Eric Allam
567e2a2c32
## Summary
During an ElastiCache role swap (failover) or node-type change (vertical
scale), the ioredis TCP/TLS connection stays open but the server starts
answering with `READONLY` (the client is talking to a node that became a
replica) or `LOADING` (node still loading data from disk). Without an
explicit hook, those errors surface to caller code as `ReplyError`
instances — every write op on the affected connection fails until the
cluster fully cuts over.
This PR adds `reconnectOnError` to every prod ioredis client so the
disconnect + reconnect + retry cycle absorbs these errors and caller
code never sees them.
## Fix
```ts
export function defaultReconnectOnError(err: Error): boolean | 1 | 2 {
const msg = err.message ?? "";
if (msg.startsWith("READONLY") || msg.startsWith("LOADING")) return 2;
return false;
}
```
Returning `2` tells ioredis to disconnect, reconnect, and re-issue the
failed command. After reconnect, DNS / SG state routes the new socket to
a writable node.
The helper lives in `@internal/redis` and is wired into both the shared
`createRedisClient` (which covers RunQueue, schedule-engine,
redis-worker, and every other internal-package consumer) and the direct
`new Redis(...)` call sites in the webapp.
V1-only marqs files are intentionally not migrated.
## Test plan
- [x] `pnpm run typecheck --filter webapp`
- [x] `pnpm run typecheck --filter @internal/run-engine`
- [x] Verified end-to-end against a live ElastiCache vertical-scale
event — caller-surfaced errors went from tens of thousands during the
cutover window down to a handful per ioredis client
- [ ] Confirm steady-state behavior unchanged after deploy
48 lines
1.3 KiB
TypeScript
48 lines
1.3 KiB
TypeScript
import { Redis } from "ioredis";
|
|
import { defaultReconnectOnError } from "@internal/redis";
|
|
import { env } from "~/env.server";
|
|
import { singleton } from "~/utils/singleton";
|
|
import { logger } from "./logger.server";
|
|
|
|
const KEY_PREFIX = "cli-notif-ctr:";
|
|
const MAX_COUNTER = 1000;
|
|
|
|
function initializeRedis(): Redis | undefined {
|
|
const host = env.CACHE_REDIS_HOST;
|
|
if (!host) return undefined;
|
|
|
|
return new Redis({
|
|
connectionName: "platformNotificationCounter",
|
|
host,
|
|
port: env.CACHE_REDIS_PORT,
|
|
username: env.CACHE_REDIS_USERNAME,
|
|
password: env.CACHE_REDIS_PASSWORD,
|
|
keyPrefix: "tr:",
|
|
enableAutoPipelining: true,
|
|
reconnectOnError: defaultReconnectOnError,
|
|
...(env.CACHE_REDIS_TLS_DISABLED === "true" ? {} : { tls: {} }),
|
|
});
|
|
}
|
|
|
|
const redis = singleton("platformNotificationCounter", initializeRedis);
|
|
|
|
/** Increment and return the user's CLI request counter (0-based, wraps at 1000→0). */
|
|
export async function incrementCliRequestCounter(userId: string): Promise<number> {
|
|
if (!redis) return 0;
|
|
|
|
try {
|
|
const key = `${KEY_PREFIX}${userId}`;
|
|
const value = await redis.incr(key);
|
|
|
|
if (value > MAX_COUNTER) {
|
|
await redis.set(key, "0");
|
|
return 0;
|
|
}
|
|
|
|
return value;
|
|
} catch (error) {
|
|
logger.error("Failed to increment CLI notification counter", { userId, error });
|
|
return 0;
|
|
}
|
|
}
|