Storage management system and method
AssigneeEMC IP Holding Company LLC
InventorsVamsi K. Vankamamidi, Philippe Armangau, Socheavy D. Heng
Life of this patent
Estimating the term…
Abstract
A method, computer program product, and computing system for processing memory page metadata received from a cache memory system within a data storage system to determine if the memory page metadata includes corruption due to a power failure event; if the memory page metadata includes post-acknowledgement data corruption, initiating a data recovery process to attempt to recover content associated with the post-acknowledgement data corruption; and if the memory page metadata includes pre-acknowledgement data corruption, reobtaining content associated with the pre-acknowledgement data corruption.
Claims13
A computer-implemented method, executed on a computing device, comprising:
- processing memory page metadata received from a cache memory system within a data storage system to determine if the memory page metadata includes corruption due to a power failure event, wherein the memory page metadata identifies a location of a memory page within the cache memory system and includes header information, a payload, and footer information, wherein processing memory page metadata received from a cache memory system within a data storage system to determine if the memory page metadata includes corruption due to a power failure event includes:
- comparing a sequence ID included within the header information of the memory page metadata to a sequence ID included within the footer information, and
- examining a checksum included within the memory page metadata to determine if the memory page metadata was corrupted during the power failure event, wherein the checksum is a checksum of the header information and the payload,
- wherein a bad checksum in combination with a mismatch between the sequence ID included within the header information and the sequence ID included within the footer information indicates a write split due to the power failure event, and
- wherein a bad checksum in combination with the sequence IDs in both the header information and the footer information being either invalid or matched indicates data corruption during the power failure event;
- in response to the sequence IDs in both the header information and the footer information being invalid, initiating a data recovery process to attempt to recover content associated with data corruption, wherein the data recovery process includes a File System Consistency Check (FSCK);
- and
- in response to a bad checksum in combination with a mismatch between the sequence ID included within the header information and the sequence ID included within the footer information, reobtaining content associated with pre-acknowledgement data corruption.
A computer program product residing on a computer readable medium having a plurality of instructions stored thereon which, when executed by a processor, cause the processor to perform operations comprising:
- processing memory page metadata received from a cache memory system within a data storage system to determine if the memory page metadata includes corruption due to a power failure event, wherein the memory page metadata identifies a location of a memory page within the cache memory system and includes header information, a payload, and footer information, wherein processing memory page metadata received from a cache memory system within a data storage system to determine if the memory page metadata includes corruption due to a power failure event includes:
- comparing a sequence ID included within the header information of the memory page metadata to a sequence ID included within the footer information, and
- examining a checksum included within the memory page metadata to determine if the memory page metadata was corrupted during the power failure event, wherein the checksum is a checksum of the header information and the payload,
- wherein a bad checksum in combination with a mismatch between the sequence ID included within the header information and the sequence ID included within the footer information indicates a write split due to the power failure event, and
- wherein a bad checksum in combination with the sequence IDs in both the header information and the footer information being either invalid or matched indicates data corruption during the power failure event;
- in response to the sequence IDs in both the header information and the footer information being invalid, initiating a data recovery process to attempt to recover content associated with data corruption, wherein the data recovery process includes a File System Consistency Check (FSCK);
- and
- in response to a bad checksum in combination with a mismatch between the sequence ID included within the header information and the sequence ID included within the footer information, reobtaining content associated with pre-acknowledgement data corruption.
A computing system including a processor and memory configured to perform operations comprising:
- processing memory page metadata received from a cache memory system within a data storage system to determine if the memory page metadata includes corruption due to a power failure event, wherein the memory page metadata identifies a location of a memory page within the cache memory system and includes header information, a payload, and footer information, wherein processing memory page metadata received from a cache memory system within a data storage system to determine if the memory page metadata includes corruption due to a power failure event includes:
- comparing a sequence ID included within the header information of the memory page metadata to a sequence ID included within the footer information, and
- examining a checksum included within the memory page metadata to determine if the memory page metadata was corrupted during the power failure event, wherein the checksum is a checksum of the header information and the payload,
- wherein a bad checksum in combination with a mismatch between the sequence ID included within the header information and the sequence ID included within the footer information indicates a write split due to the power failure event, and
- wherein a bad checksum in combination with the sequence IDs in both the header information and the footer information being either invalid or matched indicates data corruption during the power failure event;
- in response to the sequence IDs in both the header information and the footer information being invalid, initiating a data recovery process to attempt to recover content associated with data corruption, wherein the data recovery process includes a File System Consistency Check (FSCK);
- and
- in response to a bad checksum in combination with a mismatch between the sequence ID included within the header information and the sequence ID included within the footer information, reobtaining content associated with pre-acknowledgement data corruption.
Dependencies are inferred from the claim text.