Re: IBM disk replication issue
The delay also depends on the distance between the primary and secondary disk systems owing to the speed of light being regrettably finite. On Tue, 1 Feb 2022 at 18:21, Mike Schwab wrote: > It will delay synchronous writes, because the write is not returned > until the mirrored disk is updated. Asynchronous writes do not delay > the return since it occurs when the primary disc is updated. > > On Tue, Feb 1, 2022 at 5:50 PM Peter wrote: > > > > Hello > > > > Recently we were a victim of storage replication link between production > > and DR site(metro mirroring). Due to this many of our batch jobs took > more > > time than expected. So here I would like to understand how the dasd > update > > happens ? For example when a batch allocates some dataset on DASD in > > production site so does it returns back or finishes off the I/O operation > > is finished from both production and DR ? > > > > If there is latency in dark fibre connectivity between production and DR > , > > Will it impact the batch job elapsed time ? > > > > Could someone please shed some light on this? > > > > Peter > > > > -- > > For IBM-MAIN subscribe / signoff / archive access instructions, > > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN > > > > -- > 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...@listserv.ua.edu with the message: INFO IBM-MAIN > -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: IBM disk replication issue
Which site has the fastest DASD? If not the DR site, then that could be an issue. At least it used to be a decade ago when I had XRC running to slower DASD and it began pacing I/O to the point that it affected Production I/O response times very significantly. Solved problem by making DR DASD as fast or faster than production DASD. YMMV -Original Message- From: IBM Mainframe Discussion List On Behalf Of Mike Schwab Sent: Tuesday, February 1, 2022 1:21 PM To: IBM-MAIN@LISTSERV.UA.EDU Subject: Re: IBM disk replication issue It will delay synchronous writes, because the write is not returned until the mirrored disk is updated. Asynchronous writes do not delay the return since it occurs when the primary disc is updated. On Tue, Feb 1, 2022 at 5:50 PM Peter wrote: > > Hello > > Recently we were a victim of storage replication link between > production and DR site(metro mirroring). Due to this many of our batch > jobs took more time than expected. So here I would like to understand > how the dasd update happens ? For example when a batch allocates some > dataset on DASD in production site so does it returns back or finishes > off the I/O operation is finished from both production and DR ? > > If there is latency in dark fibre connectivity between production and > DR , Will it impact the batch job elapsed time ? > > Could someone please shed some light on this? > > Peter > > -- > For IBM-MAIN subscribe / signoff / archive access instructions, send > email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN -- 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...@listserv.ua.edu with the message: INFO IBM-MAIN -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: [EXTERNAL] IBM disk replication issue
Peter, Metro Mirror is synchronous replication so I/O operations need to complete (for some definition of complete - typically to a NVS in the controller rather than all the way out to the spindles) at both locations before control is given back to the system so if you had a slowdown on the link between the sites that would definitely impact your job run speeds. Rex -Original Message- From: IBM Mainframe Discussion List On Behalf Of Peter Sent: Tuesday, February 1, 2022 11:50 AM To: IBM-MAIN@LISTSERV.UA.EDU Subject: [EXTERNAL] IBM disk replication issue Hello Recently we were a victim of storage replication link between production and DR site(metro mirroring). Due to this many of our batch jobs took more time than expected. So here I would like to understand how the dasd update happens ? For example when a batch allocates some dataset on DASD in production site so does it returns back or finishes off the I/O operation is finished from both production and DR ? If there is latency in dark fibre connectivity between production and DR , Will it impact the batch job elapsed time ? Could someone please shed some light on this? Peter -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN -- The information contained in this message is confidential, protected from disclosure and may be legally privileged. If the reader of this message is not the intended recipient or an employee or agent responsible for delivering this message to the intended recipient, you are hereby notified that any disclosure, distribution, copying, or any action taken or action omitted in reliance on it, is strictly prohibited and may be unlawful. If you have received this communication in error, please notify us immediately by replying to this message and destroy the material in its entirety, whether in electronic or hard copy format. Thank you. -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
Re: IBM disk replication issue
It will delay synchronous writes, because the write is not returned until the mirrored disk is updated. Asynchronous writes do not delay the return since it occurs when the primary disc is updated. On Tue, Feb 1, 2022 at 5:50 PM Peter wrote: > > Hello > > Recently we were a victim of storage replication link between production > and DR site(metro mirroring). Due to this many of our batch jobs took more > time than expected. So here I would like to understand how the dasd update > happens ? For example when a batch allocates some dataset on DASD in > production site so does it returns back or finishes off the I/O operation > is finished from both production and DR ? > > If there is latency in dark fibre connectivity between production and DR , > Will it impact the batch job elapsed time ? > > Could someone please shed some light on this? > > Peter > > -- > For IBM-MAIN subscribe / signoff / archive access instructions, > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN -- 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...@listserv.ua.edu with the message: INFO IBM-MAIN
IBM disk replication issue
Hello Recently we were a victim of storage replication link between production and DR site(metro mirroring). Due to this many of our batch jobs took more time than expected. So here I would like to understand how the dasd update happens ? For example when a batch allocates some dataset on DASD in production site so does it returns back or finishes off the I/O operation is finished from both production and DR ? If there is latency in dark fibre connectivity between production and DR , Will it impact the batch job elapsed time ? Could someone please shed some light on this? Peter -- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN