Let me give you guys the skinny on what an engineer told me who deals a lot
with SSDs. They do have limited read write cycles. Under "normal" usage, they
last about five years. So I would have to agree with Kevin on this one.
On our backup system, the spool drives are used heavily and I would not
consider it "normal" usage. Basically, your expensive ssd drives are not going
to last very long in this kind of setup. SSD's make good system drives and
good laptop drives where the read and write cycle is more "normal". Of course,
do not get me wrong, the performance gains of SSDs is very appealing and I have
caught myself considering their application a time or two.
Of course, the price of SSD's may drop as economy of scales becomes more
apparent and SSD's move further along in the product lifecycle curve. If I had
to make a choice right now, I would go with 15K RPM drives and a good RAID
controller. Now five years from now, I would probably recommend something
else, but that is why we all love technology, right?
Randall Svancara
Systems Administrator/DBA/Developer
Main Bioinformatics Laboratory
----- Original Message -----
From: "Kevin Keane" <subscription AT kkeane DOT com>
Cc: "Bacula-Users" <bacula-users AT lists.sourceforge DOT net>
Sent: Friday, July 24, 2009 3:19:22 PM GMT -08:00 US/Canada Pacific
Subject: Re: [Bacula-users] Bacula spool on SSD -- solid state
drive?performance testing?
John Lockard wrote:
> For spool, I would worry about the limited write (erase) cycles of
> SSD. Sure, the speed of read/write is enormously appealing, but with
> how much my spool gets hit I'd hate to have to set a really early
> replacement schedule because my media can't handle many writes.
> Rather than SSD for spool, RAM-Disk looks like a better way to go.
I'm wondering about that. I haven't actually done any research into it,
but I would have assumed that a spool actually would be pretty easy on
the write cycles, because you just create the file, never modify it, and
eventually delete it. If your spool is small, you might be doing that a
few times for a full backup, but even then it seems to me that there
should only be a couple writes to each cell per day. Let's say that you
spool and despool 10 times for a full backup.
I think even the cheapest flash memory has an MTBF of 10,000 write
cycles, which means that an SSD used for spooling should last for 1000
full backups - even more differential or incremental ones.
Or is my reasoning wrong here? Without practical experience, that's
entirely possible.
--
Kevin Keane
Owner
The NetTech
Find the Uncommon: Expert Solutions for a Network You Never Have to Think About
Office: 866-642-7116
http://www.4nettech.com
This e-mail and attachments, if any, may contain confidential and/or
proprietary information. Please be advised that the unauthorized use or
disclosure of the information is strictly prohibited. The information herein is
intended only for use by the intended recipient(s) named above. If you have
received this transmission in error, please notify the sender immediately and
permanently delete the e-mail and any copies, printouts or attachments thereof.
------------------------------------------------------------------------------
_______________________________________________
Bacula-users mailing list
Bacula-users AT lists.sourceforge DOT net
https://lists.sourceforge.net/lists/listinfo/bacula-users
------------------------------------------------------------------------------
_______________________________________________
Bacula-users mailing list
Bacula-users AT lists.sourceforge DOT net
https://lists.sourceforge.net/lists/listinfo/bacula-users
|
