vinzenz/hyperhive
vinzenz/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Activity

make bao readers want swarm-bao-pki and drop its start limit

Browse source 
A pki start refused by its start limit failed every reader that
Requires= it with `dependency`. That leaves a unit inactive, not
failed, so Restart=on-failure never fired and readers without a
refresh timer never ran again (#5381: grafana 502 for ~43 min).

Readers and granting units now Wants= + After= pki; one whose leaf is
still missing fails its login with exit 1 into its existing retry.
pki gets StartLimitIntervalSec=0: it is deliberately not
RemainAfterExit, so each reader's start re-runs it.
This commit is contained in:
atlas 2026-10-16 18:29:35 +02:00
commit 265f8a47cc
12 changed files with 95 additions and 46 deletions
Download patch file Download diff file Expand all files Collapse all files

20
nix/module-eval/bao-matrix-reader.nix
View file

@ -162,26 +162,32 @@ let
&& !(builtins.elem "hive-c0re.service" (u.requires or [ ]));
}
{
# `Requires=` on a unit that does not exist fails the job, and nothing
# local mints certificates off-host — so this orders against nothing.
# Eval cannot see that failure; only the empty list here stands in for it.
name = "an off-host reader requires no unit the store's host would have provided";
# Nothing local mints certificates off-host, so this orders against
# nothing there.
name = "an off-host reader names no unit the store's host would have provided";
# Membership first, then the value: indexing a missing unit throws, and a
# table that reports which property broke must not be the thing that dies.
ok =
let
s = baoRemoteReader.systemd.services;
u = s.swarm-bao-queue-agent;
in
s ? swarm-bao-queue-agent && s.swarm-bao-queue-agent.requires == [ ];
s ? swarm-bao-queue-agent && !(lib.elem "swarm-bao-pki.service" (u.after ++ u.wants ++ u.requires));
}
{
# Presence control for the case above: the list is conditional, not gone.
name = "a co-located reader still orders after the local pki unit";
# Wanted, never required: a refused pki start fails a requirer's job with
# `dependency`, which its `Restart=on-failure` never retries.
name = "a co-located reader still orders after and wants the local pki unit, and does not require it";
ok =
let
s = baoWithMatrix.systemd.services;
u = s.swarm-bao-queue-agent;
in
s ? swarm-bao-queue-agent && s.swarm-bao-queue-agent.requires == [ "swarm-bao-pki.service" ];
s ? swarm-bao-queue-agent
&& lib.elem "swarm-bao-pki.service" u.after
&& lib.elem "swarm-bao-pki.service" u.wants
&& u.requires == [ ];
}
{
# Nothing asserted this script before, which is how it kept a branch that