ATTENTION: You are viewing a page formatted for mobile devices; to view the full web page, click HERE.

Main Area and Open Discussion > Living Room

Windows performance tips in one spot

<< < (2/4) > >>

f0dder:
One thing that made a beeg difference for me: allowing Windows to create multiple page files on separate harddrives.  It's tempting to pick your fastest drive and use that (disabling all others) but after I let Windows handle it I ended up with four pagefiles and less thrashing.
-Ralf Maximus
--- End quote ---
Good idea, although you have to keep your pagefiles on separate physical drives, not partitions.

No matter how much RAM you have, some (older?) software malfunctions if there is no pagefile, generating messages like "low on virtual memory".  Do this with one with caution.-Ralf Maximus
--- End quote ---
I haven't experienced that myself, but I did find that a few apps were too memory hungry for their own good back when I "only" had 1gig. But it could very well happen, probable cause would be bad use of memory mapped files, and I certainly wouldn't recommend no-pagefile on less than 1gig.

Gosh, that sounds pornographic.
-Ralf Maximus
--- End quote ---
BIG grin :D

Half-stroking sounds like an interesting idea, I'm not sure if it makes much of a difference if you keep your partitions (and the MFTs!) defragmented, though? I do have my 74gig raptor partitioned: 16gig for windows+apps, 4gig for source/docs, 50gig for things like games, "scratchpad", etc.

Putting two raptors in raid-stripe would certainly fly, but I'm not a fan of striping. A mirror would be nice as well, unless your raid controller is so retarded it doesn't do read-striping (hello, nForce4).

tomos:
One thing that made a beeg difference for me: allowing Windows to create multiple page files on separate harddrives.  It's tempting to pick your fastest drive and use that (disabling all others) but after I let Windows handle it I ended up with four pagefiles and less thrashing.-Ralf Maximus (October 18, 2007, 11:45 AM)
--- End quote ---

I've just ried that cause I having some trouble with an older app sometimes (Freehand 9) -
it can't start first attempt after a reboot, starts then on second attempt but has lost it's preferences.

Previously I had Pagefile on first partition (FAT32) of second harddrive,
now:
gave windows minimum pagefile of 50mb on C
still has 3GB page file on second hdd as described above
& "system managed size" on TWO other partitions.

Was very surprised to see it has created a 1.99GB paging file on each of those extra partitions
What's going on there I wonder - Freehand started perfectly this time though  :-\  :D

EDIT: PS have 2GB memory, intel dualcore

Ralf Maximus:
Half-stroking sounds like an interesting idea, I'm not sure if it makes much of a difference if you keep your partitions (and the MFTs!) defragmented, though? I do have my 74gig raptor partitioned: 16gig for windows+apps, 4gig for source/docs, 50gig for things like games, "scratchpad", etc.

--- End quote ---

You are correct.  As the drive gets fuller (more full?) this half-stroking business pays less and less of a dividend as the head moves farther afield.  Fragmentation accelerates this effect.

And partitioning a big drive up like you have is the way to go (IMHO) but if more than one partition is accessed simultaneously any half-stroking benefits are lost.

In my case, I have a pair of 500MB 7200RPM drives RAIDed together (RAID 0) via a PCi controller made by SII.  It's broken up into two partitions: one gigantic 900GB block for storing media & backups, and the other a 50GB block set up for temp files and miscellaneous transitory things.  I have my Windows temp file located there, as well as a 2GB pagefile.

In this case, so long as I'm not spooling MP3s or a movie from the big partition, the read-head stays entirely in the small partition, travelling only a wee distance.  Call it: 1/10th stroking.

This sounds wonderful in theory, but I'm not sure the experiment is working as intended.  For instance, I usually *am* listening to music or watching a movie while I work, so the big partition gets accessed often.

Also, I have a huge-ass amount of RAM devoted to file caching (SuperCache II) so the software is mediating disk access and (I think) evening out the physical accesses.  I mean, some temporary file operations generate NO disk activity, where I would expect to hear the drive going nuts.

I'm not sure the juice is worth the squeeze, though now that it's all set up I'm loathe to rip it all apart and redo it.  It's definitely the fastest drive setup I've had so far, and love it -- but I think I could have chosen the partition sizes at random and gotten similar results.

Oh, and the punch line: the two 500GB 7200 RPM drives (RAID 0) replaced an aging pair of 35GB Raptors (RAID 0).  I can detect no difference in performance or responsiveness, though HDTune seems to think the new array is slower.

tomos:
One thing that made a beeg difference for me: allowing Windows to create multiple page files on separate harddrives.  It's tempting to pick your fastest drive and use that (disabling all others) but after I let Windows handle it I ended up with four pagefiles and less thrashing.-Ralf Maximus (October 18, 2007, 11:45 AM)
--- End quote ---

I've just tried that
....
Was very surprised to see it has created a 1.99GB paging file on each of those extra partitions
What's going on there I wonder-tomos (October 19, 2007, 04:24 AM)
--- End quote ---

Ralph
would you be able to say how the pagefiles on your system are? (sizewise I mean :P*)
thanks, tom

* EDIT: well, anywise really

Ralf Maximus:
Sure.  I just checked and found TWO (not four) page files.  Dunno why there aren't four anymore -- there used to be four when I first built the rig out.  Maybe Windows decided it didn't need the other two?

Drive C: 4989MB
Drive F: 3326MB

This is on a Dell Optiplex GX620 with 4GB physical RAM (3.25GB visible to Windows).

Oh, and with Firefox, Thunderbird, VS6, 1.5GB allocated to disk cache, and a few other small things running this is what my memory usage looks like:

Navigation

[0] Message Index

[#] Next page

[*] Previous page

Go to full version