Interesting HDD Reliability Stats from BackBlaze

I didn't get it.............are the new SSD drives more reliable? Just got through swapping out all the laptops in the house with Samsung Evos.
 
What is a 'failure' in their system? I had HDDs that started losing a couple of sectors and then I had those that dented the inside of the case.
 
kgruber said:
I didn't get it.............are the new SSD drives more reliable? Just got through swapping out all the laptops in the house with Samsung Evos.
Click to expand...

It's not a reliability issue. It's a cost issue. Most places that need tens of thousands of drives still use HDDs because SSDs are still too expensive. Margins can be pretty tight in the datacenter and consumer backup markets.

Rich
 
weilke said:
What is a 'failure' in their system? I had HDDs that started losing a couple of sectors and then I had those that dented the inside of the case.
Click to expand...

From the linked page:
BackBlaze said:
What is a failed hard drive?

For Backblaze there are three reasons a drive is considered to have “failed”:
  1. The drive will not spin up or connect to the OS.
  2. The drive will not sync, or stay synced, in a RAID Array (see note below).
  3. The Smart Stats we use show values above our thresholds.
Click to expand...

Rich
 
RJM62 said:
From the linked page:


Rich
Click to expand...


So item #3 includes the following errors:

From experience, we have found the following 5 SMART metrics indicate impending disk drive failure:
  • SMART 5 – Reallocated_Sector_Count.
  • SMART 187 – Reported_Uncorrectable_Errors.
  • SMART 188 – Command_Timeout.
  • SMART 197 – Current_Pending_Sector_Count.
  • SMART 198 – Offline_Uncorrectable
https://www.backblaze.com/blog/hard-drive-smart-stats/

Basically they replace a drive once it shows 1 un^or^ec^abl^ error.

I didn't see how many of their drives failed under items #1, #2 or #3. If a drive continues to read and write data yet it is replaced based on a SMART stat, I dont think that data is terribly useful for anyone else who doesn't use those stats as a predictor of failure.
 
weilke said:
So item #3 includes the following errors:

From experience, we have found the following 5 SMART metrics indicate impending disk drive failure:
  • SMART 5 – Reallocated_Sector_Count.
  • SMART 187 – Reported_Uncorrectable_Errors.
  • SMART 188 – Command_Timeout.
  • SMART 197 – Current_Pending_Sector_Count.
  • SMART 198 – Offline_Uncorrectable
https://www.backblaze.com/blog/hard-drive-smart-stats/

Basically they replace a drive once it shows 1 un^or^ec^abl^ error.

I didn't see how many of their drives failed under items #1, #2 or #3. If a drive continues to read and write data yet it is replaced based on a SMART stat, I dont think that data is terribly useful for anyone else who doesn't use those stats as a predictor of failure.
Click to expand...

I never said it was useful. I said it was interesting. :D

Rich
 
RJM62 said:
I never said it was useful. I said it was interesting. :D

Rich
Click to expand...

The most interesting part are the differences among manufacturers and different models.
 
You must log in or register to reply here.
Back
Top