This article presents a comprehensive benchmark comparing memcached and ScyllaDB across memory, disk, and read‑only workloads, analyzes architectural trade‑offs, and offers practical guidance on when to prefer a simple in‑memory cache versus a persistent wide‑column database.
Discord’s rapid growth forced a series of massive database migrations—from MongoDB to Cassandra in 2017, then to ScyllaDB in 2023—detailing the motivations, requirements, data‑model design, performance challenges, migration tooling, and the resulting operational improvements.
This article explains why database capacity planning is challenging and presents a systematic approach—including workload analysis, performance modeling, consistency considerations, and node scaling decisions—using the open‑source NoSQL database ScyllaDB to guide accurate capacity estimation.
This article explains why sizing a database cluster is challenging, outlines a step‑by‑step methodology for estimating workload, configuration and performance, discusses the impact of consistency levels, secondary indexes, materialized views and maintenance, and shows how ScyllaDB can be used to model and simplify capacity planning.
This article explains why sizing a database cluster is challenging, outlines a systematic capacity‑planning process, examines workload characteristics, query‑operation mapping, consistency trade‑offs, and maintenance considerations, and demonstrates how the open‑source NoSQL database ScyllaDB can be used to model and simplify these decisions.
ScyllaDB, a high‑performance C++ implementation of Apache Cassandra, introduces row‑level repair to replace the traditional partition‑level repair, reducing data transfer and I/O by operating on individual rows; the presentation details its architecture, multi‑stage process, experimental results, and the resulting six‑fold speedup.
ScyllaDB, a Cassandra‑compatible NoSQL database, achieves over tenfold performance improvements through a thread‑per‑core design, asynchronous I/O, custom caching, self‑tuning schedulers, a user‑space TCP/IP stack, and LLVM‑JIT query execution, making it a compelling study for high‑performance database engineering.
