Re: Intel SSDs that may not suck - Mailing list pgsql-performance

From Merlin Moncure
Subject Re: Intel SSDs that may not suck
Date
Msg-id BANLkTi=GsyBfq+ApWPR_qCA7AN+NqT=zww@mail.gmail.com
Whole thread Raw
In response to Re: Intel SSDs that may not suck  (Greg Smith <greg@2ndQuadrant.com>)
Responses Re: Intel SSDs that may not suck  (Scott Carey <scott@richrelevance.com>)
List pgsql-performance
On Mon, Apr 4, 2011 at 8:26 PM, Greg Smith <greg@2ndquadrant.com> wrote:
> On 03/28/2011 04:21 PM, Greg Smith wrote:
>>
>> Today is the launch of Intel's 3rd generation SSD line, the 320 series.
>>  And they've finally produced a cheap consumer product that may be useful
>> for databases, too!  They've put 6 small capacitors onto the board and added
>> logic to flush the write cache if the power drops.
>
> I decided a while ago that I wasn't going to buy a personal SSD until I
> could get one without a volatile write cache for less than what a
> battery-backed caching controller costs.  That seemed the really disruptive
> technology point for the sort of database use I worry about.  According to
> http://www.newegg.com/Product/Product.aspx?Item=N82E16820167050 that point
> was today, with the new 120GB drives now selling for $240.  UPS willing,
> later this week I should have one of those here for testing.
>
> A pair of those mirrored with software RAID-1 runs $480 for 120GB.  LSI
> MegaRAID 9260-4i with 512MB cache is $330, ditto 3ware 9750-4i.  Battery
> backup runs $135 to $180 depending on model; let's call it $150.  Decent
> "enterprise" hard drive without RAID-incompatible firmware, $90 for 500GB,
> need two of them.  That's $660 total for 500GB of storage.
>
> If you really don't need more than 120GB of storage, but do care about
> random I/O speed, this is a pretty easy decision now--presuming the drive
> holds up to claims.  As the claims are reasonable relative to the
> engineering that went into the drive now, that may actually be the case.

One thing about MLC flash drives (which the industry seems to be
moving towards) is that you have to factor drive lifespan into the
total system balance of costs. Data point: had an ocz vertex 2 that
burned out in ~ 18 months.  In the post mortem, it was determined that
the drive met and exceeded its 10k write limit -- this was a busy
production box.

merlin

pgsql-performance by date:

Previous
From: Chetan Suttraway
Date:
Subject: Re: Which is better Index
Next
From: Thom Brown
Date:
Subject: Partial index slower than regular index