Methods for managing failure of a solid state device in a caching storage

摘要

Techniques for managing caching use of a solid state device are disclosed. In some embodiments, the techniques may be realized as a method for managing caching use of a solid state device. Management of the caching use may include receiving, at a host device, notification of failure of a solid state device. In response to the notification a cache mode may be set to uncached. In uncached mode input/output (I/O) requests may be directed to uncached storage (e.g., disk).

主权项

1. A method for managing caching use of a first solid state device and a second solid state device comprising:
receiving, at a host device, a first notification of failure of a first solid state device that is configured to operate as a cache memory device; setting, using a computer processor, a cache mode to uncached in response to the first notification; directing input/output (I/O) requests to uncached storage based on the cache mode setting of uncached; wherein in the event an input/output (I/O) request is sent prior to cache failure and not returned prior to the failure of the solid state device, the input/output (I/O) request may be retried and handled by uncached storage without disrupting the host device; receiving, at the host device, a second notification indicating that the second solid state device, configured to operate as a cache memory device, has been detected; comparing, upon the detection of the second solid state device, a storage size of the second solid state device and a storage size of the first solid state device; when the storage size of the second solid state device is different from the storage size of the first solid state device, adjusting an amount of data to be cached in the second solid state device; initializing the second solid state device; and receiving, at the host device, information about a process sending the I/O requests; and excluding the I/O requests in caching statistics based on the process sending the I/O requests.