railiance-apps/tools/coulomb_image_release_node.py

615 lines
24 KiB
Python
Raw Normal View History

"""Attended founder-only node release; argv/data are sealed by the reviewed capsule.
This is a supervisor command, not a new agent credential or approval boundary.
No Secret object/output is fetched. Existing approved backup custody stays local.
"""
from __future__ import annotations
import argparse
import hashlib
import json
import os
import re
import stat
import subprocess
import tempfile
import time
import urllib.request
from contextlib import ExitStack
from datetime import UTC, datetime
from pathlib import Path
JOURNAL_ROOT = Path("/var/lib/coulomb-social-backup/releases")
SNAPSHOT = Path("/opt/coulomb-social-backup/snapshot-content-and-db.py")
INSTALL_RECEIPT = Path(
"/var/lib/coulomb-social-backup-installations/20261031bacc0001/receipt.json"
)
def canonical(value):
return json.dumps(value, sort_keys=True, separators=(",", ":")).encode()
def sha(data):
return hashlib.sha256(data).hexdigest()
class Refused(RuntimeError):
pass
def private_directories(root, relative):
"""Create every component privately; never repair existing unsafe state."""
if not root.is_absolute() or relative.is_absolute() or ".." in relative.parts:
raise Refused("private_directory_path_required")
with ExitStack() as stack:
def opened(name, parent=None):
fd = os.open(name, os.O_RDONLY | os.O_DIRECTORY | os.O_NOFOLLOW, dir_fd=parent)
stack.callback(os.close, fd)
return fd
fd = opened("/")
for component in root.parts[1:]:
fd = opened(component, fd)
for component in (*relative.parts, None):
info = os.fstat(fd)
if info.st_uid != os.getuid() or stat.S_IMODE(info.st_mode) != 0o700:
raise Refused("private_owned_directory_required")
if component is None:
break
try:
os.mkdir(component, mode=0o700, dir_fd=fd)
os.fsync(fd)
except FileExistsError:
pass
fd = opened(component, fd)
class Release:
def __init__(self, capsule, expected, read_only=False):
self.root = capsule
self.plan = json.loads((capsule / "manifest.json").read_text())
frozen = {}
if "sha256:" + sha(canonical(self.plan)) != expected:
raise Refused("proposal_digest_differs")
for name, digest in self.plan["files"].items():
path = capsule / name
if (
not path.resolve().is_relative_to(capsule.resolve())
or Path(name).is_absolute()
or ".." in Path(name).parts
or path.is_symlink()
or not path.is_file()
or sha(path.read_bytes()) != digest
):
raise Refused("capsule_file_differs")
frozen[name] = path.read_bytes()
if sha(frozen[name]) != digest:
raise Refused("capsule_changed_during_verification")
if os.geteuid() != 0:
raise Refused("attended_founder_root_execution_required")
self.env = dict(os.environ, KUBECONFIG="/etc/rancher/k3s/k3s.yaml")
self.read_only = read_only
for field in ("values_file", "snapshot_file"):
if field in self.plan:
name = self.plan[field]
if (not isinstance(name, str) or not name.startswith("release/")
or ".." in Path(name).parts or name not in frozen):
raise Refused("reviewed_release_artifact_required")
self.receipt = {
"schema": "coulomb.guarded-image-release.v1",
"proposal_digest": expected,
"started_at": datetime.now(UTC).isoformat(),
"status": "preflight",
"production_data_restored": False,
"timers_activated": False,
}
self.journal = JOURNAL_ROOT / expected.removeprefix("sha256:")
self.verify_installation_prerequisite()
if read_only:
return
if self.journal.exists():
raise Refused("prior_execution_requires_review")
private_directories(JOURNAL_ROOT.parent, Path(JOURNAL_ROOT.name))
self.journal.mkdir(mode=0o700)
self.root = self.journal / "capsule"
self.root.mkdir(mode=0o700)
for name, data in frozen.items():
target = self.root / name
private_directories(self.root, Path(name).parent)
fd = os.open(target, os.O_WRONLY | os.O_CREAT | os.O_EXCL, 0o600)
with os.fdopen(fd, "wb") as stream:
stream.write(data)
self.receipt["pid"] = os.getpid()
self.save()
def save(self):
if self.read_only:
return
fd, name = tempfile.mkstemp(prefix=".receipt-", dir=self.journal)
with os.fdopen(fd, "w") as stream:
json.dump(self.receipt, stream, sort_keys=True, indent=2)
stream.flush()
os.fsync(stream.fileno())
os.replace(name, self.journal / "receipt.json")
directory = os.open(self.journal, os.O_RDONLY | os.O_DIRECTORY)
try:
os.fsync(directory)
finally:
os.close(directory)
def command(self, arguments, payload=None, env=None, timeout=180, allowed=(0,)):
# In particular, give the paired capture its existing app-resume window
# on timeout; subprocess.run would SIGKILL it before that cleanup.
with tempfile.TemporaryFile() as stdout, tempfile.TemporaryFile() as stderr:
process = subprocess.Popen(
arguments,
env=env or self.env,
stdin=subprocess.PIPE if payload is not None else subprocess.DEVNULL,
stdout=stdout,
stderr=stderr,
)
try:
process.communicate(payload, timeout=timeout)
except subprocess.TimeoutExpired:
process.terminate()
try:
process.wait(timeout=450)
except subprocess.TimeoutExpired:
process.kill()
process.wait()
raise Refused("private_child_timed_out_after_cleanup_window") from None
stdout.seek(0)
body = stdout.read(8 * 1024**2 + 1)
if len(body) > 8 * 1024**2:
raise Refused("bounded_child_output_required")
result = subprocess.CompletedProcess(arguments, process.returncode, body)
if result.returncode not in allowed:
raise Refused("private_child_refused")
return result
def kdoc(self, *arguments):
return json.loads(self.command(["kubectl", *arguments, "-o", "json"]).stdout)
def history(self):
return json.loads(
self.command(
[
"helm",
"history",
"coulomb-social",
"-n",
"coulomb-social",
"-o",
"json",
]
).stdout
)
def deployment(self):
return self.kdoc("get", "deployment", "coulomb-social", "-n", "coulomb-social")
def probe(self, mode="data"):
source = (self.root / "tools/coulomb_image_probe.py").read_text()
result = self.command(
[
"kubectl",
"exec",
"-n",
"coulomb-social",
"deploy/coulomb-social",
"--",
"python",
"-c",
source,
mode,
]
)
return json.loads(result.stdout)
def same_data(self, actual):
for name in (
"business_tables",
"business_rows",
"business_rows_sha256",
"content_files",
"content_files_sha256",
"migration_rows_sha256",
):
if actual[name] != self.plan["expected_data"][name]:
raise Refused("approved_recovered_dataset_drifted")
if actual["duplicate_slug_groups"] != 0 or actual["tenant_slug_constraint"] is not True:
raise Refused("storage_invariant_refused")
if (actual.get("global_slug_constraint") is not True
or actual.get("migration_0003_applied") is not True):
raise Refused("already_migrated_baseline_required")
def artifact_name(self, field):
return self.plan.get(field, {
"values_file": "release/identity-export-values.yaml",
"snapshot_file": "release/identity-export-snapshot.py",
}[field])
def verify_installation_prerequisite(self):
expected = self.plan.get("prerequisite_installation_digest")
if expected is None:
return
if not re.fullmatch(r"sha256:[a-f0-9]{64}", expected):
raise Refused("reviewed_installation_digest_required")
try:
info = INSTALL_RECEIPT.lstat()
except FileNotFoundError:
raise Refused("inactive_backup_installation_required_before_image_release") from None
if (not stat.S_ISREG(info.st_mode) or info.st_uid != 0
or info.st_mode & 0o077 or info.st_nlink != 1
or any(p.is_symlink() for p in INSTALL_RECEIPT.parents)):
raise Refused("private_installation_receipt_required")
receipt = json.loads(INSTALL_RECEIPT.read_bytes())
if (receipt.get("schema") != "coulomb.backup-source-supervised-installation.v1"
or receipt.get("proposal_digest") != expected
or receipt.get("status") != "sources_installed_units_inactive_verified"
or receipt.get("verified_targets") != 19
or receipt.get("timers_activated") is not False):
raise Refused("verified_inactive_backup_installation_required")
for name in ("paired-backup", "backup-freshness"):
for suffix in ("service", "timer"):
unit = f"coulomb-social-{name}.{suffix}"
raw = self.command(["systemctl", "show", unit,
"--property=LoadState,ActiveState,UnitFileState"]).stdout
state = dict(line.split("=", 1) for line in raw.decode().splitlines())
if (state.get("LoadState") != "loaded" or state.get("ActiveState") != "inactive"
or state.get("UnitFileState") not in {"disabled", "static"}):
raise Refused("backup_units_must_remain_inactive_for_image_release")
jobs = self.command(["systemctl", "list-jobs", "--no-legend", "--no-pager",
"--plain"]).stdout.decode().splitlines()
for line in jobs:
fields = line.split()
if (len(fields) != 4 or not fields[0].isdecimal()
or fields[1].startswith("coulomb-social-")):
raise Refused("queued_backup_job_requires_review")
def preflight(self):
self.verify_installation_prerequisite()
self.verify_installed_helpers()
if (
self.kdoc("get", "namespace", "kube-system")["metadata"]["uid"]
!= self.plan["cluster_uid"]
):
raise Refused("wrong_cluster")
node = self.kdoc("get", "nodes")["items"]
if len(node) != 1 or not any(
a["address"] == "92.205.62.239" for a in node[0]["status"]["addresses"]
):
raise Refused("wrong_node")
conditions = {v["type"]: v["status"] for v in node[0]["status"]["conditions"]}
if conditions.get("Ready") != "True" or any(
conditions.get(k) != "False"
for k in ("MemoryPressure", "DiskPressure", "PIDPressure")
):
raise Refused("node_pressure")
allocated = self.command(
["kubectl", "describe", "node", node[0]["metadata"]["name"]]
).stdout.decode()
requests = {}
for resource in ("cpu", "memory"):
found = re.search(
r"(?m)^\s+" + resource + r"\s+\S+\s+\((\d+)%\)", allocated
)
if not found or int(found[1]) > 90:
raise Refused("node_request_headroom_refused")
requests[resource] = int(found[1])
self.receipt["node_request_percent"] = requests
history = self.history()
if (
history[-1]["revision"] != self.plan["baseline_revision"]
or history[-1]["status"] != "deployed"
):
raise Refused("helm_baseline_changed")
manifest = self.command(
["helm", "get", "manifest", "coulomb-social", "-n", "coulomb-social"]
).stdout
if sha(manifest) != self.plan["baseline_helm_manifest_sha256"]:
raise Refused("helm_manifest_changed")
deployment = self.deployment()
if (
deployment["metadata"]["uid"] != self.plan["deployment_uid"]
or sha(canonical(deployment["spec"])) != self.plan["baseline_spec_sha256"]
):
raise Refused("live_spec_changed")
if (
deployment["status"].get("readyReplicas") != 1
or deployment["spec"]["strategy"]["type"] != "Recreate"
):
raise Refused("single_ready_writer_required")
# Helm's three-way merge preserves unmanaged pod metadata. Bind the
# complete desired live spec rather than treating kubectl apply's
# last-applied projection as Helm's result.
image_patch = [
{"op": "test", "path": "/spec", "value": deployment["spec"]},
{"op": "replace", "path": "/spec/template/spec/containers/0/image",
"value": self.plan["candidate_image"]},
]
preview = self.kdoc(
"patch", "deployment", "coulomb-social", "-n", "coulomb-social",
"--type=json", "--dry-run=server", "-p", json.dumps(image_patch),
)
if sha(canonical(preview["spec"])) != self.plan["candidate_spec_sha256"]:
raise Refused("image_only_server_preview_differs")
pvc = self.kdoc("get", "pvc", "coulomb-social-content", "-n", "coulomb-social")
if (
pvc["metadata"]["uid"] != self.plan["pvc_uid"]
or pvc["status"]["phase"] != "Bound"
):
raise Refused("pvc_changed")
apps = self.kdoc("get", "applications.argoproj.io", "-A")["items"]
if any(
a.get("spec", {}).get("destination", {}).get("namespace")
== "coulomb-social"
for a in apps
):
raise Refused("gitops_adoption_requires_owner_path")
rendered = self.command(
[
"helm",
"template",
"coulomb-social",
str(self.root / "charts/coulomb-social"),
"-f",
str(self.root / self.artifact_name("values_file")),
"-n",
"coulomb-social",
]
).stdout
if sha(rendered) != self.plan["candidate_render_sha256"]:
raise Refused("candidate_render_changed")
self.command(["kubectl", "diff", "-f", "-"], payload=rendered, allowed=(0, 1))
self.command(
["kubectl", "apply", "--dry-run=server", "-f", "-"], payload=rendered
)
self.command(
[
"helm",
"upgrade",
"coulomb-social",
str(self.root / "charts/coulomb-social"),
"-f",
str(self.root / self.artifact_name("values_file")),
"-n",
"coulomb-social",
"--dry-run=server",
]
)
before = self.probe()
self.same_data(before)
self.receipt["preflight"] = before
self.save()
def verify_installed_helpers(self):
for path, expected in self.plan["installed_helper_hashes"].items():
metadata = Path(path).lstat()
if (
not stat.S_ISREG(metadata.st_mode)
or metadata.st_uid != 0
or metadata.st_mode & 0o022
or sha(Path(path).read_bytes()) != expected
):
raise Refused("installed_backup_helper_changed")
def capture(self):
self.verify_installed_helpers()
environment = dict(self.env)
for name in ("primary.env", "recipient.env"):
path = Path("/etc/coulomb-social-backup") / name
metadata = path.lstat()
if (
not stat.S_ISREG(metadata.st_mode)
or metadata.st_uid != 0
or metadata.st_mode & 0o077
):
raise Refused("private_own_backup_configuration_required")
environment.update(
dict(
line.split("=", 1)
for line in path.read_text().splitlines()
if line and not line.startswith("#")
)
)
output = self.command(
["python3", "/opt/coulomb-social-backup/paired-backup.py", "--execute"],
env=environment,
timeout=1200,
)
point = json.loads(output.stdout)
if (
point.get("status") != "offsite_fetched_verified"
or not point.get("remote_retrieval_verified")
or not point.get("version_id")
or point.get("version_id") == "null"
or point.get("image") != self.plan["old_image"]
or point.get("age_recipient") != self.plan["public_recipient"]
or not point.get("immutable_create")
or not point.get("destination", "").startswith(
"s3://railiance-platform-pg-backup/platform-pg/application-archives/coulomb-social/"
)
):
raise Refused("fresh_paired_primary_readback_required")
self.receipt["fresh_paired_point"] = point
self.save()
self.same_data(self.probe())
def restore_pin(self, old):
path = SNAPSHOT
if (
sha(path.read_bytes())
== self.plan["files"][self.artifact_name("snapshot_file")]
):
self.replace_pin(path, old)
elif sha(path.read_bytes()) != sha(old):
raise Refused("snapshot_pin_changed_during_rollback")
def replace_pin(self, path, value):
fd, name = tempfile.mkstemp(prefix=".reviewed-snapshot-", dir=path.parent)
try:
with os.fdopen(fd, "wb") as stream:
stream.write(value)
stream.flush()
os.fsync(stream.fileno())
os.replace(name, path)
directory = os.open(path.parent, os.O_RDONLY | os.O_DIRECTORY)
try:
os.fsync(directory)
finally:
os.close(directory)
finally:
if os.path.exists(name):
os.unlink(name)
def execute(self):
began = time.monotonic()
self.preflight()
self.capture()
old_pin = SNAPSHOT.read_bytes()
self.receipt["status"] = "upgrade_started"
self.save()
try:
self.command(
[
"helm",
"upgrade",
"coulomb-social",
str(self.root / "charts/coulomb-social"),
"-f",
str(self.root / self.artifact_name("values_file")),
"-n",
"coulomb-social",
"--atomic",
"--wait",
"--timeout",
"5m",
],
timeout=660,
)
after = self.deployment()
if (
sha(canonical(after["spec"])) != self.plan["candidate_spec_sha256"]
or after["status"].get("readyReplicas") != 1
):
raise Refused("candidate_spec_or_readiness_differs")
probe = self.probe("views")
self.same_data(probe)
for suffix in ("/healthz", "/", "/static/spaces/copy-content.js"):
with urllib.request.urlopen(
"https://app.coulomb.social" + suffix, timeout=20
) as response:
body = response.read(1024**2)
if response.status != 200:
raise Refused("public_http_postflight_refused")
if (
suffix.endswith("copy-content.js")
and sha(body) != self.plan["clipboard_static_sha256"]
):
raise Refused("served_static_differs")
path = SNAPSHOT
if (
sha(path.read_bytes())
!= self.plan["installed_helper_hashes"][str(path)]
):
raise Refused("snapshot_pin_drifted")
self.replace_pin(
path, (self.root / self.artifact_name("snapshot_file")).read_bytes()
)
self.command(
[
"python3",
str(path),
"--destination",
"/tmp/csoc-post-image-server-review",
]
)
self.receipt.update(
status="image_candidate_deployed_verified",
postflight=probe,
helm_revision=self.history()[-1]["revision"],
snapshot_pin_refreshed=True,
public_health_landing_static_verified=True,
existing_global_constraint_preserved=True,
)
except Exception:
self.receipt["rollback_requested"] = True
try:
self.command(
[
"helm",
"rollback",
"coulomb-social",
str(self.plan["baseline_revision"]),
"-n",
"coulomb-social",
"--wait",
"--timeout",
"5m",
],
timeout=360,
)
self.restore_pin(old_pin)
restored = self.deployment()
if (sha(canonical(restored["spec"])) != self.plan["baseline_spec_sha256"]
or restored["status"].get("readyReplicas") != 1):
raise Refused("rollback_spec_or_readiness_differs")
self.receipt["image_rollback_completed"] = True
except Exception: # noqa: BLE001 -- retain explicit unconfirmed rollback outcome
self.receipt["image_rollback_completed"] = False
raise
self.receipt.update(
elapsed_seconds=round(time.monotonic() - began, 3),
completed_at=datetime.now(UTC).isoformat(),
private_values_printed=False,
)
self.save()
return self.receipt
def main():
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--capsule", type=Path, required=True)
parser.add_argument("--expect-digest", required=True)
parser.add_argument("--execute", action="store_true")
parser.add_argument("--preflight", action="store_true")
args = parser.parse_args()
if not args.execute and not args.preflight:
print(json.dumps({"status": "prepared", "live_changes": False}))
return
if args.execute and args.preflight:
raise SystemExit("choose read-only preflight or attended execution")
release = None
try:
release = Release(args.capsule, args.expect_digest, read_only=args.preflight)
if args.preflight:
release.preflight()
print(
json.dumps(
dict(
release.receipt,
status="live_release_preflight_verified",
live_changes=False,
)
)
)
return
print(json.dumps(release.execute()))
except Exception as error: # noqa: BLE001 -- private child diagnostics are suppressed
receipt = release.receipt if release is not None else {
"proposal_digest": args.expect_digest, "execution_started": False,
}
receipt.update(status="release_refused_or_failed", failure_type=type(error).__name__)
if isinstance(error, Refused):
receipt["failure_reason"] = str(error)
if release is not None:
release.save()
print(json.dumps(receipt))
raise SystemExit(1) from None
if __name__ == "__main__":
main()