ood_core 0.17.0 → 0.17.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 266e24cd2e11c2c712b6128bdc3f82bf9781ae9885f8f0eb21439cb80c889c90
-  data.tar.gz: 01e682b6313468371076cdfd4ff2df2f3c06c661af9b4d7d7a65b7dcf3e2d836
+  metadata.gz: 71272779185c8dee0b38f361c14419b77a9a497d46fc74a30b31735882f2f99b
+  data.tar.gz: 827b6d710a0a31f279cc370bd00d49b2d56c3cd31d009d155ee6ad8d2967e552
 SHA512:
-  metadata.gz: 22721c9d368ec44533d93914f977576ee77786ad0926976fa24067c7f353104edd32baffac34723b730e7f711c5b7581cf4f72f6232d050c719edcfc1b3cb14f
-  data.tar.gz: 5d99a3c782aad5e420333653e51073cdb6535b7689053452da7ee7ef234292769e70d4010d751aacd4576daf531700136c2aa0ef7a2efc31edcb29e4c01c8be4
+  metadata.gz: e42c8b974608a23ac3973fd68d40042e002e61c0b5a2d17877626578b7ceb178ae94ba3881c26003a8b69800075669410b226cd12c7cfe8350ba21fdd75a9329
+  data.tar.gz: 2f149dedb64a5806626a827d43ceab368cdd1f026a789bb9ece6189596e0e7cc2a5009d98053eafdcd090c49befa688fcf8ccc1f70593635a2a3a4bf5535b0e3

data/CHANGELOG.md

@@ -7,6 +7,24 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 
 ## [Unreleased]
 
+## [0.17.1] - 6-14-2021
+
+### Fixed
+
+- Fixed [278](https://github.com/OSC/ood_core/pull/278) where unschedulable pods will now show up as
+  queued_held status.
+
+### Changed
+
+- KUBECONFIG now defaults to /dev/null in the kubernetes adapter in [292](https://github.com/OSC/ood_core/pull/292).
+
+### Added
+
+- Sites can now set `batch_connect.ssh_allow` on the cluster to disable the buttons to start
+  a shell session to compute nodes in [289](https://github.com/OSC/ood_core/pull/289).
+- `POD_PORT` is now available to jobs in the kubernetes adapter in [290](https://github.com/OSC/ood_core/pull/290).
+- Kubernetes pods now support a startProbe in [291](https://github.com/OSC/ood_core/pull/291).
+
 ## [0.17.0] - 5-26-2021
 
 ### Fixed
@@ -336,7 +354,8 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 ### Added
 - Initial release!
 
-[Unreleased]: https://github.com/OSC/ood_core/compare/v0.16.0...HEAD
+[Unreleased]: https://github.com/OSC/ood_core/compare/v0.17.1...HEAD
+[0.17.1]: https://github.com/OSC/ood_core/compare/v0.17.0...v0.17.1
 [0.17.0]: https://github.com/OSC/ood_core/compare/v0.16.1...v0.17.0
 [0.16.1]: https://github.com/OSC/ood_core/compare/v0.16.0...v0.16.1
 [0.16.0]: https://github.com/OSC/ood_core/compare/v0.15.1...v0.16.0

data/lib/ood_core/cluster.rb

@@ -148,12 +148,12 @@ module OodCore
     end
 
     # Whether this cluster supports SSH to batch connect nodes
-    # @return [Boolean] whether cluster supports SSH to batch connect node
+    # @return [Boolean, nil] whether cluster supports SSH to batch connect node
     def batch_connect_ssh_allow?
       return @batch_connect_ssh_allow if defined?(@batch_connect_ssh_allow)
-      return @batch_connect_ssh_allow = true if batch_connect_config.nil?
+      return @batch_connect_ssh_allow = nil if batch_connect_config.nil?
 
-      @batch_connect_ssh_allow = batch_connect_config.fetch(:ssh_allow, true)
+      @batch_connect_ssh_allow = batch_connect_config.fetch(:ssh_allow, nil)
     end
 
     # The comparison operator

data/lib/ood_core/job/adapters/kubernetes/batch.rb

@@ -183,6 +183,7 @@ class OodCore::Job::Adapters::Kubernetes::Batch
       HOME: home_dir,
       GROUP: group,
       GID: run_as_group,
+      KUBECONFIG: '/dev/null',
     }
   end
 

data/lib/ood_core/job/adapters/kubernetes/helper.rb

@@ -54,7 +54,8 @@ class OodCore::Job::Adapters::Kubernetes::Helper
       working_dir: container[:working_dir],
       restart_policy: container[:restart_policy],
       image_pull_policy: container[:image_pull_policy],
-      image_pull_secret: container[:image_pull_secret]
+      image_pull_secret: container[:image_pull_secret],
+      startup_probe: container[:startup_probe],
     )
   end
 
@@ -239,15 +240,21 @@ class OodCore::Job::Adapters::Kubernetes::Helper
   def submission_time(json_data)
     status = json_data.dig(:status)
     start = status.dig(:startTime)
+    creation = json_data.dig(:metadata, :creationTimestamp)
 
-    if start.nil?
+    if !creation.nil?
+      str = creation
+    elsif !start.nil?
+      str = start
+    else
       # the pod is in some pending state limbo
       conditions = status.dig(:conditions)
+      return nil if conditions.nil?
+      return nil if conditions.size == 0
       # best guess to start time is just the first condition's
       # transition time
       str = conditions[0].dig(:lastTransitionTime)
-    else
-      str = start
+      return nil if str.nil?
     end
 
     DateTime.parse(str).to_time.to_i
@@ -255,11 +262,17 @@ class OodCore::Job::Adapters::Kubernetes::Helper
 
   def pod_status_from_json(json_data)
     phase = json_data.dig(:status, :phase)
+    conditions = json_data.dig(:status, :conditions)
+    unschedulable = conditions.to_a.any? { |c| c.dig(:reason) == "Unschedulable" }
     state = case phase
             when "Running"
               "running"
             when "Pending"
-              "queued"
+              if unschedulable
+                "queued_held"
+              else
+                "queued"
+              end
             when "Failed"
               "suspended"
             when "Succeeded"

data/lib/ood_core/job/adapters/kubernetes/resources.rb

@@ -33,13 +33,36 @@ module OodCore::Job::Adapters::Kubernetes::Resources
     end
   end
 
+  class TCPProbe
+    attr_accessor :port, :initial_delay_seconds, :failure_threshold, :period_seconds
+
+    def initialize(port, data)
+      data ||= {}
+      @port = port
+      @initial_delay_seconds = data[:initial_delay_seconds] || 2
+      @failure_threshold = data[:failure_threshold] || 5
+      @period_seconds = data[:period_seconds] || 5
+    end
+
+    def to_h
+      {
+        port: port,
+        initial_delay_seconds: initial_delay_seconds,
+        failure_threshold: failure_threshold,
+        period_seconds: period_seconds,
+      }
+    end
+  end
+
   class Container
     attr_accessor :name, :image, :command, :port, :env, :memory, :cpu, :working_dir,
-                  :restart_policy, :image_pull_policy, :image_pull_secret, :supplemental_groups
+                  :restart_policy, :image_pull_policy, :image_pull_secret, :supplemental_groups,
+                  :startup_probe
 
     def initialize(
         name, image, command: [], port: nil, env: {}, memory: "4Gi", cpu: "1",
-        working_dir: "", restart_policy: "Never", image_pull_policy: nil, image_pull_secret: nil, supplemental_groups: []
+        working_dir: "", restart_policy: "Never", image_pull_policy: nil, image_pull_secret: nil, supplemental_groups: [],
+        startup_probe: {}
       )
       raise ArgumentError, "containers need valid names and images" unless name && image
 
@@ -55,6 +78,7 @@ module OodCore::Job::Adapters::Kubernetes::Resources
       @image_pull_policy = image_pull_policy.nil? ? "IfNotPresent" : image_pull_policy
       @image_pull_secret = image_pull_secret
       @supplemental_groups = supplemental_groups.nil? ? [] : supplemental_groups
+      @startup_probe = TCPProbe.new(@port, startup_probe)
     end
 
     def ==(other)
@@ -69,7 +93,8 @@ module OodCore::Job::Adapters::Kubernetes::Resources
         restart_policy == other.restart_policy &&
         image_pull_policy == other.image_pull_policy &&
         image_pull_secret == other.image_pull_secret &&
-        supplemental_groups == other.supplemental_groups
+        supplemental_groups == other.supplemental_groups &&
+        startup_probe.to_h == other.startup_probe.to_h
     end
   end
 

data/lib/ood_core/job/adapters/kubernetes/templates/pod.yml.erb

@@ -52,6 +52,10 @@ spec:
       valueFrom:
         fieldRef:
           fieldPath: metadata.namespace
+    <%- unless spec.container.port.nil? -%>
+    - name: POD_PORT
+      value: "<%= spec.container.port %>"
+    <%- end -%>
     <%- spec.container.env.each_pair do |name, value| -%>
     - name: <%= name %>
       value: "<%= value %>"
@@ -65,6 +69,12 @@ spec:
     <%- unless spec.container.port.nil? -%>
     ports:
     - containerPort: <%= spec.container.port %>
+    startupProbe:
+      tcpSocket:
+        port: <%= spec.container.startup_probe.port %>
+      initialDelaySeconds: <%= spec.container.startup_probe.initial_delay_seconds %>
+      failureThreshold: <%= spec.container.startup_probe.failure_threshold %>
+      periodSeconds: <%= spec.container.startup_probe.period_seconds %>
     <%- end -%>
     <%- if !all_mounts.empty? || (!configmap.nil? && configmap.mounts?) -%>
     volumeMounts:

data/lib/ood_core/version.rb

@@ -1,4 +1,4 @@
 module OodCore
   # The current version of {OodCore}
-  VERSION = "0.17.0"
+  VERSION = "0.17.1"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ood_core
 version: !ruby/object:Gem::Version
-  version: 0.17.0
+  version: 0.17.1
 platform: ruby
 authors:
 - Eric Franz
@@ -10,7 +10,7 @@ authors:
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2021-05-26 00:00:00.000000000 Z
+date: 2021-06-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ood_support