Slow write speed for Toshiba USB disk

[MartinR]

I suspect that I've bought a duff disk, but before I write it off can I have any comments please?

I attach USB disks to a USB3 port to send backup files (in the range 0.1 - 160 GiB). I haven't got any benchmark figures for the three older disks, but typically Amanda reports speeds of up to 100,000 KB/s. As an example a 17 GiB file transferred in 4:14 and a 142 GiB in 35:42. The new disk is attached at the end of the same cable, so everything except the disk is common.

When I tried to write the 17GiB file it wrote about 2GiB quickly then ground to a halt and was still stuck several hours later. I ran again with the same file (after a reboot) and tried to use PCP to monitor the situation. PCP kept crashing, but when it was working the wait state was very high, confirmed by top(1) as 95%-99%. The system was unresponsive!

I changed back to one of the older disks (also a Toshiba) and achieved the results mentioned above.

I've run the benchmark from gnome-disk-utility 3.28.3 against it several times. On all occasions the average queue length grew in step with the disk average wait time. Both grew to 200 entries and 200 seconds respectively. When the benchmark was stopped the queue length shot up to 10,000 for 5 seconds before collapsing to zero at the same time that the wait time dropped back to milliseconds.

The new disk is a Toshiba DTB410 1TB disk p/n HDTB410MK3AA

[MartinR]

Bump?

[tunk]

If smartctl works, does it show any problems?

[MartinR]

I'd checked for SMART in the gnome-disk-utility 3.28.3 and it was grey'd out. Following your suggestion I:

Code: Select all

# smartctl -i /dev/sdh
smartctl 7.0 2018-12-30 r4883 [x86_64-linux-3.10.0-1062.12.1.el7.x86_64] (local build)
Copyright (C) 2002-18, Bruce Allen, Christian Franke, www.smartmontools.org

=== START OF INFORMATION SECTION ===
Model Family:     Toshiba 2.5" HDD MQ04UBF... (USB 3.0)
Device Model:     TOSHIBA MQ04UBF100
Serial Number:    Y9E5T17ST
LU WWN Device Id: 0 000000 000000000
Firmware Version: JU003U
User Capacity:    1,000,204,886,016 bytes [1.00 TB]
Sector Sizes:     512 bytes logical, 4096 bytes physical
Rotation Rate:    5400 rpm
Form Factor:      2.5 inches
Device is:        In smartctl database [for details use: -P show]
ATA Version is:   ACS-3 T13/2161-D revision 5
SATA Version is:  SATA 3.3, 3.0 Gb/s (current: 3.0 Gb/s)
Local Time is:    Thu Mar 19 11:31:46 2020 GMT
SMART support is: Available - device has SMART capability.
SMART support is: Disabled

So I've run smartctl -son /dev/sdh and will investigate further. Unfortunately since leaving work I don't have a colleague to bounce ideas off, hence the posting. Thanks.

[TrevorH]

smartctl -a would be more useful

[MartinR]

Once I'd seen it would turn on I started off a -t long. Results are not due for another hour.

[MartinR]

Evidently it failed with a "The self-test routine was aborted by the host" message. I'm trying again, results not due until after 19:00. Will report back after then.

[TrevorH]

Just run smartctl -a and it will report current counters and you can see the current state of it. It'll also tell you why the last test failed.

[MartinR]

It reported "The self-test routine was aborted by the host", thats why I'm re-running it to see if it completes. There was nothing obvious in the counters, but I don't like posting partial or unreliable results - wastes both your and my time! Anyhow, with that caveat, these are the results from the first run:

Code: Select all

ID# ATTRIBUTE_NAME          FLAG     VALUE WORST THRESH TYPE      UPDATED  WHEN_FAILED RAW_VALUE
  1 Raw_Read_Error_Rate     0x000b   100   100   050    Pre-fail  Always       -       0
  2 Throughput_Performance  0x0005   100   100   050    Pre-fail  Offline      -       0
  3 Spin_Up_Time            0x0027   100   100   001    Pre-fail  Always       -       2513
  4 Start_Stop_Count        0x0032   100   100   000    Old_age   Always       -       43
  5 Reallocated_Sector_Ct   0x0033   100   100   050    Pre-fail  Always       -       0
  7 Seek_Error_Rate         0x000b   100   100   050    Pre-fail  Always       -       0
  8 Seek_Time_Performance   0x0005   100   100   050    Pre-fail  Offline      -       0
  9 Power_On_Hours          0x0032   100   100   000    Old_age   Always       -       108
 10 Spin_Retry_Count        0x0033   100   100   030    Pre-fail  Always       -       0
 12 Power_Cycle_Count       0x0032   100   100   000    Old_age   Always       -       16
191 G-Sense_Error_Rate      0x0032   100   100   000    Old_age   Always       -       2
192 Power-Off_Retract_Count 0x0032   100   100   000    Old_age   Always       -       9
193 Load_Cycle_Count        0x0032   100   100   000    Old_age   Always       -       52
194 Temperature_Celsius     0x0022   100   100   000    Old_age   Always       -       30 (Min/Max 19/49)
196 Reallocated_Event_Count 0x0032   100   100   000    Old_age   Always       -       0
197 Current_Pending_Sector  0x0032   100   100   000    Old_age   Always       -       0
198 Offline_Uncorrectable   0x0030   100   100   000    Old_age   Offline      -       0
199 UDMA_CRC_Error_Count    0x0032   200   253   000    Old_age   Always       -       0
220 Disk_Shift              0x0002   100   100   000    Old_age   Always       -       33
222 Loaded_Hours            0x0032   100   100   000    Old_age   Always       -       6
223 Load_Retry_Count        0x0032   100   100   000    Old_age   Always       -       0
224 Load_Friction           0x0022   100   100   000    Old_age   Always       -       0
226 Load-in_Time            0x0026   100   100   000    Old_age   Always       -       183
240 Head_Flying_Hours       0x0001   100   100   001    Pre-fail  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  Extended offline    Aborted by host               90%       104         -

The summary was:

Code: Select all

SMART Status not supported: Incomplete response, ATA output registers missing
SMART overall-health self-assessment test result: PASSED
Warning: This result is based on an Attribute check.

Like I said, I'll post results after redoing the test.

[TrevorH]

There is nothing in the output there that shows a problem but if you look, all the ones that say "always" are continually updated during normal disk operation. Only the ones that say "Offline" need an offline test to update them.

The self-test routine was aborted by the host

Means the host did some access to the drive once the test had started and caused it to abort. You need to make sure that nothing uses the disk while the test is running or it may abort.

The disk has only been powered on for just over 4 elapsed days so it's almost brand new.