Scaling performance in a storage server with storage devices
AssigneeSamsung Electronics Co., Ltd.
InventorsBenixon Arul Dhas, Ramaraj Pandian, Ronald Lee
Life of this patent
Estimating the term…
Abstract
Provided is a method of packet processing, the method including receiving an input/output (IO) request from a host, selecting a drive corresponding to the IO request using a hashing algorithm or a round-robin technique, and establishing a connection between the host and the drive.
Claims20
A method of packet processing, the method comprising:
- receiving an input/output (IO) request from a host;
- generating a first hash result using a hashing algorithm based on inputs of both a first drive ID of a first drive and an object key of a key-value pair corresponding to the IO request;
- generating a second hash result using the hashing algorithm based on inputs of both a second drive ID of a second drive and the object key of the key-value pair corresponding to the IO request;
- selecting a drive corresponding to the IO request based on a comparison of the first hash result to the second hash result;
- and
- establishing a connection between the host and the drive,
- wherein the object key has a one-to-one correspondence with a value to be stored on the drive, the value being of the key-value pair.
A system for packet processing, the system comprising a processor comprising cores, and a drive-processing module, wherein:
- one of the cores is configured to receive an input/output (IO) request from a host;
- the drive-processing module is configured to:
- generate a first hash result using a hashing algorithm based on inputs of both a first drive ID of a first drive and an object key of a key-value pair corresponding to the IO request;
- generate a second hash result using the hashing algorithm based on inputs of both a second drive ID of a second drive and the object key of the key-value pair corresponding to the IO request;
- and
- select a drive corresponding to the IO request based on a comparison of the first hash result to the second hash result;
- the processor is configured to establish a connection between the host and the drive;
- and
- the object key has a one-to-one correspondence with a value to be stored on the drive, the value being of the key-value pair.
A non-transitory computer readable medium implemented on a system for packet processing, the non-transitory computer readable medium having computer code that implements a method of packet processing, the method comprising:
- receiving an input/output (IO) request from a host;
- generating a first hash result using a hashing algorithm based on inputs of both a first drive ID of a first drive and an object key of a key-value pair corresponding to the IO request;
- generating a second hash result using the hashing algorithm based on inputs of both a second drive ID of a second drive and the object key of the key-value pair corresponding to the IO request;
- selecting a drive corresponding to the IO request based on a comparison of the first hash result to the second hash result;
- and
- establishing a connection between the host and the drive,
- wherein the object key has a one-to-one correspondence with a value to be stored on the drive, the value being of the key-value pair.
Dependencies are inferred from the claim text.