Trim or raid?

[Forceman]

How much ram do you have and do you run very memory intensive apps?

I only have 2GB and I can easily go over that all day.

I'm at 3916 cycles, 3100GB written.

8GB and I have about 2 TB of writes on the drive. My point is that I don't think comparing "life %" between drives is very useful, since I don't think anyone really knows where those numbers come from. I know Intel reports total writes, but doesn't convert that into a percent anywhere in their tools (that I've seen), so someone else making up a percentage isn't likely to be a very good reflection of how much life is left.

Leaving the page file on SSDs is very bad advice IMO. Either shut it off or put it on a RAM Disk. Also shutoff the superfetch service permanently. And if you have a RAM disk try your temp/tmp and Internet Browser cache on the RAM disk its nice and takes wear off your SSD too. I use QSoft RAM Disk from my research its the best. and its free if you don't want to pay.

How about we all stop second guessing the engineers that made the operating system and stick with what they say - which is to leave the pagefile on the SSD, and to let the OS manage the Superfetch settings. What's the point of buying a fast SSD if you are afraid to put data on it?

Will Superfetch be disabled on SSDs?

Yes, for most systems with SSDs.

If the system disk is an SSD, and the SSD performs adequately on random reads and doesn’t have glaring performance issues with random writes or flushes, then Superfetch, boot prefetching, application launch prefetching, ReadyBoost and ReadDrive will all be disabled.

Should the pagefile be placed on SSDs?

Yes. Most pagefile operations are small random reads or larger sequential writes, both of which are types of operations that SSDs handle well.

In looking at telemetry data from thousands of traces and focusing on pagefile reads and writes, we find that

•Pagefile.sys reads outnumber pagefile.sys writes by about 40 to 1,
•Pagefile.sys read sizes are typically quite small, with 67% less than or equal to 4 KB, and 88% less than 16 KB.
•Pagefile.sys writes are relatively large, with 62% greater than or equal to 128 KB and 45% being exactly 1 MB in size.
In fact, given typical pagefile reference patterns and the favorable performance characteristics SSDs have on those patterns, there are few files better than the pagefile to place on an SSD.

http://blogs.msdn.com/b/e7/archive/2009/05/05/support-and-q-a-for-solid-state-drives-and.aspx

 

[Falcon_CMH]

The OS uses the swapfile even if you have 48GB of memory and do not need it. It uses it unecessarily. Thats why I recommend to turn it off. I personallty would never use a RAM Disk for it but some folks don't wanna tturn it off due to how the OS acts when its low on memory. It's a personal preference.

Superfetch is junk IMO always has been since Vista and still is wasting CPU and memory.

SSDs cannot handle writes very well still today. The sandforce controller being the worse culprit. So I tune my system appropriately. My system runs extremely fast I have many kinds of specs to prove it. I would put it up against any of yours with differing opinions let's do this. Choose your tool/weapon.

 

[Neb]

SSDs cannot handle writes very well still today. The sandforce controller being the worse culprit. So I tune my system appropriately. My system runs extremely fast I have many kinds of specs to prove it. I would put it up against any of yours with differing opinions let's do this. Choose your tool/weapon.

Please clarify what you mean by SSDs cannot handle writes very well still today?

I would like to see benchmarks proving that having Superfetch and a pagefile significantly effects system performance. A benchmark comparison with someone that doesn't have an identical system is essentially meaningless and would merely be an e-peen comparison of hardware. You should know this.

 

[Falcon_CMH]

Not true, AS and ATTO are benches that measure drive performance, just saying not all benching tools are e-peen you should know this. Also PC Mark or Vantage or what ever it is called would have some comparable measurements/data across disimilar machines. Heck PerfMon with its counters like page faults etc would be perfect.

You can perform your own benchmarks on your own PC like I did.

And MS says to turn off Superfetch.

Turning off the swap file is easily measureable like I said with PerfMon. Maybe you out to learn some tools to measure your PC various performances?

 

[Neb]

Not true, AS and ATTO are benches that measure drive performance, just saying not all benching tools are e-peen you should know this. Also PC Mark or Vantage or what ever it is called would have some comparable measurements/data across disimilar machines. Heck PerfMon with its counters like page faults etc would be perfect.

So what did you mean by "SSDs cannot handle writes very well still today"?

So I tune my system appropriately. My system runs extremely fast I have many kinds of specs to prove it. I would put it up against any of yours with differing opinions let's do this. Choose your tool/weapon.

From your statement it sounds like you want to compare your "tuned" system to other peoples' systems. The issue here is that you must define what you are comparing. Are you comparing the tuning of your system or the hardware of your system? You must only have one variable when doing a proper comparison, otherwise the comparison is faulty. The only proper way to benchmark the difference the tuning of a system makes would be to use two sets of the exact same hardware and configure one without and one with the tuning, then run the benchmarks.

That is why I said any comparison done between your system and another system would simply be an e-peen comparison.

You can perform your own benchmarks on your own PC like I did.

And MS says to turn off Superfetch.

Turning off the swap file is easily measureable like I said with PerfMon. Maybe you out to learn some tools to measure your PC various performances?

Sure, perfmon shows that the swap file is used, but what is the actual performance impact? Can you show any fps loss in your game? Is your render any slower? Does your PCMark Vantage score go any higher when you disable the swap file?

Microsoft says Superfetch will be automatically disabled if it is necessary, they did not say a blanket statement that people should disable it for all SSDs, which seems to be your interpretation. I'll let the superfetch argument drop, since you obviously hate it with a passion.