From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Shubert Subject: Re: RAID Class Drives` Date: Sun, 21 Mar 2010 09:14:31 -0700 Message-ID: References: <7db987b31003170648j19e3346bi1050e703ef8c811c@mail.gmail.com> <4BA258AD.5020605@gmx.net> <4BA33284.7000304@anonymous.org.uk> <4BA3BA1D.50206@gmx.net> <4BA5053D.1040607@tmr.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: In-Reply-To: <4BA5053D.1040607@tmr.com> Sender: linux-raid-owner@vger.kernel.org To: linux-raid@vger.kernel.org List-Id: linux-raid.ids Bill Davidsen wrote: > Joachim Otahal wrote: >> John Robinson schrieb: >>> On 18/03/2010 16:45, Joachim Otahal wrote: >>>> [...] You should take care of the temperature of the drives, >>>> 30=B0C to 35=B0C is preferred, above 35=B0C the lifespan goes down= , over=20 >>>> 40=B0C rapidly down. >>> >>> Do you have a reference for this? Most drives' operating temperatur= e=20 >>> range is specified up to 55=B0C, sometimes higher for enterprise=20 >>> drives, without any indication (apart from common sense perhaps) th= at=20 >>> running them this hot reduces lifespan. >>> >>> Cheers, >>> >>> John. >>> >> About a half year ago the german publisher c't did this testing (or=20 >> reported from a big testing, cannot remember) what the best=20 >> temperature of desktop drives is. The statistic varied from drive to= =20 >> drive since some are less than 5=B0C over room temperature, others a= re=20 >> 15=B0C or more over room temperature (of course mounted behind a sil= ent=20 >> fan which keeps the air moving, no turbine mode). >> The result was that 10=B0C and 15=B0C are not good for the drives. T= he=20 >> "perfect sweet spot" changes from drive to drive (even within on=20 >> manufacturer), but all of them had their sweet spot somewhere around= =20 >> 20=B0C to to 35=B0C with variation in the range of measurement error= =2E >> Some drives has a higher failure rate at 40=B0C, for some 55=B0C was= no=20 >> problem at all and showed no real change in the failure rate. The la= st=20 >> two examples were the extreme cases. >> >> Some of my drives are 2=B0C above room temperature, others are 12=B0= C over=20 >> room temperature. Sine I really take care that non reaches 40=B0C ev= en=20 >> in summer the failure rate got down from "every few month" to once i= n=20 >> the 3 years which is the time I really take care of the drive=20 >> temperatures. There are 6 drives currently in use from 750GB (the=20 >> hottest of all my drives) up to 1.5 TB in my private machines, only=20 >> one of them shows a gradual change in the SMART values (reallocated=20 >> sector count), which mean it will probably fail in about 1.5 years i= f=20 >> the error rate stays constant. At work (at least the two machines 10= 0%=20 >> under my control) I had the same effect, keep the HD's cool and they= =20 >> will live long, let them get over 40=B0C and be ready to replace the= m soon. >=20 > 40=B0C is a good target, readily available to people in the Arctic. I= t=20 > requires a lot of cooling to do it in normal climates where the ambie= nt=20 > may be mid to high 40s. Fortunately my experience looks more like=20 > Google's, as long as you move enough air over the drive to avoid hot=20 > spots they seem to do well, hitting 43-46 much of the time. If I repl= ace=20 > them because they're obsolete and working, they lasted long enough.=20 > Perhaps being "always on" is part of longevity, the ones I have on fo= r=20 > 5-6 years seldom fail, the desktop cycled daily maybe half that. >=20 > I do note that the WD drives run about 8=B0C cooler than Seagate. Tha= t's=20 > the "black" drive, I guess, the "green" drives would run cooler, base= d=20 > on power use. I will switch to them next build. >=20 I find this whole discussion of drives interesting. Thanks to everyone=20 for their input. A thought occurred to me today. Realizing that the drives are generatin= g=20 heat, *if* it's true that drives which run hotter have a shorter=20 lifetime (which is debatable), it's possible that the cause of heat=20 generation (friction?) is the contributing factor to the shorter=20 lifetime, and not the heat itself. IOW, if a drive runs hot, removing=20 the heat more quickly (reducing its operating temp) wouldn't necessaril= y=20 increase the drive's lifetime. Just a thought. --=20 -Eric 'shubes' -- To unsubscribe from this list: send the line "unsubscribe linux-raid" i= n the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html