Vibration Killing Enterprise Disk Performance? 159
An anonymous reader writes "Is vibration killing disk performance? ZDnet reports on research that a carbon fiber anti-vibration rack increased random read performance by 56% to 246% and random write [performance] by 34% to 88%. Vibration is a known disk problem, but this is one of the few attempts to quantify its impact — which looks to be much greater than suspected."
Re:not surprising really (Score:2, Insightful)
How difficult would it be to account for this vibration performance degradation in such a case?
If you had some kind of vibration sensor that measured vibration levels, couldn't it then talk back to code telling it to slow down because there's too much vibration?
Can't believe it (Score:4, Insightful)
that CS disk drives are more sensitive to the vibration from physically coupled adjacent disk drives.
and
The problem is that most civilians don’t understand the problem and are not willing to pay to solve it.
Why should most people care about vibration caused by adjacent drives if most people only have one drive.
The other issue from TFA is that I can't believe a different rack can cause 250% performance improvement, unless you really stacked the deck against steel racks - loose screws, hard drives not properly mounted...? I assume this means that current server racks see I/O rates that are only 40% of what is advertised by manufacturers. Are we expected to believe that no one has noticed this? What about multiple drives in a server. There is no rack separating those drives. This reads like marketing, not real research.
http://www.greenplatformcorp.com/ [greenplatformcorp.com] is the site if you are interested and the "research" is several months old.
Re:Anyone know why it affects SSD? (Score:4, Insightful)
Is you comment based on this part of the article?
SSD value. Flash SSDs have fast random read access. But disks can improve their performance by 50% through vibration damping, that changes value proposition for SSDs.
I think the author is saying that if you can improve performance by 50% then there's less value in moving to SSDs that previously thought.
Disks need alignment and balancing (Score:3, Insightful)
Just in time, too (Score:4, Insightful)
This is news we needed 20 years ago. SSD is going to replace mechanical HD over the next couple of years making the whole vibration issue irrelevant.
Ah well better late than never I guess.
Re:Anyone know why it affects SSD? (Score:4, Insightful)
the article does not say that it affects SSDs, but that it affects the SSD value proposition (aka, if you can spend little $$$ on carbon rack enclosures and get a significant seek performance increase, spending the large amount of $$$ to go full-ssd might not be as cost effective).
My over one year old SSD drive can do ~6,000 under a database workload, the next-gen consumer SSD drives are reaching 60,000 random IOPS, and there are enterprise drives that can do over 150,000 IOPS with streaming speeds over a gigabyte per second.
This is a little like saying that Hayes has released a new 56K modem that resists line noise 50% better than existing modems, which affects the value proposition of 1Gbps fibre.
There's also no need to go "Full SSD". The newer virtualizing SAN arrays can migrate individual blocks of data between tiers of storage to place everything on the appropriate storage depending on the need for performance.