Comments
Comment by Thomas:
¶
depends on what you test: IOPS or bandwidth?
I would expect bandwidth to be the same if you are testing 2 drives that are the same expect for the cache since the physical medium is the limiting factor. If you are testing IOPS I would expect a difference especially if you would turn on fast write cache (wich you shouldn’t do of course unless you have a UPS etc.)
Thomas
Comment by ssp:
¶
Personally I’m not testing anything…
Of course I can imagine a larger cache having advantages. But what I’m wondering about is whether I’ll see them in everyday use. To which is extent is the cache on a hard drive used? I have no idea about these things.
Comment by Thomas:
¶
The cache will be used of course by the drive, no user intervention needed and drives are quite clever. But I expect it will make very little difference… yes that 10Meg file that you have just opened might be ready to edit few seconds earlier. Or the machine might be booted a bit quicker… but over all on a home machine that sits idle for 99% of the time I don’t think it will make a lot of difference. The only expection might be if you are a regular photoshop user. Those files are ussually quite big to start with. The thing to keep in mind here is the workload.
Having no cache would probably make a noticable difference though. I guess you can always give that a try, there must be some utility somewhere that can turn of the cache.
Thomas
