Hello, I''ve decided to replace my WD10EADS and WD10EARS drives as I''ve checked the SMART values and they''ve accrued some insanely high numbers for the load/unload counts (40K+ in 120 days on one!). I was leaning towards the Black drives but now I''m a bit worried about the TLER lackingness which was a mistake made my previous sysadmin. I''m wondering what other people are using, even though the Green series has let me down, I''m still a Western Digital gal. Would you recommend any of these for use in a ZFS NAS? 4x WD2003FYYS - http://www.wdc.com/en/products/Products.asp?DriveID=732 [RE4] 4x WD2002FYPS - http://www.wdc.com/en/products/products.asp?DriveID=610 [Green] 6x WD1002FBYS - http://www.wdc.com/en/products/Products.asp?DriveID=503 [RE3] What do people already use on their enterprise level NAS''s? Any good Seagates? Thanks, Em _________________________________________________________________ New, Used, Demo, Dealer or Private? Find it at CarPoint.com.au http://clk.atdmt.com/NMN/go/206222968/direct/01/ -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://mail.opensolaris.org/pipermail/zfs-discuss/attachments/20100512/7feef34d/attachment.html>
On Wed, May 12, 2010 at 09:05:14PM +1000, Emily Grettel wrote:> > Hello, > > > > I''ve decided to replace my WD10EADS and WD10EARS drives as I''ve checked the SMART values and they''ve accrued some insanely high numbers for the load/unload counts (40K+ in 120 days on one!). > > > > I was leaning towards the Black drives but now I''m a bit worried about the TLER lackingness which was a mistake made my previous sysadmin. > > > > I''m wondering what other people are using, even though the Green series has let me down, I''m still a Western Digital gal.Try WD RE3 and RE4 series, no issues here so far. Presumably, 1 TByte would be better than 2 TByte due to resilver times. Some say Hitachis work, too.> Would you recommend any of these for use in a ZFS NAS? > > > > > 4x WD2003FYYS - http://www.wdc.com/en/products/Products.asp?DriveID=732 [RE4] > 4x WD2002FYPS - http://www.wdc.com/en/products/products.asp?DriveID=610 [Green] > 6x WD1002FBYS - http://www.wdc.com/en/products/Products.asp?DriveID=503 [RE3] > > > What do people already use on their enterprise level NAS''s? Any good Seagates?After a 7200.11 debacle (in fact, SMART just told me I''ve got another deader on my hands) I''m quite leery. Maybe the SAS Seagates are better. -- Eugen* Leitl <a href="http://leitl.org">leitl</a> http://leitl.org ______________________________________________________________ ICBM: 48.07100, 11.36820 http://www.ativel.com http://postbiota.org 8B29F6BE: 099D 78BA 2FD3 B014 B08A 7779 75B0 2443 8B29 F6BE
On Wed, May 12, 2010 at 4:05 AM, Emily Grettel < emilygrettelisnow at hotmail.com> wrote:> Hello, > > I''ve decided to replace my WD10EADS and WD10EARS drives as I''ve checked the > SMART values and they''ve accrued some insanely high numbers for the > load/unload counts (40K+ in 120 days on one!). > > I was leaning towards the Black drives but now I''m a bit worried about the > TLER lackingness which was a mistake made my previous sysadmin. > > I''m wondering what other people are using, even though the Green series has > let me down, I''m still a Western Digital gal. > > Would you recommend any of these for use in a ZFS NAS? > > > - 4x WD2003FYYS - > http://www.wdc.com/en/products/Products.asp?DriveID=732 [RE4] > - 4x WD2002FYPS - > http://www.wdc.com/en/products/products.asp?DriveID=610 [Green] > - 6x WD1002FBYS - > http://www.wdc.com/en/products/Products.asp?DriveID=503 [RE3] > > Skip anything from WD with the word "Green" in the title. They''re allcrap, even the RE Greens are crap. (Okay, they might be good for home storage, but definitely not for non-home storage setups.) It''s possible to disable the idle timeout using the wdidle3 utility (requires a boot to DOS). We have 8 WD Green 1.5 TB drives in one storage server. Even with the idle timeout disabled (no load/unload cycles), these things are slow. They''re not true 7200 RPM drives, and the 64 MB onboard cache doesn''t help to hide that. A re-silver of 1 drive takes over 65 hours on an idle system, and close to 100 hours on an active system. In our other storage server, we went with 1.5 TB Seagate 7200.11 drives. Much nicer. Only 32 MB cache, but they''re easily twice as fast as the WD Greens. A re-silver of one of these takes about 35 hours. Even when running backups. The WD RE drives are nice as well. All of our 500 GB drives in our storage servers are WD RE Black drives. All of our 400 GB drives are Seagate E-something drives. No complaints about those. But, they''re enterprise, RAID-qualified drives. -- Freddie Cash fjwcash at gmail.com -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://mail.opensolaris.org/pipermail/zfs-discuss/attachments/20100512/ee2abf51/attachment.html>
On Wed, May 12, 2010 at 4:05 AM, Emily Grettel <emilygrettelisnow at hotmail.com> wrote:> > I''m wondering what other people are using, even though the Green series has let me down, I''m still a Western Digital gal. > > What do people already use on their enterprise level NAS''s? Any good Seagates? >FWIW, I looked at the WDs, but went with the?Samsung Spinpoint F3 HD103SJ (two 500GB platters) drives instead because they were found to be faster and very reliable in general.
On Wed, May 12, 2010 at 4:05 AM, Emily Grettel <emilygrettelisnow at hotmail.com> wrote:> I''ve decided to replace my WD10EADS and WD10EARS drives as I''ve checked the > SMART values and they''ve accrued some insanely high numbers for the > load/unload counts (40K+ in 120 days on one!).Running WDIDLE.EXE on the drives as soon as you install them will help in that regard.> I was leaning towards the Black drives but now I''m a bit worried about the > TLER lackingness which was a mistake made my previous sysadmin.It was possible to enable TLER with earlier revisions of the drive, but rumors on the tubes seem to imply that the feature has been removed. I think that any of the REx drives would be fine. The 7200 RPM versions are basically the Black drives, and the Green is the GP drive, just with different TLER settings in firmware. Problems that you''re having with your current GP drives are likely to manifest with the RE-Green.> What do people already use on their enterprise level NAS''s? Any good > Seagates?The Constellation ES, but it''s harder to find at places like Newegg.>From what I''ve read, the Hitachi and Samsung drives both support CCTL,which is in the ATA-8 spec. There''s no way to toggle it on from OpenSolaris (yet) and it doesn''t persist through reboot so it''s not really ideal. Here''s a patch to smartmontools that is supposed to enable it. It''s in the SVN version 5.40 but not the current 5.39 release: http://www.csc.liv.ac.uk/~greg/projects/erc/ And a DOS-mode app that''s supposed to work: http://www.hdat2.com/ -B -- Brandon High : bhigh at freaks.com
On Wed, May 12 at 8:45, Freddie Cash wrote:> On Wed, May 12, 2010 at 4:05 AM, Emily Grettel > <[1]emilygrettelisnow at hotmail.com> wrote: > > Hello, > ? > I''ve decided to replace my WD10EADS and WD10EARS drives as I''ve checked > the SMART values and they''ve accrued some insanely high numbers for the > load/unload counts (40K+ in 120 days on one!). > ? > I was leaning towards the Black drives but now I''m a bit worried about > the TLER lackingness which was a mistake made my previous sysadmin. > ? > I''m wondering what other people are using, even though the Green series > has let me down, I''m still a Western Digital gal. > ? > Would you recommend any of these for use in a ZFS NAS? > ? > > * 4x WD2003FYYS - > [2]http://www.wdc.com/en/products/Products.asp?DriveID=732? [RE4] > * 4x WD2002FYPS - > [3]http://www.wdc.com/en/products/products.asp?DriveID=610? [Green] > * 6x WD1002FBYS - > [4]http://www.wdc.com/en/products/Products.asp?DriveID=503? [RE3] >We use the WD1002FBYS (1.0TB WD RE3) and haven''t had an issue yet in our Dell T610 chassis. -- Eric D. Mudama edmudama at mail.bounceswoosh.org
>>>>> "eg" == Emily Grettel <emilygrettelisnow at hotmail.com> writes:eg> What do people already use on their enterprise level NAS''s? For a SOHO NAS similar to the one you are running, I mix manufacturer types within a redundancy set so that a model-wide manufacturing or firmware glitch like the ones of which we''ve had several in the last few years does not take out an entire array, and to make it easier to figure out whether weird problems in iostat are controller/driver''s fault, or drive''s fault. If there are not enough manufacturers with good drives on offer, I''ll try to buy two different models of the same manufacturer, ex get one of them an older model number of the same drive size/featureset. Often you find two mini-generations are on offer at once. At the moment, I would not buy any WD drive because they have been changing drives'' behavior without changing model numbers which makes pointless discussions like this one because the model numbers become meaningless and you cannot bind your experience to a repeatable purchasing decision other than ``do/don''t buy WD''''. When the dust settles from this silent-firmware-version-bumps and 4k-sector disaster, I would buy WD again because the more mfg diversity, the more bad-batch-proofing you have for wide stripes. I used to buy near-line drives but no longer do this because it''s cheaper to buy two regular drives than one near-line drive, but this may be a mistake because of the whole vibration disaster. -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 304 bytes Desc: not available URL: <http://mail.opensolaris.org/pipermail/zfs-discuss/attachments/20100512/cb2c9574/attachment.bin>
>>>>> "bh" == Brandon High <bhigh at freaks.com> writes:bh> From what I''ve read, the Hitachi and Samsung drives both bh> support CCTL, which is in the ATA-8 spec. There''s no way to bh> toggle it on from OpenSolaris (yet) and it doesn''t persist bh> through reboot so it''s not really ideal. bh> Here''s a patch to smartmontools that is supposed to enable bh> it. It''s in the SVN version 5.40 but not the current 5.39 bh> release: http://www.csc.liv.ac.uk/~greg/projects/erc/ That''s good to know. It would be interesting to know if the smartctl command in question can actually make it through a solaris system, and on what disk driver. AHCI and mpt are different because one is SATA framework and one isn''t. I wonder also if SAS expanders cause any problems for smartctl? also, has anyone actually found this feature to have any value at all? To be clear, I do understand what the feature does. I do not need it explained to me again. but AIUI with ZFS you must remove a partially failing drive, or else the entire pool becomes slow. It does not matter if the partially-failing drive is returning commands in 30sec (the ATA maximum) or 7sec by CCTL/TLER/....---you must still find and remove it, or the zpool will become pathologically slow. If there is actual experience with the feature helping ZFS, I''d be interested, but so far I think people are just echoing wikipedia shoulds and speculations, right? -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: application/pgp-signature Size: 304 bytes Desc: not available URL: <http://mail.opensolaris.org/pipermail/zfs-discuss/attachments/20100512/10521564/attachment.bin>
Miles Nordin wrote:>>>>>> "bh" == Brandon High <bhigh at freaks.com> writes: > > bh> From what I''ve read, the Hitachi and Samsung drives both > bh> support CCTL, which is in the ATA-8 spec. There''s no way to > bh> toggle it on from OpenSolaris (yet) and it doesn''t persist > bh> through reboot so it''s not really ideal. > > bh> Here''s a patch to smartmontools that is supposed to enable > bh> it. It''s in the SVN version 5.40 but not the current 5.39 > bh> release: http://www.csc.liv.ac.uk/~greg/projects/erc/ > > That''s good to know. It would be interesting to know if the smartctl > command in question can actually make it through a solaris system, and > on what disk driver. AHCI and mpt are different because one is SATA > framework and one isn''t. I wonder also if SAS expanders cause any > problems for smartctl?So, using latest SVN of smartmontools: AHCI reads work, writes don''t (could be the drive - a WDC WD3200KS-00PFB0), must specify -d sat,12 to get anything: root:gandalf 0 # ./smartctl -d sat,12 -l scterc,70,70 /dev/rdsk/c9t0d0p0 smartctl 5.40 2010-05-12 r3104 [i386-pc-solaris2.11] (local build) Copyright (C) 2002-10 by Bruce Allen, http://smartmontools.sourceforge.net SCT Error Recovery Control: Read: 57345 (5734.5 seconds) Write: 57345 (5734.5 seconds) mpt nothing works (and I see reports from Windows that it should with this disk, a ST31500341AS with CC1H firmware): root:gandalf 1 # ./smartctl -d sat,12 -l scterc /dev/rdsk/c7t9d0 smartctl 5.40 2010-05-12 r3104 [i386-pc-solaris2.11] (local build) Copyright (C) 2002-10 by Bruce Allen, http://smartmontools.sourceforge.net Error Write SCT Error Recovery Control Command failed: scsi error unknown error (unexpected sense key) Warning: device does not support SCT (Get) Error Recovery Control command root:gandalf 4 # ./smartctl -d sat,16 -l scterc /dev/rdsk/c7t9d0 smartctl 5.40 2010-05-12 r3104 [i386-pc-solaris2.11] (local build) Copyright (C) 2002-10 by Bruce Allen, http://smartmontools.sourceforge.net Error Write SCT Error Recovery Control Command failed: scsi error unknown error (unexpected sense key) Warning: device does not support SCT (Get) Error Recovery Control command
I just tried as well on osol134. I have the Western Digital Caviar black
drives that still support tler (the older ones). Same result: no changes
occur. This is on a 3420 ibex peak chipset
Device Model: WDC WD1001FALS-00E8B0
Firmware: 05.00K05
$ pfexec ./smartctl -d sat,12 /dev/rdsk/c5t0d0s0 -l scterc,70,70
smartctl 5.40 2010-05-12 r3104 [i386-pc-solaris2.11] (local build)
Copyright (C) 2002-10 by Bruce Allen, http://smartmontools.sourceforge.net
SCT Error Recovery Control:
Read: 57345 (5734.5 seconds)
Write: 57345 (5734.5 seconds)
Now if somebody could just try it on a HD103SJ and a HD502HJ...
For those that are interested. It seems to be talking to the drive as when
I run it against an Intel x25v ssd (Model INTEL SSDSA2M040G2GC firmware:
2CV102HD):
$ pfexec ./smartctl -d sat,12 /dev/rdsk/c5t5d0s0 -l scterc
smartctl 5.40 2010-05-12 r3104 [i386-pc-solaris2.11] (local build)
Copyright (C) 2002-10 by Bruce Allen, http://smartmontools.sourceforge.net
Warning: device does not support SCT Commands
-Jacques
>>>>>>>>>>>>>>>>>>>>>
So, using latest SVN of smartmontools:
AHCI reads work, writes don''t (could be the drive - a WDC
WD3200KS-00PFB0),
must specify -d sat,12 to get anything:
root:gandalf 0 # ./smartctl -d sat,12 -l scterc,70,70
/dev/rdsk/c9t0d0p0 smartctl
5.40 2010-05-12 r3104 [i386-pc-solaris2.11] (local build)
Copyright (C) 2002-10 by Bruce Allen, http://smartmontools.sourceforge.net
SCT Error Recovery Control:
Read: 57345 (5734.5 seconds)
Write: 57345 (5734.5 seconds)
mpt nothing works (and I see reports from Windows that it should with this
disk, a ST31500341AS with CC1H firmware):
root:gandalf 1 # ./smartctl -d sat,12 -l scterc /dev/rdsk/c7t9d0
smartctl 5.40 2010-05-12 r3104 [i386-pc-solaris2.11] (local build)
Copyright (C) 2002-10 by Bruce Allen, http://smartmontools.sourceforge.net
Error Write SCT Error Recovery Control Command failed: scsi error unknown
error (unexpected sense key)
Warning: device does not support SCT (Get) Error Recovery Control command
root:gandalf 4 # ./smartctl -d sat,16 -l scterc /dev/rdsk/c7t9d0
smartctl 5.40 2010-05-12 r3104 [i386-pc-solaris2.11] (local build)
Copyright (C) 2002-10 by Bruce Allen, http://smartmontools.sourceforge.net
Error Write SCT Error Recovery Control Command failed: scsi error unknown
error (unexpected sense key)
Warning: device does not support SCT (Get) Error Recovery Control command
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://mail.opensolaris.org/pipermail/zfs-discuss/attachments/20100513/4d72e6d1/attachment.html>
I did some more research and the findings were very interesting. I bought
an Samsung HD103SJ (1tb 7200rpm with two 500gb platters).
When you boot the drive cold, SCT error recovery is set at 0 (infinite).
This is viewable via HDAT2 and a dos boot. When you load OpenSolaris
and run smartctl to set error recovery time, you get the same response as
what was received for my old-style WD Caviar Blacks:
SCT Error Recovery Control:
Read: 57345 (5734.5 seconds)
Write: 57345 (5734.5 seconds)
*However, when you reboot the machine and check the settings using HDAT2,
the settings are correctly updated to whatever you told smartctl to
do.* This was case for both the older caviar black and the Samsung
drive. So
smartctl is in fact setting the drives correctly, but apparently can''t
read
back the success.
I can also confirm that the change only holds until poweroff. As such, so
you''ll have to add it to a boot script.
So there you go, a viable replacement for the Caviar Black with short error
recovery. I plan on using the HD103SJ drives for my next build out. Now
if we can just get rid of those pesky errors that occur when running...
Couple of other interesting tidbits:
My old-style caviar black drives were originally set at 7s using wdtler.
This is what HDAT2 reveals on a cold boot for the error recovery time. You
can override that using HDAT2 or smartctl. Upon warm reboot, the updated
numbers stick. However, upon cold boot the drive goes back to what was set
using wdtler. (I guess according to spec...)
For those that are interested, WD changed the extended model number between
the old-style caviar black drives and the bad ones but they have the same
firmware revision listed (it appears). Working output:
------------------------Old Style Caviar Black with
TLER------------------------
#./smartctl -d sat,12 /dev/rdsk/c5t1d0s0 -i
=== START OF INFORMATION SECTION ==Model Family: Western Digital Caviar
Black family
Device Model: WDC WD1001FALS-00E8B0
Serial Number: WD-WMATV422xxxx
Firmware Version: 05.00K05
User Capacity: 1,000,204,886,016 bytes
Device is: In smartctl database [for details use: -P show]
ATA Version is: 8
ATA Standard is: Exact ATA specification draft version not indicated
Local Time is: Thu May 13 17:42:16 2010 PDT
SMART support is: Available - device has SMART capability.
SMART support is: Enabled
# ./smartctl -d sat,12 /dev/rdsk/c5t1d0s0 -l scterc,70,70
smartctl 5.40 2010-05-12 r3104 [i386-pc-solaris2.11] (local build)
Copyright (C) 2002-10 by Bruce Allen, http://smartmontools.sourceforge.net
SCT Error Recovery Control:
Read: 57345 (5734.5 seconds)
Write: 57345 (5734.5 seconds)
------------------------New Caviar Black without TLER
------------------------
#./smartctl -d sat,12 /dev/rdsk/c5t3d0s0 -i
=== START OF INFORMATION SECTION ==Model Family: Western Digital Caviar
Black family
Device Model: WDC WD1001FALS-00J7B1
Serial Number: WD-WMATV649xxxx
Firmware Version: 05.00K05
User Capacity: 1,000,204,886,016 bytes
Device is: In smartctl database [for details use: -P show]
ATA Version is: 8
ATA Standard is: Exact ATA specification draft version not indicated
Local Time is: Thu May 13 17:43:01 2010 PDT
SMART support is: Available - device has SMART capability.
SMART support is: Enabled
# ./smartctl -d sat,12 /dev/rdsk/c5t3d0s0 -l scterc,70,70
smartctl 5.40 2010-05-12 r3104 [i386-pc-solaris2.11] (local build)
Copyright (C) 2002-10 by Bruce Allen, http://smartmontools.sourceforge.net
Warning: device does not support SCT Error Recovery Control command
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://mail.opensolaris.org/pipermail/zfs-discuss/attachments/20100513/f7c4bc8e/attachment.html>
I use the RE4''s at work on the storage server, but at home I use the consumer 1TB green drives. My system [2009.06] uses an Intel Atom 330 based motherboard, 4 gigs of non-ecc ram, a Supermicro AOC-SAT2-MV8 controller with 5 1TB Western Digital [WD10EARS] drives in a raidz1. There are many reasons why this set-up isn''t optimal, but in the nine months it''s been online, it hasn''t produced a single error. -- This message posted from opensolaris.org