Typically, compromise can be a great thing – certainly a mandate in most relationships; but not in the world of IT, and especially not in the storage space. In IT, compromise always comes at a cost.
Today, I share with you the not ten, but eleven! things that people do to cope with storage performance issues, and over the course of the next eleven weeks, I’ll elaborate on each.
For decades, IT has been inventing and implementing workarounds to cope with the poor performance of storage systems – which are bound by mechanical hard disks. As processor, memory and network speeds have repeatedly doubled over the years, storage media have failed to keep pace, leading to unbalanced ecosystems.
Often, these compromises are so ingrained that they have become second nature – no thought is given to the overhead because no alternatives existed. That is, until now.
And…the top eleven things people do to cope with storage woes:
- Over-provisioning (more is not necessarily better)
- Short-stroking (try and keep a straight face)
- IO Scheduling (there is no app for this)
- Caching (what’s the penalty for a “cache miss”?)
- Automatic Tiering (who gets to decide?)
- Manually Distributing IO (the only manual thing we like is on a Ferrari)
- Over-Indexing (there is such a thing as “index trickery”)
- Summary Tables (who needs summary tables in a world of real-time analysis?)
- Foregoing Real-time Data (See #8)
- RAID (how many different combinations are there?)
- Coping (ice cream always helps)
In comes flash memory technology. Why not question previous assumptions and remove existing restrictions? Imagine what you could do if you no longer need to spend time and resources coping with legacy storage.
Join me over the next few weeks as I elaborate on the compromises that no longer need to be made. Not when you have storage at the speed of memory.