I don’t think this one made it through on my first attempt.
Cary Millsap -----Original Message-----
Counting bytes is far, far, FAR less important than counting I/O-per-second (IOps) requirements and making sure that you have enough total capacity to handle your system’s peak I/O loads. Counting bytes is important too, but what many people find is that the byte-counting exercise will result in the sub-verdict of needing far fewer disk drives than you’ll really, truly need.
The way I’d recommend structuring your project is to evaluate the following:
- How many bytes will you need to store your data? How many disks is that? Call the answer B. - How many disks will you need to meet your IOps requirements? Call the answer P. - How many disks will you need to meet your availability requirements? Call the answer A. - (Consider other attributes as necessary, like perhaps I/O throughput requirements…)
Roughly speaking, the number of disks you’ll need to buy is max(B, P, A, …). It’s more complicated than that because you’ll need to segment your total drive set into sensibly-sized arrays, you’ll be able to buy some disks now then some later, and so on, but this is the general gist. The important thing is to have enough hardware to meet *all* of the constraints your business will place upon your system.
Cary Millsap -----Original Message-----
|
- Disk capacity planning Rhojel_Echano
- Re: Disk capacity planning Tanel Poder
- Re: Disk capacity planning Kip . Bryant
- Re: Disk capacity planning Rhojel_Echano
- Re: FW: Disk capacity planning Cary Millsap
- Re: FW: Disk capacity planning chris
- RE: FW: Disk capacity planning Niall Litchfield
- Re: FW: Disk capacity planning Mladen Gogala
- RE: FW: Disk capacity planning Cary Millsap
- RE: FW: Disk capacity planning Cary Millsap
- RE: FW: Disk capacity planning mkline1
- RE: FW: Disk capacity planning Paul Drake
- Re: FW: Disk capacity planning chris
- Re: FW: Disk capacity planning Jared . Still
- Re: FW: Disk capacity planning Mladen Gogala