6

I'm planing an age replacement policy for our storage and servers. Most of them are for DBs and some for images (static content) so yes, they have an huge I/O everytime.

Also, we use Samsung 840 Pro SSDs for the RAID Controllers (PERC H700i) as CacheCade.

Are you guys managing the replacement of old hard drives and solid state drives?

ewwhite
  • 194,921
  • 91
  • 434
  • 799
Masterl1nk
  • 147
  • 2
  • 12
  • 6
    When they fail or begin exhibiting the symptoms of impending failure they get replaced. I've never heard of anyone proactively replacing hard drives based on age. – joeqwerty Nov 28 '13 at 18:10

2 Answers2

14

We don't proactively replace disks.

Wait until they fail or report prefailure status. This is why you have (hardware) RAID, management agents, failure indication LEDs on the server and a monitoring solution.

Keeping your gear under warranty and maintain your support contracts (within reason), having cold spares of components that fail often (disks, power supplies, RAM) and proactively monitoring the environment will take you much farther.

ewwhite
  • 194,921
  • 91
  • 434
  • 799
  • 1
    Hmm. RAM fails often? The RAM that's good from the start (no memtest errors) seems to hold out forever for me. – Halfgaar Nov 28 '13 at 19:34
  • 4
    @Halfgaar In larger environments and at large enough scale, RAM fails... No way to prevent it. – ewwhite Nov 28 '13 at 20:42
  • Yeap, RAM fails sometimes :( Power supply fails are easy to avoid when you have redundant power – Masterl1nk Dec 02 '13 at 15:11
3

We don't proactively replace disks either. Backblaze recently did a blog post on this subject. One should note that they primarily use consumer grade drives.

toppledwagon
  • 4,215
  • 24
  • 15