I have 1 parity and 10 data disks in my array.  Everything is working fine however I recently noticed that when I am writing anything to one particular disk, the file transfers are very bursty.. i.e. the transfer constantly sends and stops, sends and stops....it never transfers for more than 2 seconds at a time, then pauses for 2 seconds, etc.

 

All other drives I get transfer speeds of 17-30Mbps (depending on whether or not the drive is on a motherboard SATA port or a PCI SATA card) which is normal.  For this drive, I only see 2-5Mbps write speed.  Also I have tested transferring to another drive which is on the same PCI SATA card as the problem drive and I don't have this issue.

 

Here is the SMART attributes for that drive along with the results of a short test:

SMART Attributes Data Structure revision number: 16

Vendor Specific SMART Attributes with Thresholds:

ID# ATTRIBUTE_NAME          FLAG    VALUE WORST THRESH TYPE      UPDATED  WHEN_FAILED RAW_VALUE

  1 Raw_Read_Error_Rate    0x002f  200  200  051    Pre-fail  Always      -      0

  3 Spin_Up_Time            0x0027  171  168  021    Pre-fail  Always      -      6433

  4 Start_Stop_Count        0x0032  100  100  000    Old_age  Always      -      736

  5 Reallocated_Sector_Ct  0x0033  200  200  140    Pre-fail  Always      -      0

  7 Seek_Error_Rate        0x002e  200  200  000    Old_age  Always      -      0

  9 Power_On_Hours          0x0032  090  090  000    Old_age  Always      -      7858

10 Spin_Retry_Count        0x0032  100  100  000    Old_age  Always      -      0

11 Calibration_Retry_Count 0x0032  100  253  000    Old_age  Always      -      0

12 Power_Cycle_Count      0x0032  100  100  000    Old_age  Always      -      53

192 Power-Off_Retract_Count 0x0032  200  200  000    Old_age  Always      -      33

193 Load_Cycle_Count        0x0032  195  195  000    Old_age  Always      -      17784

194 Temperature_Celsius    0x0022  118  111  000    Old_age  Always      -      32

196 Reallocated_Event_Count 0x0032  200  200  000    Old_age  Always      -      0

197 Current_Pending_Sector  0x0032  200  200  000    Old_age  Always      -      0

198 Offline_Uncorrectable  0x0030  200  200  000    Old_age  Offline      -      0

199 UDMA_CRC_Error_Count    0x0032  200  200  000    Old_age  Always      -      0

200 Multi_Zone_Error_Rate  0x0008  200  200  000    Old_age  Offline      -      0

 

SMART Error Log Version: 1

No Errors Logged

 

SMART Self-test log structure revision number 1

Num  Test_Description    Status                  Remaining  LifeTime(hours)  LBA_of_first_error

# 1  Short offline      Completed without error      00%      7858        -

 

 

Any ideas what could be causing this?  Bad drive or something else?  If it is the drive I would like to RMA it while it is still under warranty but I'm not sure how I can RMA a drive which appears to have a clean bill of health!

What kind of net transfer rate are you getting to the drive?

... and is it connected to a PCI port or motherboard port?

 

If a PCI port, what other drives are connected to the same controller?

 

Net transfer rate is 2-5Mbps on average.  This is not sustained however as every couple of seconds during the transfer the speed will drop to zero and then start again and that pattern will continue until the transfer is complete.

 

The drive is on a PCI SATA card, but I tested the two other drives connected to that same PCI card and I get almost 20Mbps sustained transfer on those drives.

FYI it is a 2TB WD green drive:

 

Device Model:    WDC WD20EARX-00PASB0

 

Even when I try to cancel the transfer I have to wait a few seconds for windows explorer to respond as it is like the drive completely locks up and stops responding every few seconds and then starts to respond again a few seconds later.

 

I don't see any errors on the main unraid web GUI but something is obviously wrong here.  I tested every other drive in the array writing the same file to each disk share directly and they all work fine (transfer starts instantly and transfer rate is 20Mbps+ sustained the entire time).

You should try the following (probably in this order) ...

 

(a)  Use a different SATA cable (preferably a locking one)

 

(b)  Use a different SATA port (ideally a motherboard port; but one of the other ports on the same card would be okay)

 

©  If neither of those help; remove the drive; connect it to a PC; and run WD's Data Lifeguard utility.  The Quick and Extended tests are "data safe" (i.e. don't modify the drive)

 

Ok thank you, I will give those suggestions a try.

Well I tried a new cable, different port on the same card, and then another port on my second PCI SATA card and none of those changes made any difference.  I can't use a motherboard port because they are already full with my parity and other largest drives in the array so from a performance perspective I would not want to change that configuration.

 

Given that I have other drives connected to both of my PCI SATA cards which are working just fine I am concluding that the problem lies with the drive itself.  So weird though since the data on the drive is fine, and the SMART report is perfectly clean too... I am not even going to bother with the data lifeguard tests because I have a feeling that they will also report that nothing is wrong...

 

At this point I have given up and don't want to waste any more time troubleshooting, so I just RMAed the drive... WD has a new RMA category called "poor performance" which fits the bill quite nicely :-)

I'd have suggested exactly that -- just replace the drive.  WD also has an "advance RMA" you can use that will let you get the replacement before you ship back the old drive, which should work well in this case.

 

Yep, already familiar with the advanced replacement and did just that ;-)

 

Thanks for your help.