nagy%bsndbg.hepnet@LBL.ARPA.UUCP (03/04/87)
>From: "Douglas M. Olson" <DOLSON@ADA20.ISI.EDU> >Briefly, since we converted from VMS V3.7 to V4.2, and upon subsequent >upgrades (soon 4.5), our page count in MODIFIED PAGES has been miniscule. >My understanding was that when pages were forced out of a working set >by process constraints, they were placed on the modified page list just >in case they might be needed again soon. Our 11/785s have 6M and 10M, >and memory constraints have only just begun to make themselves felt. >Under V3.x, we usually had several hundred pages on the modded page list. >Now, its seldom over 10. Thats what bothers me. First of all, don't trust AUTOGEN implicitly. It is far, far from perfect or bug-free (I had lots and lots of fun with AUTOGEN doing the V4.3 to V4.4 upgrade - took 3 weekends to get it corrected). My action would be to go look at the SYSGEN parameters MPW_HILIMIT, MPW_LOLIMIT, etc. which control the modified page list. I think you might find that something is set wrong to force the modified page list to be very small. Confirming this would be to MONITOR PAGES and see if you have an excessive page write rate. This would indicate that the modified page writer was being invoked too frequently. Normally the page write rate should be rather small (assuming that your overall paging I/O rates are modest except for page reads for new image activations).