fix(alerting): ApiLatencyHigh on the 1-minute p95, ApiMemoryPressure for 1m, C-G2 at 225MB

第 3 回キャンペーンの実測を反映する。V-G1 では ILB が 1 分以内に api の接続を
遅いインスタンスから逃がすため 5 分窓の p95 が 0.5 秒を越えず、ApiLatencyHigh が
発火しなかった（1 分窓の p95 は 3 分半 2.3 秒）。式を 1 分窓にし 2 分継続に変える。
C-G2 は 200MB で working set が limit の 0.797〜0.803 を行き来して閾値 0.8 を
保てなかったため 225MB にし、ApiMemoryPressure の継続を 1 分にする。

vm/observability/grafana/provisioning/alerting/rules.yaml

@@ -41,13 +41,13 @@ groups:
   - uid: api-latency-high
     title: ApiLatencyHigh
     condition: C
-    for: 3m
+    for: 2m
     noDataState: OK
     execErrState: Error
     labels:
       layer: '2'
     annotations:
-      summary: demo api p95 latency above 500ms (grey zone)
+      summary: api p95 over the last minute above 500 ms for 2 minutes
     data:
     - refId: A
       relativeTimeRange:
@@ -57,7 +57,7 @@ groups:
       model:
         refId: A
         instant: true
-        expr: histogram_quantile(0.95, sum by (le) (rate(demo_http_request_duration_seconds_bucket{route=~"orders|price"}[5m]))) > bool 0.5
+        expr: histogram_quantile(0.95, sum by (le) (rate(demo_http_request_duration_seconds_bucket{route=~"orders|price"}[1m]))) > bool 0.5
     - refId: C
       datasourceUid: __expr__
       model:
@@ -261,13 +261,13 @@ groups:
   - uid: api-memory-pressure
     title: ApiMemoryPressure
     condition: C
-    for: 2m
+    for: 1m
     noDataState: OK
     execErrState: Error
     labels:
       layer: '2'
     annotations:
-      summary: an api container holds more than 80% of its memory limit for 2 minutes (grey zone; rollout restart after approval)
+      summary: an api container holds more than 80% of its memory limit for 1 minute (grey zone; rollout restart after approval)
     data:
     - refId: A
       relativeTimeRange: