Merge remote-tracking branch 'upstream/main' into 2024/add/tempo

Author: mrnicegyu11

.github/PULL_REQUEST_TEMPLATE.md

@@ -18,6 +18,8 @@
 - [ ] Service has placement constraints or is global
 - [ ] Service is restartable
 - [ ] Service restart is zero-downtime
+- [ ] Service is monitored (via prometheus and grafana)
 - [ ] Service is not bound to one specific node (e.g. via files or volumes)
 - [ ] Relevant OPS E2E Test are added
-- [ ] Service's Public URL is included in maintenance mode -->
+- [ ] Service's Public URL is included in maintenance mode
+- [ ] Service's Public URL is included in testing mode -->

services/monitoring/Makefile

@@ -153,15 +153,4 @@ tempo_config.yaml: tempo_config.yaml.j2 ${REPO_CONFIG_LOCATION} .env .venv
 
 .PHONY: grafana/assets
 grafana/assets: ${REPO_CONFIG_LOCATION}
-	@if [ ! -d "$(shell dirname ${REPO_CONFIG_LOCATION})/assets/grafana" ]; then \
-		echo "Error: folder does not exist $$GRAFANA_ASSETS_DIR" >&2; \
-		exit 1; \
-	fi; \
-	if [ ! -d "$(shell dirname ${REPO_CONFIG_LOCATION})/../shared/assets/grafana" ]; then \
-		echo "Error: folder does not exist $$GRAFANA_COMMON_ASSETS_DIR" >&2; \
-		exit 1; \
-	fi; \
-	rm -rf $(REPO_BASE_DIR)/services/monitoring/grafana/assets || true; \
-	mkdir -p $(REPO_BASE_DIR)/services/monitoring/grafana/assets; \
-	cp -r $(shell dirname ${REPO_CONFIG_LOCATION})/assets/grafana/* $(REPO_BASE_DIR)/services/monitoring/grafana/assets; \
-	cp -r $(shell dirname ${REPO_CONFIG_LOCATION})/../shared/assets/grafana $(REPO_BASE_DIR)/services/monitoring/grafana/assets/shared; \
+	@$(MAKE_C) grafana assets

services/monitoring/docker-compose.yml.j2

@@ -379,9 +379,12 @@ services:
     networks:
       - monitored
     environment:
-      REDIS_ADDR: redis://{{REDIS_HOST}}:{{REDIS_PORT}}
-      REDIS_EXPORTER_CHECK_KEYS: db0=user_id*client_session_id*alive,db0=user_id*client_session_id*resources,db1=project_lock*,db3=*
+      REDIS_ADDR: ${REDIS_ADDRESS}
+{%- if REDIS_USER %}
+      REDIS_USER: ${REDIS_USER}
+{%- endif %}
       REDIS_PASSWORD: ${REDIS_PASSWORD}
+      REDIS_EXPORTER_CHECK_KEYS: db0=user_id*client_session_id*alive,db0=user_id*client_session_id*resources,db1=project_lock*,db3=*
     deploy:
       labels:
       - prometheus-job=redis-exporter

services/monitoring/grafana/Makefile

@@ -6,7 +6,7 @@ include ${REPO_BASE_DIR}/scripts/common.Makefile
 
 # Internal VARIABLES ------------------------------------------------
 TF_STATE_FILE := terraform/.terraform/terraform.tfstate
-
+.PHONY: terraform/main.tf
 terraform/main.tf: terraform/main.tf.j2 .venv $(REPO_CONFIG_LOCATION)
 	# generate $@
 	@$(call jinja, $<, $(REPO_CONFIG_LOCATION), $@)
@@ -62,3 +62,18 @@ ensure-grafana-online:
 		echo "Max attempts reached, Grafana is still unreachable."; \
 		exit 1; \
 	fi;
+
+.PHONY: assets
+assets: ${REPO_CONFIG_LOCATION}
+	@if [ ! -d "$(shell dirname ${REPO_CONFIG_LOCATION})/assets/grafana" ]; then \
+		echo "Error: folder does not exist $$GRAFANA_ASSETS_DIR" >&2; \
+		exit 1; \
+	fi; \
+	if [ ! -d "$(shell dirname ${REPO_CONFIG_LOCATION})/../shared/assets/grafana" ]; then \
+		echo "Error: folder does not exist $$GRAFANA_COMMON_ASSETS_DIR" >&2; \
+		exit 1; \
+	fi; \
+	rm -rf $(REPO_BASE_DIR)/services/monitoring/grafana/assets || true; \
+	mkdir -p $(REPO_BASE_DIR)/services/monitoring/grafana/assets; \
+	cp -r $(shell dirname ${REPO_CONFIG_LOCATION})/assets/grafana/* $(REPO_BASE_DIR)/services/monitoring/grafana/assets; \
+	cp -r $(shell dirname ${REPO_CONFIG_LOCATION})/../shared/assets/grafana $(REPO_BASE_DIR)/services/monitoring/grafana/assets/shared; \

services/monitoring/grafana/terraform/main.tf.j2

@@ -12,12 +12,15 @@ terraform {
     encrypt        = false
     bucket         = "{{ TF_GRAFANA_STATE_BACKEND_S3_BUCKET_NAME }}"
     region         = "{{ TF_GRAFANA_STATE_BACKEND_AWS_REGION }}"
-    {% if GRAFANA_TERRAFORM_STATE_BACKEND_S3_ENDPOINT %}
+    {% if "amazonaws.com" not in GRAFANA_TERRAFORM_STATE_BACKEND_S3_ENDPOINT %}
+    # via https://github.com/hashicorp/terraform/issues/34086#issuecomment-1814188931
     skip_credentials_validation = true
     skip_requesting_account_id  = true
     skip_metadata_api_check     = true
+    skip_region_validation      = true
+    skip_s3_checksum            = true
     use_path_style              = true
-    endpoints = {
+    endpoints                   = {
       s3 = "{{ GRAFANA_TERRAFORM_STATE_BACKEND_S3_ENDPOINT }}"
     }
     {% endif %}

services/monitoring/template.env

@@ -13,8 +13,8 @@ POSTGRES_PORT=${POSTGRES_PORT}
 POSTGRES_HOST=${POSTGRES_HOST}
 POSTGRES_ENDPOINT=${POSTGRES_ENDPOINT}
 PREFIX_STACK_NAME=${PREFIX_STACK_NAME}
-REDIS_PORT=${REDIS_PORT}
-REDIS_HOST=${REDIS_HOST}
+REDIS_USER=${REDIS_USER}
+REDIS_ADDRESS=${REDIS_ADDRESS}
 REDIS_PASSWORD=${REDIS_PASSWORD}
 MONITORING_PROMETHEUS_CEPH_TARGETS='${MONITORING_PROMETHEUS_CEPH_TARGETS}'
 MONITORING_PROMETHEUS_PGSQL_GID_MONITORED=${MONITORING_PROMETHEUS_PGSQL_GID_MONITORED}