diff --git a/src/opticalattackmanager/service/__main__.py b/src/opticalattackmanager/service/__main__.py
index e058f4827d5ee9d81855124b14e30b8b9ef24990..575edd5ba011373443efa904a60849387f259e92 100644
--- a/src/opticalattackmanager/service/__main__.py
+++ b/src/opticalattackmanager/service/__main__.py
@@ -83,31 +83,12 @@ LOOP_TIME = Histogram(
"tfs_opticalattackmanager_loop_seconds",
"Time taken by each security loop",
buckets=(
- 1.0,
- 2.5,
- 5.0,
- 7.5,
- 10.0,
- 12.5,
- 15.0,
- 17.5,
- 20.0,
- 22.5,
- 25.0,
- 27.5,
- 30.0,
- 32.5,
- 35.0,
- 37.5,
- 40.0,
- 42.5,
- 45.0,
- 47.5,
- 50.0,
- 52.5,
- 55.0,
- 57.5,
- 60.0,
+ 1.0, 2.5, 5.0, 7.5, 10.0, 12.5,
+ 15.0, 17.5, 20.0, 22.5, 25.0, 27.5,
+ 30.0, 32.5, 35.0, 37.5, 40.0,
+ 42.5, 45.0, 47.5,
+ 50.0, 52.5, 55.0, 57.5,
+ 60.0, 70.0, 80.0, 90.0, 100.0,
float("inf"),
),
)
@@ -127,6 +108,11 @@ DESIRED_MONITORING_INTERVAL = Gauge(
"Desired loop monitoring interval",
)
+DROP_COUNTER = Counter(
+ "tfs_opticalattackmanager_dropped_assessments",
+ "Dropped assessments due to detector timeout",
+)
+
global service_list
global cache
@@ -390,6 +376,7 @@ async def monitor_services(terminate, service_list=None, cache=None):
(i + 1) * k + min(i + 1, m), # last index
host,
port,
+ DROP_COUNTER,
desired_monitoring_interval * 0.9,
)
for i in range(cur_number_workers)
diff --git a/src/opticalattackmanager/utils/monitor.py b/src/opticalattackmanager/utils/monitor.py
index 390c43dc663f6e1a90d6a834a6ec9f72cc38a45a..30d4b7e22d5fefa1f280d86a47a13bb1800b1f55 100644
--- a/src/opticalattackmanager/utils/monitor.py
+++ b/src/opticalattackmanager/utils/monitor.py
@@ -22,13 +22,7 @@ from prometheus_client import Counter
from common.proto.asyncio.optical_attack_detector_grpc import \
OpticalAttackDetectorServiceStub
from common.proto.asyncio.optical_attack_detector_pb2 import DetectionRequest
-from common.Settings import get_log_level, get_setting
-
-DROP_COUNTER = Counter(
- "tfs_opticalattackmanager_dropped_assessments",
- "Dropped assessments due to detector timeout",
-)
-
+from common.Settings import get_log_level
log_level = get_log_level()
logging.basicConfig(level=log_level)
@@ -41,6 +35,7 @@ async def detect_attack(
context_id: str,
service_id: str,
kpi_id: str,
+ drop_counter: Counter,
timeout: float = 20.0,
) -> None:
try:
@@ -61,7 +56,7 @@ async def detect_attack(
"Exception while processing service_id {}/{}".format(service_id, kpi_id)
)
# LOGGER.exception(e)
- DROP_COUNTER.inc()
+ drop_counter.inc()
def delegate_services(
@@ -70,6 +65,7 @@ def delegate_services(
end_index: int,
host: str,
port: str,
+ drop_counter: Counter,
monitoring_interval: float,
):
async def run_internal_loop():
@@ -81,6 +77,7 @@ def delegate_services(
service["context"],
service["service"],
service["kpi"],
+ drop_counter,
# allow at most 90% of the monitoring interval to succeed
monitoring_interval * 0.9,
)
diff --git a/src/tests/scenario3/optical/dashboard.json b/src/tests/scenario3/optical/dashboard.json
index 361ac70bbce1136c255c95c7fab1351083c8b93b..990ab47e95f9db5bc021ca91333f4c5fe61f7ff7 100644
--- a/src/tests/scenario3/optical/dashboard.json
+++ b/src/tests/scenario3/optical/dashboard.json
@@ -1380,7 +1380,7 @@
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
- "fillOpacity": 0,
+ "fillOpacity": 29,
"gradientMode": "none",
"hideFrom": {
"legend": false,
@@ -1397,7 +1397,7 @@
"spanNulls": false,
"stacking": {
"group": "A",
- "mode": "none"
+ "mode": "normal"
},
"thresholdsStyle": {
"mode": "off"
@@ -1416,7 +1416,8 @@
"value": 80
}
]
- }
+ },
+ "unit": "mwatt"
},
"overrides": []
},
@@ -1445,10 +1446,71 @@
"uid": "${DS_PROMETHEUS}"
},
"editorMode": "code",
- "expr": "sum(scaph_process_power_consumption_microwatts{namespace=\"tfs\", cmdline=~\".+opticalattackdetector.+\"})/1000000",
- "legendFormat": "Detector",
+ "exemplar": false,
+ "expr": "sum(scaph_process_power_consumption_microwatts{namespace=\"tfs\", cmdline=~\".+opticalattackmanager.+\"})/1000",
+ "instant": false,
+ "legendFormat": "Manager",
"range": true,
"refId": "A"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "sum(scaph_process_power_consumption_microwatts{namespace=\"tfs\", cmdline=~\".+opticalattackdetector.+\"})/1000",
+ "hide": false,
+ "instant": false,
+ "legendFormat": "Detector",
+ "range": true,
+ "refId": "B"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "sum(scaph_process_power_consumption_microwatts{namespace=\"tfs\", cmdline=~\".+dbscan.+\"})/1000",
+ "hide": false,
+ "instant": false,
+ "interval": "",
+ "legendFormat": "UL Inference",
+ "range": true,
+ "refId": "C"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "sum(scaph_process_power_consumption_microwatts{namespace=\"tfs\", cmdline=~\"redis-server.+\"})/1000",
+ "hide": false,
+ "instant": false,
+ "interval": "",
+ "legendFormat": "Cache",
+ "range": true,
+ "refId": "D"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
+ "editorMode": "code",
+ "exemplar": false,
+ "expr": "sum(scaph_process_power_consumption_microwatts{namespace=\"tfs\", cmdline=~\".+opticalattackmitigator.+\"})/1000",
+ "hide": false,
+ "instant": false,
+ "interval": "",
+ "legendFormat": "Mitigator",
+ "range": true,
+ "refId": "E"
}
],
"title": "Energy consumption",
@@ -1463,7 +1525,7 @@
"list": []
},
"time": {
- "from": "now-15m",
+ "from": "now-5m",
"to": "now"
},
"timepicker": {},
diff --git a/src/tests/scenario3/optical/ofc23/run_experiment_demo.py b/src/tests/scenario3/optical/ofc23/run_experiment_demo.py
index b0fe01547708f553a4c39fb7eb60a6006d6d23c4..99dda0dc9b2a6dc083ce07f8258a246baf5ecd94 100644
--- a/src/tests/scenario3/optical/ofc23/run_experiment_demo.py
+++ b/src/tests/scenario3/optical/ofc23/run_experiment_demo.py
@@ -32,7 +32,7 @@ v1 = client.CoreV1Api()
caching_pod = None
pods = v1.list_namespaced_pod(namespace=namespace)
for pod in pods.items:
- print(pod.metadata)
+ # print(pod.metadata)
if "app" in pod.metadata.labels and "caching" in pod.metadata.labels["app"]:
caching_pod = pod