• 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.

raid?

DougLite said:
What we mean by highest common is this, as another example:

Say you mix PC2700 and PC3200 RAM modules. Barring a weird chipset bug that makes them not work at all, they will run at PC2700, not arbitrarily run at PC2100. That's what highest common speed means. They will run at the best speed and capacity that is common to all drives. If you RAID-1 an 80GB and 120GB, you get 80GB - the highest common capacity. That's what we mean.

Ok. Sounds like a matter of semantics at this point. We're both trying to say the same thing, but are expressing it in two different ways.

Here's an example of how I use "lowest common denominator:" We'd get customers calling the support line that would install RAM backwards or fire up a CPU without a heatsink. They were more often than any other calls we would get, yet certainly of a lower level of competence than most people that attempt to put PC's together themselves for the first time. Therefore, we would refer to these people as "LCD's." They brought the IQ level of the entire customer base down by a few dozen points.

Also, on RAID-1, it would be conceivable to have three drives mirrored with the same data, thus extending fault tolerance to allow two drives to go out without data loss. This is also the fastest RAID configuration for loads that are 90%+ reads of an extremely short and random nature, as a smart RAID controller can allow each spindle to service different read requests individually, rather than tying up all the spindles for one request at a time with striping. Obviously, this doesn't work for writes, as athe writes go to all of the spindles at the same time.

I've never seen a RAID controller allow that, but I'll take your word for it. All of the controllers I've use, you select a source and you select a mirror, and the number of mirrors has to equal the number of sources and the sources are determined per drive, so the end result was always an even number. But I'm one of those old geezers that gets stuck in their ways. I see something I like and I continue to use it until it's EOL. :D So it's very likely they're out there and I've never seen them. ;)
 
Back
Top