| 21 Aug 2025 |
 K900 | Would not be great | 15:54:38 |
| K900 | But also, again, I want to first see proof that there's enough hardware | 15:54:38 |
| K900 | And that there's enough demand to justify the Hydra costs | 15:54:43 |
 Tristan Ross | What sort of costs does it make on Hydra? Is it just eval and storage? | 15:55:56 |
| K900 | Queue runner is slow | 15:56:35 |
 emily | cache for the entire jobset on a new platform is substantial (since we pay the whole cost every staging cycle) | 15:56:40 |
| K900 | Queue runner slowness scales with number of jobs | 15:56:44 |
| emily | and Hydra scheduling is a bottleneck | 15:56:53 |
| K900 | Storage is also still questionable | 15:56:59 |
| K900 | Eval is largely not an issue | 15:57:06 |
| emily | I think it would make sense to prove this externally first | 15:57:12 |
| emily | with a separate Hydra | 15:57:23 |
| emily | and see if the hardware can even keep up | 15:57:33 |
| Tristan Ross | Ok, I'll take this back to the HW team and discuss things more. | 15:57:42 |
| emily | the bottleneck right now is x86_64-darwin which I suspect is substantially faster than the best RISC-V hardware | 15:58:10 |
 dramforever | i think risc-v hydra for nixpkgs is "no" | 16:02:43 |
| dramforever | but we could have machines for y'all to play with | 16:02:58 |
 Mic92 | @hexa:lossy.network: is it queue runner or infra week? | 16:03:18 |
 hexa | infra, but I have another duty to attend to | 16:03:36 |
 Jeremy Fleischman (jfly) | infra | 16:03:40 |
| hexa | please talk about the state of the union slides | 16:03:41 |
| hexa | we need them done in time for nixcon | 16:03:49 |
| Jeremy Fleischman (jfly) | can you share them with jeremyfleischman@gmail.com? | 16:04:05 |
| Mic92 | No one in the jitsi anyway | 16:04:30 |
| dramforever | honestly my hope is on either rivos just booping out some servers in 2026 or 2027, or tenstorrent somehow making it work | 16:04:44 |
| Mic92 | Or did we use something else | 16:04:45 |
| Jeremy Fleischman (jfly) | i'm in https://meet.cccda.de/nix-osin-fra | 16:04:53 |
| dramforever | 2025 and early 2026 risc-v is just not happening | 16:05:00 |
| hexa | (the pattern is weird, because meet wants it that way 😄) | 16:05:13 |
| hexa | (will probably be changed down the road, not sure) | 16:05:22 |
