0 views collected around this technical thread.
This article explores RocketMQ's high availability mechanism, focusing on DLedger's implementation of Raft-based leader election for distributed message middleware, covering both traditional and Controller mode architectures.
Bilibili’s high‑performance distributed KV store combines hash and range partitioning, Raft‑based multi‑replica consistency, and a Metaserver‑managed topology of pools, zones, nodes, tables, shards and replicas, offering features such as partition splitting, binlog streaming, multi‑active replication, bulk loading, KV‑storage separation, and automated load, leader and health balancing for reliable, scalable data services.
GooseFS, Tencent Cloud’s distributed caching system for storage‑compute separation, links compute frameworks to underlying storage (COS, CHDFS, COSN) and boosts big‑data and AI workloads by 2‑10× through transparent acceleration, robust master‑worker architecture, Raft‑based HA, tiered caching, and metadata optimizations, delivering up to 50% cost savings and 29% faster compute jobs.
The article details eBay's 2018‑2020 design, performance testing, and fault‑tolerance architecture of a next‑generation core accounting system capable of handling millions of transactions per second, covering system goals, multi‑region deployment, event‑sourcing, Raft consensus, scalability optimizations, and the planned open‑source release.
CynosDB is Tencent Cloud’s high‑performance, highly‑available NewSQL distributed database that uses a shared‑storage architecture with primary and replica instances, log‑structured storage, RDMA/SPDK transmission, Raft consensus, SSI MVCC, two‑phase locking, and state‑machine replication to provide elastic scaling, fast recovery, and cost‑effective enterprise data management.