".. noo, 'TIS the rabbit!"

-r

What about the fact* that if something runs amok in a thin-provisioned client and pins a LUN at 100%, the underlying allocation doesn't scale back DOWN after cleanup of such an event.. ending up with the wasted space anyway?

(or the rumour that our OS of choice doesn't really like the magic happening under the covers if you thin-provision, so we're better off avoiding it anyway)

-r

* .. our arrays being EMC and this is what the storage folk tell me.. what do i know, i'm the unix guy.

people who drink the kool-aid whenever vendors of said products repeatedly swear up and down all their tasks/patching/operations are 'totally no-impact and no-visibility changes.' combine that with people unwilling to take downtime or spend $$$ to properly protect the contents ahead of time and you have just cooked a recipe for disaster.

-r (not speaking from personal experience.. of course.. :/ )

.. you do realize that each one of those listed items is itself an increased cost to the corporation which buttresses the argument you're trying to oppose? and if you're going to artificially inflate the costs to that corporation in this country.. they'll go elsewhere. check what's happening in corporate america today as some validation.

I was at the IBM location in Charlotte, NC this past week for a workshop. I was there ~3-4 years ago.. they have a nice-sized campus of a number of buildings on the north side of town. Today, I believe I heard one of the site folks mention they now occupied less than half the space. What was more disturbing was the comment that a fair amount of the work have been moved offshore.

You want to keep sqeezing the corporate sector, go right ahead. What will you do when the sponge dries out?

-r

.. do we learn nothing from SimCity?

-r

What bullshit. Go read Smedley Butler's "War Is a Racket" http://warisaracket.com/. Written in the 1930's by a guy whose "cred" beats yours, buddy. War is a "for profit" business, run by the taxing authority for the benefit of their constituents (the banksters, not you or me). Perhaps if there's no money to run wars, it would be because people don't want them. Hmmm.. The rest of your screed might as well read "I think controlling people is more important than individual freedom, as long as I get to make the choices". More bullshit. You need to wake up and smell the coffee. You don't live the USA that you think you do...

Anandtech discovered that write performance on JMICRON controllers (not used by Intel) went to practically zero with time. The writer (and other publications I believe) went looking for the same issue in non-JMICRON controllers, and discovered that while Intel controllers were by far the least affected, they still suffered some degradation. Intel quickly updated their firmware, while everyone else (who had much more severe issues) either fixed it later or not at all.

It was my understanding that the performance degradation was a known drawback to first-generation SSDs, but that Intel's controller was specifically designed to work around it and other SSD performance issues at the time. So their SSD was expected to not have the problem, which was why they were surprised when some little-known reviewer showed that the disks could suffer semi-permanent performance degradation under certain circumstances.

Disclaimer: I have an X25-M supposedly affected by the issue, and I haven't bothered to upgrade the firmware.

And you probably won't ever have to, because as I remember the description of the problem, it's not usually triggered in normal use.

Stupid people with no math skills! News at 11. ;-)