* Western Digital Green 3TB SATA3 experiences @ 2013-03-20 8:09 Andris Berzins 2013-03-20 8:28 ` Mikael Abrahamsson ` (3 more replies) 0 siblings, 4 replies; 14+ messages in thread From: Andris Berzins @ 2013-03-20 8:09 UTC (permalink / raw) To: linux-raid Hello, I am running RAID5 array on 6x 3TB WD SATA disks. I have problems with all of these disks (including replaced one). Disks are being randomly kicked out from array and SMART shows pending sectors which usually can be fixed by read-write or write to that sector. Has anyone experienced something similar with WD green series? Is this because of WD "green" series? Anyone running raid on 3TB SATA drives can suggest model disk that runs without problems? Thank you! ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: Western Digital Green 3TB SATA3 experiences 2013-03-20 8:09 Western Digital Green 3TB SATA3 experiences Andris Berzins @ 2013-03-20 8:28 ` Mikael Abrahamsson 2013-03-20 8:48 ` Roman Mamedov ` (2 subsequent siblings) 3 siblings, 0 replies; 14+ messages in thread From: Mikael Abrahamsson @ 2013-03-20 8:28 UTC (permalink / raw) To: Andris Berzins; +Cc: linux-raid On Wed, 20 Mar 2013, Andris Berzins wrote: > I am running RAID5 array on 6x 3TB WD SATA disks. > I have problems with all of these disks (including replaced one). > Disks are being randomly kicked out from array and SMART shows > pending sectors which usually can be fixed by read-write or write to that sector. Drives with pending sectors should be RMAed. > Has anyone experienced something similar with WD green series? > Is this because of WD "green" series? > > Anyone running raid on 3TB SATA drives can suggest model disk that > runs without problems? WD RED series is designed for this kind of usage and should not be kicked out because the drive will return UNC in a timely fashion. <http://en.wikipedia.org/wiki/Error_recovery_control>. The WD Green series is not designed for RAID usage and might get kicked out due to read timeouts. -- Mikael Abrahamsson email: swmike@swm.pp.se ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: Western Digital Green 3TB SATA3 experiences 2013-03-20 8:09 Western Digital Green 3TB SATA3 experiences Andris Berzins 2013-03-20 8:28 ` Mikael Abrahamsson @ 2013-03-20 8:48 ` Roman Mamedov 2013-03-20 9:21 ` Andris Berzins 2013-03-20 12:40 ` Rainer Fügenstein 2013-03-20 18:50 ` Chris Murphy 3 siblings, 1 reply; 14+ messages in thread From: Roman Mamedov @ 2013-03-20 8:48 UTC (permalink / raw) To: Andris Berzins; +Cc: linux-raid [-- Attachment #1: Type: text/plain, Size: 1084 bytes --] On Wed, 20 Mar 2013 10:09:42 +0200 "Andris Berzins" <pkix@inbox.lv> wrote: > I am running RAID5 array on 6x 3TB WD SATA disks. > I have problems with all of these disks (including replaced one). > Disks are being randomly kicked out from array and SMART shows > pending sectors which usually can be fixed by read-write or write to that sector. Perhaps you have a problem with something other than the drives, e.g.: - a bad or insufficient PSU, providing too low (or too high) voltage over 5V or 12V (this could manifest only under load, too); - not enough cooling? - inadequate case, resulting in overly high vibration or even resonance? > Has anyone experienced something similar with WD green series? If you see a sectors repeatedly appearing that become unreadable but are fixed after a write, it is usually a symptom of a drive that is partially defective and should be exchanged. But since you have this symptom with all of them, maybe the cause is different. > Is this because of WD "green" series? No. -- With respect, Roman [-- Attachment #2: signature.asc --] [-- Type: application/pgp-signature, Size: 198 bytes --] ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: Western Digital Green 3TB SATA3 experiences 2013-03-20 8:48 ` Roman Mamedov @ 2013-03-20 9:21 ` Andris Berzins 2013-03-20 9:29 ` Roman Mamedov 0 siblings, 1 reply; 14+ messages in thread From: Andris Berzins @ 2013-03-20 9:21 UTC (permalink / raw) To: Roman Mamedov; +Cc: linux-raid Quoting "Roman Mamedov" <rm@romanrm.ru>: > On Wed, 20 Mar 2013 10:09:42 +0200 > "Andris Berzins" <pkix@inbox.lv> wrote: > >> I am running RAID5 array on 6x 3TB WD SATA disks. >> I have problems with all of these disks (including replaced one). >> Disks are being randomly kicked out from array and SMART shows >> pending sectors which usually can be fixed by read-write or write to that se >>ctor. > > Perhaps you have a problem with something other than the drives, e.g.: > > - a bad or insufficient PSU, providing too low (or too high) voltage over 5V > or 12V (this could manifest only under load, too); I have bought 550W PSU specially for this. The server is connected through APC UPS. > - not enough cooling? Putting a hand temperature seems lightly warm. > - inadequate case, resulting in overly high vibration or even resonance? Well, the case is average workstation case. >> Has anyone experienced something similar with WD green series? > > If you see a sectors repeatedly appearing that become unreadable but are fix >ed > after a write, it is usually a symptom of a drive that is partially defectiv >e > and should be exchanged. That one which I exchanged worked for 3 month without problems. > > But since you have this symptom with all of them, maybe the cause is differe >nt. > > >> Is this because of WD "green" series? > > No. "Green" series are special because they spin down after 7 seconds and they do not return in timely manner when read error occurs. > > -- > With respect, > Roman ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: Western Digital Green 3TB SATA3 experiences 2013-03-20 9:21 ` Andris Berzins @ 2013-03-20 9:29 ` Roman Mamedov 0 siblings, 0 replies; 14+ messages in thread From: Roman Mamedov @ 2013-03-20 9:29 UTC (permalink / raw) To: Andris Berzins; +Cc: linux-raid [-- Attachment #1: Type: text/plain, Size: 920 bytes --] On Wed, 20 Mar 2013 11:21:32 +0200 "Andris Berzins" <pkix@inbox.lv> wrote: > >> Is this because of WD "green" series? > > > > No. > > "Green" series are special because they spin down after 7 seconds and they do not > return in timely manner when read error occurs. They do not spin down after 7 seconds, they unload their heads. In any case this behavior is not expected to ever cause Current_Pending_Sectors rising (which are plain and simple unreadable sectors no matter how hard you try or how long you wait). You can disable the 7-second unload time behavior by using either "hdparm -J" or using "idle3-tools" http://idle3-tools.sourceforge.net/ (also available in Debian). I would indeed recommend doing that to reduce wear and tear on the head mechanism from constant loads/unloads; but I somewhat doubt this will make a difference in relation to your issue. -- With respect, Roman [-- Attachment #2: signature.asc --] [-- Type: application/pgp-signature, Size: 198 bytes --] ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: Western Digital Green 3TB SATA3 experiences 2013-03-20 8:09 Western Digital Green 3TB SATA3 experiences Andris Berzins 2013-03-20 8:28 ` Mikael Abrahamsson 2013-03-20 8:48 ` Roman Mamedov @ 2013-03-20 12:40 ` Rainer Fügenstein 2013-03-20 13:23 ` joystick 2013-03-20 18:50 ` Chris Murphy 3 siblings, 1 reply; 14+ messages in thread From: Rainer Fügenstein @ 2013-03-20 12:40 UTC (permalink / raw) To: Andris Berzins; +Cc: linux-raid andris, yes, I had such a situation before. IIRC 4 out of 6 3TB WD caviar green drives were broken (3 more or less DoA, 1 failed after about 2 months). sent those 4 back via RMA, the replacement drives work without problems (knocking on wood). looks like they had a (big) bad batch manufactured and are now sending out proper ones as RMA replacements. nevertheless, next time I'll use WD RED drives, as recommended here frequently. cu AB> Hello, AB> I am running RAID5 array on 6x 3TB WD SATA disks. AB> I have problems with all of these disks (including replaced one). AB> Disks are being randomly kicked out from array and SMART shows AB> pending sectors which usually can be fixed by read-write or write to that sector. AB> Has anyone experienced something similar with WD green series? AB> Is this because of WD "green" series? AB> Anyone running raid on 3TB SATA drives can suggest model disk that AB> runs without problems? AB> Thank you! AB> -- AB> To unsubscribe from this list: send the line "unsubscribe linux-raid" in AB> the body of a message to majordomo@vger.kernel.org AB> More majordomo info at http://vger.kernel.org/majordomo-info.html ------------------------------------------------------------------------------ Unix gives you just enough rope to hang yourself -- and then a couple of more feet, just to be sure. (Eric Allman) ------------------------------------------------------------------------------ ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: Western Digital Green 3TB SATA3 experiences 2013-03-20 12:40 ` Rainer Fügenstein @ 2013-03-20 13:23 ` joystick 0 siblings, 0 replies; 14+ messages in thread From: joystick @ 2013-03-20 13:23 UTC (permalink / raw) To: Rainer Fügenstein, linux-raid The problem is the shop, or the transport, almost certainly not the model of drives... On 03/20/13 13:40, Rainer Fügenstein wrote: > andris, > > yes, I had such a situation before. IIRC 4 out of 6 3TB WD caviar > green drives were broken (3 more or less DoA, 1 failed after about 2 > months). sent those 4 back via RMA, the replacement drives work > without problems (knocking on wood). > > looks like they had a (big) bad batch manufactured and are now sending > out proper ones as RMA replacements. > > nevertheless, next time I'll use WD RED drives, as recommended here > frequently. > > cu > > > AB> Hello, > > AB> I am running RAID5 array on 6x 3TB WD SATA disks. > AB> I have problems with all of these disks (including replaced one). > AB> Disks are being randomly kicked out from array and SMART shows > AB> pending sectors which usually can be fixed by read-write or write to that sector. > > AB> Has anyone experienced something similar with WD green series? > AB> Is this because of WD "green" series? > > AB> Anyone running raid on 3TB SATA drives can suggest model disk that > AB> runs without problems? > > > AB> Thank you! > > AB> -- > AB> To unsubscribe from this list: send the line "unsubscribe linux-raid" in > AB> the body of a message to majordomo@vger.kernel.org > AB> More majordomo info at http://vger.kernel.org/majordomo-info.html > > > ------------------------------------------------------------------------------ > Unix gives you just enough rope to hang yourself -- and then a couple of more > feet, just to be sure. > (Eric Allman) > ------------------------------------------------------------------------------ > > -- > To unsubscribe from this list: send the line "unsubscribe linux-raid" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html > -- To unsubscribe from this list: send the line "unsubscribe linux-raid" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: Western Digital Green 3TB SATA3 experiences 2013-03-20 8:09 Western Digital Green 3TB SATA3 experiences Andris Berzins ` (2 preceding siblings ...) 2013-03-20 12:40 ` Rainer Fügenstein @ 2013-03-20 18:50 ` Chris Murphy 2013-03-20 20:55 ` Chris Murphy 3 siblings, 1 reply; 14+ messages in thread From: Chris Murphy @ 2013-03-20 18:50 UTC (permalink / raw) To: Andris Berzins; +Cc: linux-raid On Mar 20, 2013, at 2:09 AM, Andris Berzins <pkix@inbox.lv> wrote: > Hello, > > I am running RAID5 array on 6x 3TB WD SATA disks. > I have problems with all of these disks (including replaced one). > Disks are being randomly kicked out from array and SMART shows > pending sectors which usually can be fixed by read-write or write to that sector. Have you changed the /sys/block/sdX/device/timeout value? Cat it, report the value. For the greens I think the value needs to be at least 125 seconds. Depend on your SATA controller, it may have a separate timeout value that also needs to be changed. If a potential "hang" delay of 125 seconds isn't workable for your application, you'll need different drives. > Has anyone experienced something similar with WD green series? > Is this because of WD "green" series? Yes, the mail list achive is full of such posts. > Anyone running raid on 3TB SATA drives can suggest model disk that > runs without problems? Hitachi Deskstar reportedly still support configurable SCT ERC, so you get set the drive to fail much less than 30 seconds, e.g. 7 seconds. Then md will fix the problems, if they're encountered. These drives are offered in 4TB size also. Chris Murphy ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: Western Digital Green 3TB SATA3 experiences 2013-03-20 18:50 ` Chris Murphy @ 2013-03-20 20:55 ` Chris Murphy 2013-03-21 16:17 ` Roy Sigurd Karlsbakk 0 siblings, 1 reply; 14+ messages in thread From: Chris Murphy @ 2013-03-20 20:55 UTC (permalink / raw) To: Andris Berzins; +Cc: linux-raid On Mar 20, 2013, at 12:50 PM, Chris Murphy <lists@colorremedies.com> wrote: >> Is this because of WD "green" series? > > Yes, the mail list achive is full of such posts. Small correction. They've yanked settable SCT ERC in at least the Blue and Black laptop (Scorpio) drives, which used to have this feature. So it's not just the greens that had the feature removed. I'm pretty sure all of the desktop drives, green, blue, black, have had it removed in newer revisions. Now you can get it in reds, or RE drives only, at least WDC. Otherwise you're looking for a different vendor. Chris Murphy ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: Western Digital Green 3TB SATA3 experiences 2013-03-20 20:55 ` Chris Murphy @ 2013-03-21 16:17 ` Roy Sigurd Karlsbakk 2013-03-21 21:30 ` Chris Murphy 0 siblings, 1 reply; 14+ messages in thread From: Roy Sigurd Karlsbakk @ 2013-03-21 16:17 UTC (permalink / raw) To: Chris Murphy; +Cc: linux-raid, Andris Berzins > Small correction. They've yanked settable SCT ERC in at least the Blue > and Black laptop (Scorpio) drives, which used to have this feature. So > it's not just the greens that had the feature removed. I'm pretty sure > all of the desktop drives, green, blue, black, have had it removed in > newer revisions. Now you can get it in reds, or RE drives only, at > least WDC. Otherwise you're looking for a different vendor. This is true. The only real difference between the blacks and the 'enterprise' drives, is that the firmware isn't crippled. Seagate and (hopefully still) Hitachi drives allow setting SCT ERC. This is from my /etc/rc.local for i in b c d e f g h do dev=sd$i smartctl -l scterc,70,70 /dev/$dev || echo 180 > /sys/block/$dev/device/timeout done Vennlige hilsener / Best regards roy -- Roy Sigurd Karlsbakk (+47) 98013356 roy@karlsbakk.net http://blogg.karlsbakk.net/ GPG Public key: http://karlsbakk.net/roysigurdkarlsbakk.pubkey.txt -- I all pedagogikk er det essensielt at pensum presenteres intelligibelt. Det er et elementært imperativ for alle pedagoger å unngå eksessiv anvendelse av idiomer med xenotyp etymologi. I de fleste tilfeller eksisterer adekvate og relevante synonymer på norsk. -- To unsubscribe from this list: send the line "unsubscribe linux-raid" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: Western Digital Green 3TB SATA3 experiences 2013-03-21 16:17 ` Roy Sigurd Karlsbakk @ 2013-03-21 21:30 ` Chris Murphy 2013-03-22 3:31 ` Chris Murphy 2013-03-22 14:22 ` Roy Sigurd Karlsbakk 0 siblings, 2 replies; 14+ messages in thread From: Chris Murphy @ 2013-03-21 21:30 UTC (permalink / raw) To: Roy Sigurd Karlsbakk; +Cc: linux-raid, Andris Berzins On Mar 21, 2013, at 10:17 AM, Roy Sigurd Karlsbakk <roy@karlsbakk.net> wrote: > > This is true. The only real difference between the blacks and the 'enterprise' drives, is that the firmware isn't crippled. No, another difference is the RE drives have another order magnitude lower URE. So they're statistically more reliable. And they don't have the implicit proscription to not use them in RAID other than 1 and 0. Chris Murphy ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: Western Digital Green 3TB SATA3 experiences 2013-03-21 21:30 ` Chris Murphy @ 2013-03-22 3:31 ` Chris Murphy 2013-03-22 14:22 ` Roy Sigurd Karlsbakk 1 sibling, 0 replies; 14+ messages in thread From: Chris Murphy @ 2013-03-22 3:31 UTC (permalink / raw) To: linux-raid@vger.kernel.org Mailing List On Mar 21, 2013, at 3:30 PM, Chris Murphy <lists@colorremedies.com> wrote: > And they don't have the implicit proscription to not use them in RAID other than 1 and 0. Nice double negative. The RE drives don't have the implicit proscription to use them in RAID 5/6 (the consumer drives are only recommended for RAID 0 and 1; even Reds are recommended only for a max 4 member RAID. Chris Murphy ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: Western Digital Green 3TB SATA3 experiences 2013-03-21 21:30 ` Chris Murphy 2013-03-22 3:31 ` Chris Murphy @ 2013-03-22 14:22 ` Roy Sigurd Karlsbakk 2013-03-22 16:57 ` Chris Murphy 1 sibling, 1 reply; 14+ messages in thread From: Roy Sigurd Karlsbakk @ 2013-03-22 14:22 UTC (permalink / raw) To: Chris Murphy; +Cc: linux-raid, Andris Berzins ----- Opprinnelig melding ----- > On Mar 21, 2013, at 10:17 AM, Roy Sigurd Karlsbakk <roy@karlsbakk.net> > wrote: > > > > This is true. The only real difference between the blacks and the > > 'enterprise' drives, is that the firmware isn't crippled. > > No, another difference is the RE drives have another order magnitude > lower URE. So they're statistically more reliable. And they don't have > the implicit proscription to not use them in RAID other than 1 and 0. They have a *reported* order of magnitude lower URE, but I'm not sure if that's *real*. Vennlige hilsener / Best regards roy -- Roy Sigurd Karlsbakk (+47) 98013356 roy@karlsbakk.net http://blogg.karlsbakk.net/ GPG Public key: http://karlsbakk.net/roysigurdkarlsbakk.pubkey.txt -- I all pedagogikk er det essensielt at pensum presenteres intelligibelt. Det er et elementært imperativ for alle pedagoger å unngå eksessiv anvendelse av idiomer med xenotyp etymologi. I de fleste tilfeller eksisterer adekvate og relevante synonymer på norsk. -- To unsubscribe from this list: send the line "unsubscribe linux-raid" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html ^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: Western Digital Green 3TB SATA3 experiences 2013-03-22 14:22 ` Roy Sigurd Karlsbakk @ 2013-03-22 16:57 ` Chris Murphy 0 siblings, 0 replies; 14+ messages in thread From: Chris Murphy @ 2013-03-22 16:57 UTC (permalink / raw) To: linux-raid On Mar 22, 2013, at 8:22 AM, Roy Sigurd Karlsbakk <roy@karlsbakk.net> wrote: > ----- Opprinnelig melding ----- >> On Mar 21, 2013, at 10:17 AM, Roy Sigurd Karlsbakk <roy@karlsbakk.net> >> wrote: >>> >>> This is true. The only real difference between the blacks and the >>> 'enterprise' drives, is that the firmware isn't crippled. >> >> No, another difference is the RE drives have another order magnitude >> lower URE. So they're statistically more reliable. And they don't have >> the implicit proscription to not use them in RAID other than 1 and 0. > > They have a *reported* order of magnitude lower URE, but I'm not sure if that's *real*. It's a statistically derived spec, and that's much more reliable than reality. If you were to do a real test to find out, it would take for fricking ever, it would be really expensive, and it would collect noisy data such that two independent studies wouldn't exactly agree with each other. You'd have to do it on a large population of drives, because drives are obviously not exactly identical. The spec applies to a population of the model, not a particular unit. And since the real test would have to be done over the service life of the drive model, the study results wouldn't be available for ~5 years after the ship date of an enterprise drive model. So what's real? There are all sorts of ways to reliably predict the failure of various parts in a product, and how that affects the whole theoretical unit and thus the model. When those predictions are found to be flawed, the statistical model is used to see if and what revisions the product needs to maintain its design specs, including the URE spec. The whole point of the URE isn't about what will happen to a particular drive. It's a reflection of a model population. Clearly, unrecoverable read error is rather massive with a totally dead drive. Chris Murphy ^ permalink raw reply [flat|nested] 14+ messages in thread
end of thread, other threads:[~2013-03-22 16:57 UTC | newest] Thread overview: 14+ messages (download: mbox.gz / follow: Atom feed) -- links below jump to the message on this page -- 2013-03-20 8:09 Western Digital Green 3TB SATA3 experiences Andris Berzins 2013-03-20 8:28 ` Mikael Abrahamsson 2013-03-20 8:48 ` Roman Mamedov 2013-03-20 9:21 ` Andris Berzins 2013-03-20 9:29 ` Roman Mamedov 2013-03-20 12:40 ` Rainer Fügenstein 2013-03-20 13:23 ` joystick 2013-03-20 18:50 ` Chris Murphy 2013-03-20 20:55 ` Chris Murphy 2013-03-21 16:17 ` Roy Sigurd Karlsbakk 2013-03-21 21:30 ` Chris Murphy 2013-03-22 3:31 ` Chris Murphy 2013-03-22 14:22 ` Roy Sigurd Karlsbakk 2013-03-22 16:57 ` Chris Murphy
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.