On Wed, 30 Jan 2019 at 01:53, Ed Jaffe <edja...@phoenixsoftware.com> wrote:
> Is it no longer possible to use "old school" shared DASD RESERVE/RELEASE > to protect data? I know it won't work for sharing PDSE, but for > old-school PDS and sequential, it should still work. Reserve/Release works only if someone issues those CCWs. DADSM issues them to protect the VTOC, and maybe catalog management does (I don't know), and the Binder does if SYSLMOD is on a shared device. But data management generally does not, so e.g. if you have two jobs on separate LPARs and each has DISP=OLD for the same dataset using QSAM or BPAM, say, nothing protects the data itself from being written from both sides at the same time. You can put the Reserve/Release in your application program (via ENQ), but that's not going to work very well for your typical COBOL program, and unless you have extreme data separation by volume, performance will suck, to put it politely. Typically what is wanted is the notion of ENQ with the SYSTEMS option, and that's just not available (and is silently ignored if requested) without either GRS or one of the products popular in the 1980s that implemented GRS-like behaviour using Reserve/Release on some kind of control dataset. I don't know if any of those products are still on the market. Or why not, as another poster suggested, use a GRS ring. This can protect applications against dataset corruption at on-the-box CTC speed, and I don't see any obvious reason if would be slower than a timeshared CF on the same machine. Of course you get GRS - not Parallel Sysplex, and there are various things such as JES2 shared SPOOL that need the Sysplex. Tony H. ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
