Merge remote-tracking branch 'origin/fix/db-off-data-plane-469' into fix/db-off-data-plane-469
tracker-policy-pr / check-pr (pull_request) Successful in 9s
test / integration-docker (pull_request) Successful in 16s
test / unit (pull_request) Successful in 43s
lint / lint (push) Successful in 2m44s
test / integration-firecracker (pull_request) Successful in 3m42s
test / coverage (pull_request) Successful in 15s
test / publish-infra (pull_request) Has been skipped
tracker-policy-pr / check-pr (pull_request) Successful in 9s
test / integration-docker (pull_request) Successful in 16s
test / unit (pull_request) Successful in 43s
lint / lint (push) Successful in 2m44s
test / integration-firecracker (pull_request) Successful in 3m42s
test / coverage (pull_request) Successful in 15s
test / publish-infra (pull_request) Has been skipped
# Conflicts: # tests/unit/test_macos_infra.py
This commit is contained in:
@@ -168,13 +168,19 @@ def stop() -> None:
|
||||
recorded VMMs AND any orphaned firecracker still bound to either infra
|
||||
config — the PID files drift after crashes / out-of-band kills, and a
|
||||
survivor would hold a link's TAP so the next boot dies with "tap …
|
||||
Resource busy". Drops the version marker so a stopped pair is never
|
||||
treated as adoptable."""
|
||||
Resource busy". Also reaps a surviving *legacy* single combined-VM (the
|
||||
pre-split layout booted from `<infra>/config.json` on the orchestrator
|
||||
link): the two-VM `stop` otherwise wouldn't know about it, and it would
|
||||
hold the orchestrator TAP so the first split boot fails — so the cutover
|
||||
is self-healing, no manual host teardown. Drops the version marker so a
|
||||
stopped pair is never treated as adoptable."""
|
||||
_kill_pidfile(_orch_dir())
|
||||
_kill_pidfile(_gw_dir())
|
||||
_kill_pidfile(_infra_dir()) # legacy pre-split combined VM (migration)
|
||||
_kill_infra_firecrackers()
|
||||
_pid_file(_orch_dir()).unlink(missing_ok=True)
|
||||
_pid_file(_gw_dir()).unlink(missing_ok=True)
|
||||
_pid_file(_infra_dir()).unlink(missing_ok=True) # legacy
|
||||
_version_file().unlink(missing_ok=True)
|
||||
|
||||
|
||||
@@ -357,9 +363,15 @@ def _kill_infra_firecrackers(proc_root: Path = Path("/proc")) -> None:
|
||||
"""SIGKILL any firecracker VMM whose `--config-file` is one of this host's
|
||||
infra configs (orchestrator or gateway), independent of the PID files —
|
||||
reaps orphans it lost track of so both links' TAPs are free to rebind.
|
||||
Scoped to the two infra config paths, so the interactive pool's agent VMs
|
||||
(other config paths) are untouched."""
|
||||
cfgs = {str(_orch_dir() / "config.json"), str(_gw_dir() / "config.json")}
|
||||
Also matches the *legacy* pre-split combined-VM config (`<infra>/config.json`)
|
||||
so a surviving old singleton is cleared off the orchestrator link during the
|
||||
cutover. Scoped to these infra config paths, so the pool's agent VMs (other
|
||||
config paths) are untouched."""
|
||||
cfgs = {
|
||||
str(_orch_dir() / "config.json"),
|
||||
str(_gw_dir() / "config.json"),
|
||||
str(_infra_dir() / "config.json"), # legacy pre-split combined VM
|
||||
}
|
||||
for entry in proc_root.iterdir():
|
||||
if not entry.name.isdigit():
|
||||
continue
|
||||
|
||||
Reference in New Issue
Block a user