This is the default option. Fairness-oriented I/O scheduler. The algorithm assigns each thread a time slice in which it is allowed to submit I/O to disk. This way each thread gets a fair share of I/O throughput. This I/O scheduler also allows assigning tasks I/O priorities which are taken into account during scheduling decisions (see man 1 ionice). The CFQ scheduler has the following parameters:

A trivial scheduler that just passes down the I/O that comes to it. Useful for checking whether complex I/O scheduling decisions of other schedulers are not causing I/O performance regressions.

In some cases it can be helpful for devices that do I/O scheduling themselves, as intelligent storage, or devices that do not depend on mechanical movement, like SSDs. Usually, the DEADLINE I/O scheduler is a better choice for these devices. It is a rather lightweight I/O scheduler but already does some useful work. However, NOOP may produce better performance on certain workloads.

Latency-oriented I/O scheduler. The algorithm preferably serves reads before writes. /sys/block/<device>/queue/iosched/writes_starved controls how many reads can be sent to disk before it is possible to send writes and tries to observe given deadlines /sys/block/<device>/queue/iosched/read_expire for reads and /sys/block/<device>/queue/iosched/write_expire for writes after which I/O must be submitted to disk. This I/O scheduler can provide a superior throughput over the CFQ I/O scheduler in cases where several threads read and write and fairness is not an issue. For example, for several parallel readers from a SAN or some database-like loads.