Merge "Fix job definition for DOP backend tests"
diff --git a/jenkins/client/job/deploy/update/cloud_update.yml b/jenkins/client/job/deploy/update/cloud_update.yml
index 02cf89d..8fc84ee 100644
--- a/jenkins/client/job/deploy/update/cloud_update.yml
+++ b/jenkins/client/job/deploy/update/cloud_update.yml
@@ -55,11 +55,11 @@
             TARGET_ROLLBACKS:
               type: string
               default: ""
-              description: "Comma separated list of nodes to update (Valid values are ctl,prx,msg,dbs,log,mon,mtr,ntw,nal,gtw-virtual,cmn,rgw,cmp,kvm,osd,gtw-physical)"
+              description: "Comma separated list of nodes to rollback (Valid values are ctl,prx,msg,dbs,log,mon,mtr,ntw,nal,gtw-virtual,cmn,rgw,cmp,kvm,osd,gtw-physical)"
             TARGET_MERGES:
               type: string
               default: ""
-              description: "Comma separated list of nodes to update (Valid values are cfg,ctl,prx,msg,dbs,log,mon,mtr,ntw,nal,gtw-virtual,cmn,rgw,cid)"
+              description: "Comma separated list of nodes to merge (Valid values are cfg,ctl,prx,msg,dbs,log,mon,mtr,ntw,nal,gtw-virtual,cmn,rgw,cid)"
             CTL_TARGET:
               type: string
               default: "ctl*"
@@ -123,7 +123,7 @@
             GTW_TARGET:
               type: string
               default: "gtw01*"
-              description: "Salt targeted physical GTW nodes (ex. gtw01*)"
+              description: "Salt targeted physical or virtual GTW nodes (ex. gtw01*)"
             REBOOT:
               type: boolean
               default: 'false'
@@ -131,15 +131,15 @@
             ROLLBACK_PKG_VERSIONS:
               type: string
               default: ""
-              description: "Space separated list of pkgs=versions to rollback to (ex. pkg_name1=pkg_version1 pkg_name2=pkg_version2)"
+              description: "Space separated list of pkgs=versions to rollback to on physical targeted machines (ex. pkg_name1=pkg_version1 pkg_name2=pkg_version2)"
             PURGE_PKGS:
               type: string
               default: ""
-              description: "Space separated list of pkgs=versions to be purged (ex. pkg_name1=pkg_version1 pkg_name2=pkg_version2)"
+              description: "Space separated list of pkgs=versions to be purged on physical targeted machines (ex. pkg_name1=pkg_version1 pkg_name2=pkg_version2)"
             REMOVE_PKGS:
               type: string
               default: ""
-              description: "Space separated list of pkgs=versions to be removed (ex. pkg_name1=pkg_version1 pkg_name2=pkg_version2)"
+              description: "Space separated list of pkgs=versions to be removed on physical targeted machines (ex. pkg_name1=pkg_version1 pkg_name2=pkg_version2)"
             RESTORE_GALERA:
               type: boolean
               default: 'false'
diff --git a/jenkins/client/job/salt-models/tests.yml b/jenkins/client/job/salt-models/tests.yml
index fbc0ec1..bebc115 100644
--- a/jenkins/client/job/salt-models/tests.yml
+++ b/jenkins/client/job/salt-models/tests.yml
@@ -183,6 +183,10 @@
               RECLASS_IGNORE_CLASS_NOTFOUND:
                 type: boolean
                 default: "{{reclass_ignore_class_notfound}}"
+              RECLASS_VERSION:
+                type: string
+                default: "master"
+                description: "Version (branch) of Reclass we will use"
               LEGACY_TEST_MODE:
                 type: boolean
                 default: "{{legacy_test_mode}}"
@@ -347,6 +351,7 @@
             RECLASS_VERSION:
               type: string
               default: "master"
+              description: "Version (branch) of Reclass we will use"
             MAX_CPU_PER_JOB:
               type: string
               default: "2"
diff --git a/openssh/server/team/members/iudovichenko.yml b/openssh/server/team/members/iudovichenko.yml
new file mode 100644
index 0000000..d7e611d
--- /dev/null
+++ b/openssh/server/team/members/iudovichenko.yml
@@ -0,0 +1,20 @@
+parameters:
+  linux:
+    system:
+      user:
+        iudovichenko:
+          enabled: true
+          name: iudovichenko
+          sudo: ${_param:linux_system_user_sudo}
+          full_name: Ivan Udovichenko
+          home: /home/iudovichenko
+          email: iudovichenko@mirantis.com
+  openssh:
+    server:
+      enabled: true
+      user:
+        iudovichenko:
+          enabled: true
+          public_keys:
+            - key: ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQC1Dxt3m6w1jZjDxLJEWi2X5uXYZwpJVmfcOoXayofmxvdRyXe5OAEFZpdiPeCgwwcKZGvLjJ0/KXsoBuQw++XhdzZnE1+zaAjpB7fzkTQq4QRvEOMr3z16/AdJdYlqcZH4n3USUhahGdfhpCVDAo1YyYGDTzUH3r1DtYPAGbNiNgb7xu8H3iwp9UiI2t6kH3tx7db2wbVJ6HpnIlA1/Yj4W5j4Cz8f8MnG5oTnmZwT0hXwX/TCPyW56bHOGCAVpHINM+ZU4jUoHMUxjwd4mjMw4TIjID5b+ks91MdBhe/9IDRDrIUK2sK4h+S4ciuD6IAT637DD8/n8P6Vj8qDR0rP
+          user: ${linux:system:user:iudovichenko}
diff --git a/openssh/server/team/oscore_devops.yml b/openssh/server/team/oscore_devops.yml
index b5505a8..49207eb 100644
--- a/openssh/server/team/oscore_devops.yml
+++ b/openssh/server/team/oscore_devops.yml
@@ -3,6 +3,7 @@
 - system.openssh.server.team.members.vsaienko
 - system.openssh.server.team.members.vnogin
 - system.openssh.server.team.members.mkarpin
+- system.openssh.server.team.members.iudovichenko
 parameters:
   _param:
     linux_system_user_sudo: true
diff --git a/prometheus/server/alert/etcd.yml b/prometheus/server/alert/etcd.yml
new file mode 100644
index 0000000..9c456ab
--- /dev/null
+++ b/prometheus/server/alert/etcd.yml
@@ -0,0 +1,140 @@
+parameters:
+  prometheus:
+    server:
+        alert:
+          InsufficientMembers:
+            if: >-
+              count(up{job="etcd"} == 0) > (count(up{job="etcd"}) / 2 - 1)
+            for: 3m
+            labels:
+              severity: critical
+            annotations:
+              description: 'If one more etcd member goes down the cluster will be unavailable'
+              summary: 'etcd cluster insufficient members'
+          NoLeader:
+            if: >-
+              etcd_server_has_leader{job="etcd"} == 0
+            for: 1m
+            labels:
+              severity: critical
+            annotations:
+              description: 'etcd member {{ $labels.instance }} has no leader'
+              summary: 'etcd member has no leader'
+          HighNumberOfLeaderChanges:
+            if: >-
+              increase(etcd_server_leader_changes_seen_total{job="etcd"}[1h]) > 3
+            labels:
+              severity: warning
+            annotations:
+              description: 'etcd instance {{ $labels.instance }} has seen {{ $value }} leader changes within the last hour'
+              summary: 'a high number of leader changes within the etcd cluster are happening'
+          HighNumberOfFailedGRPCRequests:
+            if: >-
+              sum(rate(grpc_server_handled_total{grpc_code!="OK",job="etcd"}[5m])) BY (grpc_service, grpc_method) / sum(rate(grpc_server_handled_total{job="etcd"}[5m])) BY (grpc_service, grpc_method) > 0.01
+            for: 10m
+            labels:
+              severity: warning
+            annotations:
+              description: '{{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}'
+              summary: 'a high number of gRPC requests are failing'
+          HighNumberOfFailedGRPCRequests:
+            if: >-
+              sum(rate(grpc_server_handled_total{grpc_code!="OK",job="etcd"}[5m])) BY (grpc_service, grpc_method) / sum(rate(grpc_server_handled_total{job="etcd"}[5m])) BY (grpc_service, grpc_method) > 0.05
+            for: 5m
+            labels:
+              severity: critical
+            annotations:
+              description: '{{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}'
+              summary: 'a high number of gRPC requests are failing'
+          GRPCRequestsSlow:
+            if: >-
+              histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job="etcd",grpc_type="unary"}[5m])) by (grpc_service, grpc_method, le)) > 0.15
+            for: 10m
+            labels:
+              severity: critical
+            annotations:
+              description: 'on etcd instance {{ $labels.instance }} gRPC requests to {{ $labels.grpc_method }} are slow'
+              summary: 'slow gRPC requests'
+          HighNumberOfFailedHTTPRequests:
+            if: >-
+              sum(rate(etcd_http_failed_total{job="etcd"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job="etcd"}[5m])) BY (method) > 0.01
+            for: 10m
+            labels:
+              severity: warning
+            annotations:
+              description: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}'
+              summary: 'a high number of HTTP requests are failing'
+          HighNumberOfFailedHTTPRequests:
+            if: >-
+              sum(rate(etcd_http_failed_total{job="etcd"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job="etcd"}[5m])) BY (method) > 0.05
+            for: 5m
+            labels:
+              severity: critical
+            annotations:
+              description: '{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}'
+              summary: 'a high number of HTTP requests are failing'
+          HTTPRequestsSlow:
+            if: >-
+              histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[5m])) > 0.15
+            for: 10m
+            labels:
+              severity: warning
+            annotations:
+              description: 'on etcd instance {{ $labels.instance }} HTTP requests to {{ $labels.method }} are slow'
+              summary: 'slow HTTP requests'
+            record: instance:fd_utilization
+            if: >-
+              process_open_fds / process_max_fds
+          FdExhaustionClose:
+            if: >-
+              predict_linear(instance:fd_utilization[1h], 3600 * 4) > 1
+            for: 10m
+            labels:
+              severity: warning
+            annotations:
+              description: '{{ $labels.job }} instance {{ $labels.instance }} will exhaust its file descriptors soon'
+              summary: 'file descriptors soon exhausted'
+          FdExhaustionClose:
+            if: >-
+              predict_linear(instance:fd_utilization[10m], 3600) > 1
+            for: 10m
+            labels:
+              severity: critical
+            annotations:
+              description: '{{ $labels.job }} instance {{ $labels.instance }} will exhaust its file descriptors soon'
+              summary: 'file descriptors soon exhausted'
+          EtcdMemberCommunicationSlow:
+            if: >-
+              histogram_quantile(0.99, rate(etcd_network_member_round_trip_time_seconds_bucket[5m])) > 0.15
+            for: 10m
+            labels:
+              severity: warning
+            annotations:
+              description: 'etcd instance {{ $labels.instance }} member communication with {{ $labels.To }} is slow'
+              summary: 'etcd member communication is slow'
+          HighNumberOfFailedProposals:
+            if: >-
+              increase(etcd_server_proposals_failed_total{job="etcd"}[1h]) > 5
+            labels:
+              severity: warning
+            annotations:
+              description: 'etcd instance {{ $labels.instance }} has seen {{ $value }} proposal failures within the last hour'
+              summary: 'a high number of proposals within the etcd cluster are failing'
+          HighFsyncDurations:
+            if: >-
+              histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket[5m])) > 0.5
+            for: 10m
+            labels:
+              severity: warning
+            annotations:
+              description: 'etcd instance {{ $labels.instance }} fync durations are high'
+              summary: 'high fsync durations'
+          HighCommitDurations:
+            if: >-
+              histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket[5m])) > 0.25
+            for: 10m
+            labels:
+              severity: warning
+            annotations:
+              description: 'etcd instance {{ $labels.instance }} commit durations are high'
+              summary: 'high commit durations'
diff --git a/prometheus/server/target/static/etcd.yml b/prometheus/server/target/static/etcd.yml
new file mode 100644
index 0000000..61488b5
--- /dev/null
+++ b/prometheus/server/target/static/etcd.yml
@@ -0,0 +1,13 @@
+parameters:
+  _param:
+    prometheus_etcd_host: ${_param:haproxy_bind_address}
+    prometheus_etcd_port: 4001
+  prometheus:
+    server:
+      target:
+        static:
+          etcd:
+            enabled: true
+            endpoint:
+            - address: ${_param:prometheus_etcd_host}
+              port: ${_param:prometheus_etcd_port}
diff --git a/prometheus/server/target/static/kqueen.yml b/prometheus/server/target/static/kqueen.yml
new file mode 100644
index 0000000..701f4cd
--- /dev/null
+++ b/prometheus/server/target/static/kqueen.yml
@@ -0,0 +1,13 @@
+parameters:
+  _param:
+    prometheus_kqueen_api_host: ${_param:haproxy_bind_address}
+    prometheus_kqueen_api_port: 5000
+  prometheus:
+    server:
+      target:
+        static:
+          kqueen:
+            enabled: true
+            endpoint:
+            - address: ${_param:prometheus_kqueen_api_host}
+              port: ${_param:prometheus_kqueen_api_port}