Mark Zelden <[EMAIL PROTECTED]> wrote: IBM Mainframe Discussion List <IBM-MAIN@BAMA.UA.EDU> wrote on 07/11/2008 12:04:33 PM:
> On Fri, 11 Jul 2008 11:13:04 -0400, John Kington > <[EMAIL PROTECTED]> wrote: > > > >No numbers but a story from personal experience. When I first implemented > >SMS, I setup a VIO storage group with a limit of about 10 cylinders on a > >3390 and made any requests over 10 cylinders go to dasd. About six years > >later, the tape guy was making changes to STK HSC database which caused it > >to increase in size to around 12 cylinders (hsc was created using vio and > >then gener'ed to dasd, IIRC). He noticed that his runtime on the hsc gen > >increased more than triple. This was on a 9672 G5 box using EMC 8830 escon. > >I can not imagine more recent equipment could make up this difference. > >Regards, > >John > > > > I just tried that and the CDS creation program won't let you use VIO as > the output. I managed to find the jcl and it was performing a reconfig, not creation. It has not been changed since 1999 and there appears to be a newer version of the reconfig job that does not use vio. > > But I did run an IEBGENER test of a 350 CYL CDS to DASD and then > to VIO. Here are the results: > > DASD: > > IEF373I STEP/JS010 /START 2008193.1049 > IEF374I STEP/JS010 /STOP 2008193.1050 CPU 0MIN 01.42SEC > SRB 0MIN 00.74SEC VIRT 104K SYS 328K EXT 4K SYS 11812K > > > VIO: > > IEF373I STEP/JS010 /START 2008193.1050 > IEF374I STEP/JS010 /STOP 2008193.1051 CPU 0MIN 02.06SEC > SRB 0MIN 00.69SEC VIRT 104K SYS 324K EXT 4K SYS 13856K > > > I ran several test and wall clock time was slightly less with VIO. > Good to see that dasd I/O is that close on sequential processing. The reconfig may have been doing updates though. Regards, John ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html