > have a 4 nodes-3PB cluster. > > The cluster was installed manually but I am trying to use the toolkit > to upgrade. > During the precheck phase, launched with ./spectrumscale upgrade > precheck, there is an error on all 4 nodes saying > > FAILED! => {"msg": "The task includes an option with an undefined > variable. The error was: 'scale_nfs_url' is undefined\n\nThe error > appears to be in > '/usr/lpp/mmfs/5.1.9.2/ansible-toolkit/ansible/upgrade_sample/playbook_repo_create.yml': > line 455, column 11, but may\nbe elsewhere in the file depending on > the exact syntax problem.\n\nThe offending line appears to be:\n\n\n > - name: upgrade | configure nfs YUM repository\n ^ here\n"} > > Has anyone seen something like that before and/or knows where it could > come from ? > > Thanks in advance > > Paul > > _______________________________________________ > gpfsug-discuss mailing list > gpfsug-discuss at gpfsug.org > http://gpfsug.org/mailman/listinfo/gpfsug-discuss_gpfsug.org _______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at gpfsug.org http://gpfsug.org/mailman/listinfo/gpfsug-discuss_gpfsug.org From paul.musset at brain.mpg.de Tue Apr 16 09:35:44 2024 From: paul.musset at brain.mpg.de (Paul Musset) Date: Tue, 16 Apr 2024 10:35:44 +0200 Subject: [gpfsug-discuss] upgrading cluster with toolkit: precheck fails with "'scale_nfs_url' is undefined" In-Reply-To: <02c401da8ce8$88527ea0$98f77be0$@emailhosting.com> References: <02c401da8ce8$88527ea0$98f77be0$@emailhosting.com> Message-ID: Hello, so the problem comes indeed from the fact I am not using CentOS or rhel The list of rhel distribution supportedby the tool is in the `scale_rhel_distribution` list in `/usr/lpp/mmfs/5.1.9.2/ansible-toolkit/ansible/ibm-spectrum-scale-install-infra/roles/core_common/vars/main.yml` and `/usr/lpp/mmfs/5.1.9.2/ansible-toolkit/ansible/ibm-spectrum-scale-install-infra/roles/core_upgrade/vars/main.yml` or `/usr/lpp/mmfs/5.1.9.2/ansible-toolkit/ansible/ibm-spectrum-scale-install-infra/roles/core_install/vars/main.yml` depending if you upgradingare installing? your cluster You first have to find under which name ansible recognise your OS with: # ansible localhost -m'ansible.builtin.setup' | grep \"ansible_distribution\": ???????"ansible_distribution": "Scientific", Then you add it to the files described above. scale_rhel_distribution: ?- RedHat ?- CentOS ?- Scientific After that I managed to upgrade I suppose it works also for other centos/rhel alternative like rocky and alma Best Paul On 12/04/2024 16.48, scottg at emailhosting.com wrote: > I would think that if you export LINUX_DISTRIBUTION=REDHAT_AS_LINUX before you run the precheck, it might work > > -----Original Message----- > From: gpfsug-discuss On Behalf Of Paul Musset > Sent: Friday, April 12, 2024 10:33 AM > To: gpfsug-discuss at gpfsug.org > Subject: Re: [gpfsug-discuss] upgrading cluster with toolkit: precheck fails with "'scale_nfs_url' is undefined" > > Hello, > > I think I found part of the cause of the problem. > > I am using scientific linux 7 so maybe its too different from RHEL7 so the following part of the ansible code doesn't find the correct version > > - name: upgrade | nfs path > set_fact: > scale_nfs_url: 'ganesha_rpms/rhel7/' > when: ansible_distribution in scale_rhel_distribution and ansible_distribution_major_version == '7' > > would there be a way for the precheck command to understand that it is an os similar to rhel 7 ? > > For exemple, running that `LINUX_DISTRIBUTION=REDHAT_AS_LINUX > mmbuildgpl` worked previously for mmbuildgpl > > Best regards > Paul > > > On 12/04/2024 15.33, Paul Musset wrote: >> Hello, >> >> I am working for the Max Planck Institute for Brain Research where we >> have a 4 nodes-3PB cluster. >> >> The cluster was installed manually but I am trying to use the toolkit >> to upgrade. >> During the precheck phase, launched with ./spectrumscale upgrade >> precheck, there is an error on all 4 nodes saying >> >> FAILED! => {"msg": "The task includes an option with an undefined >> variable. The error was: 'scale_nfs_url' is undefined\n\nThe error >> appears to be in >> '/usr/lpp/mmfs/5.1.9.2/ansible-toolkit/ansible/upgrade_sample/playbook_repo_create.yml': >> line 455, column 11, but may\nbe elsewhere in the file depending on >> the exact syntax problem.\n\nThe offending line appears to be:\n\n\n >> - name: upgrade | configure nfs YUM repository\n ^ here\n"} >> >> Has anyone seen something like that before and/or knows where it could >> come from ? >> >> Thanks in advance >> >> Paul >> >> _______________________________________________ >> gpfsug-discuss mailing list >> gpfsug-discuss at gpfsug.org >> http://gpfsug.org/mailman/listinfo/gpfsug-discuss_gpfsug.org > > _______________________________________________ > gpfsug-discuss mailing list > gpfsug-discuss at gpfsug.org > http://gpfsug.org/mailman/listinfo/gpfsug-discuss_gpfsug.org > > > _______________________________________________ > gpfsug-discuss mailing list > gpfsug-discuss at gpfsug.org > http://gpfsug.org/mailman/listinfo/gpfsug-discuss_gpfsug.org From TROPPENS at de.ibm.com Thu Apr 18 17:01:09 2024 From: TROPPENS at de.ibm.com (Ulf Troppens) Date: Thu, 18 Apr 2024 16:01:09 +0000 Subject: [gpfsug-discuss] Upcoming User Meetings Message-ID: Hi Team, here is an overview of upcoming user meetings. 4/30 ? Midwest User Meeting 5/2 ? Midwest Hands-on Workshop 5/13 ? ISC User Meeting 6/11 ? UK New User Day 6/12+13 ? UK User Meeting Please see the link for details and registration: https://www.spectrumscaleug.org/eventslist/list/ I am looking forward to meeting many of you in person. Best, Ulf Ulf Troppens Product Manager - IBM Storage for Data and AI, Data-Intensive Workflows IBM Deutschland Research & Development GmbH Vorsitzender des Aufsichtsrats: Wolfgang Wendt / Gesch?ftsf?hrung: David Faller Sitz der Gesellschaft: B?blingen / Registergericht: Amtsgericht Stuttgart, HRB 243294 -------------- next part -------------- An HTML attachment was scrubbed... URL: