System-wide checkpoint avoidance for distributed database systems
AssigneeAmazon Technologies, Inc.
InventorsANURAG WINDLASS GUPTA, PRADEEP JNANA MADHAVARAPU, LAURION DARRELL BURCHALL, NEAL FACHAN
Life of this patent
Estimating the term…
Abstract
A database system may maintain a plurality of log records at a distributed storage system. Each of the plurality of log records may be associated with a respective change to a data page. Upon detection of a coalesce event for a particular data page, log records linked to the particular data page may be applied to generate the particular data page in its current state. Detecting the coalesce event may be a determination that the number of log records linked to the particular data page exceeds a threshold.
Claims23
A system, comprising:
- at least one database engine head node of a database service, configured to:
- generate one or more redo log records linked to a particular data page of a plurality of data pages stored on a storage node of a plurality of storage nodes implementing a distributed storage service, wherein the storage nodes stores data for a database in a plurality of data pages including the particular data page, wherein each of the one or more redo log records is generated in response to one or more access requests for data stored within the particular data page;
- send the one or more redo log records to the storage node;
- the storage node of the distributed storage service, configured to:
- store the received one or more redo log records linked to the particular data page;
- determine that the one or more redo log records linked to the particular data page exceed a coalesce threshold;
- and
- perform a coalesce operation, wherein said coalesce operation comprises applying the one or more redo log records linked to the particular data page to a previously stored version of the particular data page to generate the particular data page in its current state.
A method, comprising:
- performing, by one or more computing devices:
- maintaining one or more redo log records linked to a particular data page stored for a database;
- detecting a coalesce event for the particular data page based, at least in part, on the one or more redo log records linked to the particular data page;
- and
- in response to detecting the coalesce event for the particular data page, applying the one or more redo log records linked to the particular data page to a previously stored version of the particular data page to generate the particular data page in its current state.
A non-transitory, computer-readable storage medium, storing program instructions that when executed by one or more computing devices implement:
- maintaining one or more redo log records linked to a particular data page stored for a database;
- determining that the one or more redo log records linked to the particular data page exceed a coalesce threshold;
- and
- applying the one or more redo log records linked to the particular data page to a previously stored version of the particular data page to generate the particular data page in its current state.
Dependencies are inferred from the claim text.