Merge remote-tracking branch 'upstream/main' into introduce-sto-worker-simcore-service

Author: YuryHrytsuk

scripts/common.Makefile

@@ -274,7 +274,7 @@ $(REPO_BASE_DIR)/.venv/bin/activate:
 	$(REPO_BASE_DIR)/.venv/bin/pip3 install --upgrade pip wheel setuptools
 	$(REPO_BASE_DIR)/.venv/bin/pip3 install jinja2 j2cli[yaml] typer
 	@echo "To activate the venv, execute 'source $(REPO_BASE_DIR)/.venv/bin/activate'"
-PHONY: .venv
+.PHONY: .venv
 .venv: $(REPO_BASE_DIR)/.venv/bin/activate ## Creates a python virtual environment with dev tools (pip, pylint, ...)
 .PHONY: venv
 venv: $(REPO_BASE_DIR)/.venv/bin/activate ## Creates a python virtual environment with dev tools (pip, pylint, ...)

services/admin-panels/docker-compose.yml.j2

@@ -7,7 +7,7 @@ configs:
     file: ./data/{{ item.name }}{% endfor %}
 services:
   adminpanels:
-    image: jupyter/base-notebook:18b10e7f732d
+    image: jupyter/base-notebook:notebook-7.0.6
     user: root
     networks:
       - public

services/graylog/data/contentpacks/osparc-custom-content-pack-v2.json

@@ -1,7 +1,7 @@
 {
   "v": "1",
   "id": "dfaeea11-bde6-4203-9cfe-6ca2a23ca22e",
-  "rev": 42,
+  "rev": 43,
   "name": "osparc-custom-content-pack-v2",
   "summary": "osparc-custom-content-pack-v2",
   "description": "",

services/graylog/scripts/alerts.template.yaml

@@ -1,237 +1,3 @@
-- title: "${MACHINE_FQDN}: Interactive Study Data too large for AWS S3 and hanging"
-  description: "${MACHINE_FQDN}: Study Hanging"
-  priority: 2
-  config:
-    query: >
-      "EntityTooLarge" AND NOT container_name:/.*graylog_graylog.*/
-    query_parameters: []
-    search_within_ms: 600000
-    execute_every_ms: 600000
-    group_by: []
-    series: []
-    conditions: {}
-    type: aggregation-v1
-  field_spec:
-    source:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.source}"
-        require_values: false
-    container_name:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.container_name}"
-        require_values: false
-    full_message:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.full_message}"
-  key_spec:
-    - source
-    - container_name
-    - full_message
-  notification_settings:
-    grace_period_ms: 0
-    backlog_size: 99
-  alert: true
-- title: "${MACHINE_FQDN}: Writer Is None Error in Webserver"
-  description: "${MACHINE_FQDN}: Alert if \"writer is None\" pops up. Communication with rabbitMQ is disrupted and this will make simcore go crazy"
-  priority: 2
-  config:
-    query: >
-      "writer is None" AND NOT container_name:/.*graylog_graylog.*/
-    query_parameters: []
-    search_within_ms: 600000
-    execute_every_ms: 600000
-    group_by: []
-    series: []
-    conditions: {}
-    type: aggregation-v1
-  field_spec:
-    source:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.source}"
-        require_values: false
-    container_name:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.container_name}"
-        require_values: false
-    full_message:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.full_message}"
-  key_spec:
-    - source
-    - container_name
-    - full_message
-  notification_settings:
-    grace_period_ms: 0
-    backlog_size: 99
-  alert: true
-- title: "${MACHINE_FQDN}: Dynamic Sidecar failed to save with S3TransferError"
-  description: "${MACHINE_FQDN}: Alert if Dynamic Sidecar failed to save with S3TransferError"
-  priority: 2
-  config:
-    query: >
-      "simcore_sdk.node_ports_common.exceptions.S3TransferError: Could not upload file" AND NOT container_name:/.*graylog_graylog.*/
-    query_parameters: []
-    search_within_ms: 600000
-    execute_every_ms: 600000
-    group_by: []
-    series: []
-    conditions: {}
-    type: aggregation-v1
-  field_spec:
-    source:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.source}"
-        require_values: false
-    container_name:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.container_name}"
-        require_values: false
-    full_message:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.full_message}"
-  key_spec:
-    - source
-    - container_name
-    - full_message
-  notification_settings:
-    grace_period_ms: 0
-    backlog_size: 99
-  alert: true
-- title: "${MACHINE_FQDN}: Dynamic Sidecar failed to save - 2"
-  description: "${MACHINE_FQDN}: Alert if Dynamic Sidecar failed to save - 2"
-  priority: 2
-  config:
-    query: >
-      "Could not contact dynamic-sidecar to save service" AND NOT container_name:/.*graylog_graylog.*/
-    query_parameters: []
-    search_within_ms: 60000
-    execute_every_ms: 60000
-    group_by: []
-    series: []
-    conditions: {}
-    type: aggregation-v1
-  field_spec:
-    source:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.source}"
-        require_values: false
-    container_name:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.container_name}"
-        require_values: false
-    full_message:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.full_message}"
-  key_spec:
-    - source
-    - container_name
-    - full_message
-  notification_settings:
-    grace_period_ms: 0
-    backlog_size: 99
-  alert: true
-- title: "${MACHINE_FQDN}: simcore-agent failed pushing docker volume data to backup S3 bucket"
-  description: "${MACHINE_FQDN}: simcore-agent failed pushing docker volume data to backup S3 bucket"
-  priority: 2
-  config:
-    query: >
-      container_name: /.*agent.*/ AND "Shell subprocesses yielded nonzero error code" AND NOT container_name:/.*graylog_graylog.*/
-    query_parameters: []
-    search_within_ms: 600000
-    execute_every_ms: 600000
-    group_by: []
-    series: []
-    conditions: {}
-    type: aggregation-v1
-  field_spec:
-    source:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.source}"
-        require_values: false
-    container_name:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.container_name}"
-        require_values: false
-    full_message:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.full_message}"
-  key_spec:
-    - source
-    - container_name
-    - full_message
-  notification_settings:
-    grace_period_ms: 0
-    backlog_size: 99
-  alert: true
-- title: "${MACHINE_FQDN}: faulty env-var setup"
-  description: "${MACHINE_FQDN}: Look e.g. here https://git.speag.com/oSparc/osparc-ops-environments/-/issues/564"
-  priority: 2
-  config:
-    query: >
-      "unresolved, defaulting to None" AND NOT container_name:/.*graylog_graylog.*/
-    query_parameters: []
-    search_within_ms: 600000
-    execute_every_ms: 600000
-    group_by: []
-    series: []
-    conditions: {}
-    type: aggregation-v1
-  field_spec:
-    source:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.source}"
-        require_values: false
-    container_name:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.container_name}"
-        require_values: false
-    full_message:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.full_message}"
-  key_spec:
-    - source
-    - container_name
-    - full_message
-  notification_settings:
-    grace_period_ms: 0
-    backlog_size: 99
-  alert: true
 - title: "${MACHINE_FQDN}: DOCKER IP POOL EXHAUSTED, no service can start"
   description: "${MACHINE_FQDN}: DOCKER IP POOL EXHAUSTED, no service can start. See: https://github.com/moby/moby/issues/30820"
   priority: 3
@@ -240,6 +6,7 @@
       container_name: /.*director-v2.*/ AND "could not find an available, non-overlapping IPv4 address pool among the defaults to assign to the network" AND NOT container_name:/.*graylog_graylog.*/
     query_parameters: []
     search_within_ms: 600000
+    event_limit: 1
     execute_every_ms: 600000
     group_by: []
     series: []
@@ -271,82 +38,6 @@
     grace_period_ms: 0
     backlog_size: 99
   alert: true
-- title: "${MACHINE_FQDN}: Potential hanging dy-sidecar service detected."
-  description: "${MACHINE_FQDN}: Potential hanging dy-sidecar service detected. Human intervention required. Please investigate."
-  priority: 3
-  config:
-    query: >
-      "waiting for manual intervention" AND container_name:/.*director-v2.*/
-    query_parameters: []
-    search_within_ms: 3600000
-    execute_every_ms: 3600000
-    group_by: []
-    series: []
-    conditions: {}
-    type: aggregation-v1
-  field_spec:
-    source:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.source}"
-        require_values: false
-    container_name:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.container_name}"
-        require_values: false
-    full_message:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.full_message}"
-  key_spec:
-    - source
-    - container_name
-  notification_settings:
-    grace_period_ms: 0
-    backlog_size: 99
-  alert: true
-- title: "${MACHINE_FQDN}: Syslogs indicate OOM-Event"
-  description: "${MACHINE_FQDN}: Likely the oom-killer has reaped a container Please investigate and adjust service limitations."
-  priority: 2
-  config:
-    query: >
-      "Memory cgroup out of memory:"
-    query_parameters: []
-    search_within_ms: 3600000
-    execute_every_ms: 3600000
-    group_by: []
-    series: []
-    conditions: {}
-    type: aggregation-v1
-  field_spec:
-    source:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.source}"
-        require_values: false
-    container_name:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.container_name}"
-        require_values: false
-    full_message:
-      data_type: string
-      providers:
-      - type: template-v1
-        template: "${source.full_message}"
-  key_spec:
-    - source
-    - container_name
-  notification_settings:
-    grace_period_ms: 0
-    backlog_size: 99
-  alert: true
 - title: "${MACHINE_FQDN}: Unexpected error with redis lock detected"
   description: "${MACHINE_FQDN}: This error should only occur in unit tests due to very low timings, maybe something happene here"
   priority: 2
@@ -355,6 +46,7 @@
       "lock is no longer owned. This is unexpected and requires investigation" AND NOT container_name:/.*graylog_graylog.*/
     query_parameters: []
     search_within_ms: 3600000
+    event_limit: 1
     execute_every_ms: 3600000
     group_by: []
     series: []
@@ -393,6 +85,7 @@
       "LockNotOwnedError" AND NOT container_name:/.*graylog_graylog.*/
     query_parameters: []
     search_within_ms: 3600000
+    event_limit: 1
     execute_every_ms: 3600000
     group_by: []
     series: []
@@ -432,6 +125,7 @@
     query_parameters: []
     search_within_ms: 86400000
     execute_every_ms: 86400000
+    event_limit: 1
     group_by: []
     series: []
     conditions: {}
@@ -463,6 +157,7 @@
       query: log_service:/.+payments/ AND (log_level:ERROR OR log_level:WARNING)
       query_parameters: []
       search_within_ms: 600000
+      event_limit: 1
       execute_every_ms: 600000
       group_by: []
       series: []