ood_core 0.27.1 → 0.28.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c4cf552caaaedcb74de1091d8e9d1503b21f140b961ea8ccc3e53c1a25fa88f9
-  data.tar.gz: e69ec942c413e569d232ed8e88ee9a0abb79d5f3e9c7bf2d17cce7d3fe92b465
+  metadata.gz: cc94feaae3ffa1016b59b053179a18322a7e9c4ad1f937776864a2c2b19fc0a1
+  data.tar.gz: e41085ddcbbfff4a36723da314f41f1010e4db2fb28209ad781d5c2a6516cd46
 SHA512:
-  metadata.gz: 72e629a77d117b4c370947e72eddc96ebddf766eff5d0459c5291074ab22033ded29e032563e00112051d0ef122e36bf4beca3e81ff94d9f5e9cd5c6576939a8
-  data.tar.gz: 61a4b4d3208796c7b4e365307fd527b081e5eb1be3fbebe02272883a3b7efafbb45c31234300dbe517f2eadc576b3cb4dc11fd91615f706704396541984c91bd
+  metadata.gz: 85daa1b26fe2b973ecdbb3b9d2f72b37b142795f637d2db0a73611de0b4081c052b732c56e71ea7d37830bcf3211edc6c01109a2d2514b1a2500b38ac9ac6b98
+  data.tar.gz: 3a2f47afde0ac909f4d3ea6a7ccf2fcf48b8e13de94ad4e550ee1b2492cf28c7dcc72df179755b332b358f49accb72e8c229a1b506de6614148db14233e6c902

data/lib/ood_core/batch_connect/template.rb

@@ -209,9 +209,10 @@ module OodCore
                 export -f wait_until_port_used
 
                 # Generate random alphanumeric password with $1 (default: #{password_size}) characters
-                create_passwd () {
+                create_passwd () (
+                  set +o pipefail # ensure pipefail disabled, `head` closing stdin causes SIGPIPE
                   tr -cd 'a-zA-Z0-9' < /dev/urandom 2> /dev/null | head -c${1:-#{password_size}}
-                }
+                )
                 export -f create_passwd
               }
               export -f source_helpers

data/lib/ood_core/batch_connect/templates/vnc.rb

@@ -185,7 +185,7 @@ module OodCore
               # connection
               echo "Scanning VNC log file for user authentications..."
               while read -r line; do
-                if [[ ${line} =~ "Full-control authentication enabled for" ]]; then
+                if [[ ${line} =~ "Full-control authentication enabled" ]]; then
                   change_passwd
                   create_yml
                 fi

data/lib/ood_core/batch_connect/templates/vnc_container.rb

@@ -183,7 +183,7 @@ module OodCore
               # connection
               echo "Scanning VNC log file for user authentications..."
               while read -r line; do
-                if [[ ${line} =~ "Full-control authentication enabled for" ]]; then
+                if [[ ${line} =~ "Full-control authentication enabled" ]]; then
                   change_passwd
                   create_yml
                 fi

data/lib/ood_core/job/adapter.rb

@@ -57,6 +57,18 @@ module OodCore
         raise NotImplementedError, "subclass did not define #info_all"
       end
 
+      # Retrieve historic info for all completed jobs from the resource manager.
+      # This depends on the data retention configuration of the resource manager.
+      # @abstract Subclass is expected to implement {#info_historic}
+      # @raise [NotImplementedError] if subclass did not define {#info_historic}
+      #
+      # @param opts [#to_h] options to filter jobs in the resource manager.
+      #
+      # @return [Array<Info>] information describing the jobs
+      def info_historic(opts: {})
+        raise NotImplementedError, "subclass did not define #info_historic"
+      end
+
       # Retrieve info for all jobs for a given owner or owners from the
       # resource manager
       # @param owner [#to_s, Array<#to_s>] the owner(s) of the jobs

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

@@ -0,0 +1,170 @@
+require "ood_core/refinements/hash_extensions"
+require "json"
+
+# Utility class for the Coder adapter to interact with the Coders API.
+class OodCore::Job::Adapters::Coder::Batch
+  require_relative "coder_job_info"
+  class Error < StandardError; end
+  def initialize(config)
+    @host = config[:host]
+    @token = config[:token]
+  end
+
+  def get_os_app_credentials(username, project_id)
+    credentials_file = File.read("/home/#{username}/application_credentials.json")
+    credentials = JSON.parse(credentials_file)
+    credentials.find { |cred| cred["project_id"] == project_id }
+  end
+
+  def get_rich_parameters(coder_parameters, project_id, os_app_credentials)
+    rich_parameter_values = [
+      { name: "application_credential_name", value: os_app_credentials["name"] },
+      { name: "application_credential_id", value: os_app_credentials["id"] },
+      { name: "application_credential_secret", value: os_app_credentials["secret"] },
+      {name: "project_id", value: project_id }
+    ]
+    if coder_parameters
+      coder_parameters.each do |key, value|
+        rich_parameter_values << { name: key, value: value.to_s}
+      end
+    end
+    rich_parameter_values
+  end
+
+  def get_headers(coder_token)
+    {
+      'Content-Type' => 'application/json',
+      'Accept' => 'application/json',
+      'Coder-Session-Token' => coder_token
+    }
+  end
+
+  def submit(script)
+    org_id = script.native[:org_id]
+    project_id = script.native[:project_id]
+    coder_parameters = script.native[:coder_parameters]
+    endpoint = "https://#{@host}/api/v2/organizations/#{org_id}/members/#{username}/workspaces"
+    os_app_credentials = get_os_app_credentials(username, project_id)
+    headers = get_headers(@token)
+    body = {
+      template_id: script.native[:template_id],
+      template_version_name: script.native[:template_version_name],
+      name: "#{username}-#{script.native[:workspace_name]}-#{rand(2_821_109_907_456).to_s(36)}",
+      rich_parameter_values: get_rich_parameters(coder_parameters, project_id, os_app_credentials),
+    }
+
+    resp = api_call('post', endpoint, headers, body)
+    resp["id"]
+  end
+
+  def delete(id)
+    endpoint = "https://#{@host}/api/v2/workspaces/#{id}/builds"
+    headers = get_headers(@token)
+    body = {
+      'orphan' => false,
+      'transition' => 'delete'
+    }
+    res = api_call('post', endpoint, headers, body)
+  end
+
+  def info(id)
+    endpoint = "https://#{@host}/api/v2/workspaces/#{id}?include_deleted=true"
+    headers = get_headers(@token)
+    workspace_info_from_json(api_call('get', endpoint, headers))
+  end
+
+  def coder_state_to_ood_status(coder_state)
+    case coder_state
+    when "starting"
+      "queued"
+    when "failed"
+      "suspended"
+    when "running"
+      "running"
+    when "deleted"
+      "completed"
+    when "stopped"
+      "completed"
+    else
+      "undetermined"
+    end
+  end
+
+  def build_coder_job_info(json_data, status)
+    coder_output_metadata = json_data["latest_build"]["resources"]
+    &.find { |resource| resource["name"] == "coder_output" }
+    &.dig("metadata")
+    coder_output_hash = coder_output_metadata&.map { |meta| [meta["key"].to_sym, meta["value"]] }&.to_h || {}
+    OodCore::Job::Adapters::Coder::CoderJobInfo.new(**{
+      id: json_data["id"],
+      job_name: json_data["workspace_name"],
+      status: OodCore::Job::Status.new(state: status),
+      job_owner: json_data["workspace_owner_name"],
+      submission_time: json_data["created_at"],
+      dispatch_time: json_data.dig("updated_at"),
+      wallclock_time: wallclock_time(json_data, status),
+      ood_connection_info: { host: coder_output_hash[:floating_ip], port: 80 },
+      native: coder_output_hash
+  })
+  end
+
+  def wallclock_time(json_data, status)
+    start_time = start_time(json_data) 
+    end_time = end_time(json_data, status)
+    end_time - start_time
+  end  
+
+  def start_time(json_data)
+    start_time_string = json_data.dig("updated_at")
+    DateTime.parse(start_time_string).to_time.to_i
+  end 
+ 
+  def end_time(json_data, status)
+    if status == 'deleted'
+      end_time_string = json_data["latest_build"].dig("updated_at") 
+      et = DateTime.parse(end_time_string).to_time.to_i
+    else
+      et = DateTime.now.to_time.to_i
+    end
+    et
+  end
+
+  def workspace_info_from_json(json_data)
+    state = json_data.dig("latest_build", "status") || json_data.dig("latest_build", "job", "status")
+    status = coder_state_to_ood_status(state)
+    build_coder_job_info(json_data, status)
+  end
+
+  def api_call(method, endpoint, headers, body = nil)
+    uri = URI(endpoint)
+
+    case method.downcase
+    when 'get'
+      request = Net::HTTP::Get.new(uri, headers)
+    when 'post'
+      request = Net::HTTP::Post.new(uri, headers)
+    when 'delete'
+      request = Net::HTTP::Delete.new(uri, headers)
+    else
+      raise ArgumentError, "Invalid HTTP method: #{method}"
+    end
+
+    request.body = body.to_json if body
+
+    response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: uri.scheme == 'https') do |http|
+      http.request(request)
+    end
+
+    case response
+    when Net::HTTPSuccess
+      JSON.parse(response.body)
+    else
+      raise Error, "HTTP Error: #{response.code} #{response.message}  for request #{endpoint} and body #{body}"
+    end
+  end
+
+  def username
+    @username ||= Etc.getlogin
+  end
+
+end

data/lib/ood_core/job/adapters/coder/coder_job_info.rb

@@ -0,0 +1,8 @@
+class OodCore::Job::Adapters::Coder::CoderJobInfo < OodCore::Job::Info
+    attr_reader :ood_connection_info
+  
+    def initialize(options)
+      super(**options)
+      @ood_connection_info = options[:ood_connection_info]
+    end
+  end

data/lib/ood_core/job/adapters/coder.rb

@@ -0,0 +1,120 @@
+require "ood_core/refinements/hash_extensions"
+require "ood_core/refinements/array_extensions"
+require 'net/http'
+require 'json'
+require 'etc'
+
+module OodCore
+  module Job
+    class Factory
+      using Refinements::HashExtensions
+
+      def self.build_coder(config)
+        batch = Adapters::Coder::Batch.new(config.to_h.symbolize_keys)
+        Adapters::Coder.new(batch)
+      end
+    end
+
+    module Adapters
+      attr_reader :host, :token
+
+      # The adapter class for Kubernetes.
+      class Coder < Adapter
+
+        using Refinements::ArrayExtensions
+        using Refinements::HashExtensions
+
+        require "ood_core/job/adapters/coder/batch"
+
+        attr_reader :batch
+        def initialize(batch)
+          @batch = batch
+        end
+
+        # Submit a job with the attributes defined in the job template instance
+        # @example Submit job template to cluster
+        #   solver_id = job_adapter.submit(solver_script)
+        #   #=> "1234.server"
+        # @example Submit job that depends on previous job
+        #   post_id = job_adapter.submit(
+        #     post_script,
+        #     afterok: solver_id
+        #   )
+        #   #=> "1235.server"
+        # @param script [Script] script object that describes the
+        #   script and attributes for the submitted job
+        # @param after [#to_s, Array<#to_s>] this job may be scheduled for execution
+        #   at any point after dependent jobs have started execution
+        # @param afterok [#to_s, Array<#to_s>] this job may be scheduled for
+        #   execution only after dependent jobs have terminated with no errors
+        # @param afternotok [#to_s, Array<#to_s>] this job may be scheduled for
+        #   execution only after dependent jobs have terminated with errors
+        # @param afterany [#to_s, Array<#to_s>] this job may be scheduled for
+        #   execution after dependent jobs have terminated
+        # @return [String] the job id returned after successfully submitting a job
+        def submit(script, after: [], afterok: [], afternotok: [], afterany: [])
+          raise ArgumentError, 'Must specify the script' if script.nil?
+          batch.submit(script)
+        rescue Batch::Error => e
+          raise JobAdapterError, e.message
+        end
+
+        # Retrieve info for all jobs from the resource manager
+        # @abstract Subclass is expected to implement {#info_all}
+        # @raise [NotImplementedError] if subclass did not define {#info_all}
+        # @param attrs [Array<symbol>] defaults to nil (and all attrs are provided)
+        #   This array specifies only attrs you want, in addition to id and status.
+        #   If an array, the Info object that is returned to you is not guarenteed
+        #   to have a value for any attr besides the ones specified and id and status.
+        #
+        #   For certain adapters this may speed up the response since
+        #   adapters can get by without populating the entire Info object
+        # @return [Array<Info>] information describing submitted jobs
+        def info_all(attrs: nil)
+        # TODO - implement info all for namespaces?
+          batch.method_missing(attrs: attrs)
+        rescue Batch::Error => e
+          raise JobAdapterError, e.message
+        end
+    
+        # Whether the adapter supports job arrays
+        # @return [Boolean] - assumes true; but can be overridden by adapters that
+        #   explicitly do not
+        def supports_job_arrays?
+          false
+        end
+
+        # Retrieve job info from the resource manager
+        # @abstract Subclass is expected to implement {#info}
+        # @raise [NotImplementedError] if subclass did not define {#info}
+        # @param id [#to_s] the id of the job
+        # @return [Info] information describing submitted job
+        def info(id)
+          batch.info(id.to_s)
+        rescue Batch::Error => e
+          raise JobAdapterError, e.message
+        end
+
+        # Retrieve job status from resource manager
+        # @note Optimized slightly over retrieving complete job information from server
+        # @abstract Subclass is expected to implement {#status}
+        # @raise [NotImplementedError] if subclass did not define {#status}
+        # @param id [#to_s] the id of the job
+        # @return [Status] status of job
+        def status(id)
+          info(id)["job"]["status"]
+        end
+
+        # Delete the submitted job.
+        #
+        # @param id [#to_s] the id of the job
+        # @return [void]
+        def delete(id)
+          res = batch.delete(id)
+        rescue Batch::Error => e
+          raise JobAdapterError, e.message
+        end
+      end
+    end
+  end
+end

data/lib/ood_core/job/adapters/slurm.rb

@@ -323,6 +323,46 @@ module OodCore
             }
           end
 
+          # Job info fields requested from a formatted `sacct` call
+          def sacct_info_fields
+            {
+              # The user name of the user who ran the job.
+              user: 'User',
+              # The group name of the user who ran the job.
+              group_name: 'Group',
+              # Job Id for reference
+              job_id: 'JobId',
+              # The name of the job or job step
+              job_name: 'JobName',
+              # The job's elapsed time.
+              elapsed: 'Elapsed',
+              # Minimum required memory for the job
+              req_mem: 'ReqMem',
+              # Count of allocated CPUs
+              alloc_cpus: 'AllocCPUS',
+              # Number of requested CPUs.
+              req_cpus: 'ReqCPUS',
+              # What the timelimit was/is for the job
+              time_limit: 'Timelimit',
+              # Displays the job status, or state
+              state: 'State',
+              # The sum of the SystemCPU and UserCPU time used by the job or job step
+              total_cpu: 'TotalCPU',
+              # Maximum resident set size of all tasks in job.
+              max_rss: 'MaxRSS',
+              # Identifies the partition on which the job ran.
+              partition: 'Partition',
+              # The time the job was submitted. In the same format as End.
+              submit_time: 'Submit',
+              # Initiation time of the job. In the same format as End.
+              start_time: 'Start',
+              # Termination time of the job.
+              end: 'End',
+              # Trackable resources. These are the minimum resource counts requested by the job/step at submission time.
+              gres: 'ReqTRES'
+            }
+          end
+
           def queues
             info_raw = call('scontrol', 'show', 'part', '-o')
 
@@ -357,6 +397,31 @@ module OodCore
             end.compact
           end
 
+          def sacct_info(job_ids, states, from, to, show_steps)
+            # https://slurm.schedmd.com/sacct.html
+            fields = sacct_info_fields
+            args = ['-P'] # Output will be delimited
+            args.concat ['--delimiter', UNIT_SEPARATOR]
+            args.concat ['-n'] # No header
+            args.concat ['--units', 'G'] # Memory units in GB
+            args.concat ['--allocations'] unless show_steps # Show statistics relevant to the job, not taking steps into consideration
+            args.concat ['-o', fields.values.join(',')] # Required data
+            args.concat ['--state', states.join(',')] unless states.empty? # Filter by these states
+            args.concat ['-j', job_ids.join(',')] unless job_ids.empty? # Filter by these job ids
+            args.concat ['-S', from] if from # Filter from This date
+            args.concat ['-E', to] if to # Filter until this date
+
+            jobs_info = []
+            StringIO.open(call('sacct', *args)) do |output|
+              output.each_line do |line|
+                # Replace blank values with nil
+                values = line.strip.split(UNIT_SEPARATOR).map{ |value| value.to_s.empty? ? nil : value }
+                jobs_info << Hash[fields.keys.zip(values)] unless values.empty?
+              end
+            end
+            jobs_info
+          end
+
           private
             def str_to_queue_info(line)
               hsh = line.split(' ').map do |token|
@@ -372,7 +437,11 @@ module OodCore
                                        hsh[:AllowAccounts].to_s.split(',')
                                      end
 
-              hsh[:deny_accounts] = hsh[:DenyAccounts].nil? ? [] : hsh[:DenyAccounts].to_s.split(',')
+              hsh[:deny_accounts] = if !hsh[:allow_accounts].nil?
+                                      [] # manpage says AllowAccounts negates DenyAccounts
+                                    else
+                                      hsh[:DenyAccounts].nil? ? [] : hsh[:DenyAccounts].to_s.split(',')
+                                    end
 
               hsh[:tres] = case hsh[:TRES]
                            when nil, '(null)', ''
@@ -466,8 +535,23 @@ module OodCore
           'SE' => :completed,  # SPECIAL_EXIT
           'ST' => :running,    # STOPPED
           'S'  => :suspended,  # SUSPENDED
-          'TO' => :completed,   # TIMEOUT
-          'OOM' => :completed   # OUT_OF_MEMORY
+          'TO' => :completed,  # TIMEOUT
+          'OOM' => :completed, # OUT_OF_MEMORY
+
+          'BOOT_FAIL'     => :completed,
+          'CANCELED'      => :completed,
+          'COMPLETED'     => :completed,
+          'DEADLINE'      => :completed,
+          'FAILED'        => :completed,
+          'NODE_FAIL'     => :completed,
+          'OUT_OF_MEMORY' => :completed,
+          'PENDING'       => :queued,
+          'PREEMPTED'     => :completed,
+          'RUNNING'       => :running,
+          'REQUEUED'      => :queued,
+          'REVOKED'       => :completed,
+          'SUSPENDED'     => :suspended,
+          'TIMEOUT'       => :completed,
         }
 
         # @api private
@@ -586,6 +670,45 @@ module OodCore
           raise JobAdapterError, e.message
         end
 
+        # Retrieve historic info for all completed jobs from the resource manager.
+        #
+        # Known options:
+        # job_ids [Array<#to_s>] optional list of job ids to filter the results.
+        # states [Array<#to_s>] optional list of job state codes.
+        # Selects jobs based on their state during the time period given.
+        # from [#to_s] optional date string to filter jobs in any state after the specified time.
+        # If states are provided, filter jobs in these states after this period
+        # to [#to_s] optional date string to filter jobs in any state before the specified time.
+        # If states are provided, filter jobs in these states before this period.
+        # show_steps [#Boolean] optional boolean to filter job steps from the results.
+        #
+        # @return [Array<Info>] information describing submitted jobs
+        # @see Adapter#info_historic
+        def info_historic(opts: {})
+          job_ids    = opts.fetch(:job_ids, [])
+          states     = opts.fetch(:states, [])
+          from       = opts.fetch(:from, nil)
+          to         = opts.fetch(:to, nil)
+          show_steps = opts.fetch(:show_steps, false)
+          @slurm.sacct_info(job_ids, states, from, to, show_steps).map do |v|
+            Info.new(
+              id: v[:job_id],
+              status: get_state(v[:state]),
+              job_name: v[:job_name],
+              job_owner: v[:user],
+              procs: v[:alloc_cpus],
+              queue_name: v[:partition],
+              wallclock_time: duration_in_seconds(v[:elapsed]),
+              wallclock_limit: duration_in_seconds(v[:time_limit]),
+              cpu_time: duration_in_seconds(v[:total_cpu]),
+              submission_time: parse_time(v[:submit_time]),
+              dispatch_time: parse_time(v[:start_time]),
+              native: v,
+              gpus: self.class.gpus_from_gres(v[:gres])
+            )
+          end
+        end
+
         # Retrieve job info from the resource manager
         # @param id [#to_s] the id of the job
         # @raise [JobAdapterError] if something goes wrong getting job info
@@ -718,6 +841,13 @@ module OodCore
             "%02d:%02d:%02d" % [time/3600, time/60%60, time%60]
           end
 
+        # Parse date time string ignoring unknown values returned by Slurm
+        def parse_time(date_time)
+          return nil if date_time.empty? || %w[N/A NONE UNKNOWN].include?(date_time.to_s.upcase)
+
+          Time.parse(date_time)
+        end
+
           # Convert host list string to individual nodes
           # "em082"
           # "em[014,055-056,161]"

data/lib/ood_core/version.rb

@@ -1,4 +1,4 @@
 module OodCore
   # The current version of {OodCore}
-  VERSION = "0.27.1"
+  VERSION = "0.28.0"
 end

data/ood_core.gemspec

@@ -26,7 +26,7 @@ Gem::Specification.new do |spec|
   spec.add_runtime_dependency "ffi", "~> 1.16.3"
   spec.add_runtime_dependency "rexml", "~> 3.2"
   spec.add_development_dependency "bundler", "~> 2.1"
-  spec.add_development_dependency "rake", "~> 13.2.0"
+  spec.add_development_dependency "rake", "~> 13.3.0"
   spec.add_development_dependency "rspec", "~> 3.0"
   spec.add_development_dependency "pry", "~> 0.10"
   spec.add_development_dependency "timecop", "~> 0.8"

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ood_core
 version: !ruby/object:Gem::Version
-  version: 0.27.1
+  version: 0.28.0
 platform: ruby
 authors:
 - Eric Franz
@@ -10,7 +10,7 @@ authors:
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2025-02-10 00:00:00.000000000 Z
+date: 2025-07-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ood_support
@@ -74,14 +74,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 13.2.0
+        version: 13.3.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 13.2.0
+        version: 13.3.0
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -204,6 +204,9 @@ files:
 - lib/ood_core/job/account_info.rb
 - lib/ood_core/job/adapter.rb
 - lib/ood_core/job/adapters/ccq.rb
+- lib/ood_core/job/adapters/coder.rb
+- lib/ood_core/job/adapters/coder/batch.rb
+- lib/ood_core/job/adapters/coder/coder_job_info.rb
 - lib/ood_core/job/adapters/drmaa.rb
 - lib/ood_core/job/adapters/fujitsu_tcs.rb
 - lib/ood_core/job/adapters/helper.rb