From daniel.kidger at hpe.com Fri Mar 11 17:34:14 2022 From: daniel.kidger at hpe.com (Kidger, Daniel) Date: Fri, 11 Mar 2022 17:34:14 +0000 Subject: [gpfsug-discuss] Running the Spectrum Scale on a Compute-only Cluster ? Message-ID: The Spectrum Scale GUI is widely run on GPFS clusters that include their own storage, but what about multi-cluster with separate Storage and Compute clusters? Will the GUI run on a compute only cluster? And if so does it simply omit components that are not present - such as Recovery Groups and NSD Servers ? Daniel Daniel Kidger HPC Storage Solutions Architect, EMEA daniel.kidger at hpe.com +44 (0)7818 522266 hpe.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From krajaram at geocomputing.net Fri Mar 11 18:16:06 2022 From: krajaram at geocomputing.net (Kumaran Rajaram) Date: Fri, 11 Mar 2022 18:16:06 +0000 Subject: [gpfsug-discuss] Running the Spectrum Scale on a Compute-only Cluster ? In-Reply-To: References: Message-ID: Hi, >> The Spectrum Scale GUI is widely run on GPFS clusters that include their own storage, but what about multi-cluster with separate Storage and Compute clusters? Yes, Spectrum Scale GUI works on GPFS Multi-Cluster setup with separate Storage and Compute clusters. The GUI works fine on a compute only cluster and storage only cluster. >> And if so does it simply omit components that are not present - such as Recovery Groups and NSD Servers ? Correct. The compute cluster GUI panels will still show remotely mounted file system and filesets + show their health status. Cheers, -Kums Kumaran Rajaram [cid:image001.png at 01D83549.C3601B90] From: gpfsug-discuss-bounces at spectrumscale.org On Behalf Of Kidger, Daniel Sent: Friday, March 11, 2022 12:34 PM To: gpfsug-discuss at spectrumscale.org Subject: [gpfsug-discuss] Running the Spectrum Scale on a Compute-only Cluster ? The Spectrum Scale GUI is widely run on GPFS clusters that include their own storage, but what about multi-cluster with separate Storage and Compute clusters? Will the GUI run on a compute only cluster? And if so does it simply omit components that are not present - such as Recovery Groups and NSD Servers ? Daniel Daniel Kidger HPC Storage Solutions Architect, EMEA daniel.kidger at hpe.com +44 (0)7818 522266 hpe.com -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: image001.png Type: image/png Size: 6469 bytes Desc: image001.png URL: From systems at gpfsug.org Mon Mar 14 00:54:41 2022 From: systems at gpfsug.org (systems at gpfsug.org) Date: Mon, 14 Mar 2022 00:54:41 +0000 Subject: [gpfsug-discuss] Website and mailing list migration Message-ID: <087d851ead9d65c79e016abc6478b8f0@gpfsug.org> Dear All, Over the weekend the Mailing List was migrated to a new system, whilst we expect that this migration has been completed; as with all migrations we do expect that some issues may require further attention. The main website should work with all previous domains, gpfsug.org spectrumscaleug.org and spectrumscale.org and the new mailman list page is located at: https://spectrumscale.org/mailman/listinfo/gpfsug-discuss_gpfsug.org Should you find any errors or bugs, please email systems at spectrumscale.org Kind Regards, Systems From shaof777 at gmail.com Mon Mar 14 01:08:37 2022 From: shaof777 at gmail.com (shao feng) Date: Mon, 14 Mar 2022 09:08:37 +0800 Subject: [gpfsug-discuss] permissions in clustered watch folder events Message-ID: Hello all, I am prototyping a solution which collects all the file information into a database by utilizing the clustered watch folder feature. I found the permissions field in the JSON from kafka topic is something like "permissions": "200100600". It seems the "600" part is the same as UNIX file permission, but what does the "200100" part stand for? Thank you! -------------- next part -------------- An HTML attachment was scrubbed... URL: From jmtick at us.ibm.com Tue Mar 15 14:12:32 2022 From: jmtick at us.ibm.com (Jacob M Tick) Date: Tue, 15 Mar 2022 14:12:32 +0000 Subject: [gpfsug-discuss] permissions in clustered watch folder events In-Reply-To: References: Message-ID: <735033AD-49A7-4CD3-97C3-A1184126D627@us.ibm.com> Hi, Here is some information on those bits. It's essentially special file bits... As such: https://www.gnu.org/software/coreutils/manual/html_node/Mode-Structure.html We have the permission bits + other bits for setuid setgid and sticky bits. Regards, Jake Tick Development Manager Spectrum Scale - Scalable Data Interfaces IBM Systems Group Email: jmtick at us.ibm.com IBM From: gpfsug-discuss on behalf of shao feng Reply-To: gpfsug main discussion list Date: Sunday, March 13, 2022 at 6:10 PM To: "gpfsug-discuss at gpfsug.org" Subject: [EXTERNAL] [gpfsug-discuss] permissions in clustered watch folder events Hello all, I am prototyping a solution which collects all the file information into a database by utilizing the clustered watch folder feature. I found the permissions field in the JSON from kafka topic is something like "permissions": "200100600". It seems the "600" part is the same as UNIX file permission, but what does the "200100" part stand for? Thank you! -------------- next part -------------- An HTML attachment was scrubbed... URL: From shaof777 at gmail.com Tue Mar 15 15:54:49 2022 From: shaof777 at gmail.com (shao feng) Date: Tue, 15 Mar 2022 23:54:49 +0800 Subject: [gpfsug-discuss] permissions in clustered watch folder events In-Reply-To: <735033AD-49A7-4CD3-97C3-A1184126D627@us.ibm.com> References: <735033AD-49A7-4CD3-97C3-A1184126D627@us.ibm.com> Message-ID: Thanks Jacob, but I still don't quite understand :-) for example, I have a file a with mode set to 7755 # ls -l a -rwsr-sr-t. 1 root root 2 Mar 15 23:46 a # stat a File: 'a' Size: 2 Blocks: 2 IO Block: 4194304 regular file Device: 34h/52d Inode: 48128 Links: 1 Access: (7755/-rwsr-sr-t) Uid: ( 0/ root) Gid: ( 0/ root) Context: unconfined_u:object_r:unlabeled_t:s0 Access: 2022-03-15 23:42:19.390236000 +0800 Modify: 2022-03-15 23:48:19.760428000 +0800 Change: 2022-03-15 23:48:19.760350205 +0800 Birth: - but in the event, the permission is "200107755", so it seems the first 7 is setuid/setgid/sticky bit(all set), how about "20010"? On Tue, Mar 15, 2022 at 10:12 PM Jacob M Tick wrote: > Hi, > > > > Here is some information on those bits. It's essentially special file > bits... As such: > https://www.gnu.org/software/coreutils/manual/html_node/Mode-Structure.html > > > > We have the permission bits + other bits for setuid setgid and sticky bits. > > > > Regards, > > > > *Jake Tick* > > Development Manager > > Spectrum Scale - Scalable Data Interfaces > > IBM Systems Group > > > > Email: jmtick at us.ibm.com > > > > IBM > > > > *From: *gpfsug-discuss on behalf of > shao feng > *Reply-To: *gpfsug main discussion list > *Date: *Sunday, March 13, 2022 at 6:10 PM > *To: *"gpfsug-discuss at gpfsug.org" > *Subject: *[EXTERNAL] [gpfsug-discuss] permissions in clustered watch > folder events > > > > Hello all, > > > > I am prototyping a solution which collects all the file information into a > database by utilizing the clustered watch folder feature. I found the > permissions field in the JSON from kafka topic is something > like "permissions": "200100600". It seems the "600" part is the same as > UNIX file permission, but what does the "200100" part stand for? > > > > Thank you! > -------------- next part -------------- An HTML attachment was scrubbed... URL: From juergen.hannappel at desy.de Mon Mar 21 12:37:39 2022 From: juergen.hannappel at desy.de (Hannappel, Juergen) Date: Mon, 21 Mar 2022 13:37:39 +0100 (CET) Subject: [gpfsug-discuss] Meaning of new fields in Watchfolder output Message-ID: <1471074893.22787165.1647866259731.JavaMail.zimbra@desy.de> Hi, for a test I read from a file with dd: dd if=someFile bs=64k of=/dev/null This will do 2 reads with 64k bytes, one read with 24053 and one final read with 0 bytes. I now check the WF json output, looking for the new ReadOffset and bytesRead fields I get: kafkacat -b my-broker -t test1-watch | while read mist; do echo $mist | python -m json.tool | grep -i read ; done "bytesRead": "0", "minReadOffset": "9223372036854775807", "maxReadOffset": "0", That is the open()... "bytesRead": "65536", "minReadOffset": "0", "maxReadOffset": "65535", That is the first read().... "bytesRead": "131072", "minReadOffset": "0", "maxReadOffset": "131071", WHo reads 2x64k bytes from the beginning? Is the the accumulated read data? "bytesRead": "155125", "minReadOffset": "0", "maxReadOffset": "155124", And again, now it looks as if in one event the entire file is read? The documentation (https://www.ibm.com/docs/en/spectrum-scale/5.1.3?topic=folder-json-attributes-in-clustered-watch) doesn't explain this.... -- Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 From mike-ward at utc.edu Mon Mar 28 00:20:31 2022 From: mike-ward at utc.edu (Ward, Michael) Date: Sun, 27 Mar 2022 23:20:31 +0000 Subject: [gpfsug-discuss] Seeking cNFS/GPFS advice. Add two IPs to cNFS pool Message-ID: Hello, I am relatively new to GPFS/cNFS. I have contacted reps and IBM and DDN (our vendor) w/no concrete answers. We have two servers linux server gpfs0 infiniband IP addr 10.0.136.84 linux server gpfs1 infiniband IP addr 10.0.136.85 gpfs0 server already has cnfs node name gpfs0-adm gpfs1 server already has cnfs node name gpfs1-adm We want to bind 10.0.136.86, 10.0.136.87 to these nodes to extend the cnfs pool. Below are the commands I think will work mmchnode --cnfs-interface= 10.0.136.86 -N gpfs0-adm mmchnode --cnfs-interface= 10.0.136.87 -N gpfs1-adm Below are some information about the current setup for Ethernet. [root at gpfs1 ~]# mmlscluster --cnfs GPFS cluster information ======================== GPFS cluster name: gpfs0-adm GPFS cluster id: 5815169472987570192 Cluster NFS global parameters ----------------------------- Shared root directory: /gpfs/gsfs1/.cnfs rpc.mountd port number: 597 nfsd threads: 256 Reboot on failure enabled: no CNFS monitor enabled: yes Node Daemon node name IP address CNFS state group CNFS IP address list ------------------------------------------------------------------------------------------- 1 gpfs0-adm 192.168.202.10 enabled 0 172.17.150.13 2 gpfs1-adm 192.168.202.11 enabled 0 172.17.150.14 [root at gpfs1 ~]# mmgetstate -N nsdnodes --cnfs Node number Node name GPFS state CNFS state ----------------------------------------------------- 1 gpfs0-adm active active 2 gpfs1-adm active active [root at gpfs1 ~]# ip addr show dev ib3 11: ib3: mtu 2044 qdisc mq state UP group default qlen 256 link/infiniband 20:00:19:0e:fe:80:00:00:00:00:00:00:24:8a:07:03:00:b1:bb:c9 brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff inet 10.0.136.85/24 brd 10.0.136.255 scope global ib3 valid_lft forever preferred_lft forever inet6 fe80::268a:703:b1:bbc9/64 scope link valid_lft forever preferred_lft forever [root at gpfs1 ~]# Michael Ward, Ed.D? HPC/HTC Administrator and Advanced Cyber Infrastructure Facilitator? 111B SimCenter? UT Chattanooga? 4234254764? From olaf.weiser at de.ibm.com Mon Mar 28 08:22:20 2022 From: olaf.weiser at de.ibm.com (Olaf Weiser) Date: Mon, 28 Mar 2022 07:22:20 +0000 Subject: [gpfsug-discuss] Seeking cNFS/GPFS advice. Add two IPs to cNFS pool In-Reply-To: References: Message-ID: Not sure, what you want to know... / missing Q ?! anyway.. please be aware, cnfs IP handling is done over aliasing.. so in case you have configured the IP directly on the interface, that won't work ________________________________ Von: gpfsug-discuss im Auftrag von Ward, Michael Gesendet: Montag, 28. M?rz 2022 01:20 An: gpfsug-discuss at gpfsug.org Betreff: [EXTERNAL] [gpfsug-discuss] Seeking cNFS/GPFS advice. Add two IPs to cNFS pool Hello, I am relatively new to GPFS/cNFS. I have contacted reps and IBM and DDN (our vendor) w/no concrete answers. We have two servers linux server gpfs0 infiniband IP addr 10.0.136.84 linux server gpfs1 infiniband IP addr 10.0.136.85 gpfs0 server already has cnfs node name gpfs0-adm gpfs1 server already has cnfs node name gpfs1-adm We want to bind 10.0.136.86, 10.0.136.87 to these nodes to extend the cnfs pool. Below are the commands I think will work mmchnode --cnfs-interface= 10.0.136.86 -N gpfs0-adm mmchnode --cnfs-interface= 10.0.136.87 -N gpfs1-adm Below are some information about the current setup for Ethernet. [root at gpfs1 ~]# mmlscluster --cnfs GPFS cluster information ======================== GPFS cluster name: gpfs0-adm GPFS cluster id: 5815169472987570192 Cluster NFS global parameters ----------------------------- Shared root directory: /gpfs/gsfs1/.cnfs rpc.mountd port number: 597 nfsd threads: 256 Reboot on failure enabled: no CNFS monitor enabled: yes Node Daemon node name IP address CNFS state group CNFS IP address list ------------------------------------------------------------------------------------------- 1 gpfs0-adm 192.168.202.10 enabled 0 172.17.150.13 2 gpfs1-adm 192.168.202.11 enabled 0 172.17.150.14 [root at gpfs1 ~]# mmgetstate -N nsdnodes --cnfs Node number Node name GPFS state CNFS state ----------------------------------------------------- 1 gpfs0-adm active active 2 gpfs1-adm active active [root at gpfs1 ~]# ip addr show dev ib3 11: ib3: mtu 2044 qdisc mq state UP group default qlen 256 link/infiniband 20:00:19:0e:fe:80:00:00:00:00:00:00:24:8a:07:03:00:b1:bb:c9 brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff inet 10.0.136.85/24 brd 10.0.136.255 scope global ib3 valid_lft forever preferred_lft forever inet6 fe80::268a:703:b1:bbc9/64 scope link valid_lft forever preferred_lft forever [root at gpfs1 ~]# Michael Ward, Ed.D HPC/HTC Administrator and Advanced Cyber Infrastructure Facilitator 111B SimCenter UT Chattanooga 4234254764 _______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at gpfsug.org http://gpfsug.org/mailman/listinfo/gpfsug-discuss_gpfsug.org N -------------- next part -------------- An HTML attachment was scrubbed... URL: From shaof777 at gmail.com Mon Mar 28 10:49:53 2022 From: shaof777 at gmail.com (shao feng) Date: Mon, 28 Mar 2022 17:49:53 +0800 Subject: [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule Message-ID: Hello, What is the default value of SIZE in EXTERNAL POOL in filesystem policy? The document did not mention that, but I found it is not infinity if not specified. Thank you! SIZE sum-numberIs an optional clause of the EXTERNAL POOL and EXTERNAL LIST rules. sum-number limits the total number of bytes in all of the files named in each list of files passed to your EXEC 'script'. If a single file is larger than sum-number, it is passed to your EXEC 'script' as the only entry in a ?singleton? file list. Specify sum-number as a numeric constant or a floating-point value. Note: The value of sum-number is in kilobytes. https://www.ibm.com/docs/en/spectrum-scale/5.1.2?topic=rules-policy-terms -------------- next part -------------- An HTML attachment was scrubbed... URL: From juergen.hannappel at desy.de Mon Mar 28 10:50:50 2022 From: juergen.hannappel at desy.de (Hannappel, Juergen) Date: Mon, 28 Mar 2022 11:50:50 +0200 (CEST) Subject: [gpfsug-discuss] immutable file in an immutable folder can be touched Message-ID: <489645367.26974531.1648461050348.JavaMail.zimbra@desy.de> Hi, I have an immutable file in an immutable folder: mmchattr -i yes mutabilityTest/file mmchattr -i yes mutabilityTest ls -la mutabilityTest total 18 drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. -rw-r--r-- 1 hannappj it 30 Mar 28 11:45 file mmlsattr -L mutabilityTest mutabilityTest/file | grep immu immutable: yes immutable: yes Now i do a touch: touch mutabilityTest/file no error, and the modification time is changed: ls -la mutabilityTest total 18 drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. -rw-r--r-- 1 hannappj it 30 Mar 28 11:46 file stat mutabilityTest/file File: ?mutabilityTest/file? Size: 30 Blocks: 2 IO Block: 4194304 regular file Device: 2eh/46d Inode: 112989 Links: 1 Access: (0644/-rw-r--r--) Uid: (28851/hannappj) Gid: ( 1000/ it) Access: 2022-03-28 11:46:28.454807982 +0200 Modify: 2022-03-28 11:46:28.454807982 +0200 Change: 2022-03-28 11:46:28.454807982 +0200 Shouldn't the immutability of the file include its change time? -- Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 From juergen.hannappel at desy.de Mon Mar 28 13:25:02 2022 From: juergen.hannappel at desy.de (Hannappel, Juergen) Date: Mon, 28 Mar 2022 14:25:02 +0200 (CEST) Subject: [gpfsug-discuss] immutable file in an immutable folder can be touched In-Reply-To: <489645367.26974531.1648461050348.JavaMail.zimbra@desy.de> References: <489645367.26974531.1648461050348.JavaMail.zimbra@desy.de> Message-ID: <1654236183.27138098.1648470302405.JavaMail.zimbra@desy.de> ... if I try a similar action e.g on ext4 where I can use the posix way with ioctl(fd, FS_IOC_GETFLAGS, &flags) flags |= FS_IMMUTABLE_FL; ioctl(fd, FS_IOC_SETFLAGS, &flags) the touch fails and the mtime remains unchanged.... ----- Original Message ----- > From: "Juergen Hannappel" > To: "gpfsug main discussion list" > Sent: Monday, 28 March, 2022 11:50:50 > Subject: [gpfsug-discuss] immutable file in an immutable folder can be touched > Hi, > I have an immutable file in an immutable folder: > > mmchattr -i yes mutabilityTest/file > mmchattr -i yes mutabilityTest > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:45 file > > mmlsattr -L mutabilityTest mutabilityTest/file | grep immu > immutable: yes > immutable: yes > > > Now i do a touch: > touch mutabilityTest/file > > no error, and the modification time is changed: > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:46 file > > stat mutabilityTest/file > File: ?mutabilityTest/file? > Size: 30 Blocks: 2 IO Block: 4194304 regular file > Device: 2eh/46d Inode: 112989 Links: 1 > Access: (0644/-rw-r--r--) Uid: (28851/hannappj) Gid: ( 1000/ it) > Access: 2022-03-28 11:46:28.454807982 +0200 > Modify: 2022-03-28 11:46:28.454807982 +0200 > Change: 2022-03-28 11:46:28.454807982 +0200 > > > Shouldn't the immutability of the file include its change time? > > > > -- > Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 > > _______________________________________________ > gpfsug-discuss mailing list > gpfsug-discuss at gpfsug.org > http://gpfsug.org/mailman/listinfo/gpfsug-discuss_gpfsug.org From p.ward at nhm.ac.uk Mon Mar 28 14:23:56 2022 From: p.ward at nhm.ac.uk (Paul Ward) Date: Mon, 28 Mar 2022 13:23:56 +0000 Subject: [gpfsug-discuss] immutable file in an immutable folder can be touched In-Reply-To: <1654236183.27138098.1648470302405.JavaMail.zimbra@desy.de> References: <489645367.26974531.1648461050348.JavaMail.zimbra@desy.de> <1654236183.27138098.1648470302405.JavaMail.zimbra@desy.de> Message-ID: Hi J?rgen, We noticed this behaviour when we were trying to test immutability on our newly installed solution. We tried using touch with a date in the past to test the expiry date. We noticed although touch changed the timestamp, it didn't change wherever the policy engine checked. We found a work around for our testing, so I think we accepted it as a 'feature'. I can't find a support ticket, so I am assuming we didn't report it. Kindest regards, Paul Paul Ward TS Infrastructure Architect Natural History Museum T: 02079426450 E: p.ward at nhm.ac.uk -----Original Message----- From: gpfsug-discuss On Behalf Of Hannappel, Juergen Sent: 28 March 2022 13:25 To: gpfsug-discuss Subject: Re: [gpfsug-discuss] immutable file in an immutable folder can be touched ... if I try a similar action e.g on ext4 where I can use the posix way with ioctl(fd, FS_IOC_GETFLAGS, &flags) flags |= FS_IMMUTABLE_FL; ioctl(fd, FS_IOC_SETFLAGS, &flags) the touch fails and the mtime remains unchanged.... ----- Original Message ----- > From: "Juergen Hannappel" > To: "gpfsug main discussion list" > Sent: Monday, 28 March, 2022 11:50:50 > Subject: [gpfsug-discuss] immutable file in an immutable folder can be > touched > Hi, > I have an immutable file in an immutable folder: > > mmchattr -i yes mutabilityTest/file > mmchattr -i yes mutabilityTest > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:45 file > > mmlsattr -L mutabilityTest mutabilityTest/file | grep immu > immutable: yes > immutable: yes > > > Now i do a touch: > touch mutabilityTest/file > > no error, and the modification time is changed: > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:46 file > > stat mutabilityTest/file > File: 'mutabilityTest/file' > Size: 30 Blocks: 2 IO Block: 4194304 regular file > Device: 2eh/46d Inode: 112989 Links: 1 > Access: (0644/-rw-r--r--) Uid: (28851/hannappj) Gid: ( 1000/ it) > Access: 2022-03-28 11:46:28.454807982 +0200 > Modify: 2022-03-28 11:46:28.454807982 +0200 > Change: 2022-03-28 11:46:28.454807982 +0200 > > > Shouldn't the immutability of the file include its change time? > > > > -- > Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 > > _______________________________________________ > gpfsug-discuss mailing list > gpfsug-discuss at gpfsug.org > https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fgpfsu > g.org%2Fmailman%2Flistinfo%2Fgpfsug-discuss_gpfsug.org&data=04%7C0 > 1%7Cp.ward%40nhm.ac.uk%7C2c7afbe81224404273cf08da10b63ad3%7C73a29c014e > 78437fa0d4c8553e1960c1%7C1%7C0%7C637840672748970653%7CUnknown%7CTWFpbG > Zsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0% > 3D%7C3000&sdata=I9bS8GSW5AeZbEg%2FQR2aCQd4KNd3lRmg2K1NJ3hQTk4%3D&a > mp;reserved=0 _______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at gpfsug.org https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fgpfsug.org%2Fmailman%2Flistinfo%2Fgpfsug-discuss_gpfsug.org&data=04%7C01%7Cp.ward%40nhm.ac.uk%7C2c7afbe81224404273cf08da10b63ad3%7C73a29c014e78437fa0d4c8553e1960c1%7C1%7C0%7C637840672749126883%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=O3t6BTddF3gL4DGlRAA9eweV8Vk%2BdwXj1We4GrGU%2BY8%3D&reserved=0 From shaof777 at gmail.com Tue Mar 29 06:41:23 2022 From: shaof777 at gmail.com (shao feng) Date: Tue, 29 Mar 2022 13:41:23 +0800 Subject: [gpfsug-discuss] notification when Spectrum Archival EE finish migrating/recall for a file Message-ID: Hello, Not sure if this is the right place to ask about Spectrum Archival EE. In a GPFS+LTFS EE configuration, is there any mechanism to get notification from Spectrum Archival EE when it finishes a migrating/recall for a file, especially a transparent recall? Thank you! -------------- next part -------------- An HTML attachment was scrubbed... URL: From scale at us.ibm.com Tue Mar 29 13:57:26 2022 From: scale at us.ibm.com (IBM Spectrum Scale) Date: Tue, 29 Mar 2022 18:27:26 +0530 Subject: [gpfsug-discuss] immutable file in an immutable folder can be touched In-Reply-To: References: <489645367.26974531.1648461050348.JavaMail.zimbra@desy.de> <1654236183.27138098.1648470302405.JavaMail.zimbra@desy.de> Message-ID: >From design docs can see that Spectrum scale allows changing of timestamps for immutable files. + Haizhu to confirm this as well. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479. If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. From: "Paul Ward" To: "gpfsug main discussion list" Date: 28-03-2022 06.56 PM Subject: [EXTERNAL] Re: [gpfsug-discuss] immutable file in an immutable folder can be touched Sent by: "gpfsug-discuss" Hi J?rgen, We noticed this behaviour when we were trying to test immutability on our newly installed solution. We tried using touch with a date in the past to test the expiry date. We noticed although touch changed the timestamp, it didn't change wherever the policy engine checked. We found a work around for our testing, so I think we accepted it as a 'feature'. I can't find a support ticket, so I am assuming we didn't report it. Kindest regards, Paul Paul Ward TS Infrastructure Architect Natural History Museum T: 02079426450 E: p.ward at nhm.ac.uk -----Original Message----- From: gpfsug-discuss On Behalf Of Hannappel, Juergen Sent: 28 March 2022 13:25 To: gpfsug-discuss Subject: Re: [gpfsug-discuss] immutable file in an immutable folder can be touched ... if I try a similar action e.g on ext4 where I can use the posix way with ioctl(fd, FS_IOC_GETFLAGS, &flags) flags |= FS_IMMUTABLE_FL; ioctl(fd, FS_IOC_SETFLAGS, &flags) the touch fails and the mtime remains unchanged.... ----- Original Message ----- > From: "Juergen Hannappel" > To: "gpfsug main discussion list" > Sent: Monday, 28 March, 2022 11:50:50 > Subject: [gpfsug-discuss] immutable file in an immutable folder can be > touched > Hi, > I have an immutable file in an immutable folder: > > mmchattr -i yes mutabilityTest/file > mmchattr -i yes mutabilityTest > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:45 file > > mmlsattr -L mutabilityTest mutabilityTest/file | grep immu > immutable: yes > immutable: yes > > > Now i do a touch: > touch mutabilityTest/file > > no error, and the modification time is changed: > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:46 file > > stat mutabilityTest/file > File: 'mutabilityTest/file' > Size: 30 Blocks: 2 IO Block: 4194304 regular file > Device: 2eh/46d Inode: 112989 Links: 1 > Access: (0644/-rw-r--r--) Uid: (28851/hannappj) Gid: ( 1000/ it) > Access: 2022-03-28 11:46:28.454807982 +0200 > Modify: 2022-03-28 11:46:28.454807982 +0200 > Change: 2022-03-28 11:46:28.454807982 +0200 > > > Shouldn't the immutability of the file include its change time? > > > > -- > Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 > > _______________________________________________ > gpfsug-discuss mailing list > gpfsug-discuss at gpfsug.org > https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fgpfsu > g.org%2Fmailman%2Flistinfo%2Fgpfsug-discuss_gpfsug.org&data=04%7C0 > 1%7Cp.ward%40nhm.ac.uk%7C2c7afbe81224404273cf08da10b63ad3%7C73a29c014e > 78437fa0d4c8553e1960c1%7C1%7C0%7C637840672748970653%7CUnknown%7CTWFpbG > Zsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0% > 3D%7C3000&sdata=I9bS8GSW5AeZbEg%2FQR2aCQd4KNd3lRmg2K1NJ3hQTk4%3D&a > mp;reserved=0 _______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at gpfsug.org https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fgpfsug.org%2Fmailman%2Flistinfo%2Fgpfsug-discuss_gpfsug.org&data=04%7C01%7Cp.ward%40nhm.ac.uk%7C2c7afbe81224404273cf08da10b63ad3%7C73a29c014e78437fa0d4c8553e1960c1%7C1%7C0%7C637840672749126883%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=O3t6BTddF3gL4DGlRAA9eweV8Vk%2BdwXj1We4GrGU%2BY8%3D&reserved=0 _______________________________________________ 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: From haizhu at us.ibm.com Tue Mar 29 14:49:54 2022 From: haizhu at us.ibm.com (Haizhu Liu) Date: Tue, 29 Mar 2022 13:49:54 +0000 Subject: [gpfsug-discuss] immutable file in an immutable folder can be touched In-Reply-To: References: <489645367.26974531.1648461050348.JavaMail.zimbra@desy.de> <1654236183.27138098.1648470302405.JavaMail.zimbra@desy.de> Message-ID: <5DF860B0-159A-4F9B-88DA-8DC171B45E4B@us.ibm.com> Yes, that?s correct. Atime, mtime and ctime can be changed, in addition, if the file is under an immutable fileset, mtime and ctime can be changed, atime is overloaded with expiration time. From: on behalf of "scale at us.ibm.com" Date: Tuesday, March 29, 2022 at 8:57 AM To: gpfsug main discussion list Cc: gpfsug-discuss , "juergen.hannappel at desy.de" , "p.ward at nhm.ac.uk" , Haizhu Liu Subject: Re: [EXTERNAL] Re: [gpfsug-discuss] immutable file in an immutable folder can be touched From design docs can see that Spectrum scale allows changing of timestamps for immutable files. + Haizhu to confirm this as well. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479. If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. [Inactive hide details for "Paul Ward" ---28-03-2022 06.56.04 PM---Hi J?rgen, We noticed this behaviour when we were trying to t]"Paul Ward" ---28-03-2022 06.56.04 PM---Hi J?rgen, We noticed this behaviour when we were trying to test immutability on our newly installed From: "Paul Ward" To: "gpfsug main discussion list" Date: 28-03-2022 06.56 PM Subject: [EXTERNAL] Re: [gpfsug-discuss] immutable file in an immutable folder can be touched Sent by: "gpfsug-discuss" ________________________________ Hi J?rgen, We noticed this behaviour when we were trying to test immutability on our newly installed solution. We tried using touch with a date in the past to test the expiry date. We noticed although touch changed the timestamp, it didn't change wherever the policy engine checked. We found a work around for our testing, so I think we accepted it as a 'feature'. I can't find a support ticket, so I am assuming we didn't report it. Kindest regards, Paul Paul Ward TS Infrastructure Architect Natural History Museum T: 02079426450 E: p.ward at nhm.ac.uk -----Original Message----- From: gpfsug-discuss On Behalf Of Hannappel, Juergen Sent: 28 March 2022 13:25 To: gpfsug-discuss Subject: Re: [gpfsug-discuss] immutable file in an immutable folder can be touched ... if I try a similar action e.g on ext4 where I can use the posix way with ioctl(fd, FS_IOC_GETFLAGS, &flags) flags |= FS_IMMUTABLE_FL; ioctl(fd, FS_IOC_SETFLAGS, &flags) the touch fails and the mtime remains unchanged.... ----- Original Message ----- > From: "Juergen Hannappel" > To: "gpfsug main discussion list" > Sent: Monday, 28 March, 2022 11:50:50 > Subject: [gpfsug-discuss] immutable file in an immutable folder can be > touched > Hi, > I have an immutable file in an immutable folder: > > mmchattr -i yes mutabilityTest/file > mmchattr -i yes mutabilityTest > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:45 file > > mmlsattr -L mutabilityTest mutabilityTest/file | grep immu > immutable: yes > immutable: yes > > > Now i do a touch: > touch mutabilityTest/file > > no error, and the modification time is changed: > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:46 file > > stat mutabilityTest/file > File: 'mutabilityTest/file' > Size: 30 Blocks: 2 IO Block: 4194304 regular file > Device: 2eh/46d Inode: 112989 Links: 1 > Access: (0644/-rw-r--r--) Uid: (28851/hannappj) Gid: ( 1000/ it) > Access: 2022-03-28 11:46:28.454807982 +0200 > Modify: 2022-03-28 11:46:28.454807982 +0200 > Change: 2022-03-28 11:46:28.454807982 +0200 > > > Shouldn't the immutability of the file include its change time? > > > > -- > Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 > > _______________________________________________ > gpfsug-discuss mailing list > gpfsug-discuss at gpfsug.org > https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fgpfsu > g.org%2Fmailman%2Flistinfo%2Fgpfsug-discuss_gpfsug.org&data=04%7C0 > 1%7Cp.ward%40nhm.ac.uk%7C2c7afbe81224404273cf08da10b63ad3%7C73a29c014e > 78437fa0d4c8553e1960c1%7C1%7C0%7C637840672748970653%7CUnknown%7CTWFpbG > Zsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0% > 3D%7C3000&sdata=I9bS8GSW5AeZbEg%2FQR2aCQd4KNd3lRmg2K1NJ3hQTk4%3D&a > mp;reserved=0 _______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at gpfsug.org https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fgpfsug.org%2Fmailman%2Flistinfo%2Fgpfsug-discuss_gpfsug.org&data=04%7C01%7Cp.ward%40nhm.ac.uk%7C2c7afbe81224404273cf08da10b63ad3%7C73a29c014e78437fa0d4c8553e1960c1%7C1%7C0%7C637840672749126883%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=O3t6BTddF3gL4DGlRAA9eweV8Vk%2BdwXj1We4GrGU%2BY8%3D&reserved=0 _______________________________________________ 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: image001.gif Type: image/gif Size: 106 bytes Desc: image001.gif URL: From scale at us.ibm.com Wed Mar 30 14:46:47 2022 From: scale at us.ibm.com (IBM Spectrum Scale) Date: Wed, 30 Mar 2022 19:16:47 +0530 Subject: [gpfsug-discuss] Meaning of new fields in Watchfolder output In-Reply-To: <1471074893.22787165.1647866259731.JavaMail.zimbra@desy.de> References: <1471074893.22787165.1647866259731.JavaMail.zimbra@desy.de> Message-ID: Hi Jake, Can you please look at the below WF related query. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479. If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. From: "Hannappel, Juergen" To: "gpfsug main discussion list" Date: 21-03-2022 06.09 PM Subject: [EXTERNAL] [gpfsug-discuss] Meaning of new fields in Watchfolder output Sent by: "gpfsug-discuss" Hi, for a test I read from a file with dd: dd if=someFile bs=64k of=/dev/null This will do 2 reads with 64k bytes, one read with 24053 and one final read with 0 bytes. I now check the WF json output, looking for the new ReadOffset and bytesRead fields I get: kafkacat -b my-broker -t test1-watch | while read mist; do echo $mist | python -m json.tool | grep -i read ; done "bytesRead": "0", "minReadOffset": "9223372036854775807", "maxReadOffset": "0", That is the open()... "bytesRead": "65536", "minReadOffset": "0", "maxReadOffset": "65535", That is the first read().... "bytesRead": "131072", "minReadOffset": "0", "maxReadOffset": "131071", WHo reads 2x64k bytes from the beginning? Is the the accumulated read data? "bytesRead": "155125", "minReadOffset": "0", "maxReadOffset": "155124", And again, now it looks as if in one event the entire file is read? The documentation ( https://www.ibm.com/docs/en/spectrum-scale/5.1.3?topic=folder-json-attributes-in-clustered-watch ) doesn't explain this.... -- Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 _______________________________________________ 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: From scale at us.ibm.com Wed Mar 30 14:51:36 2022 From: scale at us.ibm.com (IBM Spectrum Scale) Date: Wed, 30 Mar 2022 19:21:36 +0530 Subject: [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule In-Reply-To: References: Message-ID: Hi Diane, Can you please look at the below policy related query. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479. If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. From: "shao feng" To: "gpfsug main discussion list" Date: 28-03-2022 03.21 PM Subject: [EXTERNAL] [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule Sent by: "gpfsug-discuss" Hello, What is the default value of SIZE in EXTERNAL POOL in filesystem policy? The document did not mention that, but I found it is not infinity if not specified. Thank you! SIZE?sum-number Is an optional clause of the?EXTERNAL POOL?and?EXTERNAL LIST?rules. sum-number?limits the total number of bytes in all of the files named in each list of files passed to your EXEC 'script'. If a single file is larger than?sum-number, it is passed to your EXEC 'script' as the only entry in a??singleton??file list. Specify?sum-number?as a numeric constant or a floating-point value. Note:?The value of?sum-number?is in kilobytes. https://www.ibm.com/docs/en/spectrum-scale/5.1.2?topic=rules-policy-terms _______________________________________________ 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: From scale at us.ibm.com Wed Mar 30 15:02:20 2022 From: scale at us.ibm.com (IBM Spectrum Scale) Date: Wed, 30 Mar 2022 19:32:20 +0530 Subject: [gpfsug-discuss] notification when Spectrum Archival EE finish migrating/recall for a file In-Reply-To: References: Message-ID: I think this can be answered by the IBM Spectrum Archive team and should go to a mailing list or discussion channel where they are involved. @Lyle: Do you know anyone who can answer this from Scale side. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479. If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. From: "shao feng" To: "gpfsug main discussion list" Date: 29-03-2022 11.13 AM Subject: [EXTERNAL] [gpfsug-discuss] notification when Spectrum Archival EE finish migrating/recall for a file Sent by: "gpfsug-discuss" Hello, Not sure if this is the right place to ask about Spectrum Archival EE. In a GPFS+LTFS EE configuration, is there any mechanism to get notification from Spectrum Archival EE when it finishes a migrating/recall for a file, especially a transparent recall? Thank you!_______________________________________________ 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: From lgayne at us.ibm.com Wed Mar 30 15:10:51 2022 From: lgayne at us.ibm.com (Lyle Gayne) Date: Wed, 30 Mar 2022 14:10:51 +0000 Subject: [gpfsug-discuss] notification when Spectrum Archival EE finish migrating/recall for a file In-Reply-To: References: Message-ID: I guess this should start with Mark Hill (and Khanh), from Spectrum Archive team. Lyle ________________________________ From: gpfsug-discuss on behalf of scale at us.ibm.com Sent: Wednesday, March 30, 2022 10:02 AM To: gpfsug main discussion list Cc: gpfsug-discuss Subject: [EXTERNAL] Re: [gpfsug-discuss] notification when Spectrum Archival EE finish migrating/recall for a file I think this can be answered by the IBM Spectrum Archive team and should go to a mailing list or discussion channel where they are involved. @Lyle: Do you know anyone who can answer this from Scale side. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479. If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. [Inactive hide details for "shao feng" ---29-03-2022 11.13.11 AM---Hello, Not sure if this is the right place to ask about Spect]"shao feng" ---29-03-2022 11.13.11 AM---Hello, Not sure if this is the right place to ask about Spectrum Archival EE. From: "shao feng" To: "gpfsug main discussion list" Date: 29-03-2022 11.13 AM Subject: [EXTERNAL] [gpfsug-discuss] notification when Spectrum Archival EE finish migrating/recall for a file Sent by: "gpfsug-discuss" ________________________________ Hello, Not sure if this is the right place to ask about Spectrum Archival EE. In a GPFS+LTFS EE configuration, is there any mechanism to get notification from Spectrum Archival EE when it finishes a migrating/recall for a file, especially a transparent recall? Thank you!_______________________________________________ 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: graycol.gif URL: From scale at us.ibm.com Wed Mar 30 23:41:33 2022 From: scale at us.ibm.com (IBM Spectrum Scale) Date: Wed, 30 Mar 2022 18:41:33 -0400 Subject: [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule In-Reply-To: References: Message-ID: Hi shao feng, It is controlled by -B option. -B MaxFiles Specifies how many files are passed for each invocation of the EXEC script. The default value is 100. If the number of files exceeds the value specified for MaxFiles, mmapplypolicy invokes the external program multiple times. For more information about file list records, refer to the IBM Spectrum Scale: Administration Guide. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. From: IBM Spectrum Scale/Poughkeepsie/IBM at IBMUS To: "gpfsug main discussion list" , Diane Chung/Poughkeepsie/IBM at IBMMail Cc: "gpfsug-discuss" Date: 03/30/2022 09:53 AM Subject: [EXTERNAL] Re: [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule Sent by: "gpfsug-discuss" Hi Diane, Can you please look at the below policy related query. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479 . If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. Inactive hide details for "shao feng" ---28-03-2022 03.21.39 PM---Hello, What is the default value of SIZE in EXTERNAL POOL in "shao feng" ---28-03-2022 03.21.39 PM---Hello, What is the default value of SIZE in EXTERNAL POOL in filesystem policy? From: "shao feng" To: "gpfsug main discussion list" Date: 28-03-2022 03.21 PM Subject: [EXTERNAL] [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule Sent by: "gpfsug-discuss" Hello, What is the default value of SIZE in EXTERNAL POOL in filesystem policy? The document did not mention that, but I found it is not infinity if not specified. Thank you! SIZE?sum-number Is an optional clause of the?EXTERNAL POOL?and?EXTERNAL LIST?rules. sum-number?limits the total number of bytes in all of the files named in each list of files passed to your EXEC 'script'. If a single file is larger than?sum-number, it is passed to your EXEC 'script' as the only entry in a ?singleton??file list. Specify?sum-number?as a numeric constant or a floating-point value. Note:?The value of?sum-number?is in kilobytes. https://www.ibm.com/docs/en/spectrum-scale/5.1.2?topic=rules-policy-terms _______________________________________________ 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 -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: From anacreo at gmail.com Thu Mar 31 00:39:24 2022 From: anacreo at gmail.com (Alec) Date: Wed, 30 Mar 2022 16:39:24 -0700 Subject: [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule In-Reply-To: References: Message-ID: I'd like to offer a dissenting opinion... I believe this is a way to limit the number of actual bytes that any execution must work on.... As in only send 500gb worth of files to each invocation. Whereas the -B is the actual number of files to be passed to each invocation. I would think that size has no default limit as I've had a single invocation stuck with 30TB of data in its 100 file grouping, lol. I however use a different mechanism to divy up my files because I need to worry about my backup streams getting choked up, and I want to take a cross section of each directory on different nights... I call mmapplypolicy with -M shares=, so let's say I increase my number by 1 every day, starting at 0, over the course of a week... In my policy I have this line: WHERE MOD(INODE,6)<=shares So then I work on 1/7th of the files in my file system and cumulatively pick up any INODES until I've hit all of the files... I could pick just the matching segment by saying = instead of <=. This is happening at the file selection phase, so the application of -B is after this selection, as my files are quite huge, I tend to use -B 1. Alec On Wed, Mar 30, 2022 at 3:44 PM IBM Spectrum Scale wrote: > Hi shao feng, > > It is controlled by -B option. > > *-B* *MaxFiles* > Specifies how many files are passed for each invocation > of the EXEC script. The default value is 100. > > If the number of files exceeds the value specified for > MaxFiles, *mmapplypolicy* invokes the external > program multiple times. > > For more information about file list records, refer to > the IBM Spectrum Scale: Administration Guide. > > Regards, The Spectrum Scale (GPFS) team > > > ------------------------------------------------------------------------------------------------------------------ > If your query concerns a potential software error in Spectrum Scale (GPFS) > and you have an IBM software maintenance contract please contact > 1-800-237-5511 in the United States or your local IBM Service Center in > other countries. > > [image: Inactive hide details for IBM Spectrum Scale---03/30/2022 09:53:51 > AM---Hi Diane, Can you please look at the below policy relat]IBM Spectrum > Scale---03/30/2022 09:53:51 AM---Hi Diane, Can you please look at the below > policy related query. > > From: IBM Spectrum Scale/Poughkeepsie/IBM at IBMUS > To: "gpfsug main discussion list" , Diane > Chung/Poughkeepsie/IBM at IBMMail > Cc: "gpfsug-discuss" > Date: 03/30/2022 09:53 AM > Subject: [EXTERNAL] Re: [gpfsug-discuss] default value of SIZE in > EXTERNAL POOL and EXTERNAL LIST rule > Sent by: "gpfsug-discuss" > ------------------------------ > > > > Hi Diane, > > Can you please look at the below policy related query. > > Regards, The Spectrum Scale (GPFS) team > > > ------------------------------------------------------------------------------------------------------------------ > If you feel that your question can benefit other users of Spectrum Scale > (GPFS), then please post it to the public IBM developerWroks Forum at > *https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479* > . > > > If your query concerns a potential software error in Spectrum Scale (GPFS) > and you have an IBM software maintenance contract please contact > 1-800-237-5511 in the United States or your local IBM Service Center in > other countries. > > The forum is informally monitored as time permits and should not be used > for priority messages to the Spectrum Scale (GPFS) team. > > [image: Inactive hide details for "shao feng" ---28-03-2022 03.21.39 > PM---Hello, What is the default value of SIZE in EXTERNAL POOL in]"shao > feng" ---28-03-2022 03.21.39 PM---Hello, What is the default value of SIZE > in EXTERNAL POOL in filesystem policy? > > From: "shao feng" > To: "gpfsug main discussion list" > Date: 28-03-2022 03.21 PM > Subject: [EXTERNAL] [gpfsug-discuss] default value of SIZE in EXTERNAL > POOL and EXTERNAL LIST rule > Sent by: "gpfsug-discuss" > ------------------------------ > > > > Hello, > > What is the default value of SIZE in EXTERNAL POOL in filesystem policy? > > The document did not mention that, but I found it is not infinity if not > specified. > > Thank you! > > *SIZE **sum-number* > Is an optional clause of the *EXTERNAL POOL* and *EXTERNAL LIST* rules. > *sum-number* limits the total number of bytes in all of the files named > in each list of files passed to your EXEC 'script'. If a single file is > larger than *sum-number*, it is passed to your EXEC 'script' as the only > entry in a ?singleton? file list. > > Specify *sum-number* as a numeric constant or a floating-point value. > > *Note:* The value of *sum-number* is in kilobytes. > *https://www.ibm.com/docs/en/spectrum-scale/5.1.2?topic=rules-policy-terms* > > _______________________________________________ > 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 > -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: From shaof777 at gmail.com Thu Mar 31 08:53:07 2022 From: shaof777 at gmail.com (shao feng) Date: Thu, 31 Mar 2022 15:53:07 +0800 Subject: [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule In-Reply-To: References: Message-ID: Thanks Alec! On Thu, Mar 31, 2022 at 7:41 AM Alec wrote: > I'd like to offer a dissenting opinion... I believe this is a way to > limit the number of actual bytes that any execution must work on.... As in > only send 500gb worth of files to each invocation. Whereas the -B is the > actual number of files to be passed to each invocation. I would think that > size has no default limit as I've had a single invocation stuck with 30TB > of data in its 100 file grouping, lol. > > I however use a different mechanism to divy up my files because I need to > worry about my backup streams getting choked up, and I want to take a cross > section of each directory on different nights... > > I call mmapplypolicy with -M shares=, so let's say > I increase my number by 1 every day, starting at 0, over the course of a > week... > > In my policy I have this line: > WHERE MOD(INODE,6)<=shares > > So then I work on 1/7th of the files in my file system and cumulatively > pick up any INODES until I've hit all of the files... I could pick just the > matching segment by saying = instead of <=. > > This is happening at the file selection phase, so the application of -B is > after this selection, as my files are quite huge, I tend to use -B 1. > > Alec > > On Wed, Mar 30, 2022 at 3:44 PM IBM Spectrum Scale > wrote: > >> Hi shao feng, >> >> It is controlled by -B option. >> >> *-B* *MaxFiles* >> Specifies how many files are passed for each invocation >> of the EXEC script. The default value is 100. >> >> If the number of files exceeds the value specified for >> MaxFiles, *mmapplypolicy* invokes the external >> program multiple times. >> >> For more information about file list records, refer to >> the IBM Spectrum Scale: Administration Guide. >> >> Regards, The Spectrum Scale (GPFS) team >> >> >> ------------------------------------------------------------------------------------------------------------------ >> If your query concerns a potential software error in Spectrum Scale >> (GPFS) and you have an IBM software maintenance contract please contact >> 1-800-237-5511 in the United States or your local IBM Service Center in >> other countries. >> >> [image: Inactive hide details for IBM Spectrum Scale---03/30/2022 >> 09:53:51 AM---Hi Diane, Can you please look at the below policy relat]IBM >> Spectrum Scale---03/30/2022 09:53:51 AM---Hi Diane, Can you please look at >> the below policy related query. >> >> From: IBM Spectrum Scale/Poughkeepsie/IBM at IBMUS >> To: "gpfsug main discussion list" , Diane >> Chung/Poughkeepsie/IBM at IBMMail >> Cc: "gpfsug-discuss" >> Date: 03/30/2022 09:53 AM >> Subject: [EXTERNAL] Re: [gpfsug-discuss] default value of SIZE in >> EXTERNAL POOL and EXTERNAL LIST rule >> Sent by: "gpfsug-discuss" >> ------------------------------ >> >> >> >> Hi Diane, >> >> Can you please look at the below policy related query. >> >> Regards, The Spectrum Scale (GPFS) team >> >> >> ------------------------------------------------------------------------------------------------------------------ >> If you feel that your question can benefit other users of Spectrum Scale >> (GPFS), then please post it to the public IBM developerWroks Forum at >> *https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479* >> . >> >> >> If your query concerns a potential software error in Spectrum Scale >> (GPFS) and you have an IBM software maintenance contract please contact >> 1-800-237-5511 in the United States or your local IBM Service Center in >> other countries. >> >> The forum is informally monitored as time permits and should not be used >> for priority messages to the Spectrum Scale (GPFS) team. >> >> [image: Inactive hide details for "shao feng" ---28-03-2022 03.21.39 >> PM---Hello, What is the default value of SIZE in EXTERNAL POOL in]"shao >> feng" ---28-03-2022 03.21.39 PM---Hello, What is the default value of SIZE >> in EXTERNAL POOL in filesystem policy? >> >> From: "shao feng" >> To: "gpfsug main discussion list" >> Date: 28-03-2022 03.21 PM >> Subject: [EXTERNAL] [gpfsug-discuss] default value of SIZE in EXTERNAL >> POOL and EXTERNAL LIST rule >> Sent by: "gpfsug-discuss" >> ------------------------------ >> >> >> >> Hello, >> >> What is the default value of SIZE in EXTERNAL POOL in filesystem policy? >> >> The document did not mention that, but I found it is not infinity if not >> specified. >> >> Thank you! >> >> *SIZE **sum-number* >> Is an optional clause of the *EXTERNAL POOL* and *EXTERNAL LIST* rules. >> *sum-number* limits the total number of bytes in all of the files named >> in each list of files passed to your EXEC 'script'. If a single file is >> larger than *sum-number*, it is passed to your EXEC 'script' as the only >> entry in a ?singleton? file list. >> >> Specify *sum-number* as a numeric constant or a floating-point value. >> >> *Note:* The value of *sum-number* is in kilobytes. >> *https://www.ibm.com/docs/en/spectrum-scale/5.1.2?topic=rules-policy-terms* >> >> _______________________________________________ >> 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 >> > _______________________________________________ > 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: From daniel.kidger at hpe.com Fri Mar 11 17:34:14 2022 From: daniel.kidger at hpe.com (Kidger, Daniel) Date: Fri, 11 Mar 2022 17:34:14 +0000 Subject: [gpfsug-discuss] Running the Spectrum Scale on a Compute-only Cluster ? Message-ID: The Spectrum Scale GUI is widely run on GPFS clusters that include their own storage, but what about multi-cluster with separate Storage and Compute clusters? Will the GUI run on a compute only cluster? And if so does it simply omit components that are not present - such as Recovery Groups and NSD Servers ? Daniel Daniel Kidger HPC Storage Solutions Architect, EMEA daniel.kidger at hpe.com +44 (0)7818 522266 hpe.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From krajaram at geocomputing.net Fri Mar 11 18:16:06 2022 From: krajaram at geocomputing.net (Kumaran Rajaram) Date: Fri, 11 Mar 2022 18:16:06 +0000 Subject: [gpfsug-discuss] Running the Spectrum Scale on a Compute-only Cluster ? In-Reply-To: References: Message-ID: Hi, >> The Spectrum Scale GUI is widely run on GPFS clusters that include their own storage, but what about multi-cluster with separate Storage and Compute clusters? Yes, Spectrum Scale GUI works on GPFS Multi-Cluster setup with separate Storage and Compute clusters. The GUI works fine on a compute only cluster and storage only cluster. >> And if so does it simply omit components that are not present - such as Recovery Groups and NSD Servers ? Correct. The compute cluster GUI panels will still show remotely mounted file system and filesets + show their health status. Cheers, -Kums Kumaran Rajaram [cid:image001.png at 01D83549.C3601B90] From: gpfsug-discuss-bounces at spectrumscale.org On Behalf Of Kidger, Daniel Sent: Friday, March 11, 2022 12:34 PM To: gpfsug-discuss at spectrumscale.org Subject: [gpfsug-discuss] Running the Spectrum Scale on a Compute-only Cluster ? The Spectrum Scale GUI is widely run on GPFS clusters that include their own storage, but what about multi-cluster with separate Storage and Compute clusters? Will the GUI run on a compute only cluster? And if so does it simply omit components that are not present - such as Recovery Groups and NSD Servers ? Daniel Daniel Kidger HPC Storage Solutions Architect, EMEA daniel.kidger at hpe.com +44 (0)7818 522266 hpe.com -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: image001.png Type: image/png Size: 6469 bytes Desc: image001.png URL: From systems at gpfsug.org Mon Mar 14 00:54:41 2022 From: systems at gpfsug.org (systems at gpfsug.org) Date: Mon, 14 Mar 2022 00:54:41 +0000 Subject: [gpfsug-discuss] Website and mailing list migration Message-ID: <087d851ead9d65c79e016abc6478b8f0@gpfsug.org> Dear All, Over the weekend the Mailing List was migrated to a new system, whilst we expect that this migration has been completed; as with all migrations we do expect that some issues may require further attention. The main website should work with all previous domains, gpfsug.org spectrumscaleug.org and spectrumscale.org and the new mailman list page is located at: https://spectrumscale.org/mailman/listinfo/gpfsug-discuss_gpfsug.org Should you find any errors or bugs, please email systems at spectrumscale.org Kind Regards, Systems From shaof777 at gmail.com Mon Mar 14 01:08:37 2022 From: shaof777 at gmail.com (shao feng) Date: Mon, 14 Mar 2022 09:08:37 +0800 Subject: [gpfsug-discuss] permissions in clustered watch folder events Message-ID: Hello all, I am prototyping a solution which collects all the file information into a database by utilizing the clustered watch folder feature. I found the permissions field in the JSON from kafka topic is something like "permissions": "200100600". It seems the "600" part is the same as UNIX file permission, but what does the "200100" part stand for? Thank you! -------------- next part -------------- An HTML attachment was scrubbed... URL: From jmtick at us.ibm.com Tue Mar 15 14:12:32 2022 From: jmtick at us.ibm.com (Jacob M Tick) Date: Tue, 15 Mar 2022 14:12:32 +0000 Subject: [gpfsug-discuss] permissions in clustered watch folder events In-Reply-To: References: Message-ID: <735033AD-49A7-4CD3-97C3-A1184126D627@us.ibm.com> Hi, Here is some information on those bits. It's essentially special file bits... As such: https://www.gnu.org/software/coreutils/manual/html_node/Mode-Structure.html We have the permission bits + other bits for setuid setgid and sticky bits. Regards, Jake Tick Development Manager Spectrum Scale - Scalable Data Interfaces IBM Systems Group Email: jmtick at us.ibm.com IBM From: gpfsug-discuss on behalf of shao feng Reply-To: gpfsug main discussion list Date: Sunday, March 13, 2022 at 6:10 PM To: "gpfsug-discuss at gpfsug.org" Subject: [EXTERNAL] [gpfsug-discuss] permissions in clustered watch folder events Hello all, I am prototyping a solution which collects all the file information into a database by utilizing the clustered watch folder feature. I found the permissions field in the JSON from kafka topic is something like "permissions": "200100600". It seems the "600" part is the same as UNIX file permission, but what does the "200100" part stand for? Thank you! -------------- next part -------------- An HTML attachment was scrubbed... URL: From shaof777 at gmail.com Tue Mar 15 15:54:49 2022 From: shaof777 at gmail.com (shao feng) Date: Tue, 15 Mar 2022 23:54:49 +0800 Subject: [gpfsug-discuss] permissions in clustered watch folder events In-Reply-To: <735033AD-49A7-4CD3-97C3-A1184126D627@us.ibm.com> References: <735033AD-49A7-4CD3-97C3-A1184126D627@us.ibm.com> Message-ID: Thanks Jacob, but I still don't quite understand :-) for example, I have a file a with mode set to 7755 # ls -l a -rwsr-sr-t. 1 root root 2 Mar 15 23:46 a # stat a File: 'a' Size: 2 Blocks: 2 IO Block: 4194304 regular file Device: 34h/52d Inode: 48128 Links: 1 Access: (7755/-rwsr-sr-t) Uid: ( 0/ root) Gid: ( 0/ root) Context: unconfined_u:object_r:unlabeled_t:s0 Access: 2022-03-15 23:42:19.390236000 +0800 Modify: 2022-03-15 23:48:19.760428000 +0800 Change: 2022-03-15 23:48:19.760350205 +0800 Birth: - but in the event, the permission is "200107755", so it seems the first 7 is setuid/setgid/sticky bit(all set), how about "20010"? On Tue, Mar 15, 2022 at 10:12 PM Jacob M Tick wrote: > Hi, > > > > Here is some information on those bits. It's essentially special file > bits... As such: > https://www.gnu.org/software/coreutils/manual/html_node/Mode-Structure.html > > > > We have the permission bits + other bits for setuid setgid and sticky bits. > > > > Regards, > > > > *Jake Tick* > > Development Manager > > Spectrum Scale - Scalable Data Interfaces > > IBM Systems Group > > > > Email: jmtick at us.ibm.com > > > > IBM > > > > *From: *gpfsug-discuss on behalf of > shao feng > *Reply-To: *gpfsug main discussion list > *Date: *Sunday, March 13, 2022 at 6:10 PM > *To: *"gpfsug-discuss at gpfsug.org" > *Subject: *[EXTERNAL] [gpfsug-discuss] permissions in clustered watch > folder events > > > > Hello all, > > > > I am prototyping a solution which collects all the file information into a > database by utilizing the clustered watch folder feature. I found the > permissions field in the JSON from kafka topic is something > like "permissions": "200100600". It seems the "600" part is the same as > UNIX file permission, but what does the "200100" part stand for? > > > > Thank you! > -------------- next part -------------- An HTML attachment was scrubbed... URL: From juergen.hannappel at desy.de Mon Mar 21 12:37:39 2022 From: juergen.hannappel at desy.de (Hannappel, Juergen) Date: Mon, 21 Mar 2022 13:37:39 +0100 (CET) Subject: [gpfsug-discuss] Meaning of new fields in Watchfolder output Message-ID: <1471074893.22787165.1647866259731.JavaMail.zimbra@desy.de> Hi, for a test I read from a file with dd: dd if=someFile bs=64k of=/dev/null This will do 2 reads with 64k bytes, one read with 24053 and one final read with 0 bytes. I now check the WF json output, looking for the new ReadOffset and bytesRead fields I get: kafkacat -b my-broker -t test1-watch | while read mist; do echo $mist | python -m json.tool | grep -i read ; done "bytesRead": "0", "minReadOffset": "9223372036854775807", "maxReadOffset": "0", That is the open()... "bytesRead": "65536", "minReadOffset": "0", "maxReadOffset": "65535", That is the first read().... "bytesRead": "131072", "minReadOffset": "0", "maxReadOffset": "131071", WHo reads 2x64k bytes from the beginning? Is the the accumulated read data? "bytesRead": "155125", "minReadOffset": "0", "maxReadOffset": "155124", And again, now it looks as if in one event the entire file is read? The documentation (https://www.ibm.com/docs/en/spectrum-scale/5.1.3?topic=folder-json-attributes-in-clustered-watch) doesn't explain this.... -- Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 From mike-ward at utc.edu Mon Mar 28 00:20:31 2022 From: mike-ward at utc.edu (Ward, Michael) Date: Sun, 27 Mar 2022 23:20:31 +0000 Subject: [gpfsug-discuss] Seeking cNFS/GPFS advice. Add two IPs to cNFS pool Message-ID: Hello, I am relatively new to GPFS/cNFS. I have contacted reps and IBM and DDN (our vendor) w/no concrete answers. We have two servers linux server gpfs0 infiniband IP addr 10.0.136.84 linux server gpfs1 infiniband IP addr 10.0.136.85 gpfs0 server already has cnfs node name gpfs0-adm gpfs1 server already has cnfs node name gpfs1-adm We want to bind 10.0.136.86, 10.0.136.87 to these nodes to extend the cnfs pool. Below are the commands I think will work mmchnode --cnfs-interface= 10.0.136.86 -N gpfs0-adm mmchnode --cnfs-interface= 10.0.136.87 -N gpfs1-adm Below are some information about the current setup for Ethernet. [root at gpfs1 ~]# mmlscluster --cnfs GPFS cluster information ======================== GPFS cluster name: gpfs0-adm GPFS cluster id: 5815169472987570192 Cluster NFS global parameters ----------------------------- Shared root directory: /gpfs/gsfs1/.cnfs rpc.mountd port number: 597 nfsd threads: 256 Reboot on failure enabled: no CNFS monitor enabled: yes Node Daemon node name IP address CNFS state group CNFS IP address list ------------------------------------------------------------------------------------------- 1 gpfs0-adm 192.168.202.10 enabled 0 172.17.150.13 2 gpfs1-adm 192.168.202.11 enabled 0 172.17.150.14 [root at gpfs1 ~]# mmgetstate -N nsdnodes --cnfs Node number Node name GPFS state CNFS state ----------------------------------------------------- 1 gpfs0-adm active active 2 gpfs1-adm active active [root at gpfs1 ~]# ip addr show dev ib3 11: ib3: mtu 2044 qdisc mq state UP group default qlen 256 link/infiniband 20:00:19:0e:fe:80:00:00:00:00:00:00:24:8a:07:03:00:b1:bb:c9 brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff inet 10.0.136.85/24 brd 10.0.136.255 scope global ib3 valid_lft forever preferred_lft forever inet6 fe80::268a:703:b1:bbc9/64 scope link valid_lft forever preferred_lft forever [root at gpfs1 ~]# Michael Ward, Ed.D? HPC/HTC Administrator and Advanced Cyber Infrastructure Facilitator? 111B SimCenter? UT Chattanooga? 4234254764? From olaf.weiser at de.ibm.com Mon Mar 28 08:22:20 2022 From: olaf.weiser at de.ibm.com (Olaf Weiser) Date: Mon, 28 Mar 2022 07:22:20 +0000 Subject: [gpfsug-discuss] Seeking cNFS/GPFS advice. Add two IPs to cNFS pool In-Reply-To: References: Message-ID: Not sure, what you want to know... / missing Q ?! anyway.. please be aware, cnfs IP handling is done over aliasing.. so in case you have configured the IP directly on the interface, that won't work ________________________________ Von: gpfsug-discuss im Auftrag von Ward, Michael Gesendet: Montag, 28. M?rz 2022 01:20 An: gpfsug-discuss at gpfsug.org Betreff: [EXTERNAL] [gpfsug-discuss] Seeking cNFS/GPFS advice. Add two IPs to cNFS pool Hello, I am relatively new to GPFS/cNFS. I have contacted reps and IBM and DDN (our vendor) w/no concrete answers. We have two servers linux server gpfs0 infiniband IP addr 10.0.136.84 linux server gpfs1 infiniband IP addr 10.0.136.85 gpfs0 server already has cnfs node name gpfs0-adm gpfs1 server already has cnfs node name gpfs1-adm We want to bind 10.0.136.86, 10.0.136.87 to these nodes to extend the cnfs pool. Below are the commands I think will work mmchnode --cnfs-interface= 10.0.136.86 -N gpfs0-adm mmchnode --cnfs-interface= 10.0.136.87 -N gpfs1-adm Below are some information about the current setup for Ethernet. [root at gpfs1 ~]# mmlscluster --cnfs GPFS cluster information ======================== GPFS cluster name: gpfs0-adm GPFS cluster id: 5815169472987570192 Cluster NFS global parameters ----------------------------- Shared root directory: /gpfs/gsfs1/.cnfs rpc.mountd port number: 597 nfsd threads: 256 Reboot on failure enabled: no CNFS monitor enabled: yes Node Daemon node name IP address CNFS state group CNFS IP address list ------------------------------------------------------------------------------------------- 1 gpfs0-adm 192.168.202.10 enabled 0 172.17.150.13 2 gpfs1-adm 192.168.202.11 enabled 0 172.17.150.14 [root at gpfs1 ~]# mmgetstate -N nsdnodes --cnfs Node number Node name GPFS state CNFS state ----------------------------------------------------- 1 gpfs0-adm active active 2 gpfs1-adm active active [root at gpfs1 ~]# ip addr show dev ib3 11: ib3: mtu 2044 qdisc mq state UP group default qlen 256 link/infiniband 20:00:19:0e:fe:80:00:00:00:00:00:00:24:8a:07:03:00:b1:bb:c9 brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff inet 10.0.136.85/24 brd 10.0.136.255 scope global ib3 valid_lft forever preferred_lft forever inet6 fe80::268a:703:b1:bbc9/64 scope link valid_lft forever preferred_lft forever [root at gpfs1 ~]# Michael Ward, Ed.D HPC/HTC Administrator and Advanced Cyber Infrastructure Facilitator 111B SimCenter UT Chattanooga 4234254764 _______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at gpfsug.org http://gpfsug.org/mailman/listinfo/gpfsug-discuss_gpfsug.org N -------------- next part -------------- An HTML attachment was scrubbed... URL: From shaof777 at gmail.com Mon Mar 28 10:49:53 2022 From: shaof777 at gmail.com (shao feng) Date: Mon, 28 Mar 2022 17:49:53 +0800 Subject: [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule Message-ID: Hello, What is the default value of SIZE in EXTERNAL POOL in filesystem policy? The document did not mention that, but I found it is not infinity if not specified. Thank you! SIZE sum-numberIs an optional clause of the EXTERNAL POOL and EXTERNAL LIST rules. sum-number limits the total number of bytes in all of the files named in each list of files passed to your EXEC 'script'. If a single file is larger than sum-number, it is passed to your EXEC 'script' as the only entry in a ?singleton? file list. Specify sum-number as a numeric constant or a floating-point value. Note: The value of sum-number is in kilobytes. https://www.ibm.com/docs/en/spectrum-scale/5.1.2?topic=rules-policy-terms -------------- next part -------------- An HTML attachment was scrubbed... URL: From juergen.hannappel at desy.de Mon Mar 28 10:50:50 2022 From: juergen.hannappel at desy.de (Hannappel, Juergen) Date: Mon, 28 Mar 2022 11:50:50 +0200 (CEST) Subject: [gpfsug-discuss] immutable file in an immutable folder can be touched Message-ID: <489645367.26974531.1648461050348.JavaMail.zimbra@desy.de> Hi, I have an immutable file in an immutable folder: mmchattr -i yes mutabilityTest/file mmchattr -i yes mutabilityTest ls -la mutabilityTest total 18 drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. -rw-r--r-- 1 hannappj it 30 Mar 28 11:45 file mmlsattr -L mutabilityTest mutabilityTest/file | grep immu immutable: yes immutable: yes Now i do a touch: touch mutabilityTest/file no error, and the modification time is changed: ls -la mutabilityTest total 18 drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. -rw-r--r-- 1 hannappj it 30 Mar 28 11:46 file stat mutabilityTest/file File: ?mutabilityTest/file? Size: 30 Blocks: 2 IO Block: 4194304 regular file Device: 2eh/46d Inode: 112989 Links: 1 Access: (0644/-rw-r--r--) Uid: (28851/hannappj) Gid: ( 1000/ it) Access: 2022-03-28 11:46:28.454807982 +0200 Modify: 2022-03-28 11:46:28.454807982 +0200 Change: 2022-03-28 11:46:28.454807982 +0200 Shouldn't the immutability of the file include its change time? -- Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 From juergen.hannappel at desy.de Mon Mar 28 13:25:02 2022 From: juergen.hannappel at desy.de (Hannappel, Juergen) Date: Mon, 28 Mar 2022 14:25:02 +0200 (CEST) Subject: [gpfsug-discuss] immutable file in an immutable folder can be touched In-Reply-To: <489645367.26974531.1648461050348.JavaMail.zimbra@desy.de> References: <489645367.26974531.1648461050348.JavaMail.zimbra@desy.de> Message-ID: <1654236183.27138098.1648470302405.JavaMail.zimbra@desy.de> ... if I try a similar action e.g on ext4 where I can use the posix way with ioctl(fd, FS_IOC_GETFLAGS, &flags) flags |= FS_IMMUTABLE_FL; ioctl(fd, FS_IOC_SETFLAGS, &flags) the touch fails and the mtime remains unchanged.... ----- Original Message ----- > From: "Juergen Hannappel" > To: "gpfsug main discussion list" > Sent: Monday, 28 March, 2022 11:50:50 > Subject: [gpfsug-discuss] immutable file in an immutable folder can be touched > Hi, > I have an immutable file in an immutable folder: > > mmchattr -i yes mutabilityTest/file > mmchattr -i yes mutabilityTest > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:45 file > > mmlsattr -L mutabilityTest mutabilityTest/file | grep immu > immutable: yes > immutable: yes > > > Now i do a touch: > touch mutabilityTest/file > > no error, and the modification time is changed: > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:46 file > > stat mutabilityTest/file > File: ?mutabilityTest/file? > Size: 30 Blocks: 2 IO Block: 4194304 regular file > Device: 2eh/46d Inode: 112989 Links: 1 > Access: (0644/-rw-r--r--) Uid: (28851/hannappj) Gid: ( 1000/ it) > Access: 2022-03-28 11:46:28.454807982 +0200 > Modify: 2022-03-28 11:46:28.454807982 +0200 > Change: 2022-03-28 11:46:28.454807982 +0200 > > > Shouldn't the immutability of the file include its change time? > > > > -- > Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 > > _______________________________________________ > gpfsug-discuss mailing list > gpfsug-discuss at gpfsug.org > http://gpfsug.org/mailman/listinfo/gpfsug-discuss_gpfsug.org From p.ward at nhm.ac.uk Mon Mar 28 14:23:56 2022 From: p.ward at nhm.ac.uk (Paul Ward) Date: Mon, 28 Mar 2022 13:23:56 +0000 Subject: [gpfsug-discuss] immutable file in an immutable folder can be touched In-Reply-To: <1654236183.27138098.1648470302405.JavaMail.zimbra@desy.de> References: <489645367.26974531.1648461050348.JavaMail.zimbra@desy.de> <1654236183.27138098.1648470302405.JavaMail.zimbra@desy.de> Message-ID: Hi J?rgen, We noticed this behaviour when we were trying to test immutability on our newly installed solution. We tried using touch with a date in the past to test the expiry date. We noticed although touch changed the timestamp, it didn't change wherever the policy engine checked. We found a work around for our testing, so I think we accepted it as a 'feature'. I can't find a support ticket, so I am assuming we didn't report it. Kindest regards, Paul Paul Ward TS Infrastructure Architect Natural History Museum T: 02079426450 E: p.ward at nhm.ac.uk -----Original Message----- From: gpfsug-discuss On Behalf Of Hannappel, Juergen Sent: 28 March 2022 13:25 To: gpfsug-discuss Subject: Re: [gpfsug-discuss] immutable file in an immutable folder can be touched ... if I try a similar action e.g on ext4 where I can use the posix way with ioctl(fd, FS_IOC_GETFLAGS, &flags) flags |= FS_IMMUTABLE_FL; ioctl(fd, FS_IOC_SETFLAGS, &flags) the touch fails and the mtime remains unchanged.... ----- Original Message ----- > From: "Juergen Hannappel" > To: "gpfsug main discussion list" > Sent: Monday, 28 March, 2022 11:50:50 > Subject: [gpfsug-discuss] immutable file in an immutable folder can be > touched > Hi, > I have an immutable file in an immutable folder: > > mmchattr -i yes mutabilityTest/file > mmchattr -i yes mutabilityTest > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:45 file > > mmlsattr -L mutabilityTest mutabilityTest/file | grep immu > immutable: yes > immutable: yes > > > Now i do a touch: > touch mutabilityTest/file > > no error, and the modification time is changed: > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:46 file > > stat mutabilityTest/file > File: 'mutabilityTest/file' > Size: 30 Blocks: 2 IO Block: 4194304 regular file > Device: 2eh/46d Inode: 112989 Links: 1 > Access: (0644/-rw-r--r--) Uid: (28851/hannappj) Gid: ( 1000/ it) > Access: 2022-03-28 11:46:28.454807982 +0200 > Modify: 2022-03-28 11:46:28.454807982 +0200 > Change: 2022-03-28 11:46:28.454807982 +0200 > > > Shouldn't the immutability of the file include its change time? > > > > -- > Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 > > _______________________________________________ > gpfsug-discuss mailing list > gpfsug-discuss at gpfsug.org > https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fgpfsu > g.org%2Fmailman%2Flistinfo%2Fgpfsug-discuss_gpfsug.org&data=04%7C0 > 1%7Cp.ward%40nhm.ac.uk%7C2c7afbe81224404273cf08da10b63ad3%7C73a29c014e > 78437fa0d4c8553e1960c1%7C1%7C0%7C637840672748970653%7CUnknown%7CTWFpbG > Zsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0% > 3D%7C3000&sdata=I9bS8GSW5AeZbEg%2FQR2aCQd4KNd3lRmg2K1NJ3hQTk4%3D&a > mp;reserved=0 _______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at gpfsug.org https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fgpfsug.org%2Fmailman%2Flistinfo%2Fgpfsug-discuss_gpfsug.org&data=04%7C01%7Cp.ward%40nhm.ac.uk%7C2c7afbe81224404273cf08da10b63ad3%7C73a29c014e78437fa0d4c8553e1960c1%7C1%7C0%7C637840672749126883%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=O3t6BTddF3gL4DGlRAA9eweV8Vk%2BdwXj1We4GrGU%2BY8%3D&reserved=0 From shaof777 at gmail.com Tue Mar 29 06:41:23 2022 From: shaof777 at gmail.com (shao feng) Date: Tue, 29 Mar 2022 13:41:23 +0800 Subject: [gpfsug-discuss] notification when Spectrum Archival EE finish migrating/recall for a file Message-ID: Hello, Not sure if this is the right place to ask about Spectrum Archival EE. In a GPFS+LTFS EE configuration, is there any mechanism to get notification from Spectrum Archival EE when it finishes a migrating/recall for a file, especially a transparent recall? Thank you! -------------- next part -------------- An HTML attachment was scrubbed... URL: From scale at us.ibm.com Tue Mar 29 13:57:26 2022 From: scale at us.ibm.com (IBM Spectrum Scale) Date: Tue, 29 Mar 2022 18:27:26 +0530 Subject: [gpfsug-discuss] immutable file in an immutable folder can be touched In-Reply-To: References: <489645367.26974531.1648461050348.JavaMail.zimbra@desy.de> <1654236183.27138098.1648470302405.JavaMail.zimbra@desy.de> Message-ID: >From design docs can see that Spectrum scale allows changing of timestamps for immutable files. + Haizhu to confirm this as well. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479. If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. From: "Paul Ward" To: "gpfsug main discussion list" Date: 28-03-2022 06.56 PM Subject: [EXTERNAL] Re: [gpfsug-discuss] immutable file in an immutable folder can be touched Sent by: "gpfsug-discuss" Hi J?rgen, We noticed this behaviour when we were trying to test immutability on our newly installed solution. We tried using touch with a date in the past to test the expiry date. We noticed although touch changed the timestamp, it didn't change wherever the policy engine checked. We found a work around for our testing, so I think we accepted it as a 'feature'. I can't find a support ticket, so I am assuming we didn't report it. Kindest regards, Paul Paul Ward TS Infrastructure Architect Natural History Museum T: 02079426450 E: p.ward at nhm.ac.uk -----Original Message----- From: gpfsug-discuss On Behalf Of Hannappel, Juergen Sent: 28 March 2022 13:25 To: gpfsug-discuss Subject: Re: [gpfsug-discuss] immutable file in an immutable folder can be touched ... if I try a similar action e.g on ext4 where I can use the posix way with ioctl(fd, FS_IOC_GETFLAGS, &flags) flags |= FS_IMMUTABLE_FL; ioctl(fd, FS_IOC_SETFLAGS, &flags) the touch fails and the mtime remains unchanged.... ----- Original Message ----- > From: "Juergen Hannappel" > To: "gpfsug main discussion list" > Sent: Monday, 28 March, 2022 11:50:50 > Subject: [gpfsug-discuss] immutable file in an immutable folder can be > touched > Hi, > I have an immutable file in an immutable folder: > > mmchattr -i yes mutabilityTest/file > mmchattr -i yes mutabilityTest > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:45 file > > mmlsattr -L mutabilityTest mutabilityTest/file | grep immu > immutable: yes > immutable: yes > > > Now i do a touch: > touch mutabilityTest/file > > no error, and the modification time is changed: > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:46 file > > stat mutabilityTest/file > File: 'mutabilityTest/file' > Size: 30 Blocks: 2 IO Block: 4194304 regular file > Device: 2eh/46d Inode: 112989 Links: 1 > Access: (0644/-rw-r--r--) Uid: (28851/hannappj) Gid: ( 1000/ it) > Access: 2022-03-28 11:46:28.454807982 +0200 > Modify: 2022-03-28 11:46:28.454807982 +0200 > Change: 2022-03-28 11:46:28.454807982 +0200 > > > Shouldn't the immutability of the file include its change time? > > > > -- > Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 > > _______________________________________________ > gpfsug-discuss mailing list > gpfsug-discuss at gpfsug.org > https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fgpfsu > g.org%2Fmailman%2Flistinfo%2Fgpfsug-discuss_gpfsug.org&data=04%7C0 > 1%7Cp.ward%40nhm.ac.uk%7C2c7afbe81224404273cf08da10b63ad3%7C73a29c014e > 78437fa0d4c8553e1960c1%7C1%7C0%7C637840672748970653%7CUnknown%7CTWFpbG > Zsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0% > 3D%7C3000&sdata=I9bS8GSW5AeZbEg%2FQR2aCQd4KNd3lRmg2K1NJ3hQTk4%3D&a > mp;reserved=0 _______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at gpfsug.org https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fgpfsug.org%2Fmailman%2Flistinfo%2Fgpfsug-discuss_gpfsug.org&data=04%7C01%7Cp.ward%40nhm.ac.uk%7C2c7afbe81224404273cf08da10b63ad3%7C73a29c014e78437fa0d4c8553e1960c1%7C1%7C0%7C637840672749126883%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=O3t6BTddF3gL4DGlRAA9eweV8Vk%2BdwXj1We4GrGU%2BY8%3D&reserved=0 _______________________________________________ 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: From haizhu at us.ibm.com Tue Mar 29 14:49:54 2022 From: haizhu at us.ibm.com (Haizhu Liu) Date: Tue, 29 Mar 2022 13:49:54 +0000 Subject: [gpfsug-discuss] immutable file in an immutable folder can be touched In-Reply-To: References: <489645367.26974531.1648461050348.JavaMail.zimbra@desy.de> <1654236183.27138098.1648470302405.JavaMail.zimbra@desy.de> Message-ID: <5DF860B0-159A-4F9B-88DA-8DC171B45E4B@us.ibm.com> Yes, that?s correct. Atime, mtime and ctime can be changed, in addition, if the file is under an immutable fileset, mtime and ctime can be changed, atime is overloaded with expiration time. From: on behalf of "scale at us.ibm.com" Date: Tuesday, March 29, 2022 at 8:57 AM To: gpfsug main discussion list Cc: gpfsug-discuss , "juergen.hannappel at desy.de" , "p.ward at nhm.ac.uk" , Haizhu Liu Subject: Re: [EXTERNAL] Re: [gpfsug-discuss] immutable file in an immutable folder can be touched From design docs can see that Spectrum scale allows changing of timestamps for immutable files. + Haizhu to confirm this as well. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479. If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. [Inactive hide details for "Paul Ward" ---28-03-2022 06.56.04 PM---Hi J?rgen, We noticed this behaviour when we were trying to t]"Paul Ward" ---28-03-2022 06.56.04 PM---Hi J?rgen, We noticed this behaviour when we were trying to test immutability on our newly installed From: "Paul Ward" To: "gpfsug main discussion list" Date: 28-03-2022 06.56 PM Subject: [EXTERNAL] Re: [gpfsug-discuss] immutable file in an immutable folder can be touched Sent by: "gpfsug-discuss" ________________________________ Hi J?rgen, We noticed this behaviour when we were trying to test immutability on our newly installed solution. We tried using touch with a date in the past to test the expiry date. We noticed although touch changed the timestamp, it didn't change wherever the policy engine checked. We found a work around for our testing, so I think we accepted it as a 'feature'. I can't find a support ticket, so I am assuming we didn't report it. Kindest regards, Paul Paul Ward TS Infrastructure Architect Natural History Museum T: 02079426450 E: p.ward at nhm.ac.uk -----Original Message----- From: gpfsug-discuss On Behalf Of Hannappel, Juergen Sent: 28 March 2022 13:25 To: gpfsug-discuss Subject: Re: [gpfsug-discuss] immutable file in an immutable folder can be touched ... if I try a similar action e.g on ext4 where I can use the posix way with ioctl(fd, FS_IOC_GETFLAGS, &flags) flags |= FS_IMMUTABLE_FL; ioctl(fd, FS_IOC_SETFLAGS, &flags) the touch fails and the mtime remains unchanged.... ----- Original Message ----- > From: "Juergen Hannappel" > To: "gpfsug main discussion list" > Sent: Monday, 28 March, 2022 11:50:50 > Subject: [gpfsug-discuss] immutable file in an immutable folder can be > touched > Hi, > I have an immutable file in an immutable folder: > > mmchattr -i yes mutabilityTest/file > mmchattr -i yes mutabilityTest > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:45 file > > mmlsattr -L mutabilityTest mutabilityTest/file | grep immu > immutable: yes > immutable: yes > > > Now i do a touch: > touch mutabilityTest/file > > no error, and the modification time is changed: > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:46 file > > stat mutabilityTest/file > File: 'mutabilityTest/file' > Size: 30 Blocks: 2 IO Block: 4194304 regular file > Device: 2eh/46d Inode: 112989 Links: 1 > Access: (0644/-rw-r--r--) Uid: (28851/hannappj) Gid: ( 1000/ it) > Access: 2022-03-28 11:46:28.454807982 +0200 > Modify: 2022-03-28 11:46:28.454807982 +0200 > Change: 2022-03-28 11:46:28.454807982 +0200 > > > Shouldn't the immutability of the file include its change time? > > > > -- > Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 > > _______________________________________________ > gpfsug-discuss mailing list > gpfsug-discuss at gpfsug.org > https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fgpfsu > g.org%2Fmailman%2Flistinfo%2Fgpfsug-discuss_gpfsug.org&data=04%7C0 > 1%7Cp.ward%40nhm.ac.uk%7C2c7afbe81224404273cf08da10b63ad3%7C73a29c014e > 78437fa0d4c8553e1960c1%7C1%7C0%7C637840672748970653%7CUnknown%7CTWFpbG > Zsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0% > 3D%7C3000&sdata=I9bS8GSW5AeZbEg%2FQR2aCQd4KNd3lRmg2K1NJ3hQTk4%3D&a > mp;reserved=0 _______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at gpfsug.org https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fgpfsug.org%2Fmailman%2Flistinfo%2Fgpfsug-discuss_gpfsug.org&data=04%7C01%7Cp.ward%40nhm.ac.uk%7C2c7afbe81224404273cf08da10b63ad3%7C73a29c014e78437fa0d4c8553e1960c1%7C1%7C0%7C637840672749126883%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=O3t6BTddF3gL4DGlRAA9eweV8Vk%2BdwXj1We4GrGU%2BY8%3D&reserved=0 _______________________________________________ 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: image001.gif Type: image/gif Size: 106 bytes Desc: image001.gif URL: From scale at us.ibm.com Wed Mar 30 14:46:47 2022 From: scale at us.ibm.com (IBM Spectrum Scale) Date: Wed, 30 Mar 2022 19:16:47 +0530 Subject: [gpfsug-discuss] Meaning of new fields in Watchfolder output In-Reply-To: <1471074893.22787165.1647866259731.JavaMail.zimbra@desy.de> References: <1471074893.22787165.1647866259731.JavaMail.zimbra@desy.de> Message-ID: Hi Jake, Can you please look at the below WF related query. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479. If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. From: "Hannappel, Juergen" To: "gpfsug main discussion list" Date: 21-03-2022 06.09 PM Subject: [EXTERNAL] [gpfsug-discuss] Meaning of new fields in Watchfolder output Sent by: "gpfsug-discuss" Hi, for a test I read from a file with dd: dd if=someFile bs=64k of=/dev/null This will do 2 reads with 64k bytes, one read with 24053 and one final read with 0 bytes. I now check the WF json output, looking for the new ReadOffset and bytesRead fields I get: kafkacat -b my-broker -t test1-watch | while read mist; do echo $mist | python -m json.tool | grep -i read ; done "bytesRead": "0", "minReadOffset": "9223372036854775807", "maxReadOffset": "0", That is the open()... "bytesRead": "65536", "minReadOffset": "0", "maxReadOffset": "65535", That is the first read().... "bytesRead": "131072", "minReadOffset": "0", "maxReadOffset": "131071", WHo reads 2x64k bytes from the beginning? Is the the accumulated read data? "bytesRead": "155125", "minReadOffset": "0", "maxReadOffset": "155124", And again, now it looks as if in one event the entire file is read? The documentation ( https://www.ibm.com/docs/en/spectrum-scale/5.1.3?topic=folder-json-attributes-in-clustered-watch ) doesn't explain this.... -- Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 _______________________________________________ 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: From scale at us.ibm.com Wed Mar 30 14:51:36 2022 From: scale at us.ibm.com (IBM Spectrum Scale) Date: Wed, 30 Mar 2022 19:21:36 +0530 Subject: [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule In-Reply-To: References: Message-ID: Hi Diane, Can you please look at the below policy related query. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479. If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. From: "shao feng" To: "gpfsug main discussion list" Date: 28-03-2022 03.21 PM Subject: [EXTERNAL] [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule Sent by: "gpfsug-discuss" Hello, What is the default value of SIZE in EXTERNAL POOL in filesystem policy? The document did not mention that, but I found it is not infinity if not specified. Thank you! SIZE?sum-number Is an optional clause of the?EXTERNAL POOL?and?EXTERNAL LIST?rules. sum-number?limits the total number of bytes in all of the files named in each list of files passed to your EXEC 'script'. If a single file is larger than?sum-number, it is passed to your EXEC 'script' as the only entry in a??singleton??file list. Specify?sum-number?as a numeric constant or a floating-point value. Note:?The value of?sum-number?is in kilobytes. https://www.ibm.com/docs/en/spectrum-scale/5.1.2?topic=rules-policy-terms _______________________________________________ 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: From scale at us.ibm.com Wed Mar 30 15:02:20 2022 From: scale at us.ibm.com (IBM Spectrum Scale) Date: Wed, 30 Mar 2022 19:32:20 +0530 Subject: [gpfsug-discuss] notification when Spectrum Archival EE finish migrating/recall for a file In-Reply-To: References: Message-ID: I think this can be answered by the IBM Spectrum Archive team and should go to a mailing list or discussion channel where they are involved. @Lyle: Do you know anyone who can answer this from Scale side. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479. If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. From: "shao feng" To: "gpfsug main discussion list" Date: 29-03-2022 11.13 AM Subject: [EXTERNAL] [gpfsug-discuss] notification when Spectrum Archival EE finish migrating/recall for a file Sent by: "gpfsug-discuss" Hello, Not sure if this is the right place to ask about Spectrum Archival EE. In a GPFS+LTFS EE configuration, is there any mechanism to get notification from Spectrum Archival EE when it finishes a migrating/recall for a file, especially a transparent recall? Thank you!_______________________________________________ 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: From lgayne at us.ibm.com Wed Mar 30 15:10:51 2022 From: lgayne at us.ibm.com (Lyle Gayne) Date: Wed, 30 Mar 2022 14:10:51 +0000 Subject: [gpfsug-discuss] notification when Spectrum Archival EE finish migrating/recall for a file In-Reply-To: References: Message-ID: I guess this should start with Mark Hill (and Khanh), from Spectrum Archive team. Lyle ________________________________ From: gpfsug-discuss on behalf of scale at us.ibm.com Sent: Wednesday, March 30, 2022 10:02 AM To: gpfsug main discussion list Cc: gpfsug-discuss Subject: [EXTERNAL] Re: [gpfsug-discuss] notification when Spectrum Archival EE finish migrating/recall for a file I think this can be answered by the IBM Spectrum Archive team and should go to a mailing list or discussion channel where they are involved. @Lyle: Do you know anyone who can answer this from Scale side. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479. If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. [Inactive hide details for "shao feng" ---29-03-2022 11.13.11 AM---Hello, Not sure if this is the right place to ask about Spect]"shao feng" ---29-03-2022 11.13.11 AM---Hello, Not sure if this is the right place to ask about Spectrum Archival EE. From: "shao feng" To: "gpfsug main discussion list" Date: 29-03-2022 11.13 AM Subject: [EXTERNAL] [gpfsug-discuss] notification when Spectrum Archival EE finish migrating/recall for a file Sent by: "gpfsug-discuss" ________________________________ Hello, Not sure if this is the right place to ask about Spectrum Archival EE. In a GPFS+LTFS EE configuration, is there any mechanism to get notification from Spectrum Archival EE when it finishes a migrating/recall for a file, especially a transparent recall? Thank you!_______________________________________________ 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: graycol.gif URL: From scale at us.ibm.com Wed Mar 30 23:41:33 2022 From: scale at us.ibm.com (IBM Spectrum Scale) Date: Wed, 30 Mar 2022 18:41:33 -0400 Subject: [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule In-Reply-To: References: Message-ID: Hi shao feng, It is controlled by -B option. -B MaxFiles Specifies how many files are passed for each invocation of the EXEC script. The default value is 100. If the number of files exceeds the value specified for MaxFiles, mmapplypolicy invokes the external program multiple times. For more information about file list records, refer to the IBM Spectrum Scale: Administration Guide. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. From: IBM Spectrum Scale/Poughkeepsie/IBM at IBMUS To: "gpfsug main discussion list" , Diane Chung/Poughkeepsie/IBM at IBMMail Cc: "gpfsug-discuss" Date: 03/30/2022 09:53 AM Subject: [EXTERNAL] Re: [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule Sent by: "gpfsug-discuss" Hi Diane, Can you please look at the below policy related query. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479 . If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. Inactive hide details for "shao feng" ---28-03-2022 03.21.39 PM---Hello, What is the default value of SIZE in EXTERNAL POOL in "shao feng" ---28-03-2022 03.21.39 PM---Hello, What is the default value of SIZE in EXTERNAL POOL in filesystem policy? From: "shao feng" To: "gpfsug main discussion list" Date: 28-03-2022 03.21 PM Subject: [EXTERNAL] [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule Sent by: "gpfsug-discuss" Hello, What is the default value of SIZE in EXTERNAL POOL in filesystem policy? The document did not mention that, but I found it is not infinity if not specified. Thank you! SIZE?sum-number Is an optional clause of the?EXTERNAL POOL?and?EXTERNAL LIST?rules. sum-number?limits the total number of bytes in all of the files named in each list of files passed to your EXEC 'script'. If a single file is larger than?sum-number, it is passed to your EXEC 'script' as the only entry in a ?singleton??file list. Specify?sum-number?as a numeric constant or a floating-point value. Note:?The value of?sum-number?is in kilobytes. https://www.ibm.com/docs/en/spectrum-scale/5.1.2?topic=rules-policy-terms _______________________________________________ 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 -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: From anacreo at gmail.com Thu Mar 31 00:39:24 2022 From: anacreo at gmail.com (Alec) Date: Wed, 30 Mar 2022 16:39:24 -0700 Subject: [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule In-Reply-To: References: Message-ID: I'd like to offer a dissenting opinion... I believe this is a way to limit the number of actual bytes that any execution must work on.... As in only send 500gb worth of files to each invocation. Whereas the -B is the actual number of files to be passed to each invocation. I would think that size has no default limit as I've had a single invocation stuck with 30TB of data in its 100 file grouping, lol. I however use a different mechanism to divy up my files because I need to worry about my backup streams getting choked up, and I want to take a cross section of each directory on different nights... I call mmapplypolicy with -M shares=, so let's say I increase my number by 1 every day, starting at 0, over the course of a week... In my policy I have this line: WHERE MOD(INODE,6)<=shares So then I work on 1/7th of the files in my file system and cumulatively pick up any INODES until I've hit all of the files... I could pick just the matching segment by saying = instead of <=. This is happening at the file selection phase, so the application of -B is after this selection, as my files are quite huge, I tend to use -B 1. Alec On Wed, Mar 30, 2022 at 3:44 PM IBM Spectrum Scale wrote: > Hi shao feng, > > It is controlled by -B option. > > *-B* *MaxFiles* > Specifies how many files are passed for each invocation > of the EXEC script. The default value is 100. > > If the number of files exceeds the value specified for > MaxFiles, *mmapplypolicy* invokes the external > program multiple times. > > For more information about file list records, refer to > the IBM Spectrum Scale: Administration Guide. > > Regards, The Spectrum Scale (GPFS) team > > > ------------------------------------------------------------------------------------------------------------------ > If your query concerns a potential software error in Spectrum Scale (GPFS) > and you have an IBM software maintenance contract please contact > 1-800-237-5511 in the United States or your local IBM Service Center in > other countries. > > [image: Inactive hide details for IBM Spectrum Scale---03/30/2022 09:53:51 > AM---Hi Diane, Can you please look at the below policy relat]IBM Spectrum > Scale---03/30/2022 09:53:51 AM---Hi Diane, Can you please look at the below > policy related query. > > From: IBM Spectrum Scale/Poughkeepsie/IBM at IBMUS > To: "gpfsug main discussion list" , Diane > Chung/Poughkeepsie/IBM at IBMMail > Cc: "gpfsug-discuss" > Date: 03/30/2022 09:53 AM > Subject: [EXTERNAL] Re: [gpfsug-discuss] default value of SIZE in > EXTERNAL POOL and EXTERNAL LIST rule > Sent by: "gpfsug-discuss" > ------------------------------ > > > > Hi Diane, > > Can you please look at the below policy related query. > > Regards, The Spectrum Scale (GPFS) team > > > ------------------------------------------------------------------------------------------------------------------ > If you feel that your question can benefit other users of Spectrum Scale > (GPFS), then please post it to the public IBM developerWroks Forum at > *https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479* > . > > > If your query concerns a potential software error in Spectrum Scale (GPFS) > and you have an IBM software maintenance contract please contact > 1-800-237-5511 in the United States or your local IBM Service Center in > other countries. > > The forum is informally monitored as time permits and should not be used > for priority messages to the Spectrum Scale (GPFS) team. > > [image: Inactive hide details for "shao feng" ---28-03-2022 03.21.39 > PM---Hello, What is the default value of SIZE in EXTERNAL POOL in]"shao > feng" ---28-03-2022 03.21.39 PM---Hello, What is the default value of SIZE > in EXTERNAL POOL in filesystem policy? > > From: "shao feng" > To: "gpfsug main discussion list" > Date: 28-03-2022 03.21 PM > Subject: [EXTERNAL] [gpfsug-discuss] default value of SIZE in EXTERNAL > POOL and EXTERNAL LIST rule > Sent by: "gpfsug-discuss" > ------------------------------ > > > > Hello, > > What is the default value of SIZE in EXTERNAL POOL in filesystem policy? > > The document did not mention that, but I found it is not infinity if not > specified. > > Thank you! > > *SIZE **sum-number* > Is an optional clause of the *EXTERNAL POOL* and *EXTERNAL LIST* rules. > *sum-number* limits the total number of bytes in all of the files named > in each list of files passed to your EXEC 'script'. If a single file is > larger than *sum-number*, it is passed to your EXEC 'script' as the only > entry in a ?singleton? file list. > > Specify *sum-number* as a numeric constant or a floating-point value. > > *Note:* The value of *sum-number* is in kilobytes. > *https://www.ibm.com/docs/en/spectrum-scale/5.1.2?topic=rules-policy-terms* > > _______________________________________________ > 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 > -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: From shaof777 at gmail.com Thu Mar 31 08:53:07 2022 From: shaof777 at gmail.com (shao feng) Date: Thu, 31 Mar 2022 15:53:07 +0800 Subject: [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule In-Reply-To: References: Message-ID: Thanks Alec! On Thu, Mar 31, 2022 at 7:41 AM Alec wrote: > I'd like to offer a dissenting opinion... I believe this is a way to > limit the number of actual bytes that any execution must work on.... As in > only send 500gb worth of files to each invocation. Whereas the -B is the > actual number of files to be passed to each invocation. I would think that > size has no default limit as I've had a single invocation stuck with 30TB > of data in its 100 file grouping, lol. > > I however use a different mechanism to divy up my files because I need to > worry about my backup streams getting choked up, and I want to take a cross > section of each directory on different nights... > > I call mmapplypolicy with -M shares=, so let's say > I increase my number by 1 every day, starting at 0, over the course of a > week... > > In my policy I have this line: > WHERE MOD(INODE,6)<=shares > > So then I work on 1/7th of the files in my file system and cumulatively > pick up any INODES until I've hit all of the files... I could pick just the > matching segment by saying = instead of <=. > > This is happening at the file selection phase, so the application of -B is > after this selection, as my files are quite huge, I tend to use -B 1. > > Alec > > On Wed, Mar 30, 2022 at 3:44 PM IBM Spectrum Scale > wrote: > >> Hi shao feng, >> >> It is controlled by -B option. >> >> *-B* *MaxFiles* >> Specifies how many files are passed for each invocation >> of the EXEC script. The default value is 100. >> >> If the number of files exceeds the value specified for >> MaxFiles, *mmapplypolicy* invokes the external >> program multiple times. >> >> For more information about file list records, refer to >> the IBM Spectrum Scale: Administration Guide. >> >> Regards, The Spectrum Scale (GPFS) team >> >> >> ------------------------------------------------------------------------------------------------------------------ >> If your query concerns a potential software error in Spectrum Scale >> (GPFS) and you have an IBM software maintenance contract please contact >> 1-800-237-5511 in the United States or your local IBM Service Center in >> other countries. >> >> [image: Inactive hide details for IBM Spectrum Scale---03/30/2022 >> 09:53:51 AM---Hi Diane, Can you please look at the below policy relat]IBM >> Spectrum Scale---03/30/2022 09:53:51 AM---Hi Diane, Can you please look at >> the below policy related query. >> >> From: IBM Spectrum Scale/Poughkeepsie/IBM at IBMUS >> To: "gpfsug main discussion list" , Diane >> Chung/Poughkeepsie/IBM at IBMMail >> Cc: "gpfsug-discuss" >> Date: 03/30/2022 09:53 AM >> Subject: [EXTERNAL] Re: [gpfsug-discuss] default value of SIZE in >> EXTERNAL POOL and EXTERNAL LIST rule >> Sent by: "gpfsug-discuss" >> ------------------------------ >> >> >> >> Hi Diane, >> >> Can you please look at the below policy related query. >> >> Regards, The Spectrum Scale (GPFS) team >> >> >> ------------------------------------------------------------------------------------------------------------------ >> If you feel that your question can benefit other users of Spectrum Scale >> (GPFS), then please post it to the public IBM developerWroks Forum at >> *https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479* >> . >> >> >> If your query concerns a potential software error in Spectrum Scale >> (GPFS) and you have an IBM software maintenance contract please contact >> 1-800-237-5511 in the United States or your local IBM Service Center in >> other countries. >> >> The forum is informally monitored as time permits and should not be used >> for priority messages to the Spectrum Scale (GPFS) team. >> >> [image: Inactive hide details for "shao feng" ---28-03-2022 03.21.39 >> PM---Hello, What is the default value of SIZE in EXTERNAL POOL in]"shao >> feng" ---28-03-2022 03.21.39 PM---Hello, What is the default value of SIZE >> in EXTERNAL POOL in filesystem policy? >> >> From: "shao feng" >> To: "gpfsug main discussion list" >> Date: 28-03-2022 03.21 PM >> Subject: [EXTERNAL] [gpfsug-discuss] default value of SIZE in EXTERNAL >> POOL and EXTERNAL LIST rule >> Sent by: "gpfsug-discuss" >> ------------------------------ >> >> >> >> Hello, >> >> What is the default value of SIZE in EXTERNAL POOL in filesystem policy? >> >> The document did not mention that, but I found it is not infinity if not >> specified. >> >> Thank you! >> >> *SIZE **sum-number* >> Is an optional clause of the *EXTERNAL POOL* and *EXTERNAL LIST* rules. >> *sum-number* limits the total number of bytes in all of the files named >> in each list of files passed to your EXEC 'script'. If a single file is >> larger than *sum-number*, it is passed to your EXEC 'script' as the only >> entry in a ?singleton? file list. >> >> Specify *sum-number* as a numeric constant or a floating-point value. >> >> *Note:* The value of *sum-number* is in kilobytes. >> *https://www.ibm.com/docs/en/spectrum-scale/5.1.2?topic=rules-policy-terms* >> >> _______________________________________________ >> 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 >> > _______________________________________________ > 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: From daniel.kidger at hpe.com Fri Mar 11 17:34:14 2022 From: daniel.kidger at hpe.com (Kidger, Daniel) Date: Fri, 11 Mar 2022 17:34:14 +0000 Subject: [gpfsug-discuss] Running the Spectrum Scale on a Compute-only Cluster ? Message-ID: The Spectrum Scale GUI is widely run on GPFS clusters that include their own storage, but what about multi-cluster with separate Storage and Compute clusters? Will the GUI run on a compute only cluster? And if so does it simply omit components that are not present - such as Recovery Groups and NSD Servers ? Daniel Daniel Kidger HPC Storage Solutions Architect, EMEA daniel.kidger at hpe.com +44 (0)7818 522266 hpe.com -------------- next part -------------- An HTML attachment was scrubbed... URL: From krajaram at geocomputing.net Fri Mar 11 18:16:06 2022 From: krajaram at geocomputing.net (Kumaran Rajaram) Date: Fri, 11 Mar 2022 18:16:06 +0000 Subject: [gpfsug-discuss] Running the Spectrum Scale on a Compute-only Cluster ? In-Reply-To: References: Message-ID: Hi, >> The Spectrum Scale GUI is widely run on GPFS clusters that include their own storage, but what about multi-cluster with separate Storage and Compute clusters? Yes, Spectrum Scale GUI works on GPFS Multi-Cluster setup with separate Storage and Compute clusters. The GUI works fine on a compute only cluster and storage only cluster. >> And if so does it simply omit components that are not present - such as Recovery Groups and NSD Servers ? Correct. The compute cluster GUI panels will still show remotely mounted file system and filesets + show their health status. Cheers, -Kums Kumaran Rajaram [cid:image001.png at 01D83549.C3601B90] From: gpfsug-discuss-bounces at spectrumscale.org On Behalf Of Kidger, Daniel Sent: Friday, March 11, 2022 12:34 PM To: gpfsug-discuss at spectrumscale.org Subject: [gpfsug-discuss] Running the Spectrum Scale on a Compute-only Cluster ? The Spectrum Scale GUI is widely run on GPFS clusters that include their own storage, but what about multi-cluster with separate Storage and Compute clusters? Will the GUI run on a compute only cluster? And if so does it simply omit components that are not present - such as Recovery Groups and NSD Servers ? Daniel Daniel Kidger HPC Storage Solutions Architect, EMEA daniel.kidger at hpe.com +44 (0)7818 522266 hpe.com -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: image001.png Type: image/png Size: 6469 bytes Desc: image001.png URL: From systems at gpfsug.org Mon Mar 14 00:54:41 2022 From: systems at gpfsug.org (systems at gpfsug.org) Date: Mon, 14 Mar 2022 00:54:41 +0000 Subject: [gpfsug-discuss] Website and mailing list migration Message-ID: <087d851ead9d65c79e016abc6478b8f0@gpfsug.org> Dear All, Over the weekend the Mailing List was migrated to a new system, whilst we expect that this migration has been completed; as with all migrations we do expect that some issues may require further attention. The main website should work with all previous domains, gpfsug.org spectrumscaleug.org and spectrumscale.org and the new mailman list page is located at: https://spectrumscale.org/mailman/listinfo/gpfsug-discuss_gpfsug.org Should you find any errors or bugs, please email systems at spectrumscale.org Kind Regards, Systems From shaof777 at gmail.com Mon Mar 14 01:08:37 2022 From: shaof777 at gmail.com (shao feng) Date: Mon, 14 Mar 2022 09:08:37 +0800 Subject: [gpfsug-discuss] permissions in clustered watch folder events Message-ID: Hello all, I am prototyping a solution which collects all the file information into a database by utilizing the clustered watch folder feature. I found the permissions field in the JSON from kafka topic is something like "permissions": "200100600". It seems the "600" part is the same as UNIX file permission, but what does the "200100" part stand for? Thank you! -------------- next part -------------- An HTML attachment was scrubbed... URL: From jmtick at us.ibm.com Tue Mar 15 14:12:32 2022 From: jmtick at us.ibm.com (Jacob M Tick) Date: Tue, 15 Mar 2022 14:12:32 +0000 Subject: [gpfsug-discuss] permissions in clustered watch folder events In-Reply-To: References: Message-ID: <735033AD-49A7-4CD3-97C3-A1184126D627@us.ibm.com> Hi, Here is some information on those bits. It's essentially special file bits... As such: https://www.gnu.org/software/coreutils/manual/html_node/Mode-Structure.html We have the permission bits + other bits for setuid setgid and sticky bits. Regards, Jake Tick Development Manager Spectrum Scale - Scalable Data Interfaces IBM Systems Group Email: jmtick at us.ibm.com IBM From: gpfsug-discuss on behalf of shao feng Reply-To: gpfsug main discussion list Date: Sunday, March 13, 2022 at 6:10 PM To: "gpfsug-discuss at gpfsug.org" Subject: [EXTERNAL] [gpfsug-discuss] permissions in clustered watch folder events Hello all, I am prototyping a solution which collects all the file information into a database by utilizing the clustered watch folder feature. I found the permissions field in the JSON from kafka topic is something like "permissions": "200100600". It seems the "600" part is the same as UNIX file permission, but what does the "200100" part stand for? Thank you! -------------- next part -------------- An HTML attachment was scrubbed... URL: From shaof777 at gmail.com Tue Mar 15 15:54:49 2022 From: shaof777 at gmail.com (shao feng) Date: Tue, 15 Mar 2022 23:54:49 +0800 Subject: [gpfsug-discuss] permissions in clustered watch folder events In-Reply-To: <735033AD-49A7-4CD3-97C3-A1184126D627@us.ibm.com> References: <735033AD-49A7-4CD3-97C3-A1184126D627@us.ibm.com> Message-ID: Thanks Jacob, but I still don't quite understand :-) for example, I have a file a with mode set to 7755 # ls -l a -rwsr-sr-t. 1 root root 2 Mar 15 23:46 a # stat a File: 'a' Size: 2 Blocks: 2 IO Block: 4194304 regular file Device: 34h/52d Inode: 48128 Links: 1 Access: (7755/-rwsr-sr-t) Uid: ( 0/ root) Gid: ( 0/ root) Context: unconfined_u:object_r:unlabeled_t:s0 Access: 2022-03-15 23:42:19.390236000 +0800 Modify: 2022-03-15 23:48:19.760428000 +0800 Change: 2022-03-15 23:48:19.760350205 +0800 Birth: - but in the event, the permission is "200107755", so it seems the first 7 is setuid/setgid/sticky bit(all set), how about "20010"? On Tue, Mar 15, 2022 at 10:12 PM Jacob M Tick wrote: > Hi, > > > > Here is some information on those bits. It's essentially special file > bits... As such: > https://www.gnu.org/software/coreutils/manual/html_node/Mode-Structure.html > > > > We have the permission bits + other bits for setuid setgid and sticky bits. > > > > Regards, > > > > *Jake Tick* > > Development Manager > > Spectrum Scale - Scalable Data Interfaces > > IBM Systems Group > > > > Email: jmtick at us.ibm.com > > > > IBM > > > > *From: *gpfsug-discuss on behalf of > shao feng > *Reply-To: *gpfsug main discussion list > *Date: *Sunday, March 13, 2022 at 6:10 PM > *To: *"gpfsug-discuss at gpfsug.org" > *Subject: *[EXTERNAL] [gpfsug-discuss] permissions in clustered watch > folder events > > > > Hello all, > > > > I am prototyping a solution which collects all the file information into a > database by utilizing the clustered watch folder feature. I found the > permissions field in the JSON from kafka topic is something > like "permissions": "200100600". It seems the "600" part is the same as > UNIX file permission, but what does the "200100" part stand for? > > > > Thank you! > -------------- next part -------------- An HTML attachment was scrubbed... URL: From juergen.hannappel at desy.de Mon Mar 21 12:37:39 2022 From: juergen.hannappel at desy.de (Hannappel, Juergen) Date: Mon, 21 Mar 2022 13:37:39 +0100 (CET) Subject: [gpfsug-discuss] Meaning of new fields in Watchfolder output Message-ID: <1471074893.22787165.1647866259731.JavaMail.zimbra@desy.de> Hi, for a test I read from a file with dd: dd if=someFile bs=64k of=/dev/null This will do 2 reads with 64k bytes, one read with 24053 and one final read with 0 bytes. I now check the WF json output, looking for the new ReadOffset and bytesRead fields I get: kafkacat -b my-broker -t test1-watch | while read mist; do echo $mist | python -m json.tool | grep -i read ; done "bytesRead": "0", "minReadOffset": "9223372036854775807", "maxReadOffset": "0", That is the open()... "bytesRead": "65536", "minReadOffset": "0", "maxReadOffset": "65535", That is the first read().... "bytesRead": "131072", "minReadOffset": "0", "maxReadOffset": "131071", WHo reads 2x64k bytes from the beginning? Is the the accumulated read data? "bytesRead": "155125", "minReadOffset": "0", "maxReadOffset": "155124", And again, now it looks as if in one event the entire file is read? The documentation (https://www.ibm.com/docs/en/spectrum-scale/5.1.3?topic=folder-json-attributes-in-clustered-watch) doesn't explain this.... -- Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 From mike-ward at utc.edu Mon Mar 28 00:20:31 2022 From: mike-ward at utc.edu (Ward, Michael) Date: Sun, 27 Mar 2022 23:20:31 +0000 Subject: [gpfsug-discuss] Seeking cNFS/GPFS advice. Add two IPs to cNFS pool Message-ID: Hello, I am relatively new to GPFS/cNFS. I have contacted reps and IBM and DDN (our vendor) w/no concrete answers. We have two servers linux server gpfs0 infiniband IP addr 10.0.136.84 linux server gpfs1 infiniband IP addr 10.0.136.85 gpfs0 server already has cnfs node name gpfs0-adm gpfs1 server already has cnfs node name gpfs1-adm We want to bind 10.0.136.86, 10.0.136.87 to these nodes to extend the cnfs pool. Below are the commands I think will work mmchnode --cnfs-interface= 10.0.136.86 -N gpfs0-adm mmchnode --cnfs-interface= 10.0.136.87 -N gpfs1-adm Below are some information about the current setup for Ethernet. [root at gpfs1 ~]# mmlscluster --cnfs GPFS cluster information ======================== GPFS cluster name: gpfs0-adm GPFS cluster id: 5815169472987570192 Cluster NFS global parameters ----------------------------- Shared root directory: /gpfs/gsfs1/.cnfs rpc.mountd port number: 597 nfsd threads: 256 Reboot on failure enabled: no CNFS monitor enabled: yes Node Daemon node name IP address CNFS state group CNFS IP address list ------------------------------------------------------------------------------------------- 1 gpfs0-adm 192.168.202.10 enabled 0 172.17.150.13 2 gpfs1-adm 192.168.202.11 enabled 0 172.17.150.14 [root at gpfs1 ~]# mmgetstate -N nsdnodes --cnfs Node number Node name GPFS state CNFS state ----------------------------------------------------- 1 gpfs0-adm active active 2 gpfs1-adm active active [root at gpfs1 ~]# ip addr show dev ib3 11: ib3: mtu 2044 qdisc mq state UP group default qlen 256 link/infiniband 20:00:19:0e:fe:80:00:00:00:00:00:00:24:8a:07:03:00:b1:bb:c9 brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff inet 10.0.136.85/24 brd 10.0.136.255 scope global ib3 valid_lft forever preferred_lft forever inet6 fe80::268a:703:b1:bbc9/64 scope link valid_lft forever preferred_lft forever [root at gpfs1 ~]# Michael Ward, Ed.D? HPC/HTC Administrator and Advanced Cyber Infrastructure Facilitator? 111B SimCenter? UT Chattanooga? 4234254764? From olaf.weiser at de.ibm.com Mon Mar 28 08:22:20 2022 From: olaf.weiser at de.ibm.com (Olaf Weiser) Date: Mon, 28 Mar 2022 07:22:20 +0000 Subject: [gpfsug-discuss] Seeking cNFS/GPFS advice. Add two IPs to cNFS pool In-Reply-To: References: Message-ID: Not sure, what you want to know... / missing Q ?! anyway.. please be aware, cnfs IP handling is done over aliasing.. so in case you have configured the IP directly on the interface, that won't work ________________________________ Von: gpfsug-discuss im Auftrag von Ward, Michael Gesendet: Montag, 28. M?rz 2022 01:20 An: gpfsug-discuss at gpfsug.org Betreff: [EXTERNAL] [gpfsug-discuss] Seeking cNFS/GPFS advice. Add two IPs to cNFS pool Hello, I am relatively new to GPFS/cNFS. I have contacted reps and IBM and DDN (our vendor) w/no concrete answers. We have two servers linux server gpfs0 infiniband IP addr 10.0.136.84 linux server gpfs1 infiniband IP addr 10.0.136.85 gpfs0 server already has cnfs node name gpfs0-adm gpfs1 server already has cnfs node name gpfs1-adm We want to bind 10.0.136.86, 10.0.136.87 to these nodes to extend the cnfs pool. Below are the commands I think will work mmchnode --cnfs-interface= 10.0.136.86 -N gpfs0-adm mmchnode --cnfs-interface= 10.0.136.87 -N gpfs1-adm Below are some information about the current setup for Ethernet. [root at gpfs1 ~]# mmlscluster --cnfs GPFS cluster information ======================== GPFS cluster name: gpfs0-adm GPFS cluster id: 5815169472987570192 Cluster NFS global parameters ----------------------------- Shared root directory: /gpfs/gsfs1/.cnfs rpc.mountd port number: 597 nfsd threads: 256 Reboot on failure enabled: no CNFS monitor enabled: yes Node Daemon node name IP address CNFS state group CNFS IP address list ------------------------------------------------------------------------------------------- 1 gpfs0-adm 192.168.202.10 enabled 0 172.17.150.13 2 gpfs1-adm 192.168.202.11 enabled 0 172.17.150.14 [root at gpfs1 ~]# mmgetstate -N nsdnodes --cnfs Node number Node name GPFS state CNFS state ----------------------------------------------------- 1 gpfs0-adm active active 2 gpfs1-adm active active [root at gpfs1 ~]# ip addr show dev ib3 11: ib3: mtu 2044 qdisc mq state UP group default qlen 256 link/infiniband 20:00:19:0e:fe:80:00:00:00:00:00:00:24:8a:07:03:00:b1:bb:c9 brd 00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff inet 10.0.136.85/24 brd 10.0.136.255 scope global ib3 valid_lft forever preferred_lft forever inet6 fe80::268a:703:b1:bbc9/64 scope link valid_lft forever preferred_lft forever [root at gpfs1 ~]# Michael Ward, Ed.D HPC/HTC Administrator and Advanced Cyber Infrastructure Facilitator 111B SimCenter UT Chattanooga 4234254764 _______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at gpfsug.org http://gpfsug.org/mailman/listinfo/gpfsug-discuss_gpfsug.org N -------------- next part -------------- An HTML attachment was scrubbed... URL: From shaof777 at gmail.com Mon Mar 28 10:49:53 2022 From: shaof777 at gmail.com (shao feng) Date: Mon, 28 Mar 2022 17:49:53 +0800 Subject: [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule Message-ID: Hello, What is the default value of SIZE in EXTERNAL POOL in filesystem policy? The document did not mention that, but I found it is not infinity if not specified. Thank you! SIZE sum-numberIs an optional clause of the EXTERNAL POOL and EXTERNAL LIST rules. sum-number limits the total number of bytes in all of the files named in each list of files passed to your EXEC 'script'. If a single file is larger than sum-number, it is passed to your EXEC 'script' as the only entry in a ?singleton? file list. Specify sum-number as a numeric constant or a floating-point value. Note: The value of sum-number is in kilobytes. https://www.ibm.com/docs/en/spectrum-scale/5.1.2?topic=rules-policy-terms -------------- next part -------------- An HTML attachment was scrubbed... URL: From juergen.hannappel at desy.de Mon Mar 28 10:50:50 2022 From: juergen.hannappel at desy.de (Hannappel, Juergen) Date: Mon, 28 Mar 2022 11:50:50 +0200 (CEST) Subject: [gpfsug-discuss] immutable file in an immutable folder can be touched Message-ID: <489645367.26974531.1648461050348.JavaMail.zimbra@desy.de> Hi, I have an immutable file in an immutable folder: mmchattr -i yes mutabilityTest/file mmchattr -i yes mutabilityTest ls -la mutabilityTest total 18 drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. -rw-r--r-- 1 hannappj it 30 Mar 28 11:45 file mmlsattr -L mutabilityTest mutabilityTest/file | grep immu immutable: yes immutable: yes Now i do a touch: touch mutabilityTest/file no error, and the modification time is changed: ls -la mutabilityTest total 18 drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. -rw-r--r-- 1 hannappj it 30 Mar 28 11:46 file stat mutabilityTest/file File: ?mutabilityTest/file? Size: 30 Blocks: 2 IO Block: 4194304 regular file Device: 2eh/46d Inode: 112989 Links: 1 Access: (0644/-rw-r--r--) Uid: (28851/hannappj) Gid: ( 1000/ it) Access: 2022-03-28 11:46:28.454807982 +0200 Modify: 2022-03-28 11:46:28.454807982 +0200 Change: 2022-03-28 11:46:28.454807982 +0200 Shouldn't the immutability of the file include its change time? -- Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 From juergen.hannappel at desy.de Mon Mar 28 13:25:02 2022 From: juergen.hannappel at desy.de (Hannappel, Juergen) Date: Mon, 28 Mar 2022 14:25:02 +0200 (CEST) Subject: [gpfsug-discuss] immutable file in an immutable folder can be touched In-Reply-To: <489645367.26974531.1648461050348.JavaMail.zimbra@desy.de> References: <489645367.26974531.1648461050348.JavaMail.zimbra@desy.de> Message-ID: <1654236183.27138098.1648470302405.JavaMail.zimbra@desy.de> ... if I try a similar action e.g on ext4 where I can use the posix way with ioctl(fd, FS_IOC_GETFLAGS, &flags) flags |= FS_IMMUTABLE_FL; ioctl(fd, FS_IOC_SETFLAGS, &flags) the touch fails and the mtime remains unchanged.... ----- Original Message ----- > From: "Juergen Hannappel" > To: "gpfsug main discussion list" > Sent: Monday, 28 March, 2022 11:50:50 > Subject: [gpfsug-discuss] immutable file in an immutable folder can be touched > Hi, > I have an immutable file in an immutable folder: > > mmchattr -i yes mutabilityTest/file > mmchattr -i yes mutabilityTest > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:45 file > > mmlsattr -L mutabilityTest mutabilityTest/file | grep immu > immutable: yes > immutable: yes > > > Now i do a touch: > touch mutabilityTest/file > > no error, and the modification time is changed: > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:46 file > > stat mutabilityTest/file > File: ?mutabilityTest/file? > Size: 30 Blocks: 2 IO Block: 4194304 regular file > Device: 2eh/46d Inode: 112989 Links: 1 > Access: (0644/-rw-r--r--) Uid: (28851/hannappj) Gid: ( 1000/ it) > Access: 2022-03-28 11:46:28.454807982 +0200 > Modify: 2022-03-28 11:46:28.454807982 +0200 > Change: 2022-03-28 11:46:28.454807982 +0200 > > > Shouldn't the immutability of the file include its change time? > > > > -- > Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 > > _______________________________________________ > gpfsug-discuss mailing list > gpfsug-discuss at gpfsug.org > http://gpfsug.org/mailman/listinfo/gpfsug-discuss_gpfsug.org From p.ward at nhm.ac.uk Mon Mar 28 14:23:56 2022 From: p.ward at nhm.ac.uk (Paul Ward) Date: Mon, 28 Mar 2022 13:23:56 +0000 Subject: [gpfsug-discuss] immutable file in an immutable folder can be touched In-Reply-To: <1654236183.27138098.1648470302405.JavaMail.zimbra@desy.de> References: <489645367.26974531.1648461050348.JavaMail.zimbra@desy.de> <1654236183.27138098.1648470302405.JavaMail.zimbra@desy.de> Message-ID: Hi J?rgen, We noticed this behaviour when we were trying to test immutability on our newly installed solution. We tried using touch with a date in the past to test the expiry date. We noticed although touch changed the timestamp, it didn't change wherever the policy engine checked. We found a work around for our testing, so I think we accepted it as a 'feature'. I can't find a support ticket, so I am assuming we didn't report it. Kindest regards, Paul Paul Ward TS Infrastructure Architect Natural History Museum T: 02079426450 E: p.ward at nhm.ac.uk -----Original Message----- From: gpfsug-discuss On Behalf Of Hannappel, Juergen Sent: 28 March 2022 13:25 To: gpfsug-discuss Subject: Re: [gpfsug-discuss] immutable file in an immutable folder can be touched ... if I try a similar action e.g on ext4 where I can use the posix way with ioctl(fd, FS_IOC_GETFLAGS, &flags) flags |= FS_IMMUTABLE_FL; ioctl(fd, FS_IOC_SETFLAGS, &flags) the touch fails and the mtime remains unchanged.... ----- Original Message ----- > From: "Juergen Hannappel" > To: "gpfsug main discussion list" > Sent: Monday, 28 March, 2022 11:50:50 > Subject: [gpfsug-discuss] immutable file in an immutable folder can be > touched > Hi, > I have an immutable file in an immutable folder: > > mmchattr -i yes mutabilityTest/file > mmchattr -i yes mutabilityTest > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:45 file > > mmlsattr -L mutabilityTest mutabilityTest/file | grep immu > immutable: yes > immutable: yes > > > Now i do a touch: > touch mutabilityTest/file > > no error, and the modification time is changed: > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:46 file > > stat mutabilityTest/file > File: 'mutabilityTest/file' > Size: 30 Blocks: 2 IO Block: 4194304 regular file > Device: 2eh/46d Inode: 112989 Links: 1 > Access: (0644/-rw-r--r--) Uid: (28851/hannappj) Gid: ( 1000/ it) > Access: 2022-03-28 11:46:28.454807982 +0200 > Modify: 2022-03-28 11:46:28.454807982 +0200 > Change: 2022-03-28 11:46:28.454807982 +0200 > > > Shouldn't the immutability of the file include its change time? > > > > -- > Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 > > _______________________________________________ > gpfsug-discuss mailing list > gpfsug-discuss at gpfsug.org > https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fgpfsu > g.org%2Fmailman%2Flistinfo%2Fgpfsug-discuss_gpfsug.org&data=04%7C0 > 1%7Cp.ward%40nhm.ac.uk%7C2c7afbe81224404273cf08da10b63ad3%7C73a29c014e > 78437fa0d4c8553e1960c1%7C1%7C0%7C637840672748970653%7CUnknown%7CTWFpbG > Zsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0% > 3D%7C3000&sdata=I9bS8GSW5AeZbEg%2FQR2aCQd4KNd3lRmg2K1NJ3hQTk4%3D&a > mp;reserved=0 _______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at gpfsug.org https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fgpfsug.org%2Fmailman%2Flistinfo%2Fgpfsug-discuss_gpfsug.org&data=04%7C01%7Cp.ward%40nhm.ac.uk%7C2c7afbe81224404273cf08da10b63ad3%7C73a29c014e78437fa0d4c8553e1960c1%7C1%7C0%7C637840672749126883%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=O3t6BTddF3gL4DGlRAA9eweV8Vk%2BdwXj1We4GrGU%2BY8%3D&reserved=0 From shaof777 at gmail.com Tue Mar 29 06:41:23 2022 From: shaof777 at gmail.com (shao feng) Date: Tue, 29 Mar 2022 13:41:23 +0800 Subject: [gpfsug-discuss] notification when Spectrum Archival EE finish migrating/recall for a file Message-ID: Hello, Not sure if this is the right place to ask about Spectrum Archival EE. In a GPFS+LTFS EE configuration, is there any mechanism to get notification from Spectrum Archival EE when it finishes a migrating/recall for a file, especially a transparent recall? Thank you! -------------- next part -------------- An HTML attachment was scrubbed... URL: From scale at us.ibm.com Tue Mar 29 13:57:26 2022 From: scale at us.ibm.com (IBM Spectrum Scale) Date: Tue, 29 Mar 2022 18:27:26 +0530 Subject: [gpfsug-discuss] immutable file in an immutable folder can be touched In-Reply-To: References: <489645367.26974531.1648461050348.JavaMail.zimbra@desy.de> <1654236183.27138098.1648470302405.JavaMail.zimbra@desy.de> Message-ID: >From design docs can see that Spectrum scale allows changing of timestamps for immutable files. + Haizhu to confirm this as well. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479. If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. From: "Paul Ward" To: "gpfsug main discussion list" Date: 28-03-2022 06.56 PM Subject: [EXTERNAL] Re: [gpfsug-discuss] immutable file in an immutable folder can be touched Sent by: "gpfsug-discuss" Hi J?rgen, We noticed this behaviour when we were trying to test immutability on our newly installed solution. We tried using touch with a date in the past to test the expiry date. We noticed although touch changed the timestamp, it didn't change wherever the policy engine checked. We found a work around for our testing, so I think we accepted it as a 'feature'. I can't find a support ticket, so I am assuming we didn't report it. Kindest regards, Paul Paul Ward TS Infrastructure Architect Natural History Museum T: 02079426450 E: p.ward at nhm.ac.uk -----Original Message----- From: gpfsug-discuss On Behalf Of Hannappel, Juergen Sent: 28 March 2022 13:25 To: gpfsug-discuss Subject: Re: [gpfsug-discuss] immutable file in an immutable folder can be touched ... if I try a similar action e.g on ext4 where I can use the posix way with ioctl(fd, FS_IOC_GETFLAGS, &flags) flags |= FS_IMMUTABLE_FL; ioctl(fd, FS_IOC_SETFLAGS, &flags) the touch fails and the mtime remains unchanged.... ----- Original Message ----- > From: "Juergen Hannappel" > To: "gpfsug main discussion list" > Sent: Monday, 28 March, 2022 11:50:50 > Subject: [gpfsug-discuss] immutable file in an immutable folder can be > touched > Hi, > I have an immutable file in an immutable folder: > > mmchattr -i yes mutabilityTest/file > mmchattr -i yes mutabilityTest > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:45 file > > mmlsattr -L mutabilityTest mutabilityTest/file | grep immu > immutable: yes > immutable: yes > > > Now i do a touch: > touch mutabilityTest/file > > no error, and the modification time is changed: > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:46 file > > stat mutabilityTest/file > File: 'mutabilityTest/file' > Size: 30 Blocks: 2 IO Block: 4194304 regular file > Device: 2eh/46d Inode: 112989 Links: 1 > Access: (0644/-rw-r--r--) Uid: (28851/hannappj) Gid: ( 1000/ it) > Access: 2022-03-28 11:46:28.454807982 +0200 > Modify: 2022-03-28 11:46:28.454807982 +0200 > Change: 2022-03-28 11:46:28.454807982 +0200 > > > Shouldn't the immutability of the file include its change time? > > > > -- > Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 > > _______________________________________________ > gpfsug-discuss mailing list > gpfsug-discuss at gpfsug.org > https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fgpfsu > g.org%2Fmailman%2Flistinfo%2Fgpfsug-discuss_gpfsug.org&data=04%7C0 > 1%7Cp.ward%40nhm.ac.uk%7C2c7afbe81224404273cf08da10b63ad3%7C73a29c014e > 78437fa0d4c8553e1960c1%7C1%7C0%7C637840672748970653%7CUnknown%7CTWFpbG > Zsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0% > 3D%7C3000&sdata=I9bS8GSW5AeZbEg%2FQR2aCQd4KNd3lRmg2K1NJ3hQTk4%3D&a > mp;reserved=0 _______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at gpfsug.org https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fgpfsug.org%2Fmailman%2Flistinfo%2Fgpfsug-discuss_gpfsug.org&data=04%7C01%7Cp.ward%40nhm.ac.uk%7C2c7afbe81224404273cf08da10b63ad3%7C73a29c014e78437fa0d4c8553e1960c1%7C1%7C0%7C637840672749126883%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=O3t6BTddF3gL4DGlRAA9eweV8Vk%2BdwXj1We4GrGU%2BY8%3D&reserved=0 _______________________________________________ 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: From haizhu at us.ibm.com Tue Mar 29 14:49:54 2022 From: haizhu at us.ibm.com (Haizhu Liu) Date: Tue, 29 Mar 2022 13:49:54 +0000 Subject: [gpfsug-discuss] immutable file in an immutable folder can be touched In-Reply-To: References: <489645367.26974531.1648461050348.JavaMail.zimbra@desy.de> <1654236183.27138098.1648470302405.JavaMail.zimbra@desy.de> Message-ID: <5DF860B0-159A-4F9B-88DA-8DC171B45E4B@us.ibm.com> Yes, that?s correct. Atime, mtime and ctime can be changed, in addition, if the file is under an immutable fileset, mtime and ctime can be changed, atime is overloaded with expiration time. From: on behalf of "scale at us.ibm.com" Date: Tuesday, March 29, 2022 at 8:57 AM To: gpfsug main discussion list Cc: gpfsug-discuss , "juergen.hannappel at desy.de" , "p.ward at nhm.ac.uk" , Haizhu Liu Subject: Re: [EXTERNAL] Re: [gpfsug-discuss] immutable file in an immutable folder can be touched From design docs can see that Spectrum scale allows changing of timestamps for immutable files. + Haizhu to confirm this as well. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479. If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. [Inactive hide details for "Paul Ward" ---28-03-2022 06.56.04 PM---Hi J?rgen, We noticed this behaviour when we were trying to t]"Paul Ward" ---28-03-2022 06.56.04 PM---Hi J?rgen, We noticed this behaviour when we were trying to test immutability on our newly installed From: "Paul Ward" To: "gpfsug main discussion list" Date: 28-03-2022 06.56 PM Subject: [EXTERNAL] Re: [gpfsug-discuss] immutable file in an immutable folder can be touched Sent by: "gpfsug-discuss" ________________________________ Hi J?rgen, We noticed this behaviour when we were trying to test immutability on our newly installed solution. We tried using touch with a date in the past to test the expiry date. We noticed although touch changed the timestamp, it didn't change wherever the policy engine checked. We found a work around for our testing, so I think we accepted it as a 'feature'. I can't find a support ticket, so I am assuming we didn't report it. Kindest regards, Paul Paul Ward TS Infrastructure Architect Natural History Museum T: 02079426450 E: p.ward at nhm.ac.uk -----Original Message----- From: gpfsug-discuss On Behalf Of Hannappel, Juergen Sent: 28 March 2022 13:25 To: gpfsug-discuss Subject: Re: [gpfsug-discuss] immutable file in an immutable folder can be touched ... if I try a similar action e.g on ext4 where I can use the posix way with ioctl(fd, FS_IOC_GETFLAGS, &flags) flags |= FS_IMMUTABLE_FL; ioctl(fd, FS_IOC_SETFLAGS, &flags) the touch fails and the mtime remains unchanged.... ----- Original Message ----- > From: "Juergen Hannappel" > To: "gpfsug main discussion list" > Sent: Monday, 28 March, 2022 11:50:50 > Subject: [gpfsug-discuss] immutable file in an immutable folder can be > touched > Hi, > I have an immutable file in an immutable folder: > > mmchattr -i yes mutabilityTest/file > mmchattr -i yes mutabilityTest > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:45 file > > mmlsattr -L mutabilityTest mutabilityTest/file | grep immu > immutable: yes > immutable: yes > > > Now i do a touch: > touch mutabilityTest/file > > no error, and the modification time is changed: > ls -la mutabilityTest > total 18 > drwxr-xr-x 2 hannappj it 4096 Mar 28 11:45 . > drwxr-xr-x 7 hannappj it 8192 Mar 28 11:45 .. > -rw-r--r-- 1 hannappj it 30 Mar 28 11:46 file > > stat mutabilityTest/file > File: 'mutabilityTest/file' > Size: 30 Blocks: 2 IO Block: 4194304 regular file > Device: 2eh/46d Inode: 112989 Links: 1 > Access: (0644/-rw-r--r--) Uid: (28851/hannappj) Gid: ( 1000/ it) > Access: 2022-03-28 11:46:28.454807982 +0200 > Modify: 2022-03-28 11:46:28.454807982 +0200 > Change: 2022-03-28 11:46:28.454807982 +0200 > > > Shouldn't the immutability of the file include its change time? > > > > -- > Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 > > _______________________________________________ > gpfsug-discuss mailing list > gpfsug-discuss at gpfsug.org > https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fgpfsu > g.org%2Fmailman%2Flistinfo%2Fgpfsug-discuss_gpfsug.org&data=04%7C0 > 1%7Cp.ward%40nhm.ac.uk%7C2c7afbe81224404273cf08da10b63ad3%7C73a29c014e > 78437fa0d4c8553e1960c1%7C1%7C0%7C637840672748970653%7CUnknown%7CTWFpbG > Zsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0% > 3D%7C3000&sdata=I9bS8GSW5AeZbEg%2FQR2aCQd4KNd3lRmg2K1NJ3hQTk4%3D&a > mp;reserved=0 _______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at gpfsug.org https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fgpfsug.org%2Fmailman%2Flistinfo%2Fgpfsug-discuss_gpfsug.org&data=04%7C01%7Cp.ward%40nhm.ac.uk%7C2c7afbe81224404273cf08da10b63ad3%7C73a29c014e78437fa0d4c8553e1960c1%7C1%7C0%7C637840672749126883%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&sdata=O3t6BTddF3gL4DGlRAA9eweV8Vk%2BdwXj1We4GrGU%2BY8%3D&reserved=0 _______________________________________________ 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: image001.gif Type: image/gif Size: 106 bytes Desc: image001.gif URL: From scale at us.ibm.com Wed Mar 30 14:46:47 2022 From: scale at us.ibm.com (IBM Spectrum Scale) Date: Wed, 30 Mar 2022 19:16:47 +0530 Subject: [gpfsug-discuss] Meaning of new fields in Watchfolder output In-Reply-To: <1471074893.22787165.1647866259731.JavaMail.zimbra@desy.de> References: <1471074893.22787165.1647866259731.JavaMail.zimbra@desy.de> Message-ID: Hi Jake, Can you please look at the below WF related query. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479. If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. From: "Hannappel, Juergen" To: "gpfsug main discussion list" Date: 21-03-2022 06.09 PM Subject: [EXTERNAL] [gpfsug-discuss] Meaning of new fields in Watchfolder output Sent by: "gpfsug-discuss" Hi, for a test I read from a file with dd: dd if=someFile bs=64k of=/dev/null This will do 2 reads with 64k bytes, one read with 24053 and one final read with 0 bytes. I now check the WF json output, looking for the new ReadOffset and bytesRead fields I get: kafkacat -b my-broker -t test1-watch | while read mist; do echo $mist | python -m json.tool | grep -i read ; done "bytesRead": "0", "minReadOffset": "9223372036854775807", "maxReadOffset": "0", That is the open()... "bytesRead": "65536", "minReadOffset": "0", "maxReadOffset": "65535", That is the first read().... "bytesRead": "131072", "minReadOffset": "0", "maxReadOffset": "131071", WHo reads 2x64k bytes from the beginning? Is the the accumulated read data? "bytesRead": "155125", "minReadOffset": "0", "maxReadOffset": "155124", And again, now it looks as if in one event the entire file is read? The documentation ( https://www.ibm.com/docs/en/spectrum-scale/5.1.3?topic=folder-json-attributes-in-clustered-watch ) doesn't explain this.... -- Dr. J?rgen Hannappel DESY/IT Tel. : +49 40 8998-4616 _______________________________________________ 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: From scale at us.ibm.com Wed Mar 30 14:51:36 2022 From: scale at us.ibm.com (IBM Spectrum Scale) Date: Wed, 30 Mar 2022 19:21:36 +0530 Subject: [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule In-Reply-To: References: Message-ID: Hi Diane, Can you please look at the below policy related query. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479. If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. From: "shao feng" To: "gpfsug main discussion list" Date: 28-03-2022 03.21 PM Subject: [EXTERNAL] [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule Sent by: "gpfsug-discuss" Hello, What is the default value of SIZE in EXTERNAL POOL in filesystem policy? The document did not mention that, but I found it is not infinity if not specified. Thank you! SIZE?sum-number Is an optional clause of the?EXTERNAL POOL?and?EXTERNAL LIST?rules. sum-number?limits the total number of bytes in all of the files named in each list of files passed to your EXEC 'script'. If a single file is larger than?sum-number, it is passed to your EXEC 'script' as the only entry in a??singleton??file list. Specify?sum-number?as a numeric constant or a floating-point value. Note:?The value of?sum-number?is in kilobytes. https://www.ibm.com/docs/en/spectrum-scale/5.1.2?topic=rules-policy-terms _______________________________________________ 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: From scale at us.ibm.com Wed Mar 30 15:02:20 2022 From: scale at us.ibm.com (IBM Spectrum Scale) Date: Wed, 30 Mar 2022 19:32:20 +0530 Subject: [gpfsug-discuss] notification when Spectrum Archival EE finish migrating/recall for a file In-Reply-To: References: Message-ID: I think this can be answered by the IBM Spectrum Archive team and should go to a mailing list or discussion channel where they are involved. @Lyle: Do you know anyone who can answer this from Scale side. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479. If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. From: "shao feng" To: "gpfsug main discussion list" Date: 29-03-2022 11.13 AM Subject: [EXTERNAL] [gpfsug-discuss] notification when Spectrum Archival EE finish migrating/recall for a file Sent by: "gpfsug-discuss" Hello, Not sure if this is the right place to ask about Spectrum Archival EE. In a GPFS+LTFS EE configuration, is there any mechanism to get notification from Spectrum Archival EE when it finishes a migrating/recall for a file, especially a transparent recall? Thank you!_______________________________________________ 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: From lgayne at us.ibm.com Wed Mar 30 15:10:51 2022 From: lgayne at us.ibm.com (Lyle Gayne) Date: Wed, 30 Mar 2022 14:10:51 +0000 Subject: [gpfsug-discuss] notification when Spectrum Archival EE finish migrating/recall for a file In-Reply-To: References: Message-ID: I guess this should start with Mark Hill (and Khanh), from Spectrum Archive team. Lyle ________________________________ From: gpfsug-discuss on behalf of scale at us.ibm.com Sent: Wednesday, March 30, 2022 10:02 AM To: gpfsug main discussion list Cc: gpfsug-discuss Subject: [EXTERNAL] Re: [gpfsug-discuss] notification when Spectrum Archival EE finish migrating/recall for a file I think this can be answered by the IBM Spectrum Archive team and should go to a mailing list or discussion channel where they are involved. @Lyle: Do you know anyone who can answer this from Scale side. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479. If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. [Inactive hide details for "shao feng" ---29-03-2022 11.13.11 AM---Hello, Not sure if this is the right place to ask about Spect]"shao feng" ---29-03-2022 11.13.11 AM---Hello, Not sure if this is the right place to ask about Spectrum Archival EE. From: "shao feng" To: "gpfsug main discussion list" Date: 29-03-2022 11.13 AM Subject: [EXTERNAL] [gpfsug-discuss] notification when Spectrum Archival EE finish migrating/recall for a file Sent by: "gpfsug-discuss" ________________________________ Hello, Not sure if this is the right place to ask about Spectrum Archival EE. In a GPFS+LTFS EE configuration, is there any mechanism to get notification from Spectrum Archival EE when it finishes a migrating/recall for a file, especially a transparent recall? Thank you!_______________________________________________ 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: graycol.gif URL: From scale at us.ibm.com Wed Mar 30 23:41:33 2022 From: scale at us.ibm.com (IBM Spectrum Scale) Date: Wed, 30 Mar 2022 18:41:33 -0400 Subject: [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule In-Reply-To: References: Message-ID: Hi shao feng, It is controlled by -B option. -B MaxFiles Specifies how many files are passed for each invocation of the EXEC script. The default value is 100. If the number of files exceeds the value specified for MaxFiles, mmapplypolicy invokes the external program multiple times. For more information about file list records, refer to the IBM Spectrum Scale: Administration Guide. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. From: IBM Spectrum Scale/Poughkeepsie/IBM at IBMUS To: "gpfsug main discussion list" , Diane Chung/Poughkeepsie/IBM at IBMMail Cc: "gpfsug-discuss" Date: 03/30/2022 09:53 AM Subject: [EXTERNAL] Re: [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule Sent by: "gpfsug-discuss" Hi Diane, Can you please look at the below policy related query. Regards, The Spectrum Scale (GPFS) team ------------------------------------------------------------------------------------------------------------------ If you feel that your question can benefit other users of Spectrum Scale (GPFS), then please post it to the public IBM developerWroks Forum at https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479 . If your query concerns a potential software error in Spectrum Scale (GPFS) and you have an IBM software maintenance contract please contact 1-800-237-5511 in the United States or your local IBM Service Center in other countries. The forum is informally monitored as time permits and should not be used for priority messages to the Spectrum Scale (GPFS) team. Inactive hide details for "shao feng" ---28-03-2022 03.21.39 PM---Hello, What is the default value of SIZE in EXTERNAL POOL in "shao feng" ---28-03-2022 03.21.39 PM---Hello, What is the default value of SIZE in EXTERNAL POOL in filesystem policy? From: "shao feng" To: "gpfsug main discussion list" Date: 28-03-2022 03.21 PM Subject: [EXTERNAL] [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule Sent by: "gpfsug-discuss" Hello, What is the default value of SIZE in EXTERNAL POOL in filesystem policy? The document did not mention that, but I found it is not infinity if not specified. Thank you! SIZE?sum-number Is an optional clause of the?EXTERNAL POOL?and?EXTERNAL LIST?rules. sum-number?limits the total number of bytes in all of the files named in each list of files passed to your EXEC 'script'. If a single file is larger than?sum-number, it is passed to your EXEC 'script' as the only entry in a ?singleton??file list. Specify?sum-number?as a numeric constant or a floating-point value. Note:?The value of?sum-number?is in kilobytes. https://www.ibm.com/docs/en/spectrum-scale/5.1.2?topic=rules-policy-terms _______________________________________________ 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 -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: From anacreo at gmail.com Thu Mar 31 00:39:24 2022 From: anacreo at gmail.com (Alec) Date: Wed, 30 Mar 2022 16:39:24 -0700 Subject: [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule In-Reply-To: References: Message-ID: I'd like to offer a dissenting opinion... I believe this is a way to limit the number of actual bytes that any execution must work on.... As in only send 500gb worth of files to each invocation. Whereas the -B is the actual number of files to be passed to each invocation. I would think that size has no default limit as I've had a single invocation stuck with 30TB of data in its 100 file grouping, lol. I however use a different mechanism to divy up my files because I need to worry about my backup streams getting choked up, and I want to take a cross section of each directory on different nights... I call mmapplypolicy with -M shares=, so let's say I increase my number by 1 every day, starting at 0, over the course of a week... In my policy I have this line: WHERE MOD(INODE,6)<=shares So then I work on 1/7th of the files in my file system and cumulatively pick up any INODES until I've hit all of the files... I could pick just the matching segment by saying = instead of <=. This is happening at the file selection phase, so the application of -B is after this selection, as my files are quite huge, I tend to use -B 1. Alec On Wed, Mar 30, 2022 at 3:44 PM IBM Spectrum Scale wrote: > Hi shao feng, > > It is controlled by -B option. > > *-B* *MaxFiles* > Specifies how many files are passed for each invocation > of the EXEC script. The default value is 100. > > If the number of files exceeds the value specified for > MaxFiles, *mmapplypolicy* invokes the external > program multiple times. > > For more information about file list records, refer to > the IBM Spectrum Scale: Administration Guide. > > Regards, The Spectrum Scale (GPFS) team > > > ------------------------------------------------------------------------------------------------------------------ > If your query concerns a potential software error in Spectrum Scale (GPFS) > and you have an IBM software maintenance contract please contact > 1-800-237-5511 in the United States or your local IBM Service Center in > other countries. > > [image: Inactive hide details for IBM Spectrum Scale---03/30/2022 09:53:51 > AM---Hi Diane, Can you please look at the below policy relat]IBM Spectrum > Scale---03/30/2022 09:53:51 AM---Hi Diane, Can you please look at the below > policy related query. > > From: IBM Spectrum Scale/Poughkeepsie/IBM at IBMUS > To: "gpfsug main discussion list" , Diane > Chung/Poughkeepsie/IBM at IBMMail > Cc: "gpfsug-discuss" > Date: 03/30/2022 09:53 AM > Subject: [EXTERNAL] Re: [gpfsug-discuss] default value of SIZE in > EXTERNAL POOL and EXTERNAL LIST rule > Sent by: "gpfsug-discuss" > ------------------------------ > > > > Hi Diane, > > Can you please look at the below policy related query. > > Regards, The Spectrum Scale (GPFS) team > > > ------------------------------------------------------------------------------------------------------------------ > If you feel that your question can benefit other users of Spectrum Scale > (GPFS), then please post it to the public IBM developerWroks Forum at > *https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479* > . > > > If your query concerns a potential software error in Spectrum Scale (GPFS) > and you have an IBM software maintenance contract please contact > 1-800-237-5511 in the United States or your local IBM Service Center in > other countries. > > The forum is informally monitored as time permits and should not be used > for priority messages to the Spectrum Scale (GPFS) team. > > [image: Inactive hide details for "shao feng" ---28-03-2022 03.21.39 > PM---Hello, What is the default value of SIZE in EXTERNAL POOL in]"shao > feng" ---28-03-2022 03.21.39 PM---Hello, What is the default value of SIZE > in EXTERNAL POOL in filesystem policy? > > From: "shao feng" > To: "gpfsug main discussion list" > Date: 28-03-2022 03.21 PM > Subject: [EXTERNAL] [gpfsug-discuss] default value of SIZE in EXTERNAL > POOL and EXTERNAL LIST rule > Sent by: "gpfsug-discuss" > ------------------------------ > > > > Hello, > > What is the default value of SIZE in EXTERNAL POOL in filesystem policy? > > The document did not mention that, but I found it is not infinity if not > specified. > > Thank you! > > *SIZE **sum-number* > Is an optional clause of the *EXTERNAL POOL* and *EXTERNAL LIST* rules. > *sum-number* limits the total number of bytes in all of the files named > in each list of files passed to your EXEC 'script'. If a single file is > larger than *sum-number*, it is passed to your EXEC 'script' as the only > entry in a ?singleton? file list. > > Specify *sum-number* as a numeric constant or a floating-point value. > > *Note:* The value of *sum-number* is in kilobytes. > *https://www.ibm.com/docs/en/spectrum-scale/5.1.2?topic=rules-policy-terms* > > _______________________________________________ > 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 > -------------- next part -------------- An HTML attachment was scrubbed... URL: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: From shaof777 at gmail.com Thu Mar 31 08:53:07 2022 From: shaof777 at gmail.com (shao feng) Date: Thu, 31 Mar 2022 15:53:07 +0800 Subject: [gpfsug-discuss] default value of SIZE in EXTERNAL POOL and EXTERNAL LIST rule In-Reply-To: References: Message-ID: Thanks Alec! On Thu, Mar 31, 2022 at 7:41 AM Alec wrote: > I'd like to offer a dissenting opinion... I believe this is a way to > limit the number of actual bytes that any execution must work on.... As in > only send 500gb worth of files to each invocation. Whereas the -B is the > actual number of files to be passed to each invocation. I would think that > size has no default limit as I've had a single invocation stuck with 30TB > of data in its 100 file grouping, lol. > > I however use a different mechanism to divy up my files because I need to > worry about my backup streams getting choked up, and I want to take a cross > section of each directory on different nights... > > I call mmapplypolicy with -M shares=, so let's say > I increase my number by 1 every day, starting at 0, over the course of a > week... > > In my policy I have this line: > WHERE MOD(INODE,6)<=shares > > So then I work on 1/7th of the files in my file system and cumulatively > pick up any INODES until I've hit all of the files... I could pick just the > matching segment by saying = instead of <=. > > This is happening at the file selection phase, so the application of -B is > after this selection, as my files are quite huge, I tend to use -B 1. > > Alec > > On Wed, Mar 30, 2022 at 3:44 PM IBM Spectrum Scale > wrote: > >> Hi shao feng, >> >> It is controlled by -B option. >> >> *-B* *MaxFiles* >> Specifies how many files are passed for each invocation >> of the EXEC script. The default value is 100. >> >> If the number of files exceeds the value specified for >> MaxFiles, *mmapplypolicy* invokes the external >> program multiple times. >> >> For more information about file list records, refer to >> the IBM Spectrum Scale: Administration Guide. >> >> Regards, The Spectrum Scale (GPFS) team >> >> >> ------------------------------------------------------------------------------------------------------------------ >> If your query concerns a potential software error in Spectrum Scale >> (GPFS) and you have an IBM software maintenance contract please contact >> 1-800-237-5511 in the United States or your local IBM Service Center in >> other countries. >> >> [image: Inactive hide details for IBM Spectrum Scale---03/30/2022 >> 09:53:51 AM---Hi Diane, Can you please look at the below policy relat]IBM >> Spectrum Scale---03/30/2022 09:53:51 AM---Hi Diane, Can you please look at >> the below policy related query. >> >> From: IBM Spectrum Scale/Poughkeepsie/IBM at IBMUS >> To: "gpfsug main discussion list" , Diane >> Chung/Poughkeepsie/IBM at IBMMail >> Cc: "gpfsug-discuss" >> Date: 03/30/2022 09:53 AM >> Subject: [EXTERNAL] Re: [gpfsug-discuss] default value of SIZE in >> EXTERNAL POOL and EXTERNAL LIST rule >> Sent by: "gpfsug-discuss" >> ------------------------------ >> >> >> >> Hi Diane, >> >> Can you please look at the below policy related query. >> >> Regards, The Spectrum Scale (GPFS) team >> >> >> ------------------------------------------------------------------------------------------------------------------ >> If you feel that your question can benefit other users of Spectrum Scale >> (GPFS), then please post it to the public IBM developerWroks Forum at >> *https://www.ibm.com/developerworks/community/forums/html/forum?id=11111111-0000-0000-0000-000000000479* >> . >> >> >> If your query concerns a potential software error in Spectrum Scale >> (GPFS) and you have an IBM software maintenance contract please contact >> 1-800-237-5511 in the United States or your local IBM Service Center in >> other countries. >> >> The forum is informally monitored as time permits and should not be used >> for priority messages to the Spectrum Scale (GPFS) team. >> >> [image: Inactive hide details for "shao feng" ---28-03-2022 03.21.39 >> PM---Hello, What is the default value of SIZE in EXTERNAL POOL in]"shao >> feng" ---28-03-2022 03.21.39 PM---Hello, What is the default value of SIZE >> in EXTERNAL POOL in filesystem policy? >> >> From: "shao feng" >> To: "gpfsug main discussion list" >> Date: 28-03-2022 03.21 PM >> Subject: [EXTERNAL] [gpfsug-discuss] default value of SIZE in EXTERNAL >> POOL and EXTERNAL LIST rule >> Sent by: "gpfsug-discuss" >> ------------------------------ >> >> >> >> Hello, >> >> What is the default value of SIZE in EXTERNAL POOL in filesystem policy? >> >> The document did not mention that, but I found it is not infinity if not >> specified. >> >> Thank you! >> >> *SIZE **sum-number* >> Is an optional clause of the *EXTERNAL POOL* and *EXTERNAL LIST* rules. >> *sum-number* limits the total number of bytes in all of the files named >> in each list of files passed to your EXEC 'script'. If a single file is >> larger than *sum-number*, it is passed to your EXEC 'script' as the only >> entry in a ?singleton? file list. >> >> Specify *sum-number* as a numeric constant or a floating-point value. >> >> *Note:* The value of *sum-number* is in kilobytes. >> *https://www.ibm.com/docs/en/spectrum-scale/5.1.2?topic=rules-policy-terms* >> >> _______________________________________________ >> 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 >> > _______________________________________________ > 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: -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: