fix(deploy): migrate after stop and shrink DB pool

Stage migrate hit ER_CON_COUNT_ERROR while live still held the pool. Build in stage with DATABASE_POOL_SIZE=5, run db:migrate only after stopping the service (with retries), and lower the default pool from 40 to 10.

Co-authored-by: Cursor <[email protected]>

.env.example

@@ -4,7 +4,7 @@
 DATABASE_URL=mysql://user:[email protected]:3306/atomcms
 
 # Optional pool tuning (defaults shown)
-DATABASE_POOL_SIZE=40
+DATABASE_POOL_SIZE=10
 DATABASE_IDLE_TIMEOUT_MS=300000
 DATABASE_CONNECT_TIMEOUT_MS=10000
 

.gitea/workflows/deploy.yaml

@@ -293,9 +293,13 @@ jobs:
           find . -maxdepth 3 -name '*.tsbuildinfo' -delete 2>/dev/null || true
           rm -rf .output dist .next .next/types .next/dev
 
+          # Stage shares MySQL with the live app + emulator. Keep the stage pool
+          # tiny so install/test/build cannot exhaust max_connections.
+          export DATABASE_POOL_SIZE="${DEPLOY_DATABASE_POOL_SIZE:-5}"
+          echo "STAGE DATABASE_POOL_SIZE=${DATABASE_POOL_SIZE}"
+
           pnpm install --frozen-lockfile
-          # Additive migrations while the old build still serves traffic.
-          pnpm db:migrate
+          # prisma generate does not need a live DB connection.
           pnpm prisma:generate
           pnpm typecheck
           pnpm test
@@ -308,10 +312,29 @@ jobs:
             exit 1
           fi
 
-          echo "Cutover: stop service, sync code, swap .next artifact..."
+          echo "Cutover: stop service (free DB connections), migrate, swap .next..."
           CUTOVER_STARTED=1
           sudo systemctl stop atom-nexst.service || true
           pkill -f 'next-server' || true
+          # Give MariaDB a moment to reclaim the live pool.
+          sleep 2
+
+          # Migrate only after live is stopped — avoids ER_CON_COUNT_ERROR while
+          # the old process still holds DATABASE_POOL_SIZE connections.
+          cd "${STAGE}"
+          MIGRATE_OK=0
+          for i in 1 2 3 4 5; do
+            if pnpm db:migrate; then
+              MIGRATE_OK=1
+              break
+            fi
+            echo "migrate attempt ${i}/5 failed (likely DB connections), retrying..."
+            sleep 3
+          done
+          if [ "${MIGRATE_OK}" != "1" ]; then
+            echo "ERROR: db:migrate failed after retries" >&2
+            exit 1
+          fi
 
           cd "${LIVE}"
           echo "Hard reset live tree to origin/main (no nuclear src wipe)..."

src/env.ts

@@ -8,7 +8,7 @@ const schema = z.object({
 		.enum(["development", "test", "production"])
 		.default("development"),
 	DATABASE_URL: z.string().url(),
-	DATABASE_POOL_SIZE: z.coerce.number().int().positive().default(40),
+	DATABASE_POOL_SIZE: z.coerce.number().int().positive().default(10),
 	DATABASE_IDLE_TIMEOUT_MS: z.coerce.number().int().positive().default(300_000),
 	DATABASE_CONNECT_TIMEOUT_MS: z.coerce
 		.number()

src/lib/deploy-workflow-contract.test.ts

@@ -14,6 +14,7 @@ describe("production deploy workflow", () => {
 		expect(deployJob).toContain("/var/tmp/atom-nexst-stage-");
 		expect(deployJob).toContain('ln -sfn "${LIVE}/.env"');
 		expect(deployJob).toContain("-e storage");
+		expect(deployJob).toContain("DATABASE_POOL_SIZE=");
 		expect(deployJob).not.toContain("SKIP_ENV_VALIDATION=1");
 		expect(deployJob).toContain("pnpm install --frozen-lockfile");
 	});
@@ -25,7 +26,7 @@ describe("production deploy workflow", () => {
 		const reclaimAt = deployJob.indexOf(
 			'sudo chown -R "$' + "{DEPLOY_USER}:" + '$' + '{DEPLOY_GROUP}"',
 		);
-		const fetchAt = deployJob.indexOf("git -C \"${LIVE}\" fetch origin --prune");
+		const fetchAt = deployJob.indexOf('git -C "${LIVE}" fetch origin --prune');
 		expect(reclaimAt).toBeGreaterThan(-1);
 		expect(fetchAt).toBeGreaterThan(reclaimAt);
 	});
@@ -48,6 +49,7 @@ describe("production deploy workflow", () => {
 		expect(deployJob).toContain("Rolling back .next to previous artifact");
 		const buildAt = deployJob.indexOf("pnpm build");
 		const stopAt = deployJob.indexOf("sudo systemctl stop atom-nexst.service");
+		const migrateAt = deployJob.indexOf("pnpm db:migrate");
 		const startLabelAt = deployJob.indexOf("Starting systemd service...");
 		const startAt = deployJob.indexOf(
 			"sudo systemctl start atom-nexst.service",
@@ -55,7 +57,9 @@ describe("production deploy workflow", () => {
 		);
 		expect(buildAt).toBeGreaterThan(-1);
 		expect(stopAt).toBeGreaterThan(buildAt);
-		expect(startLabelAt).toBeGreaterThan(stopAt);
+		// Migrate runs after stop so the live pool frees DB slots.
+		expect(migrateAt).toBeGreaterThan(stopAt);
+		expect(startLabelAt).toBeGreaterThan(migrateAt);
 		expect(startAt).toBeGreaterThan(startLabelAt);
 	});