host-modules: write credential files atomically; agent-modules: retry a failed .claude migration
Four host glue units fetched a secret from swarm-bao and rendered it with `> path; chmod`: a reader racing the write could see a truncated file, and briefly one at the wrong mode before the chmod landed. glue-matrix-bao-token.nix, glue-queue-agent-credential.nix (both files), swarm-grafana.nix and swarm-otel.nix now write to a same- directory temp file, set its final mode/owner, then `mv -f` it over the target — a shared `atomic_write_secret` helper (nix/host-modules/lib/atomic-write-secret.nix) so the five call sites share one implementation. The first-boot `/root/.claude` migration in nix/agent-modules/user.nix wrote its done-marker unconditionally, so a failed `cp` (disk full, permission error) left the marker behind and no boot ever retried the copy. The marker is now written only when there was nothing to migrate or the copy succeeded; `cp -an`'s no-clobber semantics already make a retry after a partial copy safe. Refs #4723
This commit is contained in:
parent
c978060824
commit
ed53e9abcc
7 changed files with 83 additions and 25 deletions
|
|
@ -77,6 +77,8 @@ let
|
|||
# its own use of it: it is asserted set wherever
|
||||
# `deploy.hive-controller.enable` is.
|
||||
credentialPath = "secret/swarm/hives/${hyperhiveCfg.hiveName}/queue/agent";
|
||||
|
||||
atomicWriteSecret = import ./lib/atomic-write-secret.nix { };
|
||||
in
|
||||
{
|
||||
options.services.hyperhive.deploy.hive-controller.queue = {
|
||||
|
|
@ -217,6 +219,8 @@ in
|
|||
script = ''
|
||||
set -euo pipefail
|
||||
|
||||
${atomicWriteSecret}
|
||||
|
||||
# `bao`'s own message is the only thing separating a missing value from
|
||||
# a refused identity from an unreachable host. This unit's degraded
|
||||
# mode is correct for all three, so it reports which one rather than
|
||||
|
|
@ -279,14 +283,11 @@ in
|
|||
|
||||
install -d -m 0755 ${lib.escapeShellArg credentialDir}
|
||||
|
||||
umask 077
|
||||
printf '%s\n' "$secret" > ${lib.escapeShellArg secretFile}
|
||||
chmod 0600 ${lib.escapeShellArg secretFile}
|
||||
printf '%s\n' "$secret" | atomic_write_secret 0600 "" ${lib.escapeShellArg secretFile}
|
||||
|
||||
# `0644` on purpose: an OIDC client id is presented to the token
|
||||
# endpoint on every connection and is public by construction.
|
||||
printf '%s\n' "$client_id" > ${lib.escapeShellArg clientIdFile}
|
||||
chmod 0644 ${lib.escapeShellArg clientIdFile}
|
||||
printf '%s\n' "$client_id" | atomic_write_secret 0644 "" ${lib.escapeShellArg clientIdFile}
|
||||
'';
|
||||
};
|
||||
})
|
||||
|
|
|
|||
Loading…
Reference in a new issue