Western Digital 1.5TB Green Drives - Not for your Linux Software RAID

I recently bought a couple Western Digital 1.5TB "Green" Drives (WD15EADS) to rebuild my home media storage array with higher-density disks.  I already had one Segate 1.5TB drive (ST31500341AS) I was using for a "scratch" drive  (rpm mock builds, storing MythTV recordings, secondary backup) that I had problems using at all until Seagate released a firmware update, so I was skeptical about buying more of those.  I thought the green drives would be fine; that despite their variable rotational speed, the power savings and ability to spin up to higher speeds when needed would work out fine.

Unfortunately once I had a couple of these drives in a software RAID 5 array I began to notice problems.  When copying data to the array I would see decent transfer rates of ~33MB/s for 30-40 seconds but I would then see the transfer rate drop to 200-500KB/s for 2-3 minutes.  Since the array was initially built with only the WD drives I was pretty sure the problem was isolated to those drives.  Even after adding the Seagate drive the problems remained.

To test my assumption that the WD drives were somehow causing problems I began an rsync and waited until the transfer "paused".  I then did a "dd" against each of the drives in the array, seeking to a new position in the drive between tries.  It consistently showed the WD drive only getting 100-250KB/s while the Seagate drive would get ~90MB/s.

Once replacing all the WD drives with equivalent Seagate drives the array is resyncing at ~90MB/s; almost 3 times what I was getting with the WD drives alone.

When I first started seeing these problems with the WD drives I thought it might be related to the idle command so I downloaded the WDIDLE3.exe program to increase the idle time from the default 8 seconds to 25 seconds, and then later disabling the idle time out.  When this didn't fix anything I downloaded the WDTLER.exe program to enable TLER for the drives which also didn't affect the drives at all (I didn't expect this to since I wasn't seeing data completely stop or the drives drop out of the array).

I'm not sure what to do with these WD drives; while they seem to work fine independantly, they don't perform correctly at all when put into a RAID array.  I'm beginning to get afraid that as the hard drives get larger and larger the complexity of the firmware is growing too quickly for drive manufacterers to keep them performing reliably.

6 comments

Anonymous (visitor) says:
Got the same problem, they don't work so well independently either, but better than in RAID. RAID likely causes more I/O causing the problem to appear faster.
R. Lynn Rardin (visitor) says:

My experiences with the ST31500341AS and WD15EADS differ from yours, but have been no less frustrating. I purchased 18 x ST31500341AS drives almost a year ago and started testing them for use in 3 software-based, RAID5 arrays. A surprising number of the drives began reallocating sectors during testing and I eventually returned all 18 drives to the retailer for a refund. You should take a look at the Seagate Forums thread with subject "Reallocated Sector Count increasing (ST31500341AS )." Once the WD15EADS hit retail channels, I bought a case of 20 and started testing. These drives performed much better out of the box, but some problems arose over time. I've run across numerous cases of non-zero Current_Pending_Sector, Reallocated_Sector_Ct, Multi_Zone_Error_Rate and Raw_Read_Error_Rate SMART attributes over the last 9 months. So far, I've returned 2 batches of 4 drives for RMA replacement by WD (in fact, I shipped out the second batch of 4 yesterday). It's worth noting that the first 4 replacement drives took quite awhile to arrive, but all have performed flawlessly so far. I'm knocking on wood as I type this, but I currently have 14 x WD15EADS drives running error-free in 3 arrays. Two of the arrays are installed in Xeon-based servers and comprise 5 drives each, all of which are active. The last array has 3 active drives and a hot spare and is installed in an old dual-PIII-based system. I'm using the same SIIG, sil-based, 4-port, SATA 150 controller in all 3 systems (two each in the Xeon-based servers to give me 5 ports). And I'm getting decent performance out of all of the arrays. For example, these are the results of some read tests I ran this morning using dd: PIII--101 MB/s over 8 sec, 103 MB/s over 80 sec and 105 MB/s over 800 sec; Xeon server--170 MB/s over 4 sec, 183 MB/s over 40 sec and 188 MB/s over 400 sec. Is there any chance that the controller you're using could be an issue? I had problems with the SIIG controllers until I removed the BIOS. Also, I'm running all of the WD15EADS drives with the SSC (spread spectrum clocking) jumper removed. Any chance that could be a factor?

Ace (visitor) says:

Did you take into account that thees drives have 4k sector sizes and not 512 bytes. If not aligned properly, you will see really poor performance and perhaps other issues. Perhaps thats your problem. Ace

dwarner's picture
dwarner says:

The Seagate drive is spec'd as 512bytes/sector, but I can't find any documentation on the WD drives so it's hard to make guesses as to this.  At the time the 512/4096 byte-sector thing wasn't very widely published so I never even considered it to be a potential problem.

conix (visitor) says:
EADS have 512byte sectors. EARS have 4K sectors. So these drives are not affected.

Post new comment

The content of this field is kept private and will not be shown publicly.
By submitting this form, you accept the Mollom privacy policy.