• Some users have recently had their accounts hijacked. It seems that the now defunct EVGA forums might have compromised your password there and seems many are using the same PW here. We would suggest you UPDATE YOUR PASSWORD and TURN ON 2FA for your account here to further secure it. None of the compromised accounts had 2FA turned on.
    Once you have enabled 2FA, your account will be updated soon to show a badge, letting other members know that you use 2FA to protect your account. This should be beneficial for everyone that uses FSFT.

To multilane or not?

400+whpwrx

Gawd
Joined
Sep 27, 2003
Messages
557
That is the question....


So given an intial array of 5 disks, and a card that can handle multiple arrays should i go multilane or not? What are the pros and cons of each?
 
400+whpwrx said:
That is the question....


So given an intial array of 5 disks, and a card that can handle multiple arrays should i go multilane or not? What are the pros and cons of each?

No reason not to go multilane really.

Same bandwidth, smaller cables.
 
Doesn't really matter. It's the same signaling rate, etc, just different cabling.

 
i was hoping you would answer...

maybe you can clear this up as well..

arcea 11xx series is the pcix versions of the 12xx series correct? But the 12xx series has a bit faster of a proccessor?

is using pcix worth the slight cpu decrease? (i have both on the mobo)
 
The 11xx series is pci-x based; the 12xx are (mostly (I think)) bridged from pci-x to pci-express (see also the IOP332 block diagram). The 12xxML and 1280 are IOP341 based; this means they aren't bridged designs, and the IOP341 is a good deal faster (one or two 1.2 gHz processors instead of one 800 mHz processor; I don't know how many Areca has used). I haven't seen what the performance of the *MLs are, but in theory they could be faster by quite a bit.

The 11xx series is probably a little faster - it's not bridged, and the bridge adds a little latency. The 12xx non-ML is slower. However, I think the effects of the bridge are minimal. The difference is probably a few microseconds of latency at most. I wouldn't worry about speed when considering which card to get. Which kind of slot you'll run out of first is probably a greater concern ;)

As an aside, has anyone else seen the IOP333 block diagram? I think they're linking to the wrong thing (the processor datasheet disagrees with their layout, for example) but it'd be a neat product. Everything in one chip - raid 6 and SAS - and presumably it could get high enough volume to make them cheap. I'd like that :D

 
Back
Top