| 23 Feb 2026 |
 hexa | so likely an issue with the M.2 slot on the other board | 13:08:31 |
| hexa | kudos to hetzner for being super easy to work with on this machine | 13:09:12 |
|  sinan changed their profile picture. | 13:20:05 |
| sinan | 13:20:13 |
| sinan | 13:20:24 |
| sinan | 13:21:02 |
 Vladimír Čunát | Thanks for dealing with all this. | 13:23:36 |
| hexa | Product previous price New price as of 1 April 2026
CAX11 (HEL1) € 3.29 € 4.49
CPX42 (NBG1) € 19.49 € 25.49
CX42 (HEL1) € 15.90 € 20.99
Object Storage (additional storage per 1 TB-hour) (NBG1) € 0.0067 € 0.0087
Object Storage (monthly base price) (NBG1) € 4.99 € 6.49
AX51-NVMe (FSN1) € 63.10 € 64.99
AX101 (HEL1) € 101.60 € 104.65
Mac Mini M1 (FSN1) € 52.10 € 53.66
RX170 (HEL1) € 167.30 € 172.32
RX220 (HEL1) € 217.30 € 223.82
AX102 (FSN1) € 107.30 € 122.30
EX44 (HEL1) € 37.30 € 42.30
AX162-R (FSN1) € 207.30 € 242.30
| 13:24:28 |
| hexa | https://docs.google.com/spreadsheets/d/1f3tdqcovFXO36aqRplk__XApIPF0BAMwdxzvF8cy9MI/edit?usp=sharing | 13:33:02 |
| hexa | ~165 EUR increase | 13:33:11 |
 Tom | Or in other words: nearly four AX41-NVME in additional costs per month 😥 | 14:11:08 |
| 24 Feb 2026 |
|  cdepillabout left the room. | 07:39:17 |
 K900 | Going to bonk the next unstable-small eval which should be any minute now | 12:13:11 |
| 25 Feb 2026 |
 tfc | Danke Merz | 10:24:27 |
| hexa | For once, actually not his fault | 10:26:31 |
 Emil Thorsøe | is it Schultz? | 10:31:06 |
| Emil Thorsøe | Obama? | 10:31:09 |
| Emil Thorsøe | gotta be Obama | 10:31:13 |
 lassulus | sam altman | 12:26:54 |
|  isabel changed their profile picture. | 21:51:38 |
| 26 Feb 2026 |
|  Lily Foster changed their profile picture. | 14:01:10 |
| 27 Feb 2026 |
|  amadaluzia[tde] changed their profile picture. | 03:54:05 |
 Jeremy Fleischman (jfly) | do we have any alerts to tell us if zfs scrub failed or if a zfs pool is degraded? the only zfs specific alert i see is for pool free space | 07:06:46 |
| Jeremy Fleischman (jfly) | lol nevermind, i see we just added a unhealthy check: https://github.com/NixOS/infra/commit/1c46bbda28fe056dd4a4b9a0c95e5602fdf5f738 | 07:21:28 |
| Jeremy Fleischman (jfly) | but i did play with this a bit, and i see that a pool that fails scrub stills shows up as ONLINE:
$ sudo zpool status -v
pool: tank
state: ONLINE
status: One or more devices has experienced an error resulting in data
corruption. Applications may be affected.
action: Restore the file in question if possible. Otherwise restore the
entire pool from backup.
see: https://openzfs.github.io/openzfs-docs/msg/ZFS-8000-8A
scan: scrub repaired 0B in 00:00:00 with 3 errors on Thu Feb 26 23:18:53 2026
config:
NAME STATE READ WRITE CKSUM
tank ONLINE 0 0 0
/home/jeremy/tmp/fsing/disk1 ONLINE 0 0 8
errors: Permanent errors have been detected in the following files:
/tank/hello.txt
| 07:23:03 |
| Jeremy Fleischman (jfly) | seems like the prometheus zfs exporter we use doesn't export scrub status: https://github.com/pdf/zfs_exporter/issues/20, which was closed in favor of https://github.com/pdf/zfs_exporter/issues/5, which seems to be blocked on added support for the new zfs cli json output | 07:35:27 |
| K900 | I am killing all builds on all non-staging non-darwin branches right now | 13:02:54 |
| K900 | Because of /nix/store/j4ra5i3f9x6bk3y6aq6ma17z1hlqr18d-nixos-system-konata-26.05.20260227.bde6ce6 | 13:02:57 |
| K900 | * Because of https://lore.kernel.org/all/bb9ab61c-3bed-4c3d-baf0-0bce4e142292@moonlit-rail.com/ | 13:03:05 |
| K900 | @vcunat can you pause the jobsets so we don't get any new evals | 13:03:51 |
