gsadmin/sencho
1
0
Fork 0
mirror of https://github.com/Studio-Saelix/sencho.git synced 2026-07-26 11:49:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(monitor): include node name in janitor alert and stop firing on near-empty hosts (#765)

Browse Source 
The Docker janitor watchdog had three problems on multi-node fleets:

1. The alert text said "Your system has accumulated X GB" with no node
   identifier, so on a fleet view the operator could not tell which
   node was complaining. Resolve the local node via NodeRegistry and
   put the node name in the message.

2. The threshold gate was a single comparison against the user's
   configured GB value. A small or accidentally tiny threshold made
   the alert fire on hosts with effectively no waste. Add a 100 MB
   absolute floor so trivial cruft never triggers a notification.

3. The unit parser only matched uppercase "GB|MB|KB|B" and dropped
   "TB" entirely. Modern Docker emits "kB" with a lowercase k, which
   silently contributed zero bytes to the running total. Normalise the
   unit to uppercase before the comparison and add the TB case.
This commit is contained in:
Anso
2026-04-24 23:37:09 -04:00
committed by GitHub
parent c9657b1d46
commit 9e0f521ea8
1 changed files with 16 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/src/services/MonitorService.ts
+16 -4
View File
@@ -4,6 +4,7 @@ import { promisify } from 'util';
import semver from 'semver';
import DockerController from './DockerController';
import { DatabaseService } from './DatabaseService';
import { NodeRegistry } from './NodeRegistry';
import { NotificationService } from './NotificationService';
import { isValidVersion, getSenchoVersion } from './CapabilityRegistry';
import { getLatestVersion } from '../utils/version-check';
@@ -182,9 +183,13 @@ export class MonitorService {
const match = reclaimStr.match(/^([0-9.]+)([a-zA-Z]+)/);
if (match) {
const val = parseFloat(match[1]);
const unit = match[2];
// Docker emits both "kB" (lowercase k) on newer versions and "KB"
// historically. Normalise so neither is silently dropped, and
// include "TB" for hosts with terabytes of reclaimable build cache.
const unit = match[2].toUpperCase();
let bytes = 0;
if (unit === 'GB') bytes = val * 1024 * 1024 * 1024;
if (unit === 'TB') bytes = val * 1024 * 1024 * 1024 * 1024;
else if (unit === 'GB') bytes = val * 1024 * 1024 * 1024;
else if (unit === 'MB') bytes = val * 1024 * 1024;
else if (unit === 'KB') bytes = val * 1024;
else if (unit === 'B') bytes = val;
@@ -199,10 +204,17 @@ export class MonitorService {
const reclaimGb = totalReclaimableBytes / (1024 * 1024 * 1024);
const JANITOR_COOLDOWN_MS = 24 * 60 * 60 * 1000; // 24 hours
// Sanity floor: never alert on near-empty hosts even if the user
// configured an aggressive threshold like 0.001 GB. 100 MB is the
// smallest waste worth interrupting an operator over.
const MIN_RECLAIMABLE_GB = 0.1;
if (reclaimGb >= janitorLimitGb) {
if (reclaimGb >= janitorLimitGb && reclaimGb >= MIN_RECLAIMABLE_GB) {
const registry = NodeRegistry.getInstance();
const localNode = registry.getNode(registry.getDefaultNodeId());
const nodeLabel = localNode?.name ?? 'this node';
await this.dispatchWithCooldown(HOST_ALERT_KEYS.janitor, JANITOR_COOLDOWN_MS, 'info',
`Your system has accumulated ${reclaimGb.toFixed(1)} GB of unused Docker data. Consider using the Janitor tool.`);
`Node "${nodeLabel}" has accumulated ${reclaimGb.toFixed(1)} GB of unused Docker data. Consider using the Janitor tool.`);
}
}
} catch (e) {