home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!olivea!decwrl!pa.dec.com!e2big.mko.dec.com!vertex.enet.dec.com!pettigrew
- From: pettigrew@vertex.enet.dec.com (Mike Pettigrew)
- Newsgroups: vmsnet.internals
- Subject: Re: RE: VMS Tuning
- Message-ID: <1992Aug26.174843.18995@e2big.mko.dec.com>
- Date: 26 Aug 92 17:49:23 GMT
- References: <7895152@MVB.SAIC.COM>
- Sender: guest@e2big.mko.dec.com (Guest (DECnet))
- Organization: Digital Equipment Corporation
- Lines: 26
-
-
- In article <7895152@MVB.SAIC.COM>, SYSMAIL@VAX.LIVERPOOL-POLY.AC.UK writes...
-
- >
- >...................................................However it may be better to
- >distribute some of a huge free list to WSEXTENT and MPW_HILIMIT. The modified
- >list tends to be sized conservatively, and letting users have a larger
- >working-set will cut down on even the soft-fault overhead.
- >
- >Ronan Flood, Systems Manager (pro tem),
- >Liverpool Polytechnic Computer Services.
-
-
- Raising the values for MPW_HILIMIT and WSEXTENT to WSMAX has been done at a
- number of heavily-loaded sites. The results have been uniformly positive
- in VMS 5.3 or later versions, with dramatic reductions in hard faulting,
- and soft faulting, and visible improvments in application turnaround..
-
- ----------------------------------------------------------------------------
- | -Mike Pettigrew pettigrew_mi@ripple.enet.dec.com
- | (206) 661-3032
- | Digital Equipment Corporation
- | Federal Way, Washington, USA
- |___________________________________________________________________________
- |These opinions are mine and not necessarily my employer's
- ----------------------------------------------------------------------------
-