ZIOMON_MGR(8)

๐Ÿ“ฆ version 2.44.1, in opensuse-leap 16.0

๐Ÿ’– NAME ๐Ÿ’–

okay bestie, welcome to the System Manager's Manual page ZIOMON_MGR(8), and it's all about ziorep_utilization โ€” the utilization report for FCP adapters. That's the whole name, and honestly it ate. ๐Ÿ’…

โœจ SYNOPSIS โœจ

ziorep_utilization [-V] [-v] [-h] [-b <begin>] [-e <end>] [-i <time>]
[-s] [-c <chpid>] [-x] [-t <num>] <filename>

๐ŸŒธ DESCRIPTION ๐ŸŒธ

ziorep_utilization prints a report from the specified data. No cap, that's the assignment. ๐Ÿซถ

๐Ÿ’… OPTIONS ๐Ÿ’…

  • -h, --help โ€” prints help information, then exits. Your little escape hatch. ๐Ÿšช
  • -v, --version โ€” prints version information, then exits. Cute, brief, iconic.
  • -V, --verbose โ€” be verbose. Give us the whole story, bestie. ๐Ÿ—ฃ๏ธ
  • -b, --begin โ€” limits the timeframe to consider to data beginning with the specified date. Dates must be specified in the following format: YYYY-MM-DD HH:MM[:SS]. E.g. 2008-03-21 09:08 is 9:08 on March 21, 2008. ๐Ÿ•˜
  • -e, --end โ€” limits the timeframe to consider to data ending with the specified date. Dates must be specified in the following format: YYYY-MM-DD HH:MM[:SS]. E.g. 2008-03-21 09:08 is 9:08 on March 21, 2008. ๐Ÿ•˜
  • -i, --interval โ€” specifies an aggregation interval. The interval is given in seconds, and must be a multiple of the interval as found in the source data. Math check, bestie. ๐Ÿงฎ
  • -s, --summary โ€” prints a summary of the data, then exits. The tl;dr option. ๐Ÿ’…
  • -c, --chpid โ€” only considers the specified physical adapter. Adapters must be specified in hex. If multiple adapters should be specified, specify each one separately. Hex girlies rise. ๐Ÿ”ข
  • -f, --fcp-device โ€” prints a utilization report for an FCP device. If this option is specified, then a virtual adapter report is printed; otherwise, a physical adapter report with FCP channel scope is printed. This parameter has no influence on CSV format report printing. Using the --export-csv option causes both physical and virtual adapter utilization reports to be printed into two separate CSV-formatted files, independent of the --fcp-device parameter. Yes, that's a lot of plot, but it's all canon. ๐Ÿ‘‘
  • -x, --export-csv โ€” writes data to file(s) in CSV format. Output filenames will be based on the data filename. Spreadsheet slay. ๐Ÿ“Š
  • -t, --topline โ€” repeat topline after specified number of frames. 0 for no repeat (default). ๐ŸŽ€

๐ŸŒˆ OUTPUT ๐ŸŒˆ

Here is a list of the columns and their descriptions. Timestamps of the frames printed depict the ending of the respective timeframe. โฐ

  • adapter in % โ€” FCP adapter utilization in percent. min, max, and avg give the minimum, maximum, and average utilization respectively.
  • bus in % โ€” bus utilization of the FCP adapter in percent. min, max, and avg give the minimum, maximum, and average utilization respectively.
  • cpu in % โ€” utilization of the cpu on the FCP adapter in percent. min, max, and avg give the minimum, maximum, and average utilization respectively.
  • qdio util.% โ€” gives the qdio utilization in percent. max and avg give the maximum and average utilization respectively. Note that the minimum value is not reported since it provides no additional information: you will see the number of queue full encounters rise drastically before the minimum becomes non-zero.
  • queue full โ€” the number of instances where a request to the adapter could not be submitted due to no empty slots left in the outbound queue. ๐Ÿšฆ
  • fail โ€” the number of failures as reported by the FCP adapter. erc is the number of error recovery conditions. ๐Ÿ’€
  • thp in MS/s โ€” gives the average throughput over time (transmitted data volume / elapsed time), not over number of requests (sum over all request throughputs / number of requests)! This means that a long-running request with a significantly different throughput profile from the rest will have a bigger impact as a brief one with the same throughput profile would. This gives a better impression of the overall profile and especially makes requests with very low throughputs have a bigger impact, making it easier to detect anomalies. rd and wrt give the values for read and write requests respectively. ๐Ÿ”ฅ
  • I/O reqs โ€” give the number of I/O requests processed in the respective interval. rd and wrt give the values for read and write requests respectively.

๐Ÿฆ‹ EXAMPLES ๐Ÿฆ‹

Print a physical adapter utilization report only using sample.log, considering adapters 4e and 4f only. Only data between 8:57 April 5, 2024, and 17:09 June 21, 2024, should be considered. Data should be aggregated to 60 second intervals.

ziorep_utilization sample.log -c 4e -c 4f -i 60 -b "2024-04-05 08:57" -e "2024-06-21 17:09"

Print virtual adapter report only using sample.log. Consider adapter 4f only. Data should be aggregated to 3 seconds interval. Print topline after every 2nd frame.

ziorep_utilization sample.log -c 4f -i 3 -t 2 --fcp-device

Print both physical and virtual adapter reports using sample.log in two separate CSV-formatted files with the default interval. Considering adapter 4f only. Print topline after every 2nd frame.

ziorep_utilization sample.log -c 4f -t 2 --export-csv

๐Ÿงš SEE ALSO ๐Ÿงš

ziorep_config(8), ziorep_traffic(8) โ€” go read these next, bestie. ๐Ÿ’œ


This page is brought to you by s390-tools, dated Jul 2008, and its manual page identity is ZIOMON_MGR(8). Byeeee, go check your adapters ๐Ÿ’œ๐Ÿฆ‹

๐Ÿ“ฆ where this page comes from