Updating documentation and adding monitor verb and noun.

2019-03-22 20:50:41 -07:00 · 2019-03-22 20:50:41 -07:00 · 724fdd8799
commit 724fdd8799
parent d1097f33ac
38 changed files with 188 additions and 43 deletions
--- a/2
+++ b/2
@ -1,6 +1,8 @@
 0.0.8

 * Upgraded default timeouts and durations for sla-aware draining.
+* Added monitor verb along with hosts noun.
+* Fixed bug with monitor not using the correct default values for sla-aware drain policies.

 0.0.7

--- a/cmd/monitor.go
+++ b/cmd/monitor.go
@ -0,0 +1,59 @@
+package cmd
+
+import (
+	"strings"
+	"time"
+
+	"github.com/paypal/gorealis/v2/gen-go/apache/aurora"
+	"github.com/spf13/cobra"
+)
+
+func init() {
+	rootCmd.AddCommand(monitorCmd)
+
+	monitorCmd.AddCommand(monitorHostCmd)
+	monitorHostCmd.Flags().DurationVar(&monitorInterval, "interval", time.Second*5, "Interval at which to poll scheduler.")
+	monitorHostCmd.Flags().DurationVar(&monitorTimeout, "timeout", time.Minute*10, "Time after which the monitor will stop polling and throw an error.")
+	monitorHostCmd.Flags().StringSliceVar(&statusList, "statuses", []string{aurora.MaintenanceMode_DRAINED.String()}, "List of acceptable statuses for a host to be in. (case-insensitive) [NONE, SCHEDULED, DRAINED, DRAINING]")
+}
+
+var monitorCmd = &cobra.Command{
+	Use:   "monitor",
+	Short: "Watch for a specific state change",
+}
+
+var monitorHostCmd = &cobra.Command{
+	Use:   "hosts",
+	Short: "Watch a host maintenance status until it enters one of the desired statuses.",
+	Long: `Provide a list of hosts to monitor for desired statuses. Statuses may be passed using the --statuses
+flag with a list of comma separated statuses. Statuses include [NONE, SCHEDULED, DRAINED, DRAINING]`,
+	PreRun: func(cmd *cobra.Command, args []string) {
+		// Manually initializing default values for this command as the default value for shared variables will
+		// be dependent on the order in which all commands were initialized
+		monitorTimeout = time.Minute * 10
+		monitorInterval = time.Second * 5
+	},
+	Run: monitorHost,
+}
+
+func monitorHost(cmd *cobra.Command, args []string) {
+	maintenanceModes := make([]aurora.MaintenanceMode, 0)
+
+	for _, status := range statusList {
+		mode, err := aurora.MaintenanceModeFromString(strings.ToUpper(status))
+		if err != nil {
+			log.Fatal(err)
+		}
+
+		maintenanceModes = append(maintenanceModes, mode)
+	}
+
+	log.Println(monitorTimeout)
+	log.Println(monitorInterval)
+	hostResult, err := client.HostMaintenanceMonitor(args, maintenanceModes, monitorInterval, monitorTimeout)
+
+	maintenanceMonitorPrint(hostResult, maintenanceModes)
+	if err != nil {
+		log.Fatalf("error: %+v", err)
+	}
+}
--- a/debian/changelog
+++ b/debian/changelog
@ -2,6 +2,8 @@ australis (0.0.8) unstable; urgency=medium

  * Upgraded default timeouts and durations for sla-aware draining.
  * Added ability for controlling when an SLA-Aware drain sheds SLA awareness for SLA-aware drain policies
+  * Added monitor verb along with hosts noun.
+  * Fixed bug with monitor not using the correct default values for sla-aware drain policies.

 -- Renan DelValle <renanidelvalle@gmail.com>  Fri, 22 Mar 2019 15:10:00 -0700

--- a/docs/australis.md
+++ b/docs/australis.md
@ -31,9 +31,10 @@ A light-weight command line client for use with Apache Aurora built using goreal
 * [australis fetch](australis_fetch.md)	 - Fetch information from Aurora
 * [australis force](australis_force.md)	 - Force the scheduler to do a snapshot, a backup, or a task reconciliation.
 * [australis kill](australis_kill.md)	 - Kill an Aurora Job
+* [australis monitor](australis_monitor.md)	 - Watch for a specific state change
 * [australis rollback](australis_rollback.md)	 - rollback an operation such as an Update
 * [australis set](australis_set.md)	 - Set a value in the Aurora Scheduler.
 * [australis start](australis_start.md)	 - Start a service, maintenance on a host (DRAIN), a snapshot, or a backup.
 * [australis stop](australis_stop.md)	 - Stop a service or maintenance on a host (DRAIN).

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_autocomplete.md
+++ b/docs/australis_autocomplete.md
@ -44,4 +44,4 @@ australis autocomplete [flags]

 * [australis](australis.md)	 - australis is a client for Apache Aurora

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_create.md
+++ b/docs/australis_create.md
@ -36,4 +36,4 @@ australis create [flags]

 * [australis](australis.md)	 - australis is a client for Apache Aurora

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_docs.md
+++ b/docs/australis_docs.md
@ -36,4 +36,4 @@ australis docs [flags]

 * [australis](australis.md)	 - australis is a client for Apache Aurora

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_fetch.md
+++ b/docs/australis_fetch.md
@ -36,4 +36,4 @@ Fetch information from Aurora
 * [australis fetch status](australis_fetch_status.md)	 - Fetch the maintenance status of a node from Aurora
 * [australis fetch task](australis_fetch_task.md)	 - Task information from Aurora

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_fetch_jobs.md
+++ b/docs/australis_fetch_jobs.md
@ -37,4 +37,4 @@ australis fetch jobs [flags]

 * [australis fetch](australis_fetch.md)	 - Fetch information from Aurora

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_fetch_leader.md
+++ b/docs/australis_fetch_leader.md
@ -38,4 +38,4 @@ australis fetch leader [zkNode0, zkNode1, ...zkNodeN] [flags]

 * [australis fetch](australis_fetch.md)	 - Fetch information from Aurora

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_fetch_status.md
+++ b/docs/australis_fetch_status.md
@ -36,4 +36,4 @@ australis fetch status [flags]

 * [australis fetch](australis_fetch.md)	 - Fetch information from Aurora

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_fetch_task.md
+++ b/docs/australis_fetch_task.md
@ -34,4 +34,4 @@ Task information from Aurora
 * [australis fetch task config](australis_fetch_task_config.md)	 - Fetch a list of task configurations from Aurora.
 * [australis fetch task status](australis_fetch_task_status.md)	 - Fetch task status for a Job key.

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_fetch_task_config.md
+++ b/docs/australis_fetch_task_config.md
@ -39,4 +39,4 @@ australis fetch task config [flags]

 * [australis fetch task](australis_fetch_task.md)	 - Task information from Aurora

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_fetch_task_status.md
+++ b/docs/australis_fetch_task_status.md
@ -39,4 +39,4 @@ australis fetch task status [flags]

 * [australis fetch task](australis_fetch_task.md)	 - Task information from Aurora

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_force.md
+++ b/docs/australis_force.md
@ -35,4 +35,4 @@ Force the scheduler to do a snapshot, a backup, or a task reconciliation.
 * [australis force recon](australis_force_recon.md)	 - Force the leading scheduler to perform a reconciliation.
 * [australis force snapshot](australis_force_snapshot.md)	 - Force the leading scheduler to perform a Snapshot.

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_force_backup.md
+++ b/docs/australis_force_backup.md
@ -37,4 +37,4 @@ australis force backup [flags]

 * [australis force](australis_force.md)	 - Force the scheduler to do a snapshot, a backup, or a task reconciliation.

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_force_recon.md
+++ b/docs/australis_force_recon.md
@ -41,4 +41,4 @@ state for all currently known non-terminal tasks.
 * [australis force recon explicit](australis_force_recon_explicit.md)	 - Force the leading scheduler to perform an explicit recon.
 * [australis force recon implicit](australis_force_recon_implicit.md)	 - Force the leading scheduler to perform an implicit recon.

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_force_recon_explicit.md
+++ b/docs/australis_force_recon_explicit.md
@ -38,4 +38,4 @@ australis force recon explicit [batch_size] [flags]

 * [australis force recon](australis_force_recon.md)	 - Force the leading scheduler to perform a reconciliation.

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_force_recon_implicit.md
+++ b/docs/australis_force_recon_implicit.md
@ -37,4 +37,4 @@ australis force recon implicit [flags]

 * [australis force recon](australis_force_recon.md)	 - Force the leading scheduler to perform a reconciliation.

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_force_snapshot.md
+++ b/docs/australis_force_snapshot.md
@ -37,4 +37,4 @@ australis force snapshot [flags]

 * [australis force](australis_force.md)	 - Force the scheduler to do a snapshot, a backup, or a task reconciliation.

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_kill.md
+++ b/docs/australis_kill.md
@ -34,4 +34,4 @@ Kill an Aurora Job
 * [australis kill entire-cluster](australis_kill_entire-cluster.md)	 - Kill every task in the cluster.
 * [australis kill job](australis_kill_job.md)	 - Kill an Aurora Job

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_kill_entire-cluster.md
+++ b/docs/australis_kill_entire-cluster.md
@ -36,4 +36,4 @@ australis kill entire-cluster [flags]

 * [australis kill](australis_kill.md)	 - Kill an Aurora Job

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_kill_job.md
+++ b/docs/australis_kill_job.md
@ -39,4 +39,4 @@ australis kill job [flags]

 * [australis kill](australis_kill.md)	 - Kill an Aurora Job

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_monitor.md
+++ b/docs/australis_monitor.md
@ -0,0 +1,36 @@
+## australis monitor
+
+Watch for a specific state change
+
+### Synopsis
+
+Watch for a specific state change
+
+### Options
+
+```
+  -h, --help   help for monitor
+```
+
+### Options inherited from parent commands
+
+```
+  -a, --caCertsPath string      Path where CA certificates can be found.
+  -c, --clientCert string       Client certificate to use to connect to Aurora.
+  -k, --clientKey string        Client key to use to connect to Aurora.
+      --config string           Config file to use. (default "/etc/aurora/australis.yml")
+  -l, --logLevel string         Set logging level [panic fatal error warning info debug trace]. (default "info")
+  -p, --password string         Password to use for API authentication
+  -s, --scheduler_addr string   Aurora Scheduler's address.
+  -i, --skipCertVerification    Skip CA certificate hostname verification.
+      --toJSON                  Print output in JSON format.
+  -u, --username string         Username to use for API authentication
+  -z, --zookeeper string        Zookeeper node(s) where Aurora stores information. (comma separated list)
+```
+
+### SEE ALSO
+
+* [australis](australis.md)	 - australis is a client for Apache Aurora
+* [australis monitor hosts](australis_monitor_hosts.md)	 - Watch a host maintenance status until it enters one of the desired statuses.
+
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_monitor_hosts.md
+++ b/docs/australis_monitor_hosts.md
@ -0,0 +1,43 @@
+## australis monitor hosts
+
+Watch a host maintenance status until it enters one of the desired statuses.
+
+### Synopsis
+
+Provide a list of hosts to monitor for desired statuses. Statuses may be passed using the --statuses
+flag with a list of comma separated statuses. Statuses include [NONE, SCHEDULED, DRAINED, DRAINING]
+
+```
+australis monitor hosts [flags]
+```
+
+### Options
+
+```
+  -h, --help                help for hosts
+      --interval duration   Interval at which to poll scheduler. (default 5s)
+      --statuses strings    List of acceptable statuses for a host to be in. (case-insensitive) [NONE, SCHEDULED, DRAINED, DRAINING] (default [DRAINED])
+      --timeout duration    Time after which the monitor will stop polling and throw an error. (default 10m0s)
+```
+
+### Options inherited from parent commands
+
+```
+  -a, --caCertsPath string      Path where CA certificates can be found.
+  -c, --clientCert string       Client certificate to use to connect to Aurora.
+  -k, --clientKey string        Client key to use to connect to Aurora.
+      --config string           Config file to use. (default "/etc/aurora/australis.yml")
+  -l, --logLevel string         Set logging level [panic fatal error warning info debug trace]. (default "info")
+  -p, --password string         Password to use for API authentication
+  -s, --scheduler_addr string   Aurora Scheduler's address.
+  -i, --skipCertVerification    Skip CA certificate hostname verification.
+      --toJSON                  Print output in JSON format.
+  -u, --username string         Username to use for API authentication
+  -z, --zookeeper string        Zookeeper node(s) where Aurora stores information. (comma separated list)
+```
+
+### SEE ALSO
+
+* [australis monitor](australis_monitor.md)	 - Watch for a specific state change
+
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_rollback.md
+++ b/docs/australis_rollback.md
@ -33,4 +33,4 @@ rollback an operation such as an Update
 * [australis](australis.md)	 - australis is a client for Apache Aurora
 * [australis rollback update](australis_rollback_update.md)	 - rollback an update that is currently paused

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_rollback_update.md
+++ b/docs/australis_rollback_update.md
@ -41,4 +41,4 @@ australis rollback update [flags]

 * [australis rollback](australis_rollback.md)	 - rollback an operation such as an Update

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_set.md
+++ b/docs/australis_set.md
@ -33,4 +33,4 @@ Set a value in the Aurora Scheduler.
 * [australis](australis.md)	 - australis is a client for Apache Aurora
 * [australis set quota](australis_set_quota.md)	 - Set Quota resources for a role.

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_set_quota.md
+++ b/docs/australis_set_quota.md
@ -36,4 +36,4 @@ australis set quota <role> cpu:<value> ram:<value> disk:<value> [flags]

 * [australis set](australis_set.md)	 - Set a value in the Aurora Scheduler.

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_start.md
+++ b/docs/australis_start.md
@ -35,4 +35,4 @@ Start a service, maintenance on a host (DRAIN), a snapshot, or a backup.
 * [australis start maintenance](australis_start_maintenance.md)	 - Place a list of space separated Mesos Agents into maintenance mode.
 * [australis start sla-drain](australis_start_sla-drain.md)	 - Place a list of space separated Mesos Agents into maintenance mode using SLA aware strategies.

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_start_drain.md
+++ b/docs/australis_start_drain.md
@ -41,4 +41,4 @@ australis start drain [space separated host list] [flags]

 * [australis start](australis_start.md)	 - Start a service, maintenance on a host (DRAIN), a snapshot, or a backup.

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_start_maintenance.md
+++ b/docs/australis_start_maintenance.md
@ -40,4 +40,4 @@ australis start maintenance [space separated host list] [flags]

 * [australis start](australis_start.md)	 - Start a service, maintenance on a host (DRAIN), a snapshot, or a backup.

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_start_sla-drain.md
+++ b/docs/australis_start_sla-drain.md
@ -37,4 +37,4 @@ expects a space separated list of hosts to place into maintenance mode.
 * [australis start sla-drain count](australis_start_sla-drain_count.md)	 - Place a list of space separated Mesos Agents into maintenance mode using the count SLA aware policy as a fallback.
 * [australis start sla-drain percentage](australis_start_sla-drain_percentage.md)	 - Place a list of space separated Mesos Agents into maintenance mode using the percentage SLA aware policy as a fallback.

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_start_sla-drain_count.md
+++ b/docs/australis_start_sla-drain_count.md
@ -14,11 +14,12 @@ australis start sla-drain count [space separated host list] [flags]
 ### Options

 ```
-      --count int           Instances count that should be running to meet SLA. (default 5)
-      --duration duration   Window of time from which we derive the SLA. (default 10m0s)
-  -h, --help                help for count
-      --interval duration   Interval at which to poll scheduler. (default 5s)
-      --timeout duration    Time after which the monitor will stop polling and throw an error. (default 20m0s)
+      --count int            Instances count that should be running to meet SLA. (default 5)
+      --duration RUNNING     Minimum time duration a task needs to be RUNNING to be treated as active. (default 45s)
+  -h, --help                 help for count
+      --interval duration    Interval at which to poll scheduler. (default 10s)
+      --sla-limit duration   Time limit after which SLA-Aware drain sheds SLA Awareness. (default 1h0m0s)
+      --timeout duration     Time after which the monitor will stop polling and throw an error. (default 20m0s)
 ```

 ### Options inherited from parent commands
@ -41,4 +42,4 @@ australis start sla-drain count [space separated host list] [flags]

 * [australis start sla-drain](australis_start_sla-drain.md)	 - Place a list of space separated Mesos Agents into maintenance mode using SLA aware strategies.

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_start_sla-drain_percentage.md
+++ b/docs/australis_start_sla-drain_percentage.md
@ -14,11 +14,12 @@ australis start sla-drain percentage [space separated host list] [flags]
 ### Options

 ```
-      --duration duration   Window of time from which we derive the SLA. (default 10m0s)
-  -h, --help                help for percentage
-      --interval duration   Interval at which to poll scheduler. (default 5s)
-      --percent float       Percentage of instances that should be running to meet SLA. (default 75)
-      --timeout duration    Time after which the monitor will stop polling and throw an error. (default 1m0s)
+      --duration RUNNING     Minimum time duration a task needs to be RUNNING to be treated as active. (default 45s)
+  -h, --help                 help for percentage
+      --interval duration    Interval at which to poll scheduler. (default 10s)
+      --percent float        Percentage of instances that should be running to meet SLA. (default 75)
+      --sla-limit duration   Time limit after which SLA-Aware drain sheds SLA Awareness. (default 1h0m0s)
+      --timeout duration     Time after which the monitor will stop polling and throw an error. (default 20m0s)
 ```

 ### Options inherited from parent commands
@ -41,4 +42,4 @@ australis start sla-drain percentage [space separated host list] [flags]

 * [australis start sla-drain](australis_start_sla-drain.md)	 - Place a list of space separated Mesos Agents into maintenance mode using SLA aware strategies.

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_stop.md
+++ b/docs/australis_stop.md
@ -34,4 +34,4 @@ Stop a service or maintenance on a host (DRAIN).
 * [australis stop drain](australis_stop_drain.md)	 - Stop maintenance on a host (move to NONE).
 * [australis stop update](australis_stop_update.md)	 - Stop update

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_stop_drain.md
+++ b/docs/australis_stop_drain.md
@ -38,4 +38,4 @@ australis stop drain [space separated host list] [flags]

 * [australis stop](australis_stop.md)	 - Stop a service or maintenance on a host (DRAIN).

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019
--- a/docs/australis_stop_update.md
+++ b/docs/australis_stop_update.md
@ -39,4 +39,4 @@ australis stop update [update ID] [flags]

 * [australis stop](australis_stop.md)	 - Stop a service or maintenance on a host (DRAIN).

-###### Auto generated by spf13/cobra on 21-Mar-2019
+###### Auto generated by spf13/cobra on 22-Mar-2019