[BBLISA] Fileserver opinion

[Grant Young]

In my experience there is a difference between 7200 and 15000 drives.  It can be masked to some extent by having cache on the disk controller but the difference remains.  Larger disk arrays like EMC devices are basically built around intelligent caching engines.  For the most part their performance is driven largely by how much I/O they can process through their cache and service processors but the backing drives have an impact as well.

Having a RAID controller with writeback cache will make a big difference. Buy as much cache as you can if performance is important to you.

There's a old maxim in storage:  Speed, safety, and cost; pick two.  You can buy cheaper drives but they're likely to have been less rigorously tested or tested to a lower standard and are more likely to fail earlier.  

Another less obvious lesson I've learned:  Clean power makes storage work better.  Dirty power kills drives and can kill their performance even if they appear to be working.  

Everybody likes to rag on EMC and other storage vendors for charging so much per terabyte but they engineer the headaches out of the storage.  

Grant Young
grant at toaster-repair.com

On Aug 11, 2010, at 5:45 PM, Ian Stokes-Rees wrote:

>> I don't have any advice, but I have a few questions:
>> 
>> 0) What is the drive interface card? Several cards? Do they do the RAID
>> support or is that in software?
> 
> Adaptec RAID 52445 28-Port (24 Int/4 Ext) (SAS) (SFF-8087)
> 
> Hardware RAID.  One card.
> 
>> 1) Is it obvious that one needs 12 cores to fill a single GB ethernet
>> link? Or are there more ethernet links? If more, how do you balance the
>> load (not a rhetorical question - we have systems with multiple
>> ethernets and don't have any idea how to use them effectively).
> 
> Another colleague has already given the very good advice of considering
> a Dell 6248 switch that has 2 10GigE ports so we'd then get high b/w
> network access to the file server with the addition of a 10GigE card on
> the server.
> 
>> 2) With data spanned over 5 drives, is there still a performance
>> difference between 7,200 rpm and 15,000 rpm drives? Have you the ability
>> to experiment before putting out the cash?
> 
> I don't know.  No, we can't test this before purchasing, so any
> experience on this would be appreciated.  Our best guess is that faster
> is faster, and we need faster, but it is a "best guess", hence the
> petition to bblisa.
> 
>> 3) How long do you think it will take to rebuild a volume after a drive
>> failure? Do you need such large volumes. If the volumes are smaller the
>> rebuild times are lower.  I have no experience with 15,000 rpm SAS
>> drives, but is the system really usable during a rebuild? Now if the
>> drives have 500,000 hours mean time to failure, and you have 10, that is
>> still 5 years mean time to a rebuild, but somehow I don't believe 15,000
>> rpm drives are really that durable in real life. Will the system be down
>> a day a year for RAID rebuilding?
> 
> Good question.  With RAID10 I'd hope that re-buildling can be done in
> the background with the data "at risk" during that period.  We're not in
> an operational environment where uptime demands are extremely high --
> i.e. we're only aiming for >97% uptime (down several days over the
> course of a year is acceptable).
> 
> Ian
> 
> -- 
> Ian Stokes-Rees, PhD                       W: http://hkl.hms.harvard.edu
> ijstokes at hkl.hms.harvard.edu               T: +1 617 432-5608 x75
> NEBioGrid, Harvard Medical School          C: +1 617 331-5993
> 
> <ijstokes.vcf>_______________________________________________
> bblisa mailing list
> bblisa at bblisa.org
> http://www.bblisa.org/mailman/listinfo/bblisa