Yes, each RPC will increment these stats counters by one. Traditional "IOPS" are measured with 4KB read or write, but in this case the IO sizes are variable.
Also, the client may aggregate multiple disjoint writes into a single RPC. This can be seen in the osd-ldiskfs.*.brw_stats as "discontiguous pages" so this might be considered multiple "IOs" in a single RPC. Cheers, Andreas On Jan 23, 2023, at 09:31, Passerini Marco <marco.passer...@cscs.ch> wrote: I'd like to monitor the IOPS on the Lustre OSTs. I have stats like this: [root@xxx04 ~]# lctl get_param obdfilter.xxx-OST0000.stats obdfilter.xxx-OST0000.stats= snapshot_time 348287.096066602 secs.nsecs start_time 0.000000000 secs.nsecs elapsed_time 348287.096066602 secs.nsecs read_bytes 3075 samples [bytes] 0 1134592 2891776 2568826650624 write_bytes 1312266 samples [bytes] 1 4194304 5424381521966 4303559271585613940 read 3075 samples [usecs] 0 489 31040 3417458 write 1312266 samples [usecs] 1 1630262 6193336309 3686004830368845 setattr 20373 samples [usecs] 1 61 133314 1090612 punch 4600 samples [usecs] 3 65 51155 732959 sync 4 samples [usecs] 443 997 2853 2250847 destroy 30777 samples [usecs] 11 42634 20978596 33571893182 create 993 samples [usecs] 1 29995 534579 1518818913 statfs 135519 samples [usecs] 0 24 610182 4231650 get_info 108 samples [usecs] 1 3092 6218 17971060 set_info 10047 samples [usecs] 1 22 83418 770166 From the docs https://wiki.lustre.org/Lustre_Monitoring_and_Statistics_Guide I see: """ For read_bytes and write_bytes: First number = number of times (samples) the OST has handled a read or write. """ I guess this can be considered as OST IOPS? Regards, Marco Passerini _______________________________________________ lustre-discuss mailing list lustre-discuss@lists.lustre.org http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org
_______________________________________________ lustre-discuss mailing list lustre-discuss@lists.lustre.org http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org