Alternatives to Redis while not compromising on its speed
summary
Argues that Aerospike matches Redis’s speed while solving scaling and persistence limits by using a C core, multi‑threading, SSD‑tuned storage and Lua UDFs; claims 10 seconds restart instead of long replays, automatic clustering with rack‑aware replication and async cross‑DC replication, and YCSB shows Aerospike faster than MongoDB and CouchDB. Gives an operational example: replaced 10 MongoDB servers with 2 Aerospike servers for a high‑throughput cache, and reports the system works reliably with auto‑rebalancing and low tail latency.
AI-written summary · about
chapters (11)
- 0:00Intro
- 0:49Redis and Aerospike : indirect friends
- 1:55Salient Features
- 3:48High Performance
- 6:53Data Store
- 10:53Persistence
- 13:01Replication
- 18:26Sharding
- 19:45Clustering
- 22:36Additional Features
- 26:45Redis coming to Aerospike
related talks
31mUser Attribution at Scale: All-Flash, ½ Trillion Objects
26mPowering Real-time Decisions With a Reduced Footprint
46mEdge Performance with In memory NoSQL
24mWhat a Modern Database Enables
48mThe real-time database to build your AI future
05mHighlights From Aerospike APJ Summit 2023
29mDream11: Aerospike Beyond Cache
48mRebuilding a RT Datastore: the design, deployment & performance story