Disk Throughput
Calculate sequential disk throughput from IOPS and block size.
About Disk Throughput
Throughput and IOPS describe the same underlying I/O stream from different angles — throughput is simply IOPS multiplied by the size of each operation. This is why storage vendors quote both figures separately: a workload with small blocks (e.g. 4KB random database I/O) can hit its IOPS ceiling long before saturating available MB/s bandwidth, while a workload with large sequential blocks (e.g. 256KB video streaming) tends to hit the bandwidth ceiling first even at modest IOPS.
Formula
Throughput
throughput_MBps = IOPS × block_size_KB / 1024
Worked example
With the default values below, Disk Throughput returns Throughput of 312.50. Change any input above and every figure here is recalculated in your browser.
Inputs used
- IOPSminimum 0
- 5,000
- Block / I/O Sizeminimum 0.5 KB
- 64 KB
Results
- Throughput
- 312.50 MB/s
- Throughput
- 2,500.00 Mb/s
- Throughput
- 0.3052 GB/s
Step by step
- 1Values used
- 2Throughput
- 3Throughput= 312.50 MB/s
- 4Throughput= 2,500.00 Mb/s
- 5Throughput= 0.3052 GB/s
Assumptions and limits
- The result is derived only from the 2 inputs listed above. Anything not among them is not part of the calculation.
- In particular, this calculator does not take inflation, tax or compounding frequency into account.
- Figures are rounded for display to 4 decimal places, so totals built from several rounded parts can differ slightly from the unrounded arithmetic.
How these calculators are built and tested is described on the Methodology page. If a figure looks wrong, please report it.
Frequently Asked Questions
Why does the same storage device report different throughput for different workloads?
Because throughput = IOPS × block size, the same device can be IOPS-limited with small blocks (yielding low throughput despite high IOPS) or bandwidth-limited with large blocks (yielding high throughput at comparatively low IOPS) — vendors typically publish both a max-IOPS spec (small blocks) and a max-throughput spec (large blocks) for this reason.
Should I use random or sequential IOPS in this calculator?
Use whichever IOPS figure matches your actual workload pattern — random IOPS for database/VM workloads with scattered access, sequential IOPS for backup/streaming/large-file workloads — since the two can differ by an order of magnitude on the same device.
Why divide by 1024 instead of 1000?
Storage capacity and I/O size are conventionally expressed in binary units (1 KB = 1024 bytes, 1 MB = 1024 KB) by operating systems and most storage tooling, so dividing by 1024 keeps the throughput figure consistent with how OS-level tools like iostat or Windows Perfmon report it.