How we reduced the cost of building Twitter at Twitter-scale by 100x – Blog
I’m going to cover a lot of ground in this post, so here’s the TLDR: We built a Twitter-scale Mastodon instance from scratch in only 10k lines of code. This is 100x less code than the ~1M lines Twi…
I’m going to cover a lot of ground in this post, so here’s the TLDR: We built a Twitter-scale Mastodon instance from scratch in only 10k lines of code. This is 100x less code than the ~1M lines Twitter wrote to build and scale their original consumer product, which is very similar to Mastodon. Our instance is located at https://mastodon.redplanetlabs.com and open for anyone to use. The instance has 100M bots posting 3,500 times per second at 403 average fanout to demonstrate its scale. Our implementation is built on top of a new platform called Rama that we at Red Planet Labs have developed ov
Explore this link on the map →saved by
related reading
- Production Twitter on One Machine? 100Gbps NICs and NVMe are fast - Tristan Humethume.ca
- Remains of the Dayeugenewei.com
- How to Blow Up a Timeline - Remains of the Dayeugenewei.com
- NYSRGnotes.ekzhang.com
- Threads and the Social/Communications Map – Stratechery by Ben Thompsonstratechery.com
- Building and operating a pretty big storage system called S3 | All Things Distributedallthingsdistributed.com
- Mastodon WTF timeline - Ansuz - mskala's home pageansuz.sooke.bc.ca
- The Distributed Computing Manifesto | All Things Distributedallthingsdistributed.com
- GitHub - igorbrigadir/awesome-twitter-algo: The release of the Twitter algorithm, annotated for recsys · GitHubgithub.com
- How Discord Stores Trillions of Messagesdiscord.com
- Agent swarms and the new model economics · Cursorcursor.com
- TAO: The power of the graph - Engineering at Metaengineering.fb.com