× The internal search function is temporarily non-functional. The current search engine is no longer viable and we are researching alternatives.
As a stop gap measure, we are using Google's custom search engine service.
If you know of an easy to use, open source, search engine ... please contact support@midrange.com.



Most IOs on a database,application, or web server are reads. There is no
wear-leveling issue for reads; writes are what induce wear on an SSD (and
USB Flash drive, CF/SD card, etc.). Not that wear-leveling can't be an
issue; I just think the author is overstating the potential for a problem.

And as to RAID cards being a bottleneck, so what? If people max out their
RAID controller's ability to keep up, the controller vendors will see a
financial incentive to produce higher-performing controllers. At that time,
maybe the next bottleneck will be the bus (why, for instance, we've gone
from SPD to PCI and so on). Or 6Gb SAS. Or RAM. Or the server's capacity
for network IO. Or something else.

For so many years the bottleneck has been platter-based drives. Now it's
somewhere else in the system. Yawn. There's always a bottleneck in a
system; otherwise we'd always see instant response times to everything. All
we're seeing now is the potential for the bottleneck to shift someplace else
in the architecture.


On Mon, Mar 8, 2010 at 10:47 AM, Jim Oberholtzer <jim.oberholtzer@xxxxxxxxxx
wrote:

At an IBM pre-POWER7 release meeting Larry and I asked the question
about the SSD degradation. The answer was simple, we (IBM) engineered
it with sufficient overcapacity that the lifespan of the drive will
equal that of a physical drive. They also have sufficient performance
testing to be confident in the stated performance of the RAID arrays as
long as they are built as recommended.

While I think it is too early to tell if the SSDs are in fact living up
the the high praise they are getting, it is also a bit early to start
worrying about the ill effects of the technology. It is true that SSDs
are considerably higher in cost per storage unit than traditional DASD,
but then years ago when I (and many others on the list as well) started
in IT, mass storage was Tape, only transactional data that was less than
several months old was kept on actual DASD storage. Mechanical DASD is
now the new tape, relatively cheap, easy to manage, and reliable. Makes
you wonder what's next.

Jim Oberholtzer
CEO/Chief Technical Architect
Agile Technology Architects -- LLC



David Gibbs wrote:
*This message was transferred with a trial version of CommuniGate(r) Pro*
I recently saw this on Slashdot ... and since IBM i supports both RAID
and SSD's, I thought it might be interesting ...


http://hardware.slashdot.org/story/10/03/06/1650232/Wear-Leveling-RAID-Can-Wipe-Out-SSD-Advantage

This article discusses using solid state disks in enterprise storage
networks. A couple of problems noted by the author: wear leveling can eat up
most of a drive's bandwidth and make write performance no faster than a hard
drive, and using SSDs with RAID controllers brings up its own set of
problems. 'Even the highest-performance RAID controllers today cannot
support the IOPS of just three of the fastest SSDs. I am not talking about a
disk tray; I am talking about the whole RAID controller. If you want full
performance of expensive SSDs, you need to take your $50,000 or $100,000
RAID controller and not overpopulate it with too many drives. In fact, most
vendors today have between 16 and 60 drives in a disk tray and you cannot
even populate a whole tray. Add to this that some RAID vendor's disk trays
are only designed for the performance of disk drives and you might find that
you need a disk tray per SSD drive at a huge cost.'


--
This is the Midrange Systems Technical Discussion (MIDRANGE-L) mailing list
To post a message email: MIDRANGE-L@xxxxxxxxxxxx
To subscribe, unsubscribe, or change list options,
visit: http://lists.midrange.com/mailman/listinfo/midrange-l
or email: MIDRANGE-L-request@xxxxxxxxxxxx
Before posting, please take a moment to review the archives
at http://archive.midrange.com/midrange-l.





As an Amazon Associate we earn from qualifying purchases.

This thread ...

Follow-Ups:
Replies:

Follow On AppleNews
Return to Archive home page | Return to MIDRANGE.COM home page

This mailing list archive is Copyright 1997-2024 by midrange.com and David Gibbs as a compilation work. Use of the archive is restricted to research of a business or technical nature. Any other uses are prohibited. Full details are available on our policy page. If you have questions about this, please contact [javascript protected email address].

Operating expenses for this site are earned using the Amazon Associate program and Google Adsense.