Write buffering

Abstract

A hybrid storage system is described having a mixture of different types of storage devices comprising rotational drives, flash devices, SDRAM, and SRAM. The rotational drives are used as the main storage, providing lowest cost per unit of storage memory. Flash memory is used as a higher-level cache for rotational drives. Methods for managing multiple levels of cache for this storage system is provided having a very fast Level 1 cache which consists of volatile memory (SRAM or SDRAM), and a non-volatile Level 2 cache using an array of flash devices. It describes a method of distributing the data across the rotational drives to make caching more efficient. It also describes efficient techniques for flushing data from L1 cache and L2 cache to the rotational drives, taking advantage of concurrent flash devices operations, concurrent rotational drive operations, and maximizing sequential access types in the rotational drives rather than random accesses which are relatively slower. Methods provided here may be extended for systems that have more than two cache levels.

Description

CROSS-REFERENCE(S) TO RELATED APPLICATIONS[0001]This application is a continuation of application Ser. No. 15 / 665,321, filed Jul. 31, 2017 and issuing Oct. 15, 2019 as U.S. Pat. No. 10,445,239, which is a continuation of application Ser. No. 14 / 689,045, filed Apr. 16, 2015 and issued as U.S. Pat. No. 9,734,067 on Aug. 15, 2017, which claims the benefit of and priority to U.S. Provisional App. No. 61 / 980,561, filed Apr. 16, 2014. This U.S. Provisional Application 61 / 980,561 is hereby fully incorporated herein by reference. U.S. application Ser. No. 14 / 689,045 is a continuation-in-part of application Ser. No. 14 / 217,436, filed Mar. 17, 2014 and issued as U.S. Pat. No. 9,430,386 on Aug. 30, 2016, which claims the benefit of and priority to App. No. 61 / 801,422, filed Mar. 15, 2013. U.S. application Ser. Nos. 15 / 665,321 and 14 / 689,045 and 14 / 217,436 and U.S. Provisional Application 61 / 801,422 are each hereby fully incorporated by reference herein.BACKGROUNDField[0002]This invention relat...

AI Technical Summary

Benefits of technology

[0005]The present invention describes cache management methods for a hybrid storage device having volatile and non-volatile caches. Maximizing concurrent data transfer operations to and from the different cache levels especially to and from flash-based L2 cache results in increased performance over conventional methods. Distributed striping is implemented across the rotational drives maximizing parallel operations on multiple drives. The use of Fastest-To-Fetch and Fastest-To-Flush victim data selection algorithms side-by-side with the LRU algorithm results in further improvements in performance.

[0006]Flow of data to and from the caches and the storage medium is managed using a cache state-based algorithm allowing the firmware application to choose the necessary state transitions that produces the most efficient data flow.

Problems solved by technology

In such systems, the management of the drive cache is clone by the host and the overhead brought about by this contributes to degradation of the caching performance of the storage system.

However, prior solutions that made use of non-volatile memory as cache did not take advantage of the architecture of the non-volatile memories that could have further increased the caching performance of the system.

The storage system does not make any distinction between a rotational drive and a solid-state drive cache thus failing to recognize possible improvements that can be brought about by the architecture of the solid-state drive.

Images