Skip to content

Commit 36f2276

Browse files
committed
Merge remote-tracking branch 'upstream/main' into kubernetes-introduce-longhorn
2 parents 389783b + ec1d38f commit 36f2276

File tree

8 files changed

+89
-23
lines changed

8 files changed

+89
-23
lines changed

services/graylog/scripts/alerts.template.yaml

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -6,7 +6,7 @@
66
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.*/
77
query_parameters: []
88
search_within_ms: 600000
9-
event_limit: 1
9+
event_limit: 1000
1010
execute_every_ms: 600000
1111
group_by: []
1212
series: []
@@ -46,7 +46,7 @@
4646
"lock is no longer owned. This is unexpected and requires investigation" AND NOT container_name:/.*graylog_graylog.*/
4747
query_parameters: []
4848
search_within_ms: 3600000
49-
event_limit: 1
49+
event_limit: 1000
5050
execute_every_ms: 3600000
5151
group_by: []
5252
series: []
@@ -85,7 +85,7 @@
8585
"LockNotOwnedError" AND NOT container_name:/.*graylog_graylog.*/
8686
query_parameters: []
8787
search_within_ms: 3600000
88-
event_limit: 1
88+
event_limit: 1000
8989
execute_every_ms: 3600000
9090
group_by: []
9191
series: []
@@ -125,7 +125,7 @@
125125
query_parameters: []
126126
search_within_ms: 86400000
127127
execute_every_ms: 86400000
128-
event_limit: 1
128+
event_limit: 1000
129129
group_by: []
130130
series: []
131131
conditions: {}
@@ -157,7 +157,7 @@
157157
query: log_service:/.+payments/ AND (log_level:ERROR OR log_level:WARNING)
158158
query_parameters: []
159159
search_within_ms: 600000
160-
event_limit: 1
160+
event_limit: 1000
161161
execute_every_ms: 600000
162162
group_by: []
163163
series: []

services/monitoring/Makefile

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -176,6 +176,7 @@ grafana/assets: ${REPO_CONFIG_LOCATION}
176176
.PHONY: grafana-import
177177
grafana-import: grafana/assets ## Imports the remote grafana dashboards and datasources FROM YOUR LOCAL MACHINE
178178
@pushd ${REPO_BASE_DIR}/services/monitoring/grafana && \
179+
rm -r ./terraform/.terraform 2>/dev/null | true && \
179180
$(MAKE) terraform-plan && \
180181
$(MAKE) terraform-apply; \
181182
popd > /dev/null

services/monitoring/grafana/Makefile

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -75,5 +75,5 @@ assets: ${REPO_CONFIG_LOCATION}
7575
fi; \
7676
rm -rf $(REPO_BASE_DIR)/services/monitoring/grafana/assets || true; \
7777
mkdir -p $(REPO_BASE_DIR)/services/monitoring/grafana/assets; \
78-
cp -r $(shell dirname ${REPO_CONFIG_LOCATION})/assets/grafana/* $(REPO_BASE_DIR)/services/monitoring/grafana/assets; \
7978
cp -r $(shell dirname ${REPO_CONFIG_LOCATION})/../shared/assets/grafana $(REPO_BASE_DIR)/services/monitoring/grafana/assets/shared; \
79+
cp -r $(shell dirname ${REPO_CONFIG_LOCATION})/assets/grafana/* $(REPO_BASE_DIR)/services/monitoring/grafana/assets/shared/;

services/monitoring/pgsql_query_exporter_config.yaml.j2

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -15,7 +15,7 @@ metrics:{% for _gid in MONITORING_PROMETHEUS_PGSQL_GID_MONITORED.split(",") if _
1515
osparc_total_number_of_successful_payment_transactions:
1616
type: gauge
1717
description: Total number of successful payment transactions
18-
osparc_total_number_of_dollars_paid:
18+
osparc_total_number_of_dollars_paid_successfully:
1919
type: gauge
2020
description: Total number of dollars paid successfully
2121
osparc_total_number_of_credits_purchased_successfully:
@@ -58,7 +58,7 @@ queries:{% for _gid in MONITORING_PROMETHEUS_PGSQL_GID_MONITORED.split(",") if _
5858
query_total_number_of_dollars_paid_successfully:
5959
interval: 55
6060
databases: [postgres]
61-
metrics: [osparc_total_number_of_dollars_paid]
61+
metrics: [osparc_total_number_of_dollars_paid_successfully]
6262
sql: |
6363
SELECT SUM(price_dollars) as osparc_total_number_of_dollars_paid_successfully
6464
FROM payments_transactions WHERE state = 'SUCCESS';

services/simcore/docker-compose.deploy.aws.yml

Lines changed: 15 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,6 @@ services:
33
volumes:
44
- /docker/volumes/:/docker/volumes/
55

6-
76
dask-sidecar:
87
deploy:
98
placement:
@@ -24,6 +23,7 @@ services:
2423
postgres:
2524
deploy:
2625
replicas: 0
26+
2727
traefik:
2828
command:
2929
- "--api=true"
@@ -52,7 +52,7 @@ services:
5252
- "--entryPoints.traefik_monitor.address=:8080"
5353
- "--entryPoints.traefik_monitor.forwardedHeaders.insecure"
5454
- "--providers.swarm.endpoint=unix:///var/run/docker.sock"
55-
- "--providers.swarm.network=${SWARM_STACK_NAME}_default" # https://github.com/traefik/traefik/issues/7886
55+
- "--providers.swarm.network=${SWARM_STACK_NAME}_default" # https://github.com/traefik/traefik/issues/7886
5656
- "--providers.swarm.refreshSeconds=1"
5757
- "--providers.swarm.exposedByDefault=false"
5858
- "--providers.swarm.constraints=Label(`io.simcore.zone`, `${TRAEFIK_SIMCORE_ZONE}`)"
@@ -73,9 +73,17 @@ services:
7373
deploy:
7474
replicas: 3
7575

76+
rabbit:
77+
deploy:
78+
labels:
79+
- traefik.tcp.services.rabbit.loadBalancer.server.port=5672
80+
- traefik.tcp.routers.rabbit.entrypoints=rabbit
81+
- traefik.tcp.routers.rabbit.tls=false
82+
- traefik.tcp.routers.rabbit.rule=ClientIP(`10.0.0.0/8`) || ClientIP(`172.16.0.0/12`) || ClientIP(`192.168.0.0/16`)
83+
7684
volumes:
77-
efs_volume:
78-
driver_opts:
79-
type: nfs
80-
o: addr=${EFS_DNS_NAME},rw,nfsvers=4.1,rsize=1048576,wsize=1048576,hard,timeo=600,retrans=2,noresvport
81-
device: :/
85+
efs_volume:
86+
driver_opts:
87+
type: nfs
88+
o: addr=${EFS_DNS_NAME},rw,nfsvers=4.1,rsize=1048576,wsize=1048576,hard,timeo=600,retrans=2,noresvport
89+
device: :/

services/simcore/docker-compose.yml.j2

Lines changed: 58 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -631,13 +631,13 @@ services:
631631
labels:
632632
- traefik.enable=true
633633
- traefik.docker.network=${PUBLIC_NETWORK}
634-
- traefik.http.services.${PREFIX_STACK_NAME}_rabbit.loadbalancer.server.port=15672
635-
- traefik.http.routers.${PREFIX_STACK_NAME}_rabbit.rule=Host(`${MONITORING_DOMAIN}`) && PathPrefix(`/${PREFIX_STACK_NAME}_rabbit`)
636-
- traefik.http.routers.${PREFIX_STACK_NAME}_rabbit.entrypoints=https
637-
- traefik.http.routers.${PREFIX_STACK_NAME}_rabbit.tls=true
638-
- traefik.http.middlewares.${PREFIX_STACK_NAME}_rabbit_replace_regex.replacepathregex.regex=^/${PREFIX_STACK_NAME}_rabbit/(.*)$$
639-
- traefik.http.middlewares.${PREFIX_STACK_NAME}_rabbit_replace_regex.replacepathregex.replacement=/$${1}
640-
- traefik.http.routers.${PREFIX_STACK_NAME}_rabbit.middlewares=${PREFIX_STACK_NAME}_rabbit_replace_regex@swarm, ops_gzip@swarm
634+
- traefik.http.services.${PREFIX_STACK_NAME}_rabbit_console.loadbalancer.server.port=15672
635+
- traefik.http.routers.${PREFIX_STACK_NAME}_rabbit_console.rule=Host(`${MONITORING_DOMAIN}`) && PathPrefix(`/${PREFIX_STACK_NAME}_rabbit`)
636+
- traefik.http.routers.${PREFIX_STACK_NAME}_rabbit_console.entrypoints=https
637+
- traefik.http.routers.${PREFIX_STACK_NAME}_rabbit_console.tls=true
638+
- traefik.http.middlewares.${PREFIX_STACK_NAME}_rabbit_console_replace_regex.replacepathregex.regex=^/${PREFIX_STACK_NAME}_rabbit/(.*)$$
639+
- traefik.http.middlewares.${PREFIX_STACK_NAME}_rabbit_console_replace_regex.replacepathregex.replacement=/$${1}
640+
- traefik.http.routers.${PREFIX_STACK_NAME}_rabbit_console.middlewares=${PREFIX_STACK_NAME}_rabbit_console_replace_regex@swarm, ops_gzip@swarm
641641
update_config:
642642
parallelism: 2
643643
order: start-first
@@ -931,13 +931,64 @@ services:
931931
labels:
932932
- traefik.enable=true
933933
- traefik.docker.network=${PUBLIC_NETWORK}
934+
# dynamic-scheduler service
934935
- traefik.http.services.${PREFIX_STACK_NAME}_dynamic_scheduler.loadbalancer.server.port=8000
935936
- traefik.http.services.${PREFIX_STACK_NAME}_dynamic_scheduler.loadbalancer.sticky.cookie=true
936937
- traefik.http.services.${PREFIX_STACK_NAME}_dynamic_scheduler.loadbalancer.sticky.cookie.name=sticky_session
938+
# dynamic-scheduler GUI Router
937939
- traefik.http.routers.${PREFIX_STACK_NAME}_dynamic_scheduler.rule=Host(`${MONITORING_DOMAIN}`) && PathPrefix(`/dynamic-scheduler`)
938940
- traefik.http.routers.${PREFIX_STACK_NAME}_dynamic_scheduler.entrypoints=https
939941
- traefik.http.routers.${PREFIX_STACK_NAME}_dynamic_scheduler.tls=true
940942
- traefik.http.routers.${PREFIX_STACK_NAME}_dynamic_scheduler.middlewares=ops_gzip@swarm, ops_auth@swarm
943+
# dynamic-scheduler API Router
944+
- traefik.http.routers.${PREFIX_STACK_NAME}_dynamic_scheduler_api.rule=Host(`${MONITORING_DOMAIN}`) && PathPrefix(`/dynamic-scheduler/v1`)
945+
- traefik.http.routers.${PREFIX_STACK_NAME}_dynamic_scheduler_api.entrypoints=https
946+
- traefik.http.routers.${PREFIX_STACK_NAME}_dynamic_scheduler_api.tls=true
947+
- traefik.http.middlewares.dynamic_scheduler_api_replace_regex.replacepathregex.regex=^/dynamic-scheduler/v1(.*)$$
948+
- traefik.http.middlewares.dynamic_scheduler_api_replace_regex.replacepathregex.replacement=/v1$${1}
949+
- traefik.http.routers.${PREFIX_STACK_NAME}_dynamic_scheduler_api.middlewares=ops_gzip@swarm, ops_auth@swarm, dynamic_scheduler_api_replace_regex
950+
951+
notifications:
952+
networks:
953+
- monitored
954+
deploy:
955+
replicas: ${SIMCORE_NOTIFICATIONS_REPLICAS}
956+
placement:
957+
constraints:
958+
- node.labels.simcore==true
959+
update_config:
960+
parallelism: 1
961+
order: start-first
962+
failure_action: rollback
963+
delay: 10s
964+
resources:
965+
limits:
966+
memory: 500M
967+
cpus: '0.5'
968+
reservations:
969+
memory: 50M
970+
cpus: '0.1'
971+
972+
docker-api-proxy:
973+
networks:
974+
- monitored
975+
deploy:
976+
mode: global
977+
update_config:
978+
parallelism: 2
979+
order: start-first
980+
failure_action: continue
981+
delay: 10s
982+
placement:
983+
constraints:
984+
- node.role==manager
985+
resources:
986+
reservations:
987+
cpus: "0.1"
988+
memory: "256M"
989+
limits:
990+
cpus: "0.5"
991+
memory: "512M"
941992

942993
volumes:
943994
rabbit_data:

services/traefik/docker-compose.aws.yml

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -23,6 +23,7 @@ services:
2323
- "--entryPoints.https.transport.respondingTimeouts.writeTimeout=21600s" #6h, for https://github.com/traefik/traefik/issues/10805
2424
- "--entryPoints.https.transport.respondingTimeouts.readTimeout=21600s" #6h, for https://github.com/traefik/traefik/issues/10805
2525
- "--entryPoints.smtp.address=:25"
26+
- "--entryPoints.rabbit.address=:5672"
2627
- "--providers.swarm.endpoint=unix:///var/run/docker.sock"
2728
- "--providers.swarm.exposedByDefault=false"
2829
- "--core.defaultRuleSyntax=v2"
@@ -34,6 +35,10 @@ services:
3435
- "--entryPoints.https.forwardedHeaders.insecure"
3536
- "--providers.file.directory=/etc/traefik/"
3637
- "--providers.file.watch=true"
38+
ports:
39+
- target: 5672
40+
published: 5672
41+
mode: host
3742
environment:
3843
- AWS_ACCESS_KEY_ID=${ROUTE53_DNS_CHALLANGE_ACCESS_KEY}
3944
- AWS_SECRET_ACCESS_KEY=${ROUTE53_DNS_CHALLANGE_SECRET_KEY}

services/traefik/docker-compose.yml.j2

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -105,7 +105,8 @@ services:
105105
# via https://community.traefik.io/t/v2-2-8-global-redirect-www-to-non-www-with-http-to-https/7428
106106
# see also: https://community.traefik.io/t/get-a-valid-ssl-certificate-for-www-domains-via-traefik-and-lets-encrypt/2023
107107
# Global redirection: https (www.) to https
108-
- traefik.http.routers.www-catchall.rule={{ DEPLOYMENT_FQDNS_WWW_CAPTURE_TRAEFIK_RULE.strip("\"") }}
108+
# why .strip("\"'") ? --> https://github.com/kolypto/j2cli/issues/77
109+
- traefik.http.routers.www-catchall.rule={{ DEPLOYMENT_FQDNS_WWW_CAPTURE_TRAEFIK_RULE.strip("\"'") }}
109110
- traefik.http.routers.www-catchall.priority=100000
110111
- traefik.http.routers.www-catchall.entrypoints=https,http
111112
- traefik.http.routers.www-catchall.tls=true

0 commit comments

Comments
 (0)