Related Concepts

Understand the following concepts before using OmniRuntime features.

• Homogeneous Acceleration Framework (HAF): provides user-friendly programming methods and application programming interfaces (APIs) to quickly, effectively, and securely push specified acceleration segments of your service programs to storage nodes. It works with OmniData to optimize the offload effect.
• OmniVec: An efficient off-heap memory data organization method. It supports zero-copy data read and has no serialization overhead.
• Omni operators: High-performance operators, which use native code (C/C++) to replace physical operators at the bottom layer of big data, increasing the computing speed.
• In-memory shuffle: During shuffle, data is cached in the memory instead of being directly written to drives. In this way, the drive I/O overhead is reduced to improve the data processing efficiency.
• OCKD process: After OmniShuffle is installed, you can use the OCKD process to start or stop OmniShuffle.
• Remote Shuffle Service (RSS): The shuffle service is deployed on a node outside the Spark cluster and shuffles data remotely.
• Rich execution environment (REE): A standard operating system that a device is running. Compared with a TEE, an REE is a traditional server running environment.
• Trusted execution environment (TEE): A hardware security feature that is isolated from a normal operating system, for example, an REE.
• Entropy supplementing: Entropy indicates the state of disorder. Entropy supplementing refers to using the haveged tool to increase the password generation randomness.
• Index columns: When creating an index, you can specify some columns of the data table as index columns. Those columns are used as part of the primary key of the index table to accelerate queries.
• Covering columns: When creating an index, you can specify some columns of the data table as covering columns. Those columns are redundantly stored in the index table to accelerate the query of non-index columns without querying the data table.
• Composite indexes: Multiple columns can be specified as index columns (cross-column family is supported).
• Covering indexes: Multiple columns can be specified as covering columns and are redundantly stored in the index table. Those columns are used to accelerate the query of non-index columns.