Scalable Data Storage Architecture And Methods Of Eliminating I/O Traffic Bottlenecks

• US 20130145064A1
• Filed: 12/31/2012
• Published: 06/06/2013
• Est. Priority Date: 12/02/2005
• Status: Active Grant

• Current Assignee: Branislav Radovanovic
• Original Assignee: Branislav Radovanovic
• Inventors: Radovanovic, Branislav
• Granted Patent: US 8,725,906 B2
• Time in Patent Office: Days
• US Class Current: 710/113
• CPC Class Codes: G06F 13/38 Information transfer, e.g. on bus G06F13/14 takes precedence
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0614 Improving the reliability of storage systems
• CPC Class Codes: G06F 3/0635 by changing the path, e.g. traffic rerouting, path reconfiguration
• CPC Class Codes: G06F 3/0656 Data buffering arrangements
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]

Abstract

A Storage Area Network (SAN) system has host computers, front-end SAN controllers (FE_SAN) connected via a bus or network interconnect to back-end SAN controllers (BE_SAN), and physical disk drives connected via network interconnect to the BE_SANs to provide distributed high performance centrally managed storage. Described are hardware and software architectural solutions designed to eliminate I/O traffic bottlenecks, improve scalability, and reduce the overall cost of SAN systems. In an embodiment, the BE_SAN has firmware to recognize when, in order to support a multidisc volume, such as a RAID volume, it is configured to support, it requires access to a physical disk attached to a second BE_SAN; when such a reference is recognized it passes assess commands to the second BE_SAN. Further, the BE_SAN has firmware to make use of the physical disk attached to the second BE_SAN as a hot-spare for RAID operations.

Claims

1. A data processing system comprising:

at least a first and a second Front End SAN controller (FE_SAN), including a data memory, each FE_SAN physically co-located with a host CPUs and interconnected via a host system bus to the co-located host CPU;

at least a first and a second Back End SAN controller (BE_SAN), each BE_SAN interconnected via at least one back-end network to a plurality of storage devices;

a network fabric interconnecting the FE_SAN controllers with the BE_SAN controllers; and

SAN virtualization firmware executing on the FE_SAN controllers and the BE_SAN controllers configured to request data from a particular BE_SAN of the at least a first and a second BE_SANs when data is required by a host CPU

wherein the SAN virtualization software of the FE_SAN requests a write lock from the at least one BE_SAN controllers on receiving a write command from the host, upon grant of write lock by the BE_SAN the FE_SAN writes data to the BE_SAN for writing to an appropriate storage device, and releases the write lock on completing writing of data to the BE_SAN so that data may be transferred from a host CPU to an appropriate storage device; and

wherein the particular BE_SAN is configured to recognize writes to a failed storage device of the plurality of storage devices attached thereto, and to relay those writes to a second storage device attached to a different BE_SAN controller.

2. The system of claim 1 wherein the BE_SAN includes access control software configured to restrict read or write access to specific locked logical block addresses (LBAs) during writes to prevent data corruption while allowing concurrent unrestricted access to other unlocked logical blocks;

and

wherein, if the first and second FE_SAN request simultaneous write lock to a same logical block address, the BE_SAN grants a lock request to the first FE_SAN upon when its buffer has sufficient space for the indicated amount of data of the first FE_SAN'"'"'s write lock request or when the appropriate storage device is available for writing; and

wherein the BE_SAN grants simultaneous write lock to the second FE_SAN when the BE_SAN has sufficient buffer space available both for the indicated amount of data of the first FE_SAN'"'"'s write lock request and for an indicated amount of data of the second FE_SAN'"'"'s write lock request.

3. The system of claim 1 further comprising RAID code executing on a particular BE_SAN configured to operate at least one virtual dataset as a RAID dataset;

wherein the RAID code is configured to use the second storage device as a hot-spare for the RAID dataset.

4. The system of claim 3 wherein the RAID code is configured to reconstruct data of the failed storage device onto the second device to restore redundancy to the RAID dataset.

5. The system of claim 3 wherein the BE_SAN includes access control software configured to restrict read or write access to specific locked logical block addresses (LBAs) during writes to prevent data corruption while allowing concurrent unrestricted access to other unlocked logical blocks;

and

wherein, if the first and second FE_SAN request simultaneous write lock to a same logical block address, the BE_SAN grants a lock request to the first FE_SAN upon when its buffer has sufficient space for the indicated amount of data of the first FE_SAN'"'"'s write lock request or when the appropriate storage device is available for writing; and

wherein the BE_SAN grants simultaneous write lock to the second FE_SAN when the BE_SAN has sufficient buffer space available both for the indicated amount of data of the first FE_SAN'"'"'s write lock request and for an indicated amount of data of the second FE_SAN'"'"'s write lock request.