Periodically degrades the inner and outer diameters from the disk to improve read response time

Abstract

A storage controller (102) including a cache (108) receives a command from a host (104a, 104b, ..., 104n) where a set of criteria corresponding to a read response time for execution of the command must be met (402). A downgrade application is performed that downgrades the tracks based at least on using the recency and the spatial position of the track, wherein the spatial ordering of the tracks is maintained in a data structure, and the downgrade application traverses the spatial ordering of the tracks (404). While traversing the spatial ordering of tracks, tracks are demoted at periodic intervals from at least the inner or outer diameter of the disk where a set of criteria corresponding to a read response time for executing a command is met (406).

Description

technical field [0001] The present disclosure relates to methods, systems, and articles of manufacture for periodically degrading from the inner and outer diameters of a disk to improve read response times. Background technique [0002] A storage controller may control multiple storage devices, which may include disks, tapes, and the like. A cache may also be maintained by a storage controller, where a cache may include high speed storage that may be accessed more quickly than certain other storage devices, such as hard disks, tapes, and the like. However, the total amount of storage capacity of the cache is relatively small compared to the storage capacity of some other storage devices, such as hard disks, controlled by the storage controller. A cache may include one or more of random access memory (RAM), non-volatile storage (NVS), read cache, write cache, etc., which may interoperate with each other in different ways. The NVS may include battery-backed RAM and may allow...

AI Technical Summary

Problems solved by technology

To ensure consistently low latency for writes, it may be necessary to drain the data in the NVS, ensuring that there is always some empty space for upcoming writes; otherwise, subsequent writes can effectively become Synchronous, which can negatively affect response time for host writes

On the other hand, if writes are drained too aggressively, the benefit of the write cache may be fully exploited since the average amount of NVS cache utilized may be low

Images