First IOXTREME Review

[F.E.A.R.]

Sorry about that
In Dec. 2007 i bought 2x 16GB SLC for ~ $1200 + $400 for a ARC-1210

http://www.xtremesystems.org/forums/...d.php?t=172012

[Nizzen]

only a moron will spend $1000 on an 80GB SSD

This IS Xtremesystems! Who cares about money? Expensive hardware parts FTW

[F.E.A.R.]

@ low

Tomorrow?

[Computurd]

yes we are having benching smackdowns! we need the i/o extreme in there as well!

[lowfat]

@ low

Tomorrow?

Hopefully.

[lowfat]

it arrived

[Ao1]

Nice. Looking forward to seeing how this thing performs.

[One_Hertz]

Damn now I have to check this thread every 15 minutes until you post results haha. And I have an exam in a couple of hours.

[F.E.A.R.]

[XS Janus]

[Jor3lBR]

Guys he will have to read the 142 pages on the user's manual first, calm down. I'm receiving my on Monday

[F.E.A.R.]

He need only the quickstart

[One_Hertz]

He should have read the manual before he bought it! Come on lowfat it has been over an hour!

[Ao1]

^ has you lsi turned up yet? (Good luck with your exam btw)

[One_Hertz]

^ has you lsi turned up yet? (Good luck with your exam btw)

Nope. Newegg is slow for Canada

edit: ooo lowfat is on and he is managing attachments!

[lowfat]

Quick run of the fulltest.icf from the OCZ Forums. 64 outstanding IOs.

Damn near identical to 4 x X25-Ms on ICH10R. However the above bench was w/ a stock CPU. The run I did w/ the X25-M's was @ 4.2GHz. I can't run higher clocked ones until I have the time to throw a new motherboard in (sitting on my desk).

I don't have a whole lot of time to bench today so far. As I am just on my lunch break and likely will be working for the remainder of the day.

[One_Hertz]

CPU speed actually doesn't effect IOMeter. Please do some real world tests when you get a chance. 4kb random reads and writes would be nice to see as well.

[XS Janus]

Guys he will have to read the 142 pages on the user's manual first, calm down. I'm receiving my on Monday

Who reads manuals!?

Nice scores lowfat! Bring it on!

[alfaunits]

CPU speed actually doesn't effect IOMeter.

Actually it does but not much. It uses a lot of RAM memory to do MFT-like linearization of writes (done by driver), so it does actually use CPU cycles.
I doubt it affects sequential, but I think it does affect latency of writes.

[jimhsu]

How well does this thing handle interleaving IO operations? One of the recurring weaknesses I've found with the X-25M is the inability to handle IO workloads while a large seq. write is going on. I.e. read ops simply "stop" when you try to copy a 2GB iso to the drive. This strangely does not happen with RANDOM writes.

[Computurd]

the fulltest.zip you linked is 4kwrite? 100 percent random. i thought it was something else lol. i am trying to stay away from write testing i am afraid of beating on my array too much.

[Jor3lBR]

Pcmark05 Please!

[One_Hertz]

Actually it does but not much. It uses a lot of RAM memory to do MFT-like linearization of writes (done by driver), so it does actually use CPU cycles.
I doubt it affects sequential, but I think it does affect latency of writes.

Could you link to some more info? I can't replicate any change at all with 2ghz vs 4.7.

[lowfat]

Could you link to some more info? I can't replicate any change at all with 2ghz vs 4.7.

I think he is talking about w/ the ioXtreme.

[Computurd]

cmon lowfat, we are waiting here....