Re: FICON channel utilization
Radoslaw I agree that you wouldn't do this in production, but it is a perfectly valid way to measure the throughput of a host channel. Besides fanning out through an 8Gb switch to multiple FICON blades or storage controllers, I would also suggest that you make sure the other port on the 8S channel card is not being used so that any shared paths and components do not affect your results. I always try to use only one CHPID per host card when I test in the HDS lab to minimize this sort of effect on measurement. Ron > > BTW: I'm going to connect the chpid to 8gbps switch and SFP and rerun the > test. Of course single channel attached CU is not intended to use in > production. > -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: INFO IBM-MAIN
Re: FICON channel utilization
W dniu 2012-03-07 16:52, Martin Packer pisze: Perhaps one would expect HMC and RMF to source from the same place. Tell me if I'm wrong, this not being my area. 1. I added an emoticon to my answer - that's becuase both sources showed 100%, although I really used HMC Activity Monitor. 2. HMC and RMF do differ sometimes, the difference is usually very small. I forgot details, but the difference does exist. BTW: I'm going to connect the chpid to 8gbps switch and SFP and rerun the test. Of course single channel attached CU is not intended to use in production. -- Radoslaw Skorupka Lodz, Poland -- Tre tej wiadomoci moe zawiera informacje prawnie chronione Banku przeznaczone wycznie do uytku subowego adresata. Odbiorc moe by jedynie jej adresat z wyczeniem dostpu osób trzecich. Jeeli nie jeste adresatem niniejszej wiadomoci lub pracownikiem upowanionym do jej przekazania adresatowi, informujemy, e jej rozpowszechnianie, kopiowanie, rozprowadzanie lub inne dziaanie o podobnym charakterze jest prawnie zabronione i moe by karalne. Jeeli otrzymae t wiadomo omykowo, prosimy niezwocznie zawiadomi nadawc wysyajc odpowied oraz trwale usun t wiadomo wczajc w to wszelkie jej kopie wydrukowane lub zapisane na dysku. This e-mail may contain legally privileged information of the Bank and is intended solely for business use of the addressee. This e-mail may only be received by the addressee and may not be disclosed to any third parties. If you are not the intended addressee of this e-mail or the employee authorised to forward it to the addressee, be advised that any dissemination, copying, distribution or any other similar activity is legally prohibited and may be punishable. If you received this e-mail by mistake please advise the sender immediately by using the reply facility in your e-mail software and delete permanently this e-mail including any copies of it either printed or saved to hard drive. BRE Bank SA, 00-950 Warszawa, ul. Senatorska 18, tel. +48 (22) 829 00 00, fax +48 (22) 829 00 33, www.brebank.pl, e-mail: i...@brebank.pl Sd Rejonowy dla m. st. Warszawy XII Wydzia Gospodarczy Krajowego Rejestru Sdowego, nr rejestru przedsibiorców KRS 025237, NIP: 526-021-50-88. Wedug stanu na dzie 01.01.2012 r. kapita zakadowy BRE Banku SA (w caoci wpacony) wynosi 168.410.984 zotych. -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: INFO IBM-MAIN
Re: FICON channel utilization
Perhaps one would expect HMC and RMF to source from the same place. Tell me if I'm wrong, this not being my area. Cheers, Martin Martin Packer, Mainframe Performance Consultant, zChampion Worldwide Banking Center of Excellence, IBM +44-7802-245-584 email: martin_pac...@uk.ibm.com Twitter / Facebook IDs: MartinPacker Blog: https://www.ibm.com/developerworks/mydeveloperworks/blogs/MartinPacker Unless stated otherwise above: IBM United Kingdom Limited - Registered in England and Wales with number 741598. Registered office: PO Box 41, North Harbour, Portsmouth, Hampshire PO6 3AU -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: INFO IBM-MAIN
Re: FICON channel utilization
Radoslaw, Would you be happier with this: "Actually the SAD display does not report channel utilization for FICON. It is showing you microprocessor busy on the host channel board." The blocksizes used by ADRDSSU will depend on the processing you requested. A physical DUMP will use a large data length, especially if you specify OPT(4), but a logical copy often calls a utility (REPRO, IEBCOPY) which will use a much smaller data length based on the blocking factor used by the dataset and the utility. I'm not saying that your results are incorrect or invalid, I simply find ADRDSSU not to be the most scientific of utilities for benchmarking. You may also want to check that the port(s) on the storage you are testing have not been saturated and causing a feedback effect on the host channel. I'd recommend that you fan out the single 8S channel to at least four different ports on four different storage FICON blades to mitigate usage on the storage end affecting your measurement. Ron > -Original Message- > From: IBM Mainframe Discussion List [mailto:IBM-MAIN@bama.ua.edu] On > Behalf Of R.S. > Sent: Wednesday, March 07, 2012 4:37 AM > To: IBM-MAIN@bama.ua.edu > Subject: Re: [IBM-MAIN] FICON channel utilization > > W dniu 2012-03-07 12:49, Ron Hawkins pisze: > > Radoslaw, > > > > Actually RMF does not report channel utilization for FICON. It is > > showing you microprocessor busy on the host channel board. > > Did I say RMF? :-) > I observed the utilisation on HMC. However AFAIK RMF showed similar data. > > > For the same MB/sec this metric will change depending on block size, > > data length and whether zHPF is used. > > It was non-TCW traffic, blocks were large. > > > -- > Radoslaw Skorupka > Lodz, Poland > > > -- > Tre tej wiadomoci moe zawiera informacje prawnie chronione Banku > przeznaczone wycznie do uytku subowego adresata. Odbiorc moe > by jedynie jej adresat z wyczeniem dostpu osób trzecich. Jeeli nie > jeste adresatem niniejszej wiadomoci lub pracownikiem upowanionym > do jej przekazania adresatowi, informujemy, e jej rozpowszechnianie, > kopiowanie, rozprowadzanie lub inne dziaanie o podobnym charakterze > jest prawnie zabronione i moe by karalne. Jeeli otrzymae t > wiadomo omykowo, prosimy niezwocznie zawiadomi nadawc > wysyajc odpowied oraz trwale usun t wiadomo wczajc w to > wszelkie jej kopie wydrukowane lub zapisane na dysku. > > This e-mail may contain legally privileged information of the Bank and is > intended solely for business use of the addressee. This e-mail may only be > received by the addressee and may not be disclosed to any third parties. If > you are not the intended addressee of this e-mail or the employee > authorised to forward it to the addressee, be advised that any dissemination, > copying, distribution or any other similar activity is legally prohibited and may > be punishable. If you received this e-mail by mistake please advise the > sender immediately by using the reply facility in your e-mail software and > delete permanently this e-mail including any copies of it either printed or > saved to hard drive. > > BRE Bank SA, 00-950 Warszawa, ul. Senatorska 18, tel. +48 (22) 829 00 00, fax > +48 (22) 829 00 33, www.brebank.pl, e-mail: i...@brebank.pl > Sd Rejonowy dla m. st. Warszawy XII Wydzia Gospodarczy Krajowego > Rejestru Sdowego, nr rejestru przedsibiorców KRS 025237, NIP: 526- > 021-50-88. > Wedug stanu na dzie 01.01.2012 r. kapita zakadowy BRE Banku SA (w > caoci wpacony) wynosi 168.410.984 zotych. > > -- > For IBM-MAIN subscribe / signoff / archive access instructions, > send email to lists...@bama.ua.edu with the message: INFO IBM-MAIN -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: INFO IBM-MAIN
Re: FICON channel utilization
W dniu 2012-03-07 12:49, Ron Hawkins pisze: Radoslaw, Actually RMF does not report channel utilization for FICON. It is showing you microprocessor busy on the host channel board. Did I say RMF? :-) I observed the utilisation on HMC. However AFAIK RMF showed similar data. For the same MB/sec this metric will change depending on block size, data length and whether zHPF is used. It was non-TCW traffic, blocks were large. -- Radoslaw Skorupka Lodz, Poland -- Tre tej wiadomoci moe zawiera informacje prawnie chronione Banku przeznaczone wycznie do uytku subowego adresata. Odbiorc moe by jedynie jej adresat z wyczeniem dostpu osób trzecich. Jeeli nie jeste adresatem niniejszej wiadomoci lub pracownikiem upowanionym do jej przekazania adresatowi, informujemy, e jej rozpowszechnianie, kopiowanie, rozprowadzanie lub inne dziaanie o podobnym charakterze jest prawnie zabronione i moe by karalne. Jeeli otrzymae t wiadomo omykowo, prosimy niezwocznie zawiadomi nadawc wysyajc odpowied oraz trwale usun t wiadomo wczajc w to wszelkie jej kopie wydrukowane lub zapisane na dysku. This e-mail may contain legally privileged information of the Bank and is intended solely for business use of the addressee. This e-mail may only be received by the addressee and may not be disclosed to any third parties. If you are not the intended addressee of this e-mail or the employee authorised to forward it to the addressee, be advised that any dissemination, copying, distribution or any other similar activity is legally prohibited and may be punishable. If you received this e-mail by mistake please advise the sender immediately by using the reply facility in your e-mail software and delete permanently this e-mail including any copies of it either printed or saved to hard drive. BRE Bank SA, 00-950 Warszawa, ul. Senatorska 18, tel. +48 (22) 829 00 00, fax +48 (22) 829 00 33, www.brebank.pl, e-mail: i...@brebank.pl Sd Rejonowy dla m. st. Warszawy XII Wydzia Gospodarczy Krajowego Rejestru Sdowego, nr rejestru przedsibiorców KRS 025237, NIP: 526-021-50-88. Wedug stanu na dzie 01.01.2012 r. kapita zakadowy BRE Banku SA (w caoci wpacony) wynosi 168.410.984 zotych. -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: INFO IBM-MAIN
Re: FICON channel utilization
Cathy's techpaper: IBM zEnterprise 196 and IBM zEnterprise 114 I/O and FICON Express8S Channel Performance (Cathy Cronin, Version 2, November 2011) (ZSW03196USEN01) http://public.dhe.ibm.com/common/ssi/ecm/en/zsw03196usen/ZSW03196USEN.PDF On Wed, Mar 7, 2012 at 12:49 PM, Ron Hawkins wrote: > Radoslaw, > > Actually RMF does not report channel utilization for FICON. It is showing > you microprocessor busy on the host channel board. > > For the same MB/sec this metric will change depending on block size, data > length and whether zHPF is used. > > You can quite easily saturate a host channel MP with small blocksizes. I > haven't measured the 8S channels yet - we're just installing them - but I > think that with non-zHPF and 4KiB single blocks they would run out of steam > at around 200MB/sec (50K IOPS). I think Cathy Cronin has published a paper > with better numbers than my wild asses guess. > > Ron > > > -Original Message- > > From: IBM Mainframe Discussion List [mailto:IBM-MAIN@bama.ua.edu] On > > Behalf Of Mike Schwab > > Sent: Tuesday, March 06, 2012 1:23 PM > > To: IBM-MAIN@bama.ua.edu > > Subject: Re: [IBM-MAIN] FICON channel ulitization > > > > No. You are dealing with one device and no intermediate device to buffer > > the transmission rates. Transmission rate is negotiated to the fastest > rate > > that both ends support. > > > > Both ends are transmitting at that same rate, and are busy for the same > > amount of time. > > > > In contrast, say you were downloading over the internet through several > > devices. The source could send the file at full speed, but is buffered > by > a > > device in the middle. It is relaying the data at a slower rate over a > slower link > > to you. > > > > On Tue, Mar 6, 2012 at 3:12 PM, R.S. > > wrote: > > > W dniu 2012-03-06 21:33, Mike Schwab pisze: > If the receiving switch > > > is 4G, that is the maximum transmission rate > from the 8G channel. > > > > It was busy 100% at 4G. I think I understand it now. So, chpid > > > connected to 8G sfp on the switch, then to 4G CU would show 50% > > > utilization? Radoslaw Skorupka Lodz, Poland > > -- > > Mike A Schwab, Springfield IL USA > > Where do Forest Rangers go to get away from it all? > > > > -- > > For IBM-MAIN subscribe / signoff / archive access instructions, send > email > to > > lists...@bama.ua.edu with the message: INFO IBM-MAIN > > -- > For IBM-MAIN subscribe / signoff / archive access instructions, > send email to lists...@bama.ua.edu with the message: INFO IBM-MAIN > -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: INFO IBM-MAIN
Re: FICON channel utilization
Radoslaw, Actually RMF does not report channel utilization for FICON. It is showing you microprocessor busy on the host channel board. For the same MB/sec this metric will change depending on block size, data length and whether zHPF is used. You can quite easily saturate a host channel MP with small blocksizes. I haven't measured the 8S channels yet - we're just installing them - but I think that with non-zHPF and 4KiB single blocks they would run out of steam at around 200MB/sec (50K IOPS). I think Cathy Cronin has published a paper with better numbers than my wild asses guess. Ron > -Original Message- > From: IBM Mainframe Discussion List [mailto:IBM-MAIN@bama.ua.edu] On > Behalf Of Mike Schwab > Sent: Tuesday, March 06, 2012 1:23 PM > To: IBM-MAIN@bama.ua.edu > Subject: Re: [IBM-MAIN] FICON channel ulitization > > No. You are dealing with one device and no intermediate device to buffer > the transmission rates. Transmission rate is negotiated to the fastest rate > that both ends support. > > Both ends are transmitting at that same rate, and are busy for the same > amount of time. > > In contrast, say you were downloading over the internet through several > devices. The source could send the file at full speed, but is buffered by a > device in the middle. It is relaying the data at a slower rate over a slower link > to you. > > On Tue, Mar 6, 2012 at 3:12 PM, R.S. > wrote: > > W dniu 2012-03-06 21:33, Mike Schwab pisze: > If the receiving switch > > is 4G, that is the maximum transmission rate > from the 8G channel. > > > It was busy 100% at 4G. I think I understand it now. So, chpid > > connected to 8G sfp on the switch, then to 4G CU would show 50% > > utilization? Radoslaw Skorupka Lodz, Poland > -- > Mike A Schwab, Springfield IL USA > Where do Forest Rangers go to get away from it all? > > -- > For IBM-MAIN subscribe / signoff / archive access instructions, send email to > lists...@bama.ua.edu with the message: INFO IBM-MAIN -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@bama.ua.edu with the message: INFO IBM-MAIN