!RROtHmAaQIkiJzJZZE:nixos.org

NixOS Infrastructure

396 Members
Next Infra call: 2024-07-11, 18:00 CEST (UTC+2) | Infra operational issues backlog: https://github.com/orgs/NixOS/projects/52 | See #infra-alerts:nixos.org for real time alerts from Prometheus.119 Servers

Load older messages


SenderMessageTime
13 Mar 2026
@hexa:lossy.networkhexawith no mtr result23:12:57
@hexa:lossy.networkhexawhat is peculiar is that your ipv4 latency is much higher than your ipv6 latency23:13:19
14 Mar 2026
@codayon:matrix.orgReshad Ahammed AyonIs there anything I can do from my end?06:32:09
@amadaluzia:unredacted.orgamadaluzia -> 4d2.org changed their display name from amadaluzia to amadaluzia[uorg].18:48:48
@amadaluzia:4d2.orgamadaluzia joined the room.19:29:29
@amadaluzia:unredacted.orgamadaluzia -> 4d2.org changed their display name from amadaluzia[uorg] to amadaluzia -> 4d2.org.21:22:28
@tomberek:matrix.orgtomberekScaleway is interested in sponsoring in the form of providing hardware and compute. What would the infra team be most interested in from them? They mentioned providing builders from idle availability zones and Apple Silicon. Also interest in RISC-V and a cache for it. Don't limit to just that though, what would have the greatest impact? 21:37:15
@hexa:lossy.networkhexaI guess something of each would be interesting. We do have an Apple bottleneck, but with x86_64-darwin loosing support after 26.05 we shouldn't optimize too much on that.22:11:29
@hexa:lossy.networkhexasay another chonky x86_64-linux, aarch64-linux and two mac minis22:12:10
@hexa:lossy.networkhexa* say another chonky x86_64-linux and aarch64-linux server and two mac minis22:12:21
@hexa:lossy.networkhexarisc-v is at the cusp of becoming interesting, but most cpus are potatoes from what i know22:12:43
@hexa:lossy.networkhexathe question would be when to start buying into it22:12:52
@hexa:lossy.networkhexa* the question would be when to start buying into it and if that point is already here22:13:03
@hexa:lossy.networkhexawe will not target anything below rv23a (the instruction set including vector and virtualization extensions)22:13:40
@hexa:lossy.networkhexa you can open a ticket with fastly here https://support.fastly.com/s/contactsupport 22:14:46
@hexa:lossy.networkhexayou should include the traceroute ideally and ask whether they know why your download performance over this path is slow22:15:12
@jykrwn_bot:matrix.orgjykrwn_bot joined the room.23:53:00
15 Mar 2026
@hexa:lossy.networkhexaand for the mac minis the lower bound for disk space should be 512 GB. we'll run out of disk space too often on smaller disks.00:01:19
@dramforever:matrix.orgdramforeverwhy01:09:23
@hexa:lossy.networkhexabecause no other distro does01:09:42
@hexa:lossy.networkhexamostly because the instruction set before was a grab bag01:10:03
@hexa:lossy.networkhexaand nothing you could properly target as a baseline01:10:13
@dramforever:matrix.orgdramforever ... what? only ubuntu doesn't 01:10:13
@hexa:lossy.networkhexafair, but as a distro we are much more rebuild heavy than all other distros01:11:50
@hexa:lossy.networkhexamaybe except gentoo01:11:54
@dramforever:matrix.orgdramforeverrva23 does not mean better performance01:12:04
@hexa:lossy.networkhexaand what I've seen is that they barely beat an a55/a73 setup01:12:08
@hexa:lossy.networkhexathe scaleway offer is for c910 cpus from what I can tell01:12:30
@hexa:lossy.networkhexawill they even keep up with unstable-small rebuilds between staging merges?01:13:38
@dramforever:matrix.orgdramforever it does not mean we should turn on -march=rva23u64 while building 01:14:01

Show newer messages


Back to Room ListRoom Version: 6