From 37fd36f9881e8c8e91f41661a7bc5f4aaf02e2ce Mon Sep 17 00:00:00 2001
From: sametd <samet.demir@ecmwf.int>
Date: Wed, 20 Dec 2023 17:07:45 +0100
Subject: [PATCH 01/11] custom kube_metric support is added to monitoring

---
 .../monitoring/aviso_monitoring/config.py     | 23 +++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/aviso-server/monitoring/aviso_monitoring/config.py b/aviso-server/monitoring/aviso_monitoring/config.py
index cc9ae9b..4c248c5 100644
--- a/aviso-server/monitoring/aviso_monitoring/config.py
+++ b/aviso-server/monitoring/aviso_monitoring/config.py
@@ -27,6 +27,7 @@ def __init__(
         aviso_auth_reporter=None,
         etcd_reporter=None,
         prometheus_reporter=None,
+        kube_state_metrics=None,
     ):
         try:
             # we build the configuration in priority order from the lower to the higher
@@ -41,6 +42,7 @@ def __init__(
             self.aviso_auth_reporter = aviso_auth_reporter
             self.etcd_reporter = etcd_reporter
             self.prometheus_reporter = prometheus_reporter
+            self.kube_state_metrics = kube_state_metrics
 
             logger.debug("Loading configuration completed")
 
@@ -113,6 +115,8 @@ def _create_default_config() -> Dict:
             },
         }
 
+        kube_state_metrics = {"ssl_enabled": False, "token": None}
+
         # main config
         config = {}
         config["udp_server"] = udp_server
@@ -121,6 +125,7 @@ def _create_default_config() -> Dict:
         config["aviso_auth_reporter"] = aviso_auth_reporter
         config["etcd_reporter"] = etcd_reporter
         config["prometheus_reporter"] = prometheus_reporter
+        config["kube_state_metrics"] = kube_state_metrics
         return config
 
     def _read_env_variables(self) -> Dict:
@@ -246,6 +251,23 @@ def prometheus_reporter(self, prometheus_reporter):
         assert pr.get("port") is not None, "prometheus_reporter port has not been configured"
         self._prometheus_reporter = pr
 
+    @property
+    def kube_state_metrics(self):
+        return self._kube_state_metrics
+
+    @kube_state_metrics.setter
+    def kube_state_metrics(self, kube_state_metrics):
+        ksm = self._config.get("kube_state_metrics")
+        if kube_state_metrics is not None and ksm is not None:
+            Config.deep_update(ksm, kube_state_metrics)
+        elif kube_state_metrics is not None:
+            ksm = kube_state_metrics
+        # verify is valid
+        assert ksm is not None, "kube_state_metrics has not been configured"
+        assert ksm.get("ssl_enabled") is not None, "kube_state_metrics ssl_enabled has not been configured"
+        assert ksm.get("token") is not None, "kube_state_metrics token has not been configured"
+        self._kube_state_metrics = ksm
+
     def __str__(self):
         config_string = (
             f"udp_server: {self.udp_server}"
@@ -254,6 +276,7 @@ def __str__(self):
             + f", aviso_auth_reporter: {self.aviso_auth_reporter}"
             + f", etcd_reporter: {self.etcd_reporter}"
             + f", prometheus_reporter: {self.prometheus_reporter}"
+            + f", kube_state_metrics: {self.kube_state_metrics}"
         )
         return config_string
 

From 03aebe7d27910ba46d1b3da103de22565399e6eb Mon Sep 17 00:00:00 2001
From: sametd <samet.demir@ecmwf.int>
Date: Wed, 20 Dec 2023 17:19:45 +0100
Subject: [PATCH 02/11] token should only be checked if ssl is enabled

---
 aviso-server/monitoring/aviso_monitoring/config.py | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/aviso-server/monitoring/aviso_monitoring/config.py b/aviso-server/monitoring/aviso_monitoring/config.py
index 4c248c5..a6ded4d 100644
--- a/aviso-server/monitoring/aviso_monitoring/config.py
+++ b/aviso-server/monitoring/aviso_monitoring/config.py
@@ -184,7 +184,7 @@ def aviso_rest_reporter(self, aviso_rest_reporter):
         assert ar is not None, "aviso_rest_reporter has not been configured"
         assert ar.get("tlms") is not None, "aviso_rest_reporter tlms has not been configured"
         assert ar.get("enabled") is not None, "aviso_rest_reporter enabled has not been configured"
-        if type(ar["enabled"]) is str:
+        if isinstance(ar["enabled"], str):
             ar["enabled"] = ar["enabled"].casefold() == "true".casefold()
         assert ar.get("frequency") is not None, "aviso_rest_reporter frequency has not been configured"
         self._aviso_rest_reporter = ar
@@ -204,7 +204,7 @@ def aviso_auth_reporter(self, aviso_auth_reporter):
         assert aa is not None, "aviso_auth_reporter has not been configured"
         assert aa.get("tlms") is not None, "aviso_auth_reporter tlms has not been configured"
         assert aa.get("enabled") is not None, "aviso_auth_reporter enabled has not been configured"
-        if type(aa["enabled"]) is str:
+        if isinstance(aa["enabled"], str):
             aa["enabled"] = aa["enabled"].casefold() == "true".casefold()
         assert aa.get("frequency") is not None, "aviso_auth_reporter frequency has not been configured"
         self._aviso_auth_reporter = aa
@@ -224,7 +224,7 @@ def etcd_reporter(self, etcd_reporter):
         assert e is not None, "etcd_reporter has not been configured"
         assert e.get("tlms") is not None, "etcd_reporter tlms has not been configured"
         assert e.get("enabled") is not None, "etcd_reporter enabled has not been configured"
-        if type(e["enabled"]) is str:
+        if isinstance(e["enabled"], str):
             e["enabled"] = e["enabled"].casefold() == "true".casefold()
         assert e.get("frequency") is not None, "etcd_reporter frequency has not been configured"
         assert e.get("member_urls") is not None, "etcd_reporter member_urls has not been configured"
@@ -246,7 +246,7 @@ def prometheus_reporter(self, prometheus_reporter):
         assert pr is not None, "prometheus_reporter has not been configured"
         assert pr.get("host") is not None, "prometheus_reporter host has not been configured"
         assert pr.get("enabled") is not None, "prometheus_reporter enabled has not been configured"
-        if type(pr["enabled"]) is str:
+        if isinstance(pr["enabled"], str):
             pr["enabled"] = pr["enabled"].casefold() == "true".casefold()
         assert pr.get("port") is not None, "prometheus_reporter port has not been configured"
         self._prometheus_reporter = pr
@@ -265,7 +265,8 @@ def kube_state_metrics(self, kube_state_metrics):
         # verify is valid
         assert ksm is not None, "kube_state_metrics has not been configured"
         assert ksm.get("ssl_enabled") is not None, "kube_state_metrics ssl_enabled has not been configured"
-        assert ksm.get("token") is not None, "kube_state_metrics token has not been configured"
+        if ksm["ssl_enabled"]:
+            assert ksm.get("token") is not None, "kube_state_metrics token has not been configured"
         self._kube_state_metrics = ksm
 
     def __str__(self):

From 7032e597549423f0d0d8ef43d441100516222885 Mon Sep 17 00:00:00 2001
From: sametd <samet.demir@ecmwf.int>
Date: Wed, 20 Dec 2023 18:06:12 +0100
Subject: [PATCH 03/11] metric token support added for retrieve metrics
 function

---
 .../aviso_monitoring/reporter/opsview_reporter.py      | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/aviso-server/monitoring/aviso_monitoring/reporter/opsview_reporter.py b/aviso-server/monitoring/aviso_monitoring/reporter/opsview_reporter.py
index 09ba543..4dd81c9 100644
--- a/aviso-server/monitoring/aviso_monitoring/reporter/opsview_reporter.py
+++ b/aviso-server/monitoring/aviso_monitoring/reporter/opsview_reporter.py
@@ -24,6 +24,9 @@ def __init__(self, config: Config, msg_receiver=None):
         self.monitor_servers = config.monitor_servers
         self.msg_receiver = msg_receiver
         self.token = {}
+        if config.kube_state_metrics["ssl_enabled"]:
+            self.metric_ssl_enabled = True
+            self.metric_token = config.kube_state_metrics["token"]
 
     def ms_authenticate(self, m_server):
         """
@@ -199,7 +202,7 @@ def aggregate_unique_counter_tlms(tlms):
         }
         return agg_tlm
 
-    def retrieve_metrics(metric_servers, req_timeout):
+    def retrieve_metrics(self, metric_servers, req_timeout):
         """
         This methods retrieves the metrics provided by specific metric servers using a Prometheus interface.
         """
@@ -207,8 +210,11 @@ def retrieve_metrics(metric_servers, req_timeout):
         for u in metric_servers:
             url = u + "/metrics"
             logger.debug(f"Retrieving metrics from {url}...")
+            headers = {}
             try:
-                resp = requests.get(url, verify=False, timeout=req_timeout)
+                if self.metric_ssl_enabled:
+                    headers["Authorization"] = f"Bearer {self.metric_token}"
+                resp = requests.get(url, verify=False, timeout=req_timeout, headers=headers)
             except Exception as e:
                 logger.exception(f"Not able to get metrics from {url}, error {e}")
                 raw_tlms[u] = None

From 4089bc243a1938d3dcb24b1dd44d04faba30a592 Mon Sep 17 00:00:00 2001
From: sametd <samet.demir@ecmwf.int>
Date: Wed, 20 Dec 2023 18:31:44 +0100
Subject: [PATCH 04/11] opsviewreporter instantiated when necessary to retrieve
 logs

---
 .../aviso_monitoring/reporter/aviso_auth_reporter.py         | 5 +++--
 .../aviso_monitoring/reporter/aviso_rest_reporter.py         | 5 +++--
 .../monitoring/aviso_monitoring/reporter/etcd_reporter.py    | 3 ++-
 3 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py
index 7a118f8..8d50cd9 100644
--- a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py
+++ b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py
@@ -198,6 +198,7 @@ def __init__(self, *args, **kwargs):
         self.critical_t = kwargs["critical_t"]
         self.req_timeout = kwargs["req_timeout"]
         self.metric_server_url = kwargs["metric_server_url"]
+        self.opsview_reporter = OpsviewReporter()
         super().__init__(*args, **kwargs)
 
     def metric(self):
@@ -209,13 +210,13 @@ def metric(self):
 
         # fetch the cluster metrics
         if self.metric_server_url:
-            metrics = OpsviewReporter.retrieve_metrics([self.metric_server_url], self.req_timeout)[
+            metrics = self.opsview_reporter.retrieve_metrics([self.metric_server_url], self.req_timeout)[
                 self.metric_server_url
             ]
             if metrics:
                 logger.debug(f"Processing tlm {self.metric_name}...")
 
-                av_pod = OpsviewReporter.read_from_metrics(metrics, pattern)
+                av_pod = self.opsview_reporter.read_from_metrics(metrics, pattern)
                 if av_pod:
                     av_pod = int(av_pod)
                     if av_pod <= self.critical_t:
diff --git a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py
index da520a8..cfa1e66 100644
--- a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py
+++ b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py
@@ -179,6 +179,7 @@ def __init__(self, *args, **kwargs):
         self.critical_t = kwargs["critical_t"]
         self.req_timeout = kwargs["req_timeout"]
         self.metric_server_url = kwargs["metric_server_url"]
+        self.opsview_reporter = OpsviewReporter()
         super().__init__(*args, **kwargs)
 
     def metric(self):
@@ -190,13 +191,13 @@ def metric(self):
 
         # fetch the cluster metrics
         if self.metric_server_url:
-            metrics = OpsviewReporter.retrieve_metrics([self.metric_server_url], self.req_timeout)[
+            metrics = self.opsview_reporter.retrieve_metrics([self.metric_server_url], self.req_timeout)[
                 self.metric_server_url
             ]
             if metrics:
                 logger.debug(f"Processing tlm {self.metric_name}...")
 
-                av_pod = OpsviewReporter.read_from_metrics(metrics, pattern)
+                av_pod = self.opsview_reporter.read_from_metrics(metrics, pattern)
                 if av_pod:
                     av_pod = int(av_pod)
                     if av_pod <= self.critical_t:
diff --git a/aviso-server/monitoring/aviso_monitoring/reporter/etcd_reporter.py b/aviso-server/monitoring/aviso_monitoring/reporter/etcd_reporter.py
index 6d6900b..bb705c7 100644
--- a/aviso-server/monitoring/aviso_monitoring/reporter/etcd_reporter.py
+++ b/aviso-server/monitoring/aviso_monitoring/reporter/etcd_reporter.py
@@ -23,6 +23,7 @@ def __init__(self, config, *args, **kwargs):
         self.req_timeout = self.etcd_config["req_timeout"]
         self.member_urls = self.etcd_config["member_urls"]
         self.tlms = self.etcd_config["tlms"]
+        self.opsview_reporter = OpsviewReporter()
         super().__init__(config, *args, **kwargs)
 
     def process_messages(self):
@@ -33,7 +34,7 @@ def process_messages(self):
         logger.debug("Etcd processing metrics...")
 
         # fetch the raw tlms provided by etcd
-        raw_tlms = OpsviewReporter.retrieve_metrics(self.member_urls, self.req_timeout)  # noqa: F841
+        raw_tlms = self.opsview_reporter.retrieve_metrics(self.member_urls, self.req_timeout)  # noqa: F841
 
         # array of metric to return
         metrics = []

From 637b5d49b3004c5d773515f2c1b03c5436e29156 Mon Sep 17 00:00:00 2001
From: sametd <samet.demir@ecmwf.int>
Date: Wed, 20 Dec 2023 18:40:15 +0100
Subject: [PATCH 05/11] Revert "opsviewreporter instantiated when necessary to
 retrieve logs"

This reverts commit 4089bc243a1938d3dcb24b1dd44d04faba30a592.
---
 .../aviso_monitoring/reporter/aviso_auth_reporter.py         | 5 ++---
 .../aviso_monitoring/reporter/aviso_rest_reporter.py         | 5 ++---
 .../monitoring/aviso_monitoring/reporter/etcd_reporter.py    | 3 +--
 3 files changed, 5 insertions(+), 8 deletions(-)

diff --git a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py
index 8d50cd9..7a118f8 100644
--- a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py
+++ b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py
@@ -198,7 +198,6 @@ def __init__(self, *args, **kwargs):
         self.critical_t = kwargs["critical_t"]
         self.req_timeout = kwargs["req_timeout"]
         self.metric_server_url = kwargs["metric_server_url"]
-        self.opsview_reporter = OpsviewReporter()
         super().__init__(*args, **kwargs)
 
     def metric(self):
@@ -210,13 +209,13 @@ def metric(self):
 
         # fetch the cluster metrics
         if self.metric_server_url:
-            metrics = self.opsview_reporter.retrieve_metrics([self.metric_server_url], self.req_timeout)[
+            metrics = OpsviewReporter.retrieve_metrics([self.metric_server_url], self.req_timeout)[
                 self.metric_server_url
             ]
             if metrics:
                 logger.debug(f"Processing tlm {self.metric_name}...")
 
-                av_pod = self.opsview_reporter.read_from_metrics(metrics, pattern)
+                av_pod = OpsviewReporter.read_from_metrics(metrics, pattern)
                 if av_pod:
                     av_pod = int(av_pod)
                     if av_pod <= self.critical_t:
diff --git a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py
index cfa1e66..da520a8 100644
--- a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py
+++ b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py
@@ -179,7 +179,6 @@ def __init__(self, *args, **kwargs):
         self.critical_t = kwargs["critical_t"]
         self.req_timeout = kwargs["req_timeout"]
         self.metric_server_url = kwargs["metric_server_url"]
-        self.opsview_reporter = OpsviewReporter()
         super().__init__(*args, **kwargs)
 
     def metric(self):
@@ -191,13 +190,13 @@ def metric(self):
 
         # fetch the cluster metrics
         if self.metric_server_url:
-            metrics = self.opsview_reporter.retrieve_metrics([self.metric_server_url], self.req_timeout)[
+            metrics = OpsviewReporter.retrieve_metrics([self.metric_server_url], self.req_timeout)[
                 self.metric_server_url
             ]
             if metrics:
                 logger.debug(f"Processing tlm {self.metric_name}...")
 
-                av_pod = self.opsview_reporter.read_from_metrics(metrics, pattern)
+                av_pod = OpsviewReporter.read_from_metrics(metrics, pattern)
                 if av_pod:
                     av_pod = int(av_pod)
                     if av_pod <= self.critical_t:
diff --git a/aviso-server/monitoring/aviso_monitoring/reporter/etcd_reporter.py b/aviso-server/monitoring/aviso_monitoring/reporter/etcd_reporter.py
index bb705c7..6d6900b 100644
--- a/aviso-server/monitoring/aviso_monitoring/reporter/etcd_reporter.py
+++ b/aviso-server/monitoring/aviso_monitoring/reporter/etcd_reporter.py
@@ -23,7 +23,6 @@ def __init__(self, config, *args, **kwargs):
         self.req_timeout = self.etcd_config["req_timeout"]
         self.member_urls = self.etcd_config["member_urls"]
         self.tlms = self.etcd_config["tlms"]
-        self.opsview_reporter = OpsviewReporter()
         super().__init__(config, *args, **kwargs)
 
     def process_messages(self):
@@ -34,7 +33,7 @@ def process_messages(self):
         logger.debug("Etcd processing metrics...")
 
         # fetch the raw tlms provided by etcd
-        raw_tlms = self.opsview_reporter.retrieve_metrics(self.member_urls, self.req_timeout)  # noqa: F841
+        raw_tlms = OpsviewReporter.retrieve_metrics(self.member_urls, self.req_timeout)  # noqa: F841
 
         # array of metric to return
         metrics = []

From 3a202f7b52fcde0847c0e628a9f73799e9fb02c6 Mon Sep 17 00:00:00 2001
From: sametd <samet.demir@ecmwf.int>
Date: Wed, 20 Dec 2023 19:43:26 +0100
Subject: [PATCH 06/11] metric token support added for retrieve metrics
 function

---
 .../aviso_monitoring/reporter/opsview_reporter.py          | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/aviso-server/monitoring/aviso_monitoring/reporter/opsview_reporter.py b/aviso-server/monitoring/aviso_monitoring/reporter/opsview_reporter.py
index 4dd81c9..14d7be6 100644
--- a/aviso-server/monitoring/aviso_monitoring/reporter/opsview_reporter.py
+++ b/aviso-server/monitoring/aviso_monitoring/reporter/opsview_reporter.py
@@ -202,7 +202,8 @@ def aggregate_unique_counter_tlms(tlms):
         }
         return agg_tlm
 
-    def retrieve_metrics(self, metric_servers, req_timeout):
+    @classmethod
+    def retrieve_metrics(cls, metric_servers, req_timeout):
         """
         This methods retrieves the metrics provided by specific metric servers using a Prometheus interface.
         """
@@ -212,8 +213,8 @@ def retrieve_metrics(self, metric_servers, req_timeout):
             logger.debug(f"Retrieving metrics from {url}...")
             headers = {}
             try:
-                if self.metric_ssl_enabled:
-                    headers["Authorization"] = f"Bearer {self.metric_token}"
+                if cls.metric_ssl_enabled:
+                    headers["Authorization"] = f"Bearer {cls.metric_token}"
                 resp = requests.get(url, verify=False, timeout=req_timeout, headers=headers)
             except Exception as e:
                 logger.exception(f"Not able to get metrics from {url}, error {e}")

From 1026913a6e19a58ad22564af545b3c6fdaf4ca2a Mon Sep 17 00:00:00 2001
From: sametd <samet.demir@ecmwf.int>
Date: Wed, 20 Dec 2023 20:02:49 +0100
Subject: [PATCH 07/11] mitigate metric variable installation

---
 .../reporter/aviso_rest_reporter.py                |  2 ++
 .../aviso_monitoring/reporter/opsview_reporter.py  | 14 ++++++++++++--
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py
index da520a8..b0ec55b 100644
--- a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py
+++ b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py
@@ -18,6 +18,8 @@ def __init__(self, config, *args, **kwargs):
         self.frequency = aviso_rest_config["frequency"]
         self.enabled = aviso_rest_config["enabled"]
         self.tlms = aviso_rest_config["tlms"]
+        #configure the metric vars once only here
+        OpsviewReporter.configure_metric_vars(config)
         super().__init__(config, *args, **kwargs)
 
     def process_messages(self):
diff --git a/aviso-server/monitoring/aviso_monitoring/reporter/opsview_reporter.py b/aviso-server/monitoring/aviso_monitoring/reporter/opsview_reporter.py
index 14d7be6..1dc3b6a 100644
--- a/aviso-server/monitoring/aviso_monitoring/reporter/opsview_reporter.py
+++ b/aviso-server/monitoring/aviso_monitoring/reporter/opsview_reporter.py
@@ -19,14 +19,24 @@
 
 
 class OpsviewReporter(ABC):
+    metric_ssl_enabled = False
+    metric_token = ""
+
     def __init__(self, config: Config, msg_receiver=None):
         urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
         self.monitor_servers = config.monitor_servers
         self.msg_receiver = msg_receiver
         self.token = {}
+
+    @classmethod
+    def configure_metric_vars(cls, config):
+        """
+        Configures the class attributes based on the provided config.
+        """
+        urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
         if config.kube_state_metrics["ssl_enabled"]:
-            self.metric_ssl_enabled = True
-            self.metric_token = config.kube_state_metrics["token"]
+            cls.metric_ssl_enabled = True
+            cls.metric_token = config.kube_state_metrics["token"]
 
     def ms_authenticate(self, m_server):
         """

From 964d4c05ddb2a991da0e02db9587064dcc83d529 Mon Sep 17 00:00:00 2001
From: sametd <samet.demir@ecmwf.int>
Date: Wed, 20 Dec 2023 22:55:31 +0100
Subject: [PATCH 08/11] namespace is now taken from the pod instead of a fixed
 name

---
 .../reporter/aviso_rest_reporter.py           | 38 ++++++++++++++++++-
 1 file changed, 36 insertions(+), 2 deletions(-)

diff --git a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py
index b0ec55b..4b6752b 100644
--- a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py
+++ b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py
@@ -18,7 +18,7 @@ def __init__(self, config, *args, **kwargs):
         self.frequency = aviso_rest_config["frequency"]
         self.enabled = aviso_rest_config["enabled"]
         self.tlms = aviso_rest_config["tlms"]
-        #configure the metric vars once only here
+        # configure the metric vars once only here
         OpsviewReporter.configure_metric_vars(config)
         super().__init__(config, *args, **kwargs)
 
@@ -184,7 +184,14 @@ def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
 
     def metric(self):
-        pattern = r'kube_deployment_status_replicas{namespace="aviso",deployment="aviso-rest-\w+"}'
+        namespace = self.get_k8s_pod_namespace()
+        if namespace:
+            logger.info(f"The pod is running in the '{namespace}' namespace.")
+        else:
+            logger.warning("Could not determine the pod's namespace.")
+            namespace = "aviso"
+
+        pattern = rf'kube_deployment_status_replicas{{namespace="{namespace}",deployment="aviso-rest-\w+"}}'
         # defaults
         status = 0
         message = "All pods available"
@@ -226,3 +233,30 @@ def metric(self):
             m_status = {"name": self.metric_name, "status": 1, "message": "Metric could not be retrieved"}
         logger.debug(f"{self.metric_name} metric: {m_status}")
         return m_status
+
+    @staticmethod
+    def get_k8s_pod_namespace():
+        """
+        Retrieves the Kubernetes (k8s) namespace in which the current pod is running.
+
+        This function reads the namespace name from a file that Kubernetes automatically
+        mounts inside the pod. This file is typically located at:
+        '/var/run/secrets/kubernetes.io/serviceaccount/namespace'
+
+        Returns:
+            str: The namespace in which the pod is running. If the namespace cannot be determined
+                (e.g., the file doesn't exist or the pod is not running in a k8s environment),
+                the function returns None.
+        """
+        namespace_file = "/var/run/secrets/kubernetes.io/serviceaccount/namespace"
+        try:
+            with open(namespace_file, "r") as file:
+                return file.read().strip()
+        except FileNotFoundError:
+            logger.error(f"Namespace file not found: {namespace_file}")
+        except IOError as e:
+            logger.error(f"I/O error occurred when reading namespace file: {e}")
+        except Exception as e:
+            logger.exception(f"Unexpected error occurred when reading namespace file: {e}")
+
+        return None

From 884fd4f9aa9c069e4c318ebc343f72af3b249f40 Mon Sep 17 00:00:00 2001
From: sametd <samet.demir@ecmwf.int>
Date: Wed, 20 Dec 2023 23:03:23 +0100
Subject: [PATCH 09/11] namespace is now taken from the pod instead of a fixed
 name

---
 .../reporter/aviso_auth_reporter.py           | 36 ++++++++++++++++++-
 1 file changed, 35 insertions(+), 1 deletion(-)

diff --git a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py
index 7a118f8..2a2fc97 100644
--- a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py
+++ b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py
@@ -201,7 +201,14 @@ def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
 
     def metric(self):
-        pattern = r'kube_deployment_status_replicas{namespace="aviso",deployment="aviso-auth-\w+"}'
+        namespace = self.get_k8s_pod_namespace()
+        if namespace:
+            logger.info(f"The pod is running in the '{namespace}' namespace.")
+        else:
+            logger.warning("Could not determine the pod's namespace.")
+            namespace = "aviso"
+
+        pattern = rf'kube_deployment_status_replicas{{namespace="{namespace}",deployment="aviso-auth-\w+"}}'
         # defaults
         status = 0
         message = "All pods available"
@@ -243,3 +250,30 @@ def metric(self):
             m_status = {"name": self.metric_name, "status": 1, "message": "Metric could not be retrieved"}
         logger.debug(f"{self.metric_name} metric: {m_status}")
         return m_status
+
+    @staticmethod
+    def get_k8s_pod_namespace():
+        """
+        Retrieves the Kubernetes (k8s) namespace in which the current pod is running.
+
+        This function reads the namespace name from a file that Kubernetes automatically
+        mounts inside the pod. This file is typically located at:
+        '/var/run/secrets/kubernetes.io/serviceaccount/namespace'
+
+        Returns:
+            str: The namespace in which the pod is running. If the namespace cannot be determined
+                (e.g., the file doesn't exist or the pod is not running in a k8s environment),
+                the function returns None.
+        """
+        namespace_file = "/var/run/secrets/kubernetes.io/serviceaccount/namespace"
+        try:
+            with open(namespace_file, "r") as file:
+                return file.read().strip()
+        except FileNotFoundError:
+            logger.error(f"Namespace file not found: {namespace_file}")
+        except IOError as e:
+            logger.error(f"I/O error occurred when reading namespace file: {e}")
+        except Exception as e:
+            logger.exception(f"Unexpected error occurred when reading namespace file: {e}")
+
+        return None

From 7675c3c9eafb32f008d40c8812ba99517094662b Mon Sep 17 00:00:00 2001
From: sametd <samet.demir@ecmwf.int>
Date: Wed, 20 Dec 2023 23:28:27 +0100
Subject: [PATCH 10/11] name correction for the metric

---
 .../monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py | 2 +-
 .../monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py
index 2a2fc97..c34022b 100644
--- a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py
+++ b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py
@@ -208,7 +208,7 @@ def metric(self):
             logger.warning("Could not determine the pod's namespace.")
             namespace = "aviso"
 
-        pattern = rf'kube_deployment_status_replicas{{namespace="{namespace}",deployment="aviso-auth-\w+"}}'
+        pattern = rf'kube_deployment_status_replicas{{namespace="{namespace}",deployment="aviso-auth"}}'
         # defaults
         status = 0
         message = "All pods available"
diff --git a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py
index 4b6752b..91f2f45 100644
--- a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py
+++ b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py
@@ -191,7 +191,7 @@ def metric(self):
             logger.warning("Could not determine the pod's namespace.")
             namespace = "aviso"
 
-        pattern = rf'kube_deployment_status_replicas{{namespace="{namespace}",deployment="aviso-rest-\w+"}}'
+        pattern = rf'kube_deployment_status_replicas{{namespace="{namespace}",deployment="aviso-rest"}}'
         # defaults
         status = 0
         message = "All pods available"

From 9478e9ff63f4814952ef1925ed97d9a41d4e0227 Mon Sep 17 00:00:00 2001
From: sametd <samet.demir@ecmwf.int>
Date: Wed, 20 Dec 2023 23:34:29 +0100
Subject: [PATCH 11/11] unnecessary info log is removed, otherwise same log
 would be written over and over

---
 .../aviso_monitoring/reporter/aviso_auth_reporter.py          | 4 +---
 .../aviso_monitoring/reporter/aviso_rest_reporter.py          | 4 +---
 2 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py
index c34022b..6526930 100644
--- a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py
+++ b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_auth_reporter.py
@@ -202,9 +202,7 @@ def __init__(self, *args, **kwargs):
 
     def metric(self):
         namespace = self.get_k8s_pod_namespace()
-        if namespace:
-            logger.info(f"The pod is running in the '{namespace}' namespace.")
-        else:
+        if not namespace:
             logger.warning("Could not determine the pod's namespace.")
             namespace = "aviso"
 
diff --git a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py
index 91f2f45..384f59d 100644
--- a/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py
+++ b/aviso-server/monitoring/aviso_monitoring/reporter/aviso_rest_reporter.py
@@ -185,9 +185,7 @@ def __init__(self, *args, **kwargs):
 
     def metric(self):
         namespace = self.get_k8s_pod_namespace()
-        if namespace:
-            logger.info(f"The pod is running in the '{namespace}' namespace.")
-        else:
+        if not namespace:
             logger.warning("Could not determine the pod's namespace.")
             namespace = "aviso"