feat(etl): report 2206

Signed-off-by: Peter Mikus <pmikus@cisco.com>
Change-Id: I159860b7da1bd03f5cdf6a35c59221c079c863b1

1 files changed, 147 insertions, 143 deletions

diff --git a/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl.hcl.tftpl b/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl.hcl.tftpl
index e0b56c1843..0cad171ab0 100644
--- a/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl.hcl.tftpl
+++ b/fdio.infra.terraform/terraform-nomad-pyspark-etl/conf/nomad/etl.hcl.tftpl
@@ -172,147 +172,151 @@ job "${job_name}" {
       }
     }
   }
-#  group "${job_name}-rls2202" {
-#    # The restart stanza configures a tasks's behavior on task failure. Restarts
-#    # happen on the client that is running the task.
-#    #
-#    # https://www.nomadproject.io/docs/job-specification/restart
-#    #
-#    restart {
-#      mode = "fail"
-#    }
-#
-#    # The constraint allows restricting the set of eligible nodes. Constraints
-#    # may filter on attributes or client metadata.
-#    #
-#    # For more information and examples on the "volume" stanza, please see
-#    # the online documentation at:
-#    #
-#    #     https://www.nomadproject.io/docs/job-specification/constraint
-#    #
-#    constraint {
-#      attribute       = "$${attr.cpu.arch}"
-#      operator        = "!="
-#      value           = "arm64"
-#    }
-#
-#    constraint {
-#      attribute      = "$${node.class}"
-#      value          = "builder"
-#    }
-#
-#    # The "task" stanza creates an individual unit of work, such as a Docker
-#    # container, web application, or batch processing.
-#    #
-#    #     https://www.nomadproject.io/docs/job-specification/task.html
-#    #
-#    task "${job_name}-coverage" {
-#      # The artifact stanza instructs Nomad to fetch and unpack a remote
-#      # resource, such as a file, tarball, or binary.
-#      #
-#      #     https://www.nomadproject.io/docs/job-specification/artifact
-#      #
-#      artifact {
-#        source      = "git::https://github.com/FDio/csit"
-#        destination = "local/csit"
-#      }
-#
-#      # The "driver" parameter specifies the task driver that should be used to
-#      # run the task.
-#      driver = "docker"
-#
-#      # The "config" stanza specifies the driver configuration, which is passed
-#      # directly to the driver to start the task. The details of configurations
-#      # are specific to each driver, so please see specific driver
-#      # documentation for more information.
-#      config {
-#        image   = "${image}"
-#        command = "gluesparksubmit"
-#        args = [
-#          "--driver-memory", "20g",
-#          "--executor-memory", "20g",
-#          "coverage_rls2202.py"
-#        ]
-#        work_dir = "/local/csit/csit.infra.etl"
-#      }
-#
-#      # The env stanza configures a list of environment variables to populate
-#      # the task's environment before starting.
-#      env {
-#        AWS_ACCESS_KEY_ID         = "${aws_access_key_id}"
-#        AWS_SECRET_ACCESS_KEY     = "${aws_secret_access_key}"
-#        AWS_DEFAULT_REGION        = "${aws_default_region}"
-#        OUT_AWS_ACCESS_KEY_ID     = "${out_aws_access_key_id}"
-#        OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}"
-#        OUT_AWS_DEFAULT_REGION    = "${out_aws_default_region}"
-#        ${ envs }
-#      }
-#
-#      # The "resources" stanza describes the requirements a task needs to
-#      # execute. Resource requirements include memory, network, cpu, and more.
-#      # This ensures the task will execute on a machine that contains enough
-#      # resource capacity.
-#      #
-#      #     https://www.nomadproject.io/docs/job-specification/resources
-#      #
-#      resources {
-#        cpu    = ${cpu}
-#        memory = ${memory}
-#      }
-#    }
-#    task "${job_name}-iterative" {
-#      # The artifact stanza instructs Nomad to fetch and unpack a remote
-#      # resource, such as a file, tarball, or binary.
-#      #
-#      #     https://www.nomadproject.io/docs/job-specification/artifact
-#      #
-#      artifact {
-#        source      = "git::https://github.com/FDio/csit"
-#        destination = "local/csit"
-#      }
-#
-#      # The "driver" parameter specifies the task driver that should be used to
-#      # run the task.
-#      driver = "docker"
-#
-#      # The "config" stanza specifies the driver configuration, which is passed
-#      # directly to the driver to start the task. The details of configurations
-#      # are specific to each driver, so please see specific driver
-#      # documentation for more information.
-#      config {
-#        image   = "${image}"
-#        command = "gluesparksubmit"
-#        args = [
-#          "--driver-memory", "20g",
-#          "--executor-memory", "20g",
-#          "iterative_rls2202.py"
-#        ]
-#        work_dir = "/local/csit/csit.infra.etl"
-#      }
-#
-#      # The env stanza configures a list of environment variables to populate
-#      # the task's environment before starting.
-#      env {
-#        AWS_ACCESS_KEY_ID         = "${aws_access_key_id}"
-#        AWS_SECRET_ACCESS_KEY     = "${aws_secret_access_key}"
-#        AWS_DEFAULT_REGION        = "${aws_default_region}"
-#        OUT_AWS_ACCESS_KEY_ID     = "${out_aws_access_key_id}"
-#        OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}"
-#        OUT_AWS_DEFAULT_REGION    = "${out_aws_default_region}"
-#        ${ envs }
-#      }
-#
-#      # The "resources" stanza describes the requirements a task needs to
-#      # execute. Resource requirements include memory, network, cpu, and more.
-#      # This ensures the task will execute on a machine that contains enough
-#      # resource capacity.
-#      #
-#      #     https://www.nomadproject.io/docs/job-specification/resources
-#      #
-#      resources {
-#        cpu    = ${cpu}
-#        memory = ${memory}
-#      }
-#    }
-#  }
+  group "${job_name}-rls2206" {
+    # The restart stanza configures a tasks's behavior on task failure. Restarts
+    # happen on the client that is running the task.
+    #
+    # https://www.nomadproject.io/docs/job-specification/restart
+    #
+    restart {
+      mode = "fail"
+    }
+
+    # The constraint allows restricting the set of eligible nodes. Constraints
+    # may filter on attributes or client metadata.
+    #
+    # For more information and examples on the "volume" stanza, please see
+    # the online documentation at:
+    #
+    #     https://www.nomadproject.io/docs/job-specification/constraint
+    #
+    constraint {
+      attribute       = "$${attr.cpu.arch}"
+      operator        = "!="
+      value           = "arm64"
+    }
+
+    constraint {
+      attribute      = "$${node.class}"
+      value          = "builder"
+    }
+
+    # The "task" stanza creates an individual unit of work, such as a Docker
+    # container, web application, or batch processing.
+    #
+    #     https://www.nomadproject.io/docs/job-specification/task.html
+    #
+    task "${job_name}-coverage" {
+      # The artifact stanza instructs Nomad to fetch and unpack a remote
+      # resource, such as a file, tarball, or binary.
+      #
+      #     https://www.nomadproject.io/docs/job-specification/artifact
+      #
+      artifact {
+        source      = "git::https://github.com/FDio/csit"
+        destination = "local/csit"
+      }
+
+      # The "driver" parameter specifies the task driver that should be used to
+      # run the task.
+      driver = "docker"
+
+      # The "config" stanza specifies the driver configuration, which is passed
+      # directly to the driver to start the task. The details of configurations
+      # are specific to each driver, so please see specific driver
+      # documentation for more information.
+      config {
+        image   = "${image}"
+        command = "gluesparksubmit"
+        args = [
+          "--driver-memory", "20g",
+          "--executor-memory", "20g",
+          "--executor-cores", "2",
+          "--master", "local[2]",
+          "coverage_rls2202.py"
+        ]
+        work_dir = "/local/csit/csit.infra.etl"
+      }
+
+      # The env stanza configures a list of environment variables to populate
+      # the task's environment before starting.
+      env {
+        AWS_ACCESS_KEY_ID         = "${aws_access_key_id}"
+        AWS_SECRET_ACCESS_KEY     = "${aws_secret_access_key}"
+        AWS_DEFAULT_REGION        = "${aws_default_region}"
+        OUT_AWS_ACCESS_KEY_ID     = "${out_aws_access_key_id}"
+        OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}"
+        OUT_AWS_DEFAULT_REGION    = "${out_aws_default_region}"
+        ${ envs }
+      }
+
+      # The "resources" stanza describes the requirements a task needs to
+      # execute. Resource requirements include memory, network, cpu, and more.
+      # This ensures the task will execute on a machine that contains enough
+      # resource capacity.
+      #
+      #     https://www.nomadproject.io/docs/job-specification/resources
+      #
+      resources {
+        cpu    = ${cpu}
+        memory = ${memory}
+      }
+    }
+    task "${job_name}-iterative" {
+      # The artifact stanza instructs Nomad to fetch and unpack a remote
+      # resource, such as a file, tarball, or binary.
+      #
+      #     https://www.nomadproject.io/docs/job-specification/artifact
+      #
+      artifact {
+        source      = "git::https://github.com/FDio/csit"
+        destination = "local/csit"
+      }
+
+      # The "driver" parameter specifies the task driver that should be used to
+      # run the task.
+      driver = "docker"
+
+      # The "config" stanza specifies the driver configuration, which is passed
+      # directly to the driver to start the task. The details of configurations
+      # are specific to each driver, so please see specific driver
+      # documentation for more information.
+      config {
+        image   = "${image}"
+        command = "gluesparksubmit"
+        args = [
+          "--driver-memory", "20g",
+          "--executor-memory", "20g",
+          "--executor-cores", "2",
+          "--master", "local[2]",
+          "iterative_rls2206.py"
+        ]
+        work_dir = "/local/csit/csit.infra.etl"
+      }
+
+      # The env stanza configures a list of environment variables to populate
+      # the task's environment before starting.
+      env {
+        AWS_ACCESS_KEY_ID         = "${aws_access_key_id}"
+        AWS_SECRET_ACCESS_KEY     = "${aws_secret_access_key}"
+        AWS_DEFAULT_REGION        = "${aws_default_region}"
+        OUT_AWS_ACCESS_KEY_ID     = "${out_aws_access_key_id}"
+        OUT_AWS_SECRET_ACCESS_KEY = "${out_aws_secret_access_key}"
+        OUT_AWS_DEFAULT_REGION    = "${out_aws_default_region}"
+        ${ envs }
+      }
+
+      # The "resources" stanza describes the requirements a task needs to
+      # execute. Resource requirements include memory, network, cpu, and more.
+      # This ensures the task will execute on a machine that contains enough
+      # resource capacity.
+      #
+      #     https://www.nomadproject.io/docs/job-specification/resources
+      #
+      resources {
+        cpu    = ${cpu}
+        memory = ${memory}
+      }
+    }
+  }
 }