rollbridge 0.1.58 → 0.1.60
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/changelog.d/20261105-owner-mutation-lease-diagnostics.md +20 -0
- package/changelog.d/20261106-release-dependency-boot-budgets.md +32 -0
- package/docs/config.md +40 -0
- package/docs/troubleshooting.md +43 -6
- package/package.json +1 -1
- package/src/config.js +91 -2
- package/src/daemon.js +10 -8
- package/src/guardian-client.js +13 -2
- package/src/health.js +99 -8
- package/src/process-guardian.js +125 -15
- package/src/process-order.js +26 -0
- package/src/release-group.js +157 -22
- package/test/config-validation.test.js +53 -0
- package/test/fixtures/deferred-boot-app.js +106 -0
- package/test/guardian-client.test.js +32 -0
- package/test/health.test.js +74 -1
- package/test/rollbridge.test.js +128 -0
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
### Fixed
|
|
2
|
+
|
|
3
|
+
- A refused owner mutation now names its holder. The refusal used to read
|
|
4
|
+
`Another owner mutation is already in progress` with no context, so an
|
|
5
|
+
operator could not tell which command held the fence, which process held it,
|
|
6
|
+
for how long, or what it was blocked on. The guardian now records the
|
|
7
|
+
mutation's operation, lease id, holding PID, start time and current blocker
|
|
8
|
+
(`waitingFor`, refinable while the mutation runs through
|
|
9
|
+
`reportOwnerMutationWait`) and reports them in every refusal, including the
|
|
10
|
+
replacement-prepare fence.
|
|
11
|
+
|
|
12
|
+
### Changed
|
|
13
|
+
|
|
14
|
+
- The owner-mutation fence is bounded. A mutation that outruns its lease
|
|
15
|
+
(default 15 minutes, per-command override through `mutationTimeoutMs`) is
|
|
16
|
+
logged as `OWNER_MUTATION_LEASE_EXPIRED`, reported to the holder, and
|
|
17
|
+
released, so a stuck mutation can no longer lock out every later deploy. The
|
|
18
|
+
holder fails loudly when it next ends that mutation instead of silently
|
|
19
|
+
keeping the fence. Retained generation drains are unaffected: they are not
|
|
20
|
+
owner mutations and may still run for hours.
|
|
@@ -0,0 +1,32 @@
|
|
|
1
|
+
### Added
|
|
2
|
+
|
|
3
|
+
- `processes[].dependsOn` names the same-release processes a process needs, and
|
|
4
|
+
Rollbridge now waits for each dependency's allocated port **before** spawning
|
|
5
|
+
the dependent, on `processes[].dependencyTimeoutMs` (default 30 seconds) — a
|
|
6
|
+
budget of its own that is never charged to `health.timeoutMs`. Each wait is
|
|
7
|
+
logged as `release process dependency wait` and `release process dependency
|
|
8
|
+
ready` with `attempts` and `elapsedMs`. `validate` rejects a dependency on
|
|
9
|
+
itself, an unknown process, a `singleton`, a process with no `port`, and a
|
|
10
|
+
process Rollbridge starts after the dependent, which also rules out cycles.
|
|
11
|
+
|
|
12
|
+
### Fixed
|
|
13
|
+
|
|
14
|
+
- A release-scoped process no longer spends the proxied health deadline waiting
|
|
15
|
+
for a dependency. Measured on production 2026-11-06: `background-jobs-main`
|
|
16
|
+
took 11 817 ms to start listening (14:33:39.175 → 14:33:50.992) and the web
|
|
17
|
+
command's own `wait-port` hop then ate part of the same 30 000 ms that
|
|
18
|
+
`proxy.healthTimeoutMs` and `health.timeoutMs` allowed for the whole start
|
|
19
|
+
sequence, leaving the app about 16 seconds to boot before Rollbridge killed a
|
|
20
|
+
release that was still starting normally. The health gate now measures only
|
|
21
|
+
the proxied process's own boot and reports `bootMs`, `healthGateMs`, and
|
|
22
|
+
`waitedForDependenciesMs` in `release candidate health ready`.
|
|
23
|
+
- A failed release start is diagnostic. The health failure now reads
|
|
24
|
+
`Health check failed for <url>: <reason> (process <id>: 18 probes, 941ms
|
|
25
|
+
elapsed of the 900ms health deadline)` instead of naming only the connection
|
|
26
|
+
error, and `release startup failed` carries `deadlineMs`, `dependencyWaitMs`,
|
|
27
|
+
`elapsedMs`, `releaseElapsedMs`, `stage` (`dependency` or `health`), `probes`,
|
|
28
|
+
`failedProcessId`, `readyProcesses`, `unreadyProcesses`, and the failed
|
|
29
|
+
process's `lastOutput`/`lastOutputAt`. A dependency gate that expires fails
|
|
30
|
+
the deploy as `Process <id> could not start because dependency <id> was not
|
|
31
|
+
ready: …` on its own budget; the health gate is unchanged, so a genuinely
|
|
32
|
+
unhealthy release still fails and the incumbent keeps serving.
|
package/docs/config.md
CHANGED
|
@@ -233,6 +233,8 @@ legacyTakeover: {
|
|
|
233
233
|
| `env` | object of string → string | `{}` | Extra environment variables (values templated). Merged over the injected `ROLLBRIDGE_*` vars. |
|
|
234
234
|
| `port` | number or `{from, to}` | unset | Port (or range) allocated per release. **Required for the `proxied` process.** A plain number `n` means the fixed port `n` (`{from: n, to: n}`). |
|
|
235
235
|
| `health` | object or `false` | enabled with defaults | Health check for the `proxied` process; set `false` to disable (see below). |
|
|
236
|
+
| `dependsOn` | array of process ids | `[]` | Processes whose allocated port must accept a connection before Rollbridge starts this process (see [`processes[].dependsOn`](#processesdependson)). |
|
|
237
|
+
| `dependencyTimeoutMs` | positive number | `30000` | Budget for each `dependsOn` wait. Charged to its own clock, never to `health.timeoutMs`. |
|
|
236
238
|
| `stopSignal` | signal name (e.g. `"SIGTERM"`, `"SIGINT"`, `"SIGQUIT"`) | `"SIGTERM"` | Signal sent to gracefully stop the process; after `gracefulStopMs` it is `SIGKILL`ed. Use a worker's quit signal so it finishes in-flight work before exiting. |
|
|
237
239
|
| `nonBlockingDrain` | boolean | `false` | When a release is retired, drain this process **immediately** (in parallel with the proxied connection drain) instead of after it. Companion processes only — typically background workers (see below). |
|
|
238
240
|
| `lifecycle` | object | no hooks | Command hooks run when gracefully stopping the process (see below). |
|
|
@@ -447,6 +449,43 @@ release). Set `health: false` to disable it.
|
|
|
447
449
|
| `health.intervalMs` | number | `250` | Delay between probes. |
|
|
448
450
|
| `health.startDelayMs` | non-negative number | `0` | Wait this long after the process starts before the first probe (runs before the `timeoutMs` window). |
|
|
449
451
|
|
|
452
|
+
### `processes[].dependsOn`
|
|
453
|
+
|
|
454
|
+
A release-scoped process that talks to a same-release service usually waits for
|
|
455
|
+
that service inside its own command (`wait-port … && exec <app>`). That wait
|
|
456
|
+
runs after Rollbridge has started the process, so it is charged against
|
|
457
|
+
`health.timeoutMs`: a dependency that takes 12 seconds to bind leaves the app 18
|
|
458
|
+
seconds of a 30-second health deadline, and the deploy fails while the app is
|
|
459
|
+
still booting normally.
|
|
460
|
+
|
|
461
|
+
Declare the dependency instead, and Rollbridge waits for each `dependsOn`
|
|
462
|
+
process's allocated port **before** spawning the dependent, on a budget of its
|
|
463
|
+
own (`dependencyTimeoutMs`):
|
|
464
|
+
|
|
465
|
+
```js
|
|
466
|
+
{
|
|
467
|
+
id: "web",
|
|
468
|
+
policy: "proxied",
|
|
469
|
+
dependsOn: ["background-jobs-main"],
|
|
470
|
+
dependencyTimeoutMs: 30000,
|
|
471
|
+
command: "exec node build/bin/velocious.js server --port {{port}}",
|
|
472
|
+
port: {from: 14500, to: 14599},
|
|
473
|
+
health: {path: "/ping", timeoutMs: 120000}
|
|
474
|
+
}
|
|
475
|
+
```
|
|
476
|
+
|
|
477
|
+
`health.timeoutMs` then measures only the app's own boot. Both waits are logged
|
|
478
|
+
separately: `release process dependency wait` / `release process dependency
|
|
479
|
+
ready` (with `attempts` and `elapsedMs`) and `release candidate health ready`
|
|
480
|
+
(with `bootMs`, `healthGateMs`, and `waitedForDependenciesMs`).
|
|
481
|
+
|
|
482
|
+
`dependsOn` accepts ids of processes Rollbridge starts before this one —
|
|
483
|
+
persistent services, handoff services, companions, and the proxied process. A
|
|
484
|
+
dependency must have a `port` (there is nothing to wait for otherwise), may not
|
|
485
|
+
be a `singleton` (singleton ownership is not per-release), and may not be this
|
|
486
|
+
process itself. Dependencies that Rollbridge would start after this process are
|
|
487
|
+
rejected, which also rules out cycles.
|
|
488
|
+
|
|
450
489
|
## `compose[]`
|
|
451
490
|
|
|
452
491
|
Optional Docker Compose services this app updates. Each entry is a unit Rollbridge
|
|
@@ -548,6 +587,7 @@ Rollbridge sets these in every managed process's environment (the process's own
|
|
|
548
587
|
- `replicas` must be a positive integer; `replicas > 1` is allowed only on a `companion` process without a `port`. Process ids must not contain `#` (reserved for replica instance ids).
|
|
549
588
|
- `lifecycle.activateCommand`/`quietCommand`/`drainCommand`/`stopCommand` must be non-empty strings when set, and `lifecycle.drainTimeoutMs` a non-negative number; `lifecycle.drainCommand` requires a positive `lifecycle.drainTimeoutMs`. `activateCommand` is allowed on at most one handoff service, requires that service's `quietCommand`, and requires `statePath` plus `ownerRecovery`. A `lifecycle.stopCommand` may not be combined with a custom `stopSignal` (the `stopCommand` runs instead of the signal, so the signal would be ignored).
|
|
550
589
|
- `nonBlockingDrain` must be a boolean, and is allowed only on a `companion` process.
|
|
590
|
+
- `dependsOn` must be an array of configured process ids: not the process itself, not a `singleton`, not a process without a `port`, and not a process Rollbridge starts after it. `dependencyTimeoutMs` must be a positive number.
|
|
551
591
|
- `statePath` must be a string when set.
|
|
552
592
|
- `compose` must be a non-empty array of unit mappings. Each unit needs `id`, `service`, `projectDirectory`, and a valid `image` reference (a tag, or a `@sha256:` digest with 64 hex characters; no whitespace, no leading `-`).
|
|
553
593
|
- Compose unit `id`s must be unique and must not collide with a process `id`.
|
package/docs/troubleshooting.md
CHANGED
|
@@ -54,14 +54,27 @@ Health check failed for http://127.0.0.1:18182/ping: HTTP 503
|
|
|
54
54
|
new release never went live; the previous release stays active.
|
|
55
55
|
|
|
56
56
|
**Diagnose.** The new release's `proxied` process didn't return a healthy
|
|
57
|
-
response in time.
|
|
58
|
-
|
|
59
|
-
|
|
60
|
-
|
|
57
|
+
response in time. The reason names what it spent that budget on —
|
|
58
|
+
`(process web: 18 probes, 941ms elapsed of the 900ms health deadline)` — and the
|
|
59
|
+
`release startup failed` event carries `deadlineMs`, `elapsedMs`,
|
|
60
|
+
`dependencyWaitMs`, `probes`, `stage` (`"dependency"` or `"health"`),
|
|
61
|
+
`failedProcessId`, `readyProcesses`/`unreadyProcesses`, and the process's
|
|
62
|
+
`lastOutput`. Check that process's output with `rollbridge logs --process <id>`
|
|
63
|
+
and its state/`exitCode` with `rollbridge status`. Common causes: the app doesn't
|
|
64
|
+
listen on the templated `{{port}}`, the `health.path` returns a non-2xx status, or
|
|
65
|
+
the app boots slower than `health.timeoutMs`.
|
|
66
|
+
|
|
67
|
+
If the boot itself is fine but the app waits for a same-release service inside
|
|
68
|
+
its own command, that wait is inside the health deadline. `stage: "dependency"`
|
|
69
|
+
plus a `release process dependency ready` event shows the wait Rollbridge did on
|
|
70
|
+
the dependency's own budget.
|
|
61
71
|
|
|
62
72
|
**Fix.** Make the proxied command bind `{{port}}` and serve `health.path` with a
|
|
63
|
-
2xx status. For slow boots, raise `health.timeoutMs`
|
|
64
|
-
so probing begins after the app is up.
|
|
73
|
+
2xx status. For slow boots, raise `health.timeoutMs` to above the measured boot
|
|
74
|
+
time (or set `health.startDelayMs` so probing begins after the app is up). For a
|
|
75
|
+
same-release service dependency, declare `dependsOn` (see
|
|
76
|
+
[`processes[].dependsOn`](config.md#processesdependson)) so the wait runs on
|
|
77
|
+
`dependencyTimeoutMs` instead of eating the boot budget.
|
|
65
78
|
|
|
66
79
|
## Port conflicts / exhausted ranges
|
|
67
80
|
|
|
@@ -148,3 +161,27 @@ separate destructive `--takeover-owner` path. If
|
|
|
148
161
|
`retirementError` is set,
|
|
149
162
|
inspect the quiet-hook events. Rollbridge deliberately leaves that generation
|
|
150
163
|
alive rather than signaling arbitrary PIDs or continuing its stop sequence.
|
|
164
|
+
|
|
165
|
+
## A command is refused with "Another owner mutation is already in progress"
|
|
166
|
+
|
|
167
|
+
**Symptom.** `deploy`, `stop`, `restart`, `rollback` or
|
|
168
|
+
`recover-generation-transition` fails with
|
|
169
|
+
`Another owner mutation is already in progress: owner mutation "<operation>";
|
|
170
|
+
mutation <id>; held by process <pid>; since <ISO-8601>; <n>s elapsed; waiting
|
|
171
|
+
for <blocker>; refused <operation>`.
|
|
172
|
+
|
|
173
|
+
**Cause.** The committed daemon holds the guardian's owner-mutation fence for
|
|
174
|
+
one control mutation at a time, and a second mutation arrived while it was still
|
|
175
|
+
held.
|
|
176
|
+
|
|
177
|
+
**Fix.** Read the named holder before touching anything: the message states
|
|
178
|
+
which mutation holds the fence, its lease id, the PID of the process that
|
|
179
|
+
started it, when it started, how long it has run, and the blocker that holder
|
|
180
|
+
last reported (`waitingFor`, which a running mutation can refine through
|
|
181
|
+
`reportOwnerMutationWait`). That is the command to inspect — not the one that
|
|
182
|
+
was refused. A mutation that outruns its lease (15 minutes by default,
|
|
183
|
+
overridable per command with `mutationTimeoutMs`) is logged as
|
|
184
|
+
`OWNER_MUTATION_LEASE_EXPIRED`, reported to the holder, and released, so the
|
|
185
|
+
next mutation proceeds and the stuck one fails loudly when it next ends its
|
|
186
|
+
lease. A retained jobs generation is not an owner mutation and may still drain
|
|
187
|
+
for hours; only the fence is bounded.
|
package/package.json
CHANGED
package/src/config.js
CHANGED
|
@@ -6,6 +6,7 @@ import {createRequire} from "node:module"
|
|
|
6
6
|
import os from "node:os"
|
|
7
7
|
import path from "node:path"
|
|
8
8
|
import {pathToFileURL} from "node:url"
|
|
9
|
+
import {processStartOrder} from "./process-order.js"
|
|
9
10
|
|
|
10
11
|
/**
|
|
11
12
|
* @typedef {import("./json.js").JsonValue} JsonValue
|
|
@@ -17,7 +18,7 @@ import {pathToFileURL} from "node:url"
|
|
|
17
18
|
* @typedef {{activateCommand?: string, activateTimeoutMs?: number, drainCommand?: string, drainTimeoutMs: number, quietCommand?: string, reactivateCommand?: string, stopCommand?: string}} LifecycleConfig
|
|
18
19
|
* @typedef {number | "indefinite"} StopTimeoutMs
|
|
19
20
|
* @typedef {"persistent" | "handoff"} ServiceDeployStrategy
|
|
20
|
-
* @typedef {{cwd?: string, deployStrategy: ServiceDeployStrategy, env: Record<string, string>, gracefulStopMs: StopTimeoutMs, health?: HealthConfig, id: string, lifecycle: LifecycleConfig, memory?: MemoryConfig, nonBlockingDrain: boolean, outputLines: number, policy: ProcessPolicy, port?: PortRange, replicas: number, restart: RestartConfig, restartDelayMs: number, stopSignal: string, command: string}} ProcessConfig
|
|
21
|
+
* @typedef {{cwd?: string, dependencyTimeoutMs: number, dependsOn: string[], deployStrategy: ServiceDeployStrategy, env: Record<string, string>, gracefulStopMs: StopTimeoutMs, health?: HealthConfig, id: string, lifecycle: LifecycleConfig, memory?: MemoryConfig, nonBlockingDrain: boolean, outputLines: number, policy: ProcessPolicy, port?: PortRange, replicas: number, restart: RestartConfig, restartDelayMs: number, stopSignal: string, command: string}} ProcessConfig
|
|
21
22
|
* @typedef {{group?: number | string, mode?: number, owner?: number | string, path: string}} ControlConfig
|
|
22
23
|
* @typedef {{drainTimeoutMs: number, forceStopTimeoutMs: number, healthPath: string, healthTimeoutMs: number, host: string, port: number, upstreamHost: string}} ProxyConfig
|
|
23
24
|
* @typedef {{includes: string[], name: string}} LegacyTakeoverProcessConfig
|
|
@@ -35,6 +36,13 @@ import {pathToFileURL} from "node:url"
|
|
|
35
36
|
|
|
36
37
|
const PROCESS_POLICIES = new Set(["proxied", "companion", "singleton", "service"])
|
|
37
38
|
const DEFAULT_CONFIG_FILENAMES = ["rollbridge.js"]
|
|
39
|
+
// Budget for one process waiting for a dependency's port, separate from the health budget.
|
|
40
|
+
// Measured on TensorBuzz production (server3, 2026-11-06): the candidate's
|
|
41
|
+
// background-jobs-main took 11817ms (14:33:39.175 start -> 14:33:50.992 listening) before
|
|
42
|
+
// the web process could reach its own boot, and the production command chain already waited
|
|
43
|
+
// 30000ms per hop. 30000ms keeps that dependency budget, so the health deadline measures
|
|
44
|
+
// only the app boot.
|
|
45
|
+
const DEFAULT_DEPENDENCY_TIMEOUT_MS = 30000
|
|
38
46
|
const commonJsRequire = createRequire(import.meta.url)
|
|
39
47
|
|
|
40
48
|
/**
|
|
@@ -232,7 +240,7 @@ function normalizeProcess(value, index, proxy, issues) {
|
|
|
232
240
|
if (!isPlainObject(value)) {
|
|
233
241
|
issues.push({fix: `Define processes[${index}] as a mapping with id, policy, and command.`, message: `processes[${index}] must be an object`})
|
|
234
242
|
|
|
235
|
-
return {command: "", cwd: undefined, deployStrategy: "persistent", env: {}, gracefulStopMs: proxy.forceStopTimeoutMs, health: undefined, id: "", lifecycle: {drainTimeoutMs: 0}, memory: undefined, nonBlockingDrain: false, outputLines: 50, policy: "companion", port: undefined, replicas: 1, restart: defaultRestartConfig(), restartDelayMs: 1000, stopSignal: "SIGTERM"}
|
|
243
|
+
return {command: "", cwd: undefined, dependencyTimeoutMs: DEFAULT_DEPENDENCY_TIMEOUT_MS, dependsOn: [], deployStrategy: "persistent", env: {}, gracefulStopMs: proxy.forceStopTimeoutMs, health: undefined, id: "", lifecycle: {drainTimeoutMs: 0}, memory: undefined, nonBlockingDrain: false, outputLines: 50, policy: "companion", port: undefined, replicas: 1, restart: defaultRestartConfig(), restartDelayMs: 1000, stopSignal: "SIGTERM"}
|
|
236
244
|
}
|
|
237
245
|
|
|
238
246
|
const source = value
|
|
@@ -240,6 +248,8 @@ function normalizeProcess(value, index, proxy, issues) {
|
|
|
240
248
|
return {
|
|
241
249
|
command: normalizeString(source.command, `processes[${index}].command`, issues),
|
|
242
250
|
cwd: source.cwd === undefined ? undefined : normalizeString(source.cwd, `processes[${index}].cwd`, issues),
|
|
251
|
+
dependencyTimeoutMs: normalizeDependencyTimeoutMs(source.dependencyTimeoutMs, `processes[${index}].dependencyTimeoutMs`, issues),
|
|
252
|
+
dependsOn: normalizeDependsOn(source.dependsOn, `processes[${index}].dependsOn`, issues),
|
|
243
253
|
deployStrategy: normalizeDeployStrategy(source.deployStrategy, `processes[${index}].deployStrategy`, issues),
|
|
244
254
|
env: normalizeEnv(source.env, `processes[${index}].env`, issues),
|
|
245
255
|
gracefulStopMs: normalizeStopTimeout(source.gracefulStopMs, `processes[${index}].gracefulStopMs`, proxy.forceStopTimeoutMs, issues),
|
|
@@ -765,6 +775,34 @@ function normalizeDeployStrategy(value, key, issues) {
|
|
|
765
775
|
return "persistent"
|
|
766
776
|
}
|
|
767
777
|
|
|
778
|
+
/**
|
|
779
|
+
* @param {JsonValue} value - Raw dependency list.
|
|
780
|
+
* @param {string} key - Config key.
|
|
781
|
+
* @param {ConfigIssue[]} issues - Issue collector.
|
|
782
|
+
* @returns {string[]} Ids of the processes this process waits for before it starts.
|
|
783
|
+
*/
|
|
784
|
+
function normalizeDependsOn(value, key, issues) {
|
|
785
|
+
return normalizeStringList(value, key, issues)
|
|
786
|
+
}
|
|
787
|
+
|
|
788
|
+
/**
|
|
789
|
+
* @param {JsonValue} value - Raw dependency wait budget.
|
|
790
|
+
* @param {string} key - Config key.
|
|
791
|
+
* @param {ConfigIssue[]} issues - Issue collector.
|
|
792
|
+
* @returns {number} Milliseconds this process may spend waiting for its dependency ports.
|
|
793
|
+
*/
|
|
794
|
+
function normalizeDependencyTimeoutMs(value, key, issues) {
|
|
795
|
+
const timeoutMs = normalizeNumber(value, key, issues, {default: DEFAULT_DEPENDENCY_TIMEOUT_MS})
|
|
796
|
+
|
|
797
|
+
if (timeoutMs < 1) {
|
|
798
|
+
issues.push({fix: `Set ${key} to a positive number of milliseconds, e.g. 30000, or omit it for the default.`, message: `${key} must be a positive number`})
|
|
799
|
+
|
|
800
|
+
return DEFAULT_DEPENDENCY_TIMEOUT_MS
|
|
801
|
+
}
|
|
802
|
+
|
|
803
|
+
return timeoutMs
|
|
804
|
+
}
|
|
805
|
+
|
|
768
806
|
/**
|
|
769
807
|
* @param {JsonValue} value - Raw output retention value.
|
|
770
808
|
* @param {string} key - Config key.
|
|
@@ -949,6 +987,57 @@ function validateProcessSet(processes, issues) {
|
|
|
949
987
|
|
|
950
988
|
issues.push({fix: `Add a port range to the proxied process "${processConfig.id || "(unnamed)"}", e.g. port: {from: 18000, to: 18099}.`, message: `Proxied process ${processConfig.id || "(unnamed)"} must define a port range`})
|
|
951
989
|
}
|
|
990
|
+
|
|
991
|
+
validateProcessDependencies(processes, issues)
|
|
992
|
+
}
|
|
993
|
+
|
|
994
|
+
/**
|
|
995
|
+
* Validates `dependsOn`: a dependency must name a ported process that Rollbridge starts
|
|
996
|
+
* before the dependent. Waiting is done on the dependency's allocated port, and an edge that
|
|
997
|
+
* points backwards in the start order can never be satisfied, which also rules out cycles.
|
|
998
|
+
* @param {ProcessConfig[]} processes - Normalized processes.
|
|
999
|
+
* @param {ConfigIssue[]} issues - Issue collector.
|
|
1000
|
+
* @returns {void}
|
|
1001
|
+
*/
|
|
1002
|
+
function validateProcessDependencies(processes, issues) {
|
|
1003
|
+
const declared = new Map(processes.filter((processConfig) => processConfig.id).map((processConfig) => [processConfig.id, processConfig]))
|
|
1004
|
+
const startOrder = new Map(processStartOrder(processes, {includePersistentServices: true}).map((processConfig, index) => [processConfig.id, index]))
|
|
1005
|
+
|
|
1006
|
+
for (const processConfig of processes) {
|
|
1007
|
+
if (!processConfig.id || processConfig.dependsOn.length === 0) continue
|
|
1008
|
+
|
|
1009
|
+
const dependentIndex = startOrder.get(processConfig.id)
|
|
1010
|
+
|
|
1011
|
+
for (const dependencyId of processConfig.dependsOn) {
|
|
1012
|
+
if (dependencyId === processConfig.id) {
|
|
1013
|
+
issues.push({fix: `Remove "${processConfig.id}" from its own dependsOn.`, message: `Process "${processConfig.id}" cannot depend on itself`})
|
|
1014
|
+
continue
|
|
1015
|
+
}
|
|
1016
|
+
|
|
1017
|
+
const dependency = declared.get(dependencyId)
|
|
1018
|
+
|
|
1019
|
+
if (!dependency) {
|
|
1020
|
+
issues.push({fix: `Name a configured process in "${processConfig.id}".dependsOn; "${dependencyId}" is not one of: ${[...declared.keys()].join(", ")}.`, message: `Process "${processConfig.id}" depends on unknown process "${dependencyId}"`})
|
|
1021
|
+
continue
|
|
1022
|
+
}
|
|
1023
|
+
|
|
1024
|
+
if (dependency.policy === "singleton") {
|
|
1025
|
+
issues.push({fix: `Remove "${dependencyId}" from "${processConfig.id}".dependsOn; a singleton is not part of a release generation, so Rollbridge cannot gate a release start on it.`, message: `Process "${processConfig.id}" cannot depend on singleton "${dependencyId}"`})
|
|
1026
|
+
continue
|
|
1027
|
+
}
|
|
1028
|
+
|
|
1029
|
+
if (!dependency.port) {
|
|
1030
|
+
issues.push({fix: `Give "${dependencyId}" a port, or remove it from "${processConfig.id}".dependsOn; Rollbridge waits for a dependency on its allocated port.`, message: `Process "${dependencyId}" has no port, so "${processConfig.id}" cannot wait for it`})
|
|
1031
|
+
continue
|
|
1032
|
+
}
|
|
1033
|
+
|
|
1034
|
+
const dependencyIndex = startOrder.get(dependencyId)
|
|
1035
|
+
|
|
1036
|
+
if (dependencyIndex === undefined || dependentIndex === undefined || dependencyIndex > dependentIndex) {
|
|
1037
|
+
issues.push({fix: `Move "${dependencyId}" before "${processConfig.id}" in processes[]; Rollbridge starts persistent services, then handoff services, companions, and the proxied process.`, message: `Process "${processConfig.id}" depends on "${dependencyId}", which Rollbridge starts after it`})
|
|
1038
|
+
}
|
|
1039
|
+
}
|
|
1040
|
+
}
|
|
952
1041
|
}
|
|
953
1042
|
|
|
954
1043
|
/**
|
package/src/daemon.js
CHANGED
|
@@ -146,7 +146,7 @@ export default class RollbridgeDaemon {
|
|
|
146
146
|
this.logger("release generation transition recovery failed", {error: error instanceof Error ? error.message : String(error), releaseId: transition.candidateReleaseId})
|
|
147
147
|
}
|
|
148
148
|
return {}
|
|
149
|
-
})
|
|
149
|
+
}, {waitingFor: "the retained release generations to settle"})
|
|
150
150
|
} finally {
|
|
151
151
|
this.generationTransitionRecovery = false
|
|
152
152
|
}
|
|
@@ -1389,7 +1389,7 @@ export default class RollbridgeDaemon {
|
|
|
1389
1389
|
releaseId: stringOrUndefined(data.releaseId),
|
|
1390
1390
|
releasePath: requiredString(data.releasePath, "releasePath"),
|
|
1391
1391
|
revision: stringOrUndefined(data.revision)
|
|
1392
|
-
}))
|
|
1392
|
+
}), {waitingFor: "candidate activation and the retired generation handoff"})
|
|
1393
1393
|
}
|
|
1394
1394
|
|
|
1395
1395
|
if (commandName === "recover-generation-transition") {
|
|
@@ -1399,7 +1399,7 @@ export default class RollbridgeDaemon {
|
|
|
1399
1399
|
releaseId: requiredString(data.releaseId, "releaseId"),
|
|
1400
1400
|
releasePath: requiredString(data.releasePath, "releasePath"),
|
|
1401
1401
|
revision: requiredString(data.revision, "revision")
|
|
1402
|
-
}))
|
|
1402
|
+
}), {waitingFor: "the retained release generations to settle"})
|
|
1403
1403
|
}
|
|
1404
1404
|
|
|
1405
1405
|
if (commandName === "status") {
|
|
@@ -1414,18 +1414,18 @@ export default class RollbridgeDaemon {
|
|
|
1414
1414
|
return await this.executeOwnerMutation("stop", async () => {
|
|
1415
1415
|
await this.stopRelease(stringOrUndefined(data.releaseId))
|
|
1416
1416
|
return this.status()
|
|
1417
|
-
})
|
|
1417
|
+
}, {waitingFor: "the release's managed processes to stop"})
|
|
1418
1418
|
}
|
|
1419
1419
|
|
|
1420
1420
|
if (commandName === "restart") {
|
|
1421
1421
|
return await this.executeOwnerMutation("restart", async () => await this.restartProcesses({
|
|
1422
1422
|
policy: stringOrUndefined(data.policy),
|
|
1423
1423
|
processId: stringOrUndefined(data.processId)
|
|
1424
|
-
}))
|
|
1424
|
+
}), {waitingFor: "the managed process to stop and start again"})
|
|
1425
1425
|
}
|
|
1426
1426
|
|
|
1427
1427
|
if (commandName === "rollback") {
|
|
1428
|
-
return await this.executeOwnerMutation("rollback", async () => await this.rollback({releaseId: stringOrUndefined(data.releaseId)}))
|
|
1428
|
+
return await this.executeOwnerMutation("rollback", async () => await this.rollback({releaseId: stringOrUndefined(data.releaseId)}), {waitingFor: "the previous release to activate"})
|
|
1429
1429
|
}
|
|
1430
1430
|
|
|
1431
1431
|
if (commandName === "shutdown") {
|
|
@@ -1489,11 +1489,13 @@ export default class RollbridgeDaemon {
|
|
|
1489
1489
|
* Runs one owner mutation under the guardian's prepare/commit exclusion fence.
|
|
1490
1490
|
* @param {string} operation - Mutation diagnostic name.
|
|
1491
1491
|
* @param {() => Promise<Record<string, JsonValue>>} callback - Mutating operation.
|
|
1492
|
+
* @param {{waitingFor?: string}} [options] - What this mutation blocks on, so a refused
|
|
1493
|
+
* later mutation names the real blocker instead of just "in progress".
|
|
1492
1494
|
* @returns {Promise<Record<string, JsonValue>>} Operation result.
|
|
1493
1495
|
*/
|
|
1494
|
-
async executeOwnerMutation(operation, callback) {
|
|
1496
|
+
async executeOwnerMutation(operation, callback, {waitingFor} = {}) {
|
|
1495
1497
|
if (!this.guardian) return await callback()
|
|
1496
|
-
const mutationId = await this.guardian.beginOwnerMutation(operation)
|
|
1498
|
+
const mutationId = await this.guardian.beginOwnerMutation(operation, {ownerPid: process.pid, waitingFor})
|
|
1497
1499
|
let result
|
|
1498
1500
|
let operationError
|
|
1499
1501
|
|
package/src/guardian-client.js
CHANGED
|
@@ -323,10 +323,11 @@ export default class GuardianClient {
|
|
|
323
323
|
/**
|
|
324
324
|
* Acquires the committed owner's mutation fence.
|
|
325
325
|
* @param {string} operation - Control mutation name.
|
|
326
|
+
* @param {{mutationTimeoutMs?: number, ownerPid?: number, waitingFor?: string}} [details] - Lease bound, holding PID and what the mutation blocks on.
|
|
326
327
|
* @returns {Promise<string>} Mutation lease id.
|
|
327
328
|
*/
|
|
328
|
-
async beginOwnerMutation(operation) {
|
|
329
|
-
const result = /** @type {{mutationId: string}} */ (await this.request({command: "begin-owner-mutation", operation}))
|
|
329
|
+
async beginOwnerMutation(operation, {mutationTimeoutMs, ownerPid, waitingFor} = {}) {
|
|
330
|
+
const result = /** @type {{mutationId: string}} */ (await this.request({command: "begin-owner-mutation", mutationTimeoutMs, operation, ownerPid, waitingFor}))
|
|
330
331
|
|
|
331
332
|
return result.mutationId
|
|
332
333
|
}
|
|
@@ -336,6 +337,16 @@ export default class GuardianClient {
|
|
|
336
337
|
await this.request({command: "end-owner-mutation", mutationId})
|
|
337
338
|
}
|
|
338
339
|
|
|
340
|
+
/**
|
|
341
|
+
* Refines what a held mutation is waiting for, so a later refusal names the real blocker.
|
|
342
|
+
* @param {string} mutationId - Mutation lease id.
|
|
343
|
+
* @param {string} waitingFor - Current blocker.
|
|
344
|
+
* @returns {Promise<void>} Report acknowledged.
|
|
345
|
+
*/
|
|
346
|
+
async reportOwnerMutationWait(mutationId, waitingFor) {
|
|
347
|
+
await this.request({command: "report-owner-mutation-wait", mutationId, waitingFor})
|
|
348
|
+
}
|
|
349
|
+
|
|
339
350
|
/** @returns {Promise<{committedReplacementId: string | null, ownerClaimed: boolean, retirementFailed?: boolean, retirementPending?: boolean, retirementReady?: boolean}>} Transaction status. */
|
|
340
351
|
async replacementStatus() {
|
|
341
352
|
return /** @type {{committedReplacementId: string | null, ownerClaimed: boolean, retirementFailed?: boolean, retirementPending?: boolean, retirementReady?: boolean}} */ (await this.request({command: "replacement-status"}))
|
package/src/health.js
CHANGED
|
@@ -1,35 +1,126 @@
|
|
|
1
1
|
// @ts-check
|
|
2
2
|
|
|
3
|
+
import net from "node:net"
|
|
4
|
+
|
|
5
|
+
/**
|
|
6
|
+
* @typedef {import("./config.js").HealthConfig} HealthConfig
|
|
7
|
+
* @typedef {{attempts: number, deadlineMs: number, elapsedMs: number, processId: string, url: string}} HealthCheckDiagnostics
|
|
8
|
+
* @typedef {Error & {healthCheck?: HealthCheckDiagnostics}} HealthCheckError
|
|
9
|
+
*/
|
|
10
|
+
|
|
11
|
+
/**
|
|
12
|
+
* @param {number} ms - Milliseconds.
|
|
13
|
+
* @returns {Promise<void>} Resolves after the delay.
|
|
14
|
+
*/
|
|
15
|
+
function sleep(ms) {
|
|
16
|
+
return new Promise((resolve) => setTimeout(resolve, ms))
|
|
17
|
+
}
|
|
18
|
+
|
|
3
19
|
/**
|
|
4
20
|
* Waits for a process HTTP health endpoint.
|
|
21
|
+
*
|
|
22
|
+
* The failure names its own budget: `Health check failed ...: fetch failed` cannot tell a
|
|
23
|
+
* slow boot apart from a health deadline that was simply too short.
|
|
5
24
|
* @param {object} args - Options.
|
|
6
25
|
* @param {string} args.host - Host.
|
|
7
26
|
* @param {number} args.port - Port.
|
|
8
|
-
* @param {
|
|
9
|
-
* @
|
|
27
|
+
* @param {HealthConfig} args.health - Health config.
|
|
28
|
+
* @param {string} [args.processId] - Process the probe belongs to, named in the failure.
|
|
29
|
+
* @returns {Promise<{elapsedMs: number}>} Time spent reaching the first healthy response.
|
|
10
30
|
*/
|
|
11
|
-
export async function waitForHealth({health, host, port}) {
|
|
31
|
+
export async function waitForHealth({health, host, port, processId = "proxied"}) {
|
|
32
|
+
const startedAtMs = Date.now()
|
|
33
|
+
|
|
12
34
|
if (health.startDelayMs > 0) {
|
|
13
|
-
await
|
|
35
|
+
await sleep(health.startDelayMs)
|
|
14
36
|
}
|
|
15
37
|
|
|
16
|
-
const
|
|
38
|
+
const deadlineMs = health.timeoutMs
|
|
39
|
+
const deadline = Date.now() + deadlineMs
|
|
17
40
|
const url = `http://${host}:${port}${health.path}`
|
|
41
|
+
let attempts = 0
|
|
18
42
|
let lastError = "no attempts"
|
|
19
43
|
|
|
20
44
|
while (Date.now() <= deadline) {
|
|
45
|
+
attempts += 1
|
|
46
|
+
|
|
21
47
|
try {
|
|
22
48
|
const response = await fetch(url)
|
|
23
49
|
|
|
24
|
-
if (response.ok) return
|
|
50
|
+
if (response.ok) return {elapsedMs: Date.now() - startedAtMs}
|
|
25
51
|
|
|
26
52
|
lastError = `HTTP ${response.status}`
|
|
27
53
|
} catch (error) {
|
|
28
54
|
lastError = error instanceof Error ? error.message : String(error)
|
|
29
55
|
}
|
|
30
56
|
|
|
31
|
-
await
|
|
57
|
+
await sleep(health.intervalMs)
|
|
32
58
|
}
|
|
33
59
|
|
|
34
|
-
|
|
60
|
+
const elapsedMs = Date.now() - startedAtMs
|
|
61
|
+
/** @type {HealthCheckError} */
|
|
62
|
+
const failure = new Error(`Health check failed for ${url}: ${lastError} (process ${processId}: ${attempts} probes, ${elapsedMs}ms elapsed of the ${deadlineMs}ms health deadline)`)
|
|
63
|
+
|
|
64
|
+
failure.healthCheck = {attempts, deadlineMs, elapsedMs, processId, url}
|
|
65
|
+
|
|
66
|
+
throw failure
|
|
67
|
+
}
|
|
68
|
+
|
|
69
|
+
/**
|
|
70
|
+
* Waits until a TCP endpoint accepts a connection, on a budget of its own.
|
|
71
|
+
*
|
|
72
|
+
* This is the dependency leg of a release start: waiting for a process that must bind a
|
|
73
|
+
* port before another one can boot. Charged to the health deadline it measures the
|
|
74
|
+
* dependency instead of the app, so it is timed here on a separate budget.
|
|
75
|
+
* @param {object} args - Options.
|
|
76
|
+
* @param {string} args.host - Host to connect to.
|
|
77
|
+
* @param {number} args.intervalMs - Delay between connection attempts.
|
|
78
|
+
* @param {number} args.port - Port that must accept a connection.
|
|
79
|
+
* @param {number} args.timeoutMs - Budget for the wait.
|
|
80
|
+
* @returns {Promise<{attempts: number, elapsedMs: number}>} Time and attempts spent waiting.
|
|
81
|
+
*/
|
|
82
|
+
export async function waitForListeningPort({host, intervalMs, port, timeoutMs}) {
|
|
83
|
+
const startedAtMs = Date.now()
|
|
84
|
+
const deadline = startedAtMs + timeoutMs
|
|
85
|
+
let attempts = 0
|
|
86
|
+
|
|
87
|
+
while (Date.now() <= deadline) {
|
|
88
|
+
attempts += 1
|
|
89
|
+
|
|
90
|
+
if (await tryConnect({deadline, host, intervalMs, port})) {
|
|
91
|
+
return {attempts, elapsedMs: Date.now() - startedAtMs}
|
|
92
|
+
}
|
|
93
|
+
|
|
94
|
+
await sleep(Math.max(1, Math.min(intervalMs, deadline - Date.now())))
|
|
95
|
+
}
|
|
96
|
+
|
|
97
|
+
throw new Error(`Dependency endpoint ${host}:${port} did not accept a connection within ${timeoutMs}ms (${attempts} attempts, ${Date.now() - startedAtMs}ms waited)`)
|
|
98
|
+
}
|
|
99
|
+
|
|
100
|
+
/**
|
|
101
|
+
* @param {object} args - Attempt options.
|
|
102
|
+
* @param {number} args.deadline - Absolute deadline that bounds this attempt.
|
|
103
|
+
* @param {string} args.host - Host to connect to.
|
|
104
|
+
* @param {number} args.intervalMs - Delay between connection attempts.
|
|
105
|
+
* @param {number} args.port - Port to connect to.
|
|
106
|
+
* @returns {Promise<boolean>} True when the endpoint accepted the connection.
|
|
107
|
+
*/
|
|
108
|
+
function tryConnect({deadline, host, intervalMs, port}) {
|
|
109
|
+
return new Promise((resolve) => {
|
|
110
|
+
const socket = net.createConnection({host, port})
|
|
111
|
+
let settled = false
|
|
112
|
+
|
|
113
|
+
/** @param {boolean} connected - Whether the endpoint accepted the connection. */
|
|
114
|
+
const finish = (connected) => {
|
|
115
|
+
if (settled) return
|
|
116
|
+
settled = true
|
|
117
|
+
socket.destroy()
|
|
118
|
+
resolve(connected)
|
|
119
|
+
}
|
|
120
|
+
|
|
121
|
+
socket.setTimeout(Math.max(1, Math.min(intervalMs, deadline - Date.now())))
|
|
122
|
+
socket.once("connect", () => finish(true))
|
|
123
|
+
socket.once("error", () => finish(false))
|
|
124
|
+
socket.once("timeout", () => finish(false))
|
|
125
|
+
})
|
|
35
126
|
}
|