Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 30 Dec 2011 23:09:17 +1000
From:      Da Rock <freebsd-questions@herveybayaustralia.com.au>
To:        freebsd-questions@freebsd.org
Subject:   Re: Why do I feel like compact flash is more reliable than SSD ?
Message-ID:  <4EFDB7FD.4040606@herveybayaustralia.com.au>
In-Reply-To: <20111230124153.GA18989@slackbox.erewhon.net>
References:  <1325229204.34713.YahooMailNeo@web140405.mail.bf1.yahoo.com> <20111230124153.GA18989@slackbox.erewhon.net>

next in thread | previous in thread | raw e-mail | index | archive | help
On 12/30/11 22:41, Roland Smith wrote:
> On Thu, Dec 29, 2011 at 11:13:24PM -0800, UFS User wrote:
>
>> I have run a lot of different FreeBSD systems off (fileservers, firewalls,
>> routers, etc.) off of compact flash cards[1] and have never had a CF part
>> fail.
>>
>> Most of these were read-only mode, but some of them were left mounted 'rw'
>> for years (with no swapping, of course).  The bottom line is, they never
>> failed, and some were (and are) in the field for over 8 years now.
>>
>> But everyone I know (including me) has had an SSD fail, usually with no
>> explanation.
> It seems that unlike disk drives, SMART doesn't really give you a warning with
> SSDs.
>
> But as a counterpoint, who hasn't ever had a harddrive fail? And there might
> be some negativity bias [http://en.wikipedia.org/wiki/Negativity_bias] at work
> here too.
>
>> So is this just chance, or ... are CF cards really a lot more reliable than
>> SSD ?
> Although I've been looking at SSD's, I've held off for now because of cost and
> small disk sizes. But concrete data is relatively scarce, probably due to the
> fact that SSD's haven't been available _that_ long.
>
> There are several studies available for harddisks, e.g. from google
> [http://labs.google.com/papers/disk_failures.pdf] and Carnagie Mellon [http://www.usenix.org/events/fast07/tech/schroeder/schroeder_html/index.html].
> Generally, more disks fail as they age.
>
> But studies concerning SSD's seem to be almost nonexistant. The most interesting
> inventarization I found was on Tom's Hardware
> [http://www.tomshardware.com/reviews/ssd-reliability-failure-rate,2923.html].
> Some interesting quotes covering the main points;
>
> 	Even though our data set is one-twentieth the size of previous studies on
> 	hard drives, our information starts to suggest that SLC-based SSDs are no more
> 	reliable than SAS and SATA hard drives.
> 	...
> 	Our data center survey exclusively covers Intel SSD failure rates because
> 	those are the drives that big businesses currently trust the most.
> 	...
> 	Should you be deterred from adopting a solid-state solution? So long as
> 	you protect your data through regular backups, which is imperative regardless
> 	of your preferred storage technology, then we don't see any reason to shy away
> 	from SSDs.
>
> Currently SSD's are too small for my taste. But when that changes, I'll
> seriously consider switching to an SSD with an equal sized HDD for nightly
> backups.
I'd only consider them in laptops- and even then I don't see too much 
difference in power use, only shock resistance. And I'd back them up to 
the network anyway- store most of the data on a fileserver and only copy 
what was being worked on to the lap.

I can't see too much point otherwise, 60Gb is reasonable for a desktop 
with the usual suspects and is reasonably priced (not too over the top 
anyway...).



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4EFDB7FD.4040606>