Dear Eric, thanks a lot for this information. And what about the gpfs_vfs metric group? What is the difference beteween for example
“gpfs_fis_read_calls" and “gpfs_vfs_read” ? Again I see the second one being tipically higher than the first one. In addition gpfs_vfs_read is not related to a specific file system... [root@ela5 ~]# mmperfmon query gpfs_fis_read_calls -n1 -b 60 Legend: 1: ela5.cscs.ch<http://ela5.cscs.ch>|GPFSFilesystemAPI|durand.cscs.ch<http://durand.cscs.ch>|store|gpfs_fis_read_calls 2: ela5.cscs.ch<http://ela5.cscs.ch>|GPFSFilesystemAPI|por.login.cscs.ch<http://por.login.cscs.ch>|apps|gpfs_fis_read_calls 3: ela5.cscs.ch<http://ela5.cscs.ch>|GPFSFilesystemAPI|por.login.cscs.ch<http://por.login.cscs.ch>|project|gpfs_fis_read_calls 4: ela5.cscs.ch<http://ela5.cscs.ch>|GPFSFilesystemAPI|por.login.cscs.ch<http://por.login.cscs.ch>|users|gpfs_fis_read_calls Row Timestamp gpfs_fis_read_calls gpfs_fis_read_calls gpfs_fis_read_calls gpfs_fis_read_calls 1 2018-07-03-10:03:00 0 0 7274 0 [root@ela5 ~]# mmperfmon query gpfs_vfs_read -n1 -b 60 Legend: 1: ela5.cscs.ch<http://ela5.cscs.ch>|GPFSVFS|gpfs_vfs_read Row Timestamp gpfs_vfs_read 1 2018-07-03-10:03:00 45123 Cheers, Giuseppe *********************************************************************** Giuseppe Lo Re CSCS - Swiss National Supercomputing Center Via Trevano 131 CH-6900 Lugano (TI) Tel: + 41 (0)91 610 8225 Switzerland Email: [email protected]<mailto:[email protected]> *********************************************************************** Hello Giuseppe, Following was my attempt to answer a similar question some months ago. When reading about the different viewpoints of the Zimon sensors, please note that gpfs_fis_bytes_read is a metric provided by the GPFSFileSystemAPI sensor, while gpfs_fs_bytes_read is a metric provided by the GPFSFileSystem sensor. Therefore, gpfs_fis_bytes_read reflects application reads, while gpfs_fs_bytes_read reflects NSD reads. The GPFSFileSystemAPI and GPFSNodeAPI sensor metrics are from the point of view of "applications" in the sense that they provide stats about I/O requests made to files in GPFS file systems from user level applications using POSIX interfaces like open(), close(), read(), write(), etc. This is in contrast to similarly named sensors without the "API" suffix, like GPFSFilesystem and GPFSNode. Those sensors provide stats about I/O requests made by the GPFS code to NSDs (disks) making up GPFS file systems. The relationship between application I/O and disk I/O might or might not be obvious. Consider some examples. An application that starts sequentially reading a file might, at least initially, cause more disk I/O than expected because GPFS has decided to prefetch data. An application write() might not immediately cause the writing of disk blocks, due to the operation of the pagepool. Ultimately, application write()s might cause twice as much data written to disk due to the replication factor of the file system. Application I/O concerns itself with user data; disk I/O might have to occur to handle the user data and associated file system metadata (like inodes and indirect blocks). The difference between GPFSFileSystemAPI and GPFSNodeAPI: GPFSFileSystemAPI reports stats for application I/O per filesystem per node; GPFSNodeAPI reports application I/O stats per node. Similarly, GPFSFilesystem reports stats for disk I/O per filesystem per node; GPFSNode reports disk I/O stats per node. Eric M. Agar [email protected]<mailto:[email protected]> IBM Spectrum Scale Level 2 Software Defined Infrastructure, IBM Systems From: Kristy Kallback-Rose <[email protected]> To: gpfsug main discussion list <[email protected]> Date: 07/02/2018 10:06 AM Subject: Re: [gpfsug-discuss] Zimon metrics details Sent by: [email protected] +1 Would love to see more detailed descriptions on Zimon metrics. Sent from my iPhone On Jul 2, 2018, at 6:50 AM, Lo Re Giuseppe <[email protected]> wrote: Hi everybody, I am extracting the Zimon performance data and uploading them to our elasticsearch cluster. Now that I have the mechanism in place it?s time to understand what I am actually uploading ;) Maybe this has been already asked.. where can I find a (as much as possible) detailed explaination of the different Zimon metrics? The SS probelm determination guide doens?t spend more than half a line for each. In particular I would like to understand the difference between these ones: - gpfs_fs_bytes_read - gpfs_fis_bytes_read The second gives tipically higher values than the first one. Thanks for any hit. Regards, Giuseppe *********************************************************************** Giuseppe Lo Re CSCS - Swiss National Supercomputing Center Via Trevano 131 CH-6900 Lugano (TI) Tel: + 41 (0)91 610 8225 Switzerland Email: [email protected] *********************************************************************** _______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at spectrumscale.org http://gpfsug.org/mailman/listinfo/gpfsug-discuss _______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at spectrumscale.org http://gpfsug.org/mailman/listinfo/gpfsug-discuss -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://gpfsug.org/pipermail/gpfsug-discuss/attachments/20180702/3aa08500/attachment.html> -------------- next part -------------- A non-text attachment was scrubbed... Name: graycol.gif Type: image/gif Size: 105 bytes Desc: not available URL: <http://gpfsug.org/pipermail/gpfsug-discuss/attachments/20180702/3aa08500/attachment.gif> ------------------------------ _______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at spectrumscale.org http://gpfsug.org/mailman/listinfo/gpfsug-discuss End of gpfsug-discuss Digest, Vol 78, Issue 6 *********************************************
_______________________________________________ gpfsug-discuss mailing list gpfsug-discuss at spectrumscale.org http://gpfsug.org/mailman/listinfo/gpfsug-discuss
