Alibaba Cloud Hologres achieved 8,443,627 QphH@3000GB, ranking first on the TPC‑H 3TB performance list with a 54% lead over the runner‑up and the lowest cost‑per‑QphH at 390.47 CNY, demonstrating superior speed and efficiency for real‑time analytics.
This article explains why correlated subqueries are a performance bottleneck, introduces the Apply (Correlated Join) operator and a systematic set of transformation rules that push Apply down and replace subqueries with efficient joins, covering scalar, existential, and quantified subqueries, aggregation handling, and set operations, all illustrated with TPC‑H examples.
A comprehensive TPC‑H benchmark compares ClickHouse, Oracle, and the open‑source esProc SPL across simple and complex queries, showing ClickHouse excels at single‑table scans, while SPL consistently outperforms both in complex calculations and offers more concise code.
This article benchmarks ClickHouse, Oracle, and the open‑source esProc SPL on the TPC‑H suite, showing ClickHouse excels at simple scans, Oracle handles many complex queries, while SPL consistently outperforms both in speed and code simplicity across a range of workloads.
OceanBase achieved a world‑record TPC‑H performance of 15.26 million QphH, illustrating its HTAP capabilities and detailing the technical evolution, challenges, and future direction of hybrid transactional/analytical processing in modern distributed databases.
This article explains how OceanBase, a distributed relational database, achieved a new TPC‑H world record, discusses the evolution of HTAP technology, the architectural challenges of combining transactional and analytical workloads, and the future direction of the product.
OceanBase, the distributed relational database from Ant Group, set a new TPC‑H world record by leveraging its HTAP architecture, blending transaction and analytical processing, and the article details the technical evolution, challenges, and future direction of this hybrid database technology.
This article explains how InnoDB’s B+ tree storage works, calculates the approximate number of rows a single tree can hold based on page size, record size, and tree height, and shows how to determine the tree height from the tablespace file.
The article explains PostgreSQL 11’s new JIT expression compiler, describes how it was benchmarked using the TPC‑H Q1 query on a 22 GB dataset, presents performance improvements over PostgreSQL 10, and provides details on the testing environment, configuration files, and future expectations.
