RAID 0

Block-level striping with no redundancy. Maximum capacity and speed; any drive failure wipes the array.

Min. drives
2
Usable capacity
N × smallest
Fault tolerance
0
Performance
Fastest reads + writes

How it works

Data is split into blocks and spread across all drives in parallel. Every drive participates in every read and write, multiplying throughput by N. The catch: no copy, no parity. Lose one drive and the stripes that touched it are unrecoverable.

Formula: N × min(drives)

RAID 0 — D = dataDrive 1D1D4D7D10Drive 2D2D5D8D11Drive 3D3D6D9D12
Layout diagram

Pros / Cons

Pros

  • Maximum usable capacity (100%)
  • Excellent read AND write performance
  • Universally supported by every RAID controller
  • Simple to configure

Cons

  • Zero fault tolerance — one drive fails, everything is lost
  • Probability of array failure grows with drive count
  • Never appropriate for important data
  • Mixed-size drives are wasteful (capped at smallest)

When to use

Scratch space, video editing cache, transient data that lives elsewhere. Game-load drives. Anything you can lose without consequence.

When NOT to use

Anything you would miss if it disappeared. Always pair with backups, or pick a redundant RAID.

Try it now

Related

RAID 1 →Mirror across drives. Survives N−1 failures. Simplest path to reliable storage in a 2-bay ... RAID 10 →Striped mirrors. Each pair is RAID 1, then RAID 0 across pairs. The fastest traditional RA... RAID 5 →Block-level striping with single distributed parity. Survives any 1 drive failure. The cla... JBOD →Just a Bunch of Disks. Drives concatenated without redundancy. Each drive lives independen... Browse all RAID levels →RAID Levels
Bottom line: Use RAID 0 only when the data is disposable or perfectly backed up. The performance is real, but so is the risk.