• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

Turning Superfetch off

Page 2 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
Originally posted by: bsobel
Eh, theres far more in that folder than just the instructions for the SF cache that I wouldnt want to erase. (Boot traces, app prefetch files, optical disk layout for defrag, etc)

It's all rebuildable if you nuke the dir (you can also nuke the superfetch database, but its easier to just nuke the dir, after a reboot or two the world is rebuilt). There is nothing in there that is dangerous to nuke.

Bill

For sure, but I rarely reboot nowadays.
 
I wonder what will happen to Superfetch and Readyboost if MS comes up with a relational file system in Windows vienna like WinFS 😛 and also I think there will be no performance boost with solid state drives.
 
Originally posted by: Aberforth
I wonder what will happen to Superfetch and Readyboost if MS comes up with a relational file system in Windows vienna like WinFS 😛 and also I think there will be no performance boost with solid state drives.

Solid state drives are fast, but theyre nowhere near as fast as DDR in random or sequential reads. Theres no seek time in either case, but the transfer rate is a mere fraction of DDR. If anything, SF and SS will go hand in hand - low priority I/O will work effortlessly to fill the cache, so not only will there be zero actual performance hit while precaching, it will also be dead silent and have zero perceptual performance hit.

Readyboost would be pretty much useless though, and low memory systems would benefit greatly by having the page file on a fast solid state drive.
 
Originally posted by: Aberforth
I wonder what will happen to Superfetch and Readyboost... and also I think there will be no performance boost with solid state drives.

I digress...

IMHO, there is a huge benefit to notebook users - not so sure about desktops.

Laptops and desktops are two different animals. For instance, desktop users seem to prefer big monitors - the bigger the better! However, big panels on a lappy are a PITA - anything over 15.4" borders on being too big to use efficiently and effectively (and carry around) so, 12"-13" is the hot spot for most experienced mobile users, e.g. less is more.

There are also other important differences - battery vs AC wall power - small, low performance drives with slow rotational speeds (to save battery power) vs big, fast, RAID arrays with 120mm fans blowing across them, yada, yada, yada.

SuperFetch/ReadyBoost on a notebook (once it's fully locked n' loaded [about 5 min]) makes a big difference in performance because the HD basically goes dormant - no spin up, spin down, spin up, spin down, spin up, spin down...

Your lappy can get data from both volatile/non-volatile memory faster than the HD can move the head(s)! 😀

Not only is there a performance increase, but your lappy will run a lot cooler, and battery life will be extended - so, there are many counterintuitive/ancillary benefits to running SuperFetch/ReadyBoost on notebooks!

My Toshiba came with a warning about burning yourself on the palm rests and case. HERE is a pic.

This is due primarily to drive heat, from CONSTANTLY being accessed (without ReadyBoost). With SuperFetch/ReadyBoost implemented (4GB RAM - 4GB ReadyBoost in my instance) my palm rests are now stone cold!

Soooooo... I guess the subject of 'solid state' performance increases (or not) afforded by SuperFetch/ReadyBoost/ReadyDrive depends on the context and application... 🙂
 
Back
Top