Page Faults and Rosetta

Message boards : Number crunching : Page Faults and Rosetta

To post messages, you must log in.

Previous · 1 · 2

AuthorMessage
Profile Steve Cressman
Avatar

Send message
Joined: 25 Jul 06
Posts: 23
Credit: 9,432
RAC: 0
Message 21860 - Posted: 4 Aug 2006, 19:10:49 UTC

On older os's like mine, I lock the swapfile size so that windows does not waste time resizing it all the time. Also in the registry I set conservative swapfile useage so that windows won't actually use any swapfile until it uses up all available memory. If you don't set that in the registry windows starts swapping before you have even used up half of the physical memory. Maybe there are similar settings in xp that you could take advantage of.
:)
98SE XP2500+ @ 2.1GHz Boinc v5.8.8

And God said"Let there be light."But then the program crashed because he was trying to access the 'light' property of a NULL universe pointer.
ID: 21860 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
Profile Vester
Avatar

Send message
Joined: 2 Nov 05
Posts: 258
Credit: 3,651,260
RAC: 0
Message 21862 - Posted: 4 Aug 2006, 19:45:00 UTC

If it needs paging files and there are none, your computer will hang or you will get a message as described, Ethan: http://support.microsoft.com/kb/315270/EN-US/. I never had a problem when I tried it. More gigs to you!
ID: 21862 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
Bob Guy

Send message
Joined: 7 Oct 05
Posts: 39
Credit: 24,895
RAC: 0
Message 21871 - Posted: 5 Aug 2006, 0:31:38 UTC

See this TechNet article regarding
Memory Usage and System Cache.

While it may not be entirely applicable to WinXP see the section 'Confirming Hard Page Faults' for some useful diagnostic techniques.

The page faults reported by WinXP (i.e. TaskManager) include both hard and soft page faults so you shouldn't rely on that information alone to make a performance analysis.

Soft page faults often occur as a result of the OS reserving memory (real or virtual) for possible future use - it does not indicate that the memory is actually being used or that an actual memory read/write occurred or that an actual disk IO occurred. The page file (virtual memory) may also contain these reserved blocks of memory that in many cases are never written/read - so the size of the paged memory is not a good indicator of its actual use.
ID: 21871 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
Profile Jack Shaftoe
Avatar

Send message
Joined: 30 Apr 06
Posts: 115
Credit: 1,307,916
RAC: 0
Message 21899 - Posted: 5 Aug 2006, 12:36:14 UTC - in response to Message 21871.  

Lots of great info in this thread, many thanks to all of you for responding.

-F.
Team Starfire World BOINC
ID: 21899 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
Profile Vester
Avatar

Send message
Joined: 2 Nov 05
Posts: 258
Credit: 3,651,260
RAC: 0
Message 22064 - Posted: 8 Aug 2006, 22:15:52 UTC

Bill Castner, on the forum at www.aumha.org, referred to this article by Daniel Petri on virtual memory: http://www.petri.co.il/pagefile_optimization.htm.
ID: 22064 · Rating: 0 · rate: Rate + / Rate - Report as offensive    Reply Quote
Previous · 1 · 2

Message boards : Number crunching : Page Faults and Rosetta



©2025 University of Washington
https://www.bakerlab.org