NewsLab
Oct 27 20:45 UTC

Migrate Your 300-Node Redis Cluster to Just 3 Lavik Nodes (lavik.dev)

16 points|by hubertzhang||9 comments|Read full story on lavik.dev

Comments (9)

9 shown
  1. 1. stuaxo||context
    What on earth is running on that, Panantirs spying database ?
  2. 2. hubertzhang||context
    Do you mean the use case of a 300-node Redis Cluster?

    It’s very common. Since Redis typically runs with 2 vCores per node, a 300-node cluster can only store about 2.4 TB of data.

    It’s common in human-centric feature stores and profile stores. But it’s even more common in agent profile stores, since agent profiles are a much larger category.

  3. 3. timcobb||context
    what is anagent profile store that is deployed at the scale of terabytes? Do you mean, for example, logs of agent sessions that run on providers?
  4. 4. CAP_NET_ADMIN||context
    > 2 vCores per node, a 300-node cluster can only store about 2.4 TB of data.

    Haven't seen anything more "hyperscaler-brained" in a while.

  5. 5. dotnwat||context
    Do you have comparisons against Dragonfly?
  6. 6. stephbook||context
    Does anyone read websites like these? AI scrapers maybe?
  7. 7. jacquesm||context
    I swear I've seen this link a couple of days ago.
  8. 8. throw20261022||context
    GitHub link: https://github.com/eloqdata/lavik
  9. 9. throw20261022||context
    The three node setup doesn't make sense to me. Why not offer a user-selectable RAID-like choice instead (or even no redundancy)? Also, I don't like the idea of having any node labeled as Primary.