Forum Vs Naplam - Fasted real world storage solution

[NapalmV5]

Napalm, sorry if this is already mentioned, but what is your array? How long does it take to reformat the whole thing to ntfs? (full)

areca 1231/512mb/4x jmicron slc ssd raid0

reformat? ntfs? xp installed on the array along with games/apps on NTFS not FAT/FAT32

@ xp setup full NTFS format takes 2-3 seconds

[NapalmV5]

The secret is to load the game 2 or more times. Then it will load the game fra cache

But you aleready know that

my loadups that fast because its cached ?

with your tendency to claim 5x @ 6x/4x @ 5x.. and who knows what cache.. can you back up this claim ^ ??

with your 1680/2gb~4gb/6x vertex you should put my 1231/512mb/4x jmicron cod4/cod5 loadups to shame


you think my app *.bat loadup was cached also ?

i will bring another video of that

everything you guys see in the videos is pure/raw power no tricks no bs

[Rhys]

you think my 100 app *.bat loadup was cached also ?

i will bring another video of that

everything you guys see in the videos is pure/raw power no tricks no bs

Not saying it is bs etc, but you could easily prove it's not by doing a video of the bootup from when you press the power switch, and then load COD4 & 5 then exit them and then run the .bat file.

If the times are just as fast, then you have one crazy fast setup and a 12xx might have to be under my christmas tree.

[XS Janus]

People need to much proof. This isn't even official benchmarking, just people telling their experiences and showing their setups for advice.
Why don't you guys pull some strings in the e-zine communities and make them start testing setups like these in real world stuff. I mean every site could do their ovn script and load up windows and a bunch of chosen apps and post a score and compare.
Than more people would learn the real truth and avoid all this bickering.

I'm more curious about what makes this Areca so special that makes it perform better in Raid0 in these real world tasks? It shouldn't be it processor, right?
And I feel sorry for myself cause it has 12ports, and I don't need them on my main rig.
Is there a card with less ports that would give same results?

[Gilhooley]

COD4 COD5 loadups @ 1920x1080 and running on the xp ^

http://www.youtube.com/watch?v=DMd6BclLcxs

http://i30.tinypic.com/r8avis.jpg

Intense

[EniGmA1987]

Wow Napalm, those loading time are amazing. Now I wish I had a couple thousand extra to spend on a nice controller and a bunch of super nice drives.

[Boogerlad]

they're normal crappy jmicron drives, just backed by an uber raid card.

[Rhys]

they're normal crappy jmicron drives, just backed by an uber raid card.

They are not crappy as they are SLC, not the MLC versions, and the only week point on the drives was lack of cache which the Areca solves.

Your x25-m's would stutter if there wasn't any cache.

[Boogerlad]

yeah, I thought it was the mlc drives. Sorry.

[One_Hertz]

Your x25-m's would stutter if there wasn't any cache.

Not really. They only use 256kb for write buffering in the first place. The rest is for wear leveling operations.

[Spoiler]

Not really. They only use 256kb for write buffering in the first place. The rest is for wear leveling operations.

Playing devil's advocate? Yes, really. Without ANY cache, I believe the drive would stutter.

[One_Hertz]

Playing devil's advocate? Yes, really. Without ANY cache, I believe the drive would stutter.

Without ANY cache the drive would not work AT ALL. It would not stutter without a write buffer. The performance would be less, but it would not stutter. I believe you can turn this write buffer off and try it yourself.

[Spoiler]

I'd love to try. Just waiting on Intel to get that new firmware out there on the new drives!

[Rhys]

Without ANY cache the drive would not work AT ALL. It would not stutter without a write buffer. The performance would be less, but it would not stutter. I believe you can turn this write buffer off and try it yourself.

Intel uses 16x more cache than J-micron!
Stop trying to mislead, 256k is huge compared to 16k!

[One_Hertz]

Intel uses 16x more cache than J-micron!
Stop trying to mislead, 256k is huge compared to 16k!

The only thing I was saying the whole time is that it is not the cache that is making the X25 stutter-free. Cache is for performance improvements.

[Rhys]

The only thing I was saying the whole time is that it is not the cache that is making the X25 stutter-free. Cache is for performance improvements.

I wonder how stutter free it will be with 16kb of cache.
How would the x25-m write combine etc?...... It could't!

[One_Hertz]

I wonder how stutter free it will be with 16kb of cache.
How would the x25-m write combine etc?...... It could't!

dude I am telling you, you can turn off the cache that's on the drive and see for yourself. Works fine, just a lot slower. Doesn't stutter.

[Rhys]

Without ANY cache the drive would not work AT ALL. It would not stutter without a write buffer. The performance would be less, but it would not stutter. I believe you can turn this write buffer off and try it yourself.

dude I am telling you, you can turn off the cache that's on the drive and see for yourself. Works fine, just a lot slower. Doesn't stutter.

You second quote suggests that when you disable the cache in WINDOWS, the drive uses 0 cache in the drive. (Atleast for your quote/point to make sense that is what it would need to suggest)

The first thing that doesn't sound correct, is that you have previously stated that a drive with 0 cache will not work at all.

So which is it?

The drive either uses the minimum 256k cache but not the remaining 15.75mb used for wear leveling when you disable caching, or it uses NO cache at all and as you stated previously the drive will not function.

If the x25-m still uses the 256k cache then my point still stands because the x25-m is still opperating with 1600% more cache than the j-micron even with the wear levelling cache disabled.

So with performance already hit with the wear levelling cache disabled, how do you think the x25-m would fare if you replaced the 256k cache with 16k?

[Rhys]

^^^
My hunch is your defending a careless comment that hadn't been thought through!
It's ok to be wrong on this forum occasionallly.

[Jor3lBR]

Hey Napalm, what RAM you're using in the ARS-1231?

Great results as always mate.

[One_Hertz]

You second quote suggests that when you disable the cache in WINDOWS, the drive uses 0 cache in the drive. (Atleast for your quote/point to make sense that is what it would need to suggest)

The first thing that doesn't sound correct, is that you have previously stated that a drive with 0 cache will not work at all.

So which is it?

The drive either uses the minimum 256k cache but not the remaining 15.75mb used for wear leveling when you disable caching, or it uses NO cache at all and as you stated previously the drive will not function.

If the x25-m still uses the 256k cache then my point still stands because the x25-m is still opperating with 1600% more cache than the j-micron even with the wear levelling cache disabled.

So with performance already hit with the wear levelling cache disabled, how do you think the x25-m would fare if you replaced the 256k cache with 16k?

You can't turn off the cache that is used for wear leveling. It doesn't let you because the drive wouldn't work at all. When it erases a block, where do you think it would keep the previous contents until it has to write the modified data back?

My second quote suggests what it says. When you click the turn off cache button in windows, there is no stuttering. We are clearly talking about the write buffer at that point as I've already said wear leveling cache can not be disabled.

It lets you turn off the write buffer because that is just for performance purposes. You can turn off the read/write buffer an an HDD too. Will be 5-10x slower. It is the same idea but SSDs don't suffer anywhere near as much. My point stands, the X25 would not stutter even with a 0kb write buffer. It would be slow, but it would not stutter. Stuttering is due to bad controller design and not due to cache. Cache can somewhat remedy the bad controller design, but if the controller is fine to begin with then there is nothing to remedy.

[Ao1]

I wonder how stutter free it will be with 16kb of cache.
How would the x25-m write combine etc?...... It could't!

Is the cache not DRAM that is used as memory by the controller for deciding exactly where to write data? It's not used for user data because of the risk of data loss.

The FAQ's on Kingstons web site (X25-M) states Data caching is limited to the controller for enhanced performance. Disabling Write Cache simply adds latency and provides no significant additional data loss protection.

[Rhys]

Is the cache not DRAM that is used as memory by the controller for deciding exactly where to write data? It's not used for user data because of the risk of data loss.

The FAQ's on Kingstons web site (X25-M) states Data caching is limited to the controller for enhanced performance. Disabling Write Cache simply adds latency and provides no significant additional data loss protection.

Data loss Lol!
You really think it's an issue to use cache as a buffer before it get to disk?
This is nearly as bad as the write back cache argument.
Chances are if your writing a file and sudden power failure happens the data has
a) Already been written to disk
b) Has only written part of file so it's going to be corrupt anyway.

[Rhys]

You can't turn off the cache that is used for wear leveling. It doesn't let you because the drive wouldn't work at all. When it erases a block, where do you think it would keep the previous contents until it has to write the modified data back?

My second quote suggests what it says. When you click the turn off cache button in windows, there is no stuttering. We are clearly talking about the write buffer at that point as I've already said wear leveling cache can not be disabled.

It lets you turn off the write buffer because that is just for performance purposes. You can turn off the read/write buffer an an HDD too. Will be 5-10x slower. It is the same idea but SSDs don't suffer anywhere near as much. My point stands, the X25 would not stutter even with a 0kb write buffer. It would be slow, but it would not stutter. Stuttering is due to bad controller design and not due to cache. Cache can somewhat remedy the bad controller design, but if the controller is fine to begin with then there is nothing to remedy.

Simple question, if I disable cache on my x25-m in windows, how much cache is it using to remain operational?

[One_Hertz]

Simple question, if I disable cache on my x25-m in windows, how much cache is it using to remain operational?

I dont know. I would assume somewhere in the 15mb range. This cache has nothing in common with the cache that Areca provides. Completely different things.

Your original statement of "Your x25-m's would stutter if there wasn't any cache" is completely and utterly false. If you were talking about all cache, then no it wouldn't stutter because it wouldn't even work due to the controller design. If you were talking about write buffer then no, it wouldn't stutter without it.