You've already forked node-redis
mirror of
https://github.com/redis/node-redis.git
synced 2025-12-25 00:40:59 +03:00
Hitless upgrades (#3021)
* feat(errors): Add specialized timeout error types for maintenance scenarios - Added `SocketTimeoutDuringMaintananceError`, a subclass of `TimeoutError`, to handle socket timeouts during maintenance. - Added `CommandTimeoutDuringMaintenanceError`, another subclass of `TimeoutError`, to address command write timeouts during maintenance. * feat(linked-list): Add EmptyAwareSinglyLinkedList and enhance DoublyLinkedList functionality - Introduced `EmptyAwareSinglyLinkedList`, a subclass of `SinglyLinkedList` that emits an `empty` event when the list becomes empty due to `reset`, `shift`, or `remove` operations. - Added `nodes()` iterator method to `DoublyLinkedList` for iterating over nodes directly. - Enhanced unit tests for `DoublyLinkedList` and `SinglyLinkedList` to cover edge cases and new functionality. - Added comprehensive tests for `EmptyAwareSinglyLinkedList` to validate `empty` event emission under various scenarios. - Improved code formatting and consistency. * refactor(commands-queue): Improve push notification handling - Replaced `setInvalidateCallback` with a more flexible `addPushHandler` method, allowing multiple handlers for push notifications. - Introduced the `PushHandler` type to standardize push notification processing. - Refactored `RedisCommandsQueue` to use a `#pushHandlers` array, enabling dynamic and modular handling of push notifications. - Updated `RedisClient` to leverage the new handler mechanism for `invalidate` push notifications, simplifying and decoupling logic. * feat(commands-queue): Add method to wait for in-flight commands to complete - Introduced `waitForInflightCommandsToComplete` method to asynchronously wait for all in-flight commands to finish processing. - Utilized the `empty` event from `#waitingForReply` to signal when all commands have been completed. * feat(commands-queue): Introduce maintenance mode support for commands-queue - Added `#maintenanceCommandTimeout` and `setMaintenanceCommandTimeout` method to dynamically adjust command timeouts during maintenance * refator(client): Extract socket event listener setup into helper method * refactor(socket): Add maintenance mode support and dynamic timeout handling - Added `#maintenanceTimeout` and `setMaintenanceTimeout` method to dynamically adjust socket timeouts during maintenance. * feat(client): Add Redis Enterprise maintenance configuration options - Added `maintPushNotifications` option to control how the client handles Redis Enterprise maintenance push notifications (`disabled`, `enabled`, `au to`). - Added `maintMovingEndpointType` option to specify the endpoint type for reconnecting during a MOVING notification (`auto`, `internal-ip`, `external-ip`, etc.). - Added `maintRelaxedCommandTimeout` option to define a relaxed timeout for commands during maintenance. - Added `maintRelaxedSocketTimeout` option to define a relaxed timeout for the socket during maintenance. - Enforced RESP3 requirement for maintenance-related features (`maintPushNotifications`). * feat(client): Add socket helpers and pause mechanism - Introduced `#paused` flag with corresponding `_pause` and `_unpause` methods to temporarily halt writing commands to the socket during maintenance windows. - Updated `#write` method to respect the `#paused` flag, preventing new commands from being written during maintenance. - Added `_ejectSocket` method to safely detach from and return the current socket - Added `_insertSocket` method to receive and start using a new socket * feat(client): Add Redis Enterprise maintenance handling capabilities - Introduced `EnterpriseMaintenanceManager` to manage Redis Enterprise maintenance events and push notifications. - Integrated `EnterpriseMaintenanceManager` into `RedisClient` to handle maintenance push notifications and manage socket transitions. - Implemented graceful handling of MOVING, MIGRATING, and FAILOVER push notifications, including socket replacement and timeout adjustments. * test: add E2E test infrastructure for Redis maintenance scenarios * test: add E2E tests for Redis Enterprise maintenance timeout handling (#3) * test: add connection handoff test --------- Co-authored-by: Pavel Pashov <pavel.pashov@redis.com> Co-authored-by: Pavel Pashov <60297174+PavelPashov@users.noreply.github.com>
This commit is contained in:
committed by
GitHub
parent
6ad4c68655
commit
208a0d250f
@@ -0,0 +1,126 @@
|
||||
import diagnostics_channel from "node:diagnostics_channel";
|
||||
import { FaultInjectorClient } from "./fault-injector-client";
|
||||
import {
|
||||
getDatabaseConfig,
|
||||
getDatabaseConfigFromEnv,
|
||||
getEnvConfig,
|
||||
RedisConnectionConfig,
|
||||
} from "./test-scenario.util";
|
||||
import { createClient } from "../../..";
|
||||
import { DiagnosticsEvent } from "../../client/enterprise-maintenance-manager";
|
||||
import { before } from "mocha";
|
||||
import { spy } from "sinon";
|
||||
import assert from "node:assert";
|
||||
import { TestCommandRunner } from "./test-command-runner";
|
||||
import net from "node:net";
|
||||
|
||||
describe("Connection Handoff", () => {
|
||||
const diagnosticsLog: DiagnosticsEvent[] = [];
|
||||
|
||||
const onMessageHandler = (message: unknown) => {
|
||||
diagnosticsLog.push(message as DiagnosticsEvent);
|
||||
};
|
||||
|
||||
let clientConfig: RedisConnectionConfig;
|
||||
let client: ReturnType<typeof createClient<any, any, any, 3>>;
|
||||
let faultInjectorClient: FaultInjectorClient;
|
||||
let connectSpy = spy(net, "createConnection");
|
||||
|
||||
before(() => {
|
||||
const envConfig = getEnvConfig();
|
||||
const redisConfig = getDatabaseConfigFromEnv(
|
||||
envConfig.redisEndpointsConfigPath,
|
||||
);
|
||||
|
||||
faultInjectorClient = new FaultInjectorClient(envConfig.faultInjectorUrl);
|
||||
clientConfig = getDatabaseConfig(redisConfig);
|
||||
});
|
||||
|
||||
beforeEach(async () => {
|
||||
diagnosticsLog.length = 0;
|
||||
diagnostics_channel.subscribe("redis.maintenance", onMessageHandler);
|
||||
|
||||
connectSpy.resetHistory();
|
||||
|
||||
client = createClient({
|
||||
socket: {
|
||||
host: clientConfig.host,
|
||||
port: clientConfig.port,
|
||||
...(clientConfig.tls === true ? { tls: true } : {}),
|
||||
},
|
||||
password: clientConfig.password,
|
||||
username: clientConfig.username,
|
||||
RESP: 3,
|
||||
maintPushNotifications: "auto",
|
||||
maintMovingEndpointType: "external-ip",
|
||||
maintRelaxedCommandTimeout: 10000,
|
||||
maintRelaxedSocketTimeout: 10000,
|
||||
});
|
||||
|
||||
client.on("error", (err: Error) => {
|
||||
throw new Error(`Client error: ${err.message}`);
|
||||
});
|
||||
|
||||
await client.connect();
|
||||
await client.flushAll();
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
diagnostics_channel.unsubscribe("redis.maintenance", onMessageHandler);
|
||||
client.destroy();
|
||||
});
|
||||
|
||||
describe("New Connection Establishment", () => {
|
||||
it("should establish new connection", async () => {
|
||||
assert.equal(connectSpy.callCount, 1);
|
||||
|
||||
const { action_id: lowTimeoutBindAndMigrateActionId } =
|
||||
await faultInjectorClient.migrateAndBindAction({
|
||||
bdbId: clientConfig.bdbId,
|
||||
clusterIndex: 0,
|
||||
});
|
||||
|
||||
const lowTimeoutWaitPromise = faultInjectorClient.waitForAction(
|
||||
lowTimeoutBindAndMigrateActionId,
|
||||
);
|
||||
|
||||
await lowTimeoutWaitPromise;
|
||||
assert.equal(connectSpy.callCount, 2);
|
||||
});
|
||||
});
|
||||
|
||||
describe("TLS Connection Handoff", () => {
|
||||
it("TODO receiveMessagesWithTLSEnabledTest", async () => {
|
||||
//
|
||||
});
|
||||
it("TODO connectionHandoffWithStaticInternalNameTest", async () => {
|
||||
//
|
||||
});
|
||||
it("TODO connectionHandoffWithStaticExternalNameTest", async () => {
|
||||
//
|
||||
});
|
||||
});
|
||||
|
||||
describe("Traffic Resumption", () => {
|
||||
it("Traffic resumed after handoff", async () => {
|
||||
const { action_id } = await faultInjectorClient.migrateAndBindAction({
|
||||
bdbId: clientConfig.bdbId,
|
||||
clusterIndex: 0,
|
||||
});
|
||||
|
||||
const workloadPromise = faultInjectorClient.waitForAction(action_id);
|
||||
|
||||
const commandPromises =
|
||||
await TestCommandRunner.fireCommandsUntilStopSignal(
|
||||
client,
|
||||
workloadPromise,
|
||||
);
|
||||
|
||||
const rejected = (
|
||||
await Promise.all(commandPromises.commandPromises)
|
||||
).filter((result) => result.status === "rejected");
|
||||
|
||||
assert.ok(rejected.length === 0);
|
||||
});
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user