• Some users have recently had their accounts hijacked. It seems that the now defunct EVGA forums might have compromised your password there and seems many are using the same PW here. We would suggest you UPDATE YOUR PASSWORD and TURN ON 2FA for your account here to further secure it. None of the compromised accounts had 2FA turned on.
    Once you have enabled 2FA, your account will be updated soon to show a badge, letting other members know that you use 2FA to protect your account. This should be beneficial for everyone that uses FSFT.

Unusually slow hard disk

webbrowser

n00b
Joined
Jun 12, 2013
Messages
31
One of my hard disks is being excruciatingly slow, and I can't quite figure out why. Hope you can help.

How slow is it?

Code:
# hdparm -Tt /dev/sdm

/dev/sdm:
 Timing cached reads:   15042 MB in  2.00 seconds = 7526.71 MB/sec
 Timing buffered disk reads:  26 MB in  3.26 seconds =   7.99 MB/sec

For comparison, another hard disk provides:

Code:
# hdparm -Tt /dev/sdl

/dev/sdl:
 Timing cached reads:   20710 MB in  2.00 seconds = 10365.46 MB/sec
 Timing buffered disk reads: 428 MB in  3.01 seconds = 142.31 MB/sec

Both of these are Samsung Spinpoint F4 EG 2TB disks. They are connected to Dell H200 controllers, using VT-d pass-through to the machine that was running the above.

I've tried connecting the dodgy disk (sdm) to to a different H200 HBA, and to use a different SAS-SATA breakout cable. This disk is consistently producing poor performance.

When I do a large streaming read, eg. dd if=/dev/sdm of=/dev/null bs=1024768, iostat says that 50% of my cpu is stuck in iowait state. But how do I tell what's the cause?

Code:
Device:            tps    kB_read/s    kB_wrtn/s    kB_read    kB_wrtn
sdm              48.50      6208.00         0.00      12416          0

avg-cpu:  %user   %nice %system %iowait  %steal   %idle
           0.25    0.00    0.25   49.25    0.00   50.25

Any idea what might be wrong / what to look for?
 
Last edited:
smartctl has this to say:

Code:
# smartctl -a /dev/sdm
smartctl 5.41 2011-06-09 r3365 [x86_64-linux-3.2.0-4-amd64] (local build)
Copyright (C) 2002-11 by Bruce Allen, http://smartmontools.sourceforge.net

=== START OF INFORMATION SECTION ===
Model Family:     SAMSUNG SpinPoint F4 EG (AFT)
Device Model:     SAMSUNG HD204UI
Serial Number:    S2H7J90B203975
LU WWN Device Id: 5 0024e9 2049b3017
Firmware Version: 1AQ10001
User Capacity:    2,000,398,934,016 bytes [2.00 TB]
Sector Size:      512 bytes logical/physical
Device is:        In smartctl database [for details use: -P show]
ATA Version is:   8
ATA Standard is:  ATA-8-ACS revision 6
Local Time is:    Sat Nov 23 00:41:00 2013 SGT

==> WARNING: Using smartmontools or hdparm with this
drive may result in data loss due to a firmware bug.
****** THIS DRIVE MAY OR MAY NOT BE AFFECTED! ******
Buggy and fixed firmware report same version number!
See the following web pages for details:
http://www.samsung.com/global/business/hdd/faqView.do?b2b_bbs_msg_id=386
http://sourceforge.net/apps/trac/smartmontools/wiki/SamsungF4EGBadBlocks

SMART support is: Available - device has SMART capability.
SMART support is: Enabled

=== START OF READ SMART DATA SECTION ===
SMART overall-health self-assessment test result: PASSED

General SMART Values:
Offline data collection status:  (0x03)	Offline data collection activity
					is in progress.
					Auto Offline Data Collection: Disabled.
Self-test execution status:      (   0)	The previous self-test routine completed
					without error or no self-test has ever 
					been run.
Total time to complete Offline 
data collection: 		(20580) seconds.
Offline data collection
capabilities: 			 (0x5b) SMART execute Offline immediate.
					Auto Offline data collection on/off support.
					Suspend Offline collection upon new
					command.
					Offline surface scan supported.
					Self-test supported.
					No Conveyance Self-test supported.
					Selective Self-test supported.
SMART capabilities:            (0x0003)	Saves SMART data before entering
					power-saving mode.
					Supports SMART auto save timer.
Error logging capability:        (0x01)	Error logging supported.
					General Purpose Logging supported.
Short self-test routine 
recommended polling time: 	 (   2) minutes.
Extended self-test routine
recommended polling time: 	 ( 255) minutes.
SCT capabilities: 	       (0x003f)	SCT Status supported.
					SCT Error Recovery Control supported.
					SCT Feature Control supported.
					SCT Data Table supported.

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   100   100   051    Pre-fail  Always       -       847
  2 Throughput_Performance  0x0026   001   001   000    Old_age   Always       -       107314
  3 Spin_Up_Time            0x0023   067   062   025    Pre-fail  Always       -       10278
  4 Start_Stop_Count        0x0032   100   100   000    Old_age   Always       -       345
  5 Reallocated_Sector_Ct   0x0033   252   252   010    Pre-fail  Always       -       0
  7 Seek_Error_Rate         0x002e   252   252   051    Old_age   Always       -       0
  8 Seek_Time_Performance   0x0024   252   252   015    Old_age   Offline      -       0
  9 Power_On_Hours          0x0032   100   100   000    Old_age   Always       -       21779
 10 Spin_Retry_Count        0x0032   252   252   051    Old_age   Always       -       0
 11 Calibration_Retry_Count 0x0032   100   100   000    Old_age   Always       -       55
 12 Power_Cycle_Count       0x0032   100   100   000    Old_age   Always       -       98
181 Program_Fail_Cnt_Total  0x0022   096   096   000    Old_age   Always       -       100293324
191 G-Sense_Error_Rate      0x0022   100   100   000    Old_age   Always       -       160
192 Power-Off_Retract_Count 0x0022   252   252   000    Old_age   Always       -       0
194 Temperature_Celsius     0x0002   062   057   000    Old_age   Always       -       38 (Min/Max 26/43)
195 Hardware_ECC_Recovered  0x003a   100   100   000    Old_age   Always       -       0
196 Reallocated_Event_Count 0x0032   252   252   000    Old_age   Always       -       0
197 Current_Pending_Sector  0x0032   252   252   000    Old_age   Always       -       0
198 Offline_Uncorrectable   0x0030   252   252   000    Old_age   Offline      -       0
199 UDMA_CRC_Error_Count    0x0036   200   200   000    Old_age   Always       -       0
200 Multi_Zone_Error_Rate   0x002a   001   001   000    Old_age   Always       -       86825
223 Load_Retry_Count        0x0032   100   100   000    Old_age   Always       -       55
225 Load_Cycle_Count        0x0032   100   100   000    Old_age   Always       -       414

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  Extended offline    Completed without error       00%     21705         -
# 2  Extended offline    Aborted by host               90%     21680         -
# 3  Extended offline    Completed without error       00%     21551         -
# 4  Short offline       Completed without error       00%     21544         -
# 5  Short offline       Completed without error       00%     21520         -
# 6  Short offline       Completed without error       00%     21496         -
# 7  Extended offline    Completed without error       00%     21479         -
# 8  Short offline       Completed without error       00%     21472         -
# 9  Short offline       Completed without error       00%     21448         -
#10  Short offline       Completed without error       00%     21424         -
#11  Extended offline    Completed without error       00%     21407         -
#12  Short offline       Completed without error       00%     21400         -
#13  Short offline       Completed without error       00%     21376         -
#14  Short offline       Completed without error       00%     21352         -
#15  Extended offline    Completed without error       00%     21335         -
#16  Short offline       Completed without error       00%     21328         -
#17  Short offline       Completed without error       00%     21304         -
#18  Short offline       Completed without error       00%     21280         -
#19  Extended offline    Completed without error       00%     21263         -
#20  Short offline       Completed without error       00%     21256         -
#21  Short offline       Completed without error       00%     21232         -

Note: selective self-test log revision number (0) not 1 implies that no selective self-test has ever been run
SMART Selective self-test log data structure revision number 0
Note: revision number not 1 implies that no selective self-test has ever been run
 SPAN  MIN_LBA  MAX_LBA  CURRENT_TEST_STATUS
    1        0        0  Completed [00% left] (0-65535)
    2        0        0  Not_testing
    3        0        0  Not_testing
    4        0        0  Not_testing
    5        0        0  Not_testing
Selective self-test flags (0x0):
  After scanning selected spans, do NOT read-scan remainder of disk.
If Selective self-test is pending on power-up, resume after 0 minute delay.
 
What's Calibration_Retry_Count? Does it go up and what does the good disk say?

I would say wiping it (with a full write) to make sure it has no recovery of any kind going on is the way to go here.
 
Code:
[B][I]200 Multi_Zone_Error_Rate   0x002a   001   001   000    Old_age   Always       -       86825[/I][/B]

It's dead.

With the old samsung drives the SMART attrib 200 is essentially the value to watch for.
 
Code:
[B][I]200 Multi_Zone_Error_Rate   0x002a   001   001   000    Old_age   Always       -       86825[/I][/B]

It's dead.

With the old samsung drives the SMART attrib 200 is essentially the value to watch for.

What's the value to watch out for in new ones? :)
 
What's the value to watch out for in new ones? :)

Since Samsung's mechanical division was sold to seagate, they have changed the firmware on any remaining mechanical drives to be more like seagates SMART reporting.

And seagates have aggregate data encoded in their raw values so they are tricky for some programs to read. Essentially on seagates I look at the typical values of reallocated sectors, or ecc errors.
 
Oops, Samsung.

I thought Toshiba.

<== should not touch disks today
 
Thanks guys. My 3 good drives say:
Code:
 11 Calibration_Retry_Count 0x0032   252   252   000    Old_age   Always       -       0
200 Multi_Zone_Error_Rate   0x002a   100   100   000    Old_age   Always       -       19

 11 Calibration_Retry_Count 0x0032   252   252   000    Old_age   Always       -       0
200 Multi_Zone_Error_Rate   0x002a   100   100   000    Old_age   Always       -       17

 11 Calibration_Retry_Count 0x0032   252   252   000    Old_age   Always       -       0
200 Multi_Zone_Error_Rate   0x002a   100   100   000    Old_age   Always       -       210


And thanks staticlag. So this indicates that the drive is going to die slowly? I'll prepare to replace it.
 
@staticlag,

I understand that Reallocated_Sector_Ct and Current_Pending_Sector are generally the attributes to look out for on mechanical drives. But how about SSDs? I'm a bit nervous with my Crucal M500 SSD because it already shows these after a few months. Are they of concern?
Code:
  1 Raw_Read_Error_Rate     0x0032   100   100   ---    Old_age   Always       -       167
181 Program_Fail_Cnt_Total  0x0022   100   100   ---    Old_age   Always       -       386550005805
188 Command_Timeout         0x0032   100   100   ---    Old_age   Always       -       139
195 Hardware_ECC_Recovered  0x003a   100   100   ---    Old_age   Always       -       4294967295
196 Reallocated_Event_Count 0x0032   100   100   ---    Old_age   Always       -       16

Is there anything special to look out for on Hitachi Deskstar 7k3000?
 
SSDs are another type of disk that likes to give large aggregate values instead of human readable RAW values.

If you look at this value of 386550005805

Code:
181 Program_Fail_Cnt_Total  0x0022   100   100   ---    Old_age   Always       -       386550005805

That's NOT how many "Program_Fail_Cnt_Total" events there are. It is probably a combination of 2-4 other values that gives an estimate on how many events per million or tens of million. But only the manufacturer really knows, so its not something to be alarmed about.

One thing that is helpful to the end user is that each SMART value gives a normalized fitness value in column 4 to watch. The value of 100 is what I am talking about. The value of 100 in the 5th column shows the lifetime low value of this number. and the 6th column with shows as --- should be the manufacturer's official "dead" level. These numbers get lower as problems arise. As you can see from this SSD, they all have high RAW values, but the normalized values of 100 show that there is absolutely nothing to worry about.

But if we look at your last disk:

Code:
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   100   100   051    Pre-fail  Always       -       847
  2 Throughput_Performance  0x0026   001   001   000    Old_age   Always       -       107314
  3 Spin_Up_Time            0x0023   067   062   025    Pre-fail  Always       -       10278
  4 Start_Stop_Count        0x0032   100   100   000    Old_age   Always       -       345
  5 Reallocated_Sector_Ct   0x0033   252   252   010    Pre-fail  Always       -       0
  7 Seek_Error_Rate         0x002e   252   252   051    Old_age   Always       -       0
  8 Seek_Time_Performance   0x0024   252   252   015    Old_age   Offline      -       0
  9 Power_On_Hours          0x0032   100   100   000    Old_age   Always       -       21779
 10 Spin_Retry_Count        0x0032   252   252   051    Old_age   Always       -       0
 11 Calibration_Retry_Count 0x0032   100   100   000    Old_age   Always       -       55
 12 Power_Cycle_Count       0x0032   100   100   000    Old_age   Always       -       98
181 Program_Fail_Cnt_Total  0x0022   096   096   000    Old_age   Always       -       100293324
191 G-Sense_Error_Rate      0x0022   100   100   000    Old_age   Always       -       160
192 Power-Off_Retract_Count 0x0022   252   252   000    Old_age   Always       -       0
194 Temperature_Celsius     0x0002   062   057   000    Old_age   Always       -       38 (Min/Max 26/43)
195 Hardware_ECC_Recovered  0x003a   100   100   000    Old_age   Always       -       0
196 Reallocated_Event_Count 0x0032   252   252   000    Old_age   Always       -       0
197 Current_Pending_Sector  0x0032   252   252   000    Old_age   Always       -       0
198 Offline_Uncorrectable   0x0030   252   252   000    Old_age   Offline      -       0
199 UDMA_CRC_Error_Count    0x0036   200   200   000    Old_age   Always       -       0
200 Multi_Zone_Error_Rate   0x002a   001   001   000    Old_age   Always       -       86825
223 Load_Retry_Count        0x0032   100   100   000    Old_age   Always       -       55
225 Load_Cycle_Count        0x0032   100   100   000    Old_age   Always       -       414

If you see here the ultra low numbers of 001 in two attributes you can see something is terribly wrong. Typically if you get any value below 020 even if the disk is not showing as dead in some of these smart diagnostics, you should replace it.

As far as hitachi's I only have 1 and haven't had many problems with it, so I'm really unsure of clear indicators like I am with the samsungs (of which I have 15)

But one very important thing you can do to keep an eye on all your disks is to benchmark them every now and again. Watching decline in performance and increases in latency like you noticed with your disk is probably the best indicator of dying disks.
 
Back
Top