Hybrid cache for autonomous vehicle infrastructure
AssigneeGM Cruise Holdings LLC
InventorsHui Dai, Seth Alexander Bunce
Life of this patent
Estimating the term…
Abstract
A method of caching large data objects of greater than 1 GB, comprising: populating a sharded cache with large data objects backfilled from a data store; servicing large data object requests from a plurality of worker nodes via the sharded cache, comprising deterministically addressing objects within the sharded cache; and if a number of requests for an object within a time exceeds a threshold: after receiving a request from a worker node for the object, sending the worker node a redirect message directed to a hot cache, wherein the hot cache is to backfill from a hot cache backfill, and wherein the hot cache backfill is to backfill from the sharded cache.
Claims8
A method for caching, the method comprising:
- storing non-replicated sharded objects in a consistent hash cache, wherein the non-replicated sharded objects are backfilled from a backend data store;
- replicating hot cache objects in a first tier of a hot cache;
- evicting a hot cache object to a second tier of the hot cache when a time to live of the hot cache object expires;
- and
- responding, by the consistent hash cache, to a request from worker node for an object stored in the hot cache with a redirect message for the worker node to obtain the object from the hot cache.
Dependencies are inferred from the claim text.