IOPS budget
also: I/O budget, throughput limit, I/O throttling quota
IOPS budget is the maximum number of input/output operations per second that a storage device or cloud instance is allocated or guaranteed to perform. It's a rate limit that prevents excessive disk I/O from consuming shared resources.
IOPS budget (Input/Output Operations Per Second) refers to the performance quota assigned to a storage system. In cloud environments like AWS or Azure, instances are given a baseline IOPS allowance; exceeding it may trigger throttling or incur additional charges.
IOPS measures discrete read/write operations, not data volume. For example, 1,000 IOPS means the storage can handle 1,000 separate operations like file reads or database queries per second, regardless of whether each operation touches 1 KB or 1 MB of data.
Systems often have burst budgets that allow temporary spikes above the baseline. For instance, an AWS gp3 volume might have a baseline of 3,000 IOPS but accumulate burst credits allowing brief periods at higher rates, useful for workloads with uneven I/O patterns.