[Discuss] SSD

[jay at lentecs.com (Jason Normand)]

I was just recently digging into sees for some database logging.  What I
have found is that newer consumer drives are faster and cheaper but have a
shorter write life than older generation drives.  This is because the 25nm
mlc has fewer write cycles than the old 34nm.  And fewer still than "high
endurance" mlc which is found in enterprise sees such as Intel 710 .  And
of course fewer still than slc. That being said for most applications even
consumer drives will outlay their 3-5 year warranty.

There is also the facter of controller reliability an features. And there
is alot to consider there.

We ended up Going with the Samsung 830s.  256gig was on sale at newegg for
$220.  This has consumer mlc but 256 gave us plenty of over provisioning.
And the Samsung controller is right there in reliability with Intel at a
lower price.
On May 31, 2012 1:00 PM, "Jack Coats" <jack at coats.org> wrote:

> I ran virtual systems on mainframes back when.
>
> There was a neat thing they did then was to basically NOT do virtual
> memory on the 'client OS'.  The 'client OS' could figure out it was
> being run as a virtual machine, and through special communications
> (called Diag back when) would tell the host OS what it needed done.
> That way the hostOS actually did all the virtual memory management for
> the guest systems.  ... If we turned that off, the overhead on the
> guestOS went WAY up.
>
> Normal cpu overhead back then was about 5% to run as in a guestOS
> rather than directly in the hostOS.  The first time I remember being
> told we were running 'second level', we had been running for a week in
> production and no one had noticed any problems. ...
>
> I wonder how todays virtualized systems overhead runs?
> _______________________________________________
> Discuss mailing list
> Discuss at blu.org
> http://lists.blu.org/mailman/listinfo/discuss
>