# This is an example of how you can use the Google Pipelines API backend
# provider. *This is not a complete configuration file!* The
# content here should be copy pasted into the backend -> providers section
# of cromwell.example.backends/cromwell.examples.conf in the root of the repository.
# You should uncomment lines that you want to define, and read carefully to customize
# the file. If you have any questions, please open an issue at
# https://broadworkbench.atlassian.net/projects/BA/issues

# Documentation
# https://cromwell.readthedocs.io/en/stable/backends/Google/

google {
  application-name = "cromwell"
  auths = [
    {
      name = "application-default"
      scheme = "application_default"
    },
    {
      name = "service-account"
      scheme = "service_account"
      service-account-id = "<service account email>"
      json-file = "credentials.json"
    },
    {
      name = "user-service-account"
      scheme = "user_service_account"
    }
  ]
}
# Filesystems available in this Crowmell instance
# They can be enabled individually in the engine.filesystems stanza and in the config.filesystems stanza of backends
# There is a default built-in local filesytem that can also be referenced as "local" as well.
filesystems {
  gcs {
    class = "cromwell.filesystems.gcs.GcsPathBuilderFactory"
  }
}	

engine {
  filesystems {
    gcs {
      auth = "service-account"
    }
  }
}

backend {
  default = PAPIv2
  

  providers {
    PAPIv2 {
      actor-factory = "cromwell.backend.google.pipelines.v2beta.PipelinesApiLifecycleActorFactory"
      config {
        # Google project
        project = "<project-id>"

        # Base bucket for workflow executions
        root = "gs://<bucket-name>"

        # Make the name of the backend used for call caching purposes insensitive to the PAPI version.
        name-for-call-caching-purposes: PAPI

        # Emit a warning if jobs last longer than this amount of time. This might indicate that something got stuck in PAPI.
        slow-job-warning-time: 24 hours

        # Set this to the lower of the two values "Queries per 100 seconds" and "Queries per 100 seconds per user" for
        # your project.
        #
        # Used to help determine maximum throughput to the Google Genomics API. Setting this value too low will
        # cause a drop in performance. Setting this value too high will cause QPS based locks from Google.
        # 1000 is the default "Queries per 100 seconds per user", 50000 is the default "Queries per 100 seconds"
        # See https://cloud.google.com/genomics/quotas for more information
        genomics-api-queries-per-100-seconds = 1000

        # Polling for completion backs-off gradually for slower-running jobs.
        # This is the maximum polling interval (in seconds):
        maximum-polling-interval = 600

        # Optional Dockerhub Credentials. Can be used to access private docker images.
        dockerhub {
          # account = ""
          # token = ""
        }

        # Number of workers to assign to PAPI requests
        request-workers = 3

        # Optional configuration to use high security network (Virtual Private Cloud) for running jobs.
        # See https://cromwell.readthedocs.io/en/stable/backends/Google/ for more details.
        # virtual-private-cloud {
        #  network-label-key = "network-key"
        #  auth = "application-default"
        # }

        # Global pipeline timeout
        # Defaults to 7 days; max 30 days
        # pipeline-timeout = 7 days

        genomics {
          # A reference to an auth defined in the `google` stanza at the top.  This auth is used to create
          # Pipelines and manipulate auth JSONs.
          auth = "service-account"


          // alternative service account to use on the launched compute instance
          // NOTE: If combined with service account authorization, both that serivce account and this service account
          // must be able to read and write to the 'root' GCS path
          compute-service-account = "default"

          
          # Currently Cloud Life Sciences API is available now in more locations for the full list check
          # https://cloud.google.com/life-sciences/docs/concepts/locations
          location = "us-central1"

          # Endpoint for APIs. For locations other than us-central1, the endpoint needs to be updated to match the location
          # For example for "europe-west4" location the endpoint-url should be "https://europe-west4-lifesciences.googleapis.com"
          endpoint-url = "https://lifesciences.googleapis.com"

          # Restrict access to VM metadata. Useful in cases when untrusted containers are running under a service
          # account not owned by the submitting user
          restrict-metadata-access = false

          # Pipelines v2 only: specify the number of times localization and delocalization operations should be attempted
          # There is no logic to determine if the error was transient or not, everything is retried upon failure
          # Defaults to 3
          localization-attempts = 3

          # Specifies the minimum file size for `gsutil cp` to use parallel composite uploads during delocalization.
          # Parallel composite uploads can result in a significant improvement in delocalization speed for large files
          # but may introduce complexities in downloading such files from GCS, please see
          # https://cloud.google.com/storage/docs/gsutil/commands/cp#parallel-composite-uploads for more information.
          #
          # If set to 0 parallel composite uploads are turned off. The default Cromwell configuration turns off
          # parallel composite uploads, this sample configuration turns it on for files of 150M or larger.
          parallel-composite-upload-threshold="150M"
        }

        # Controls how batched requests to PAPI are handled:
        batch-requests {
          timeouts {
            # Timeout when attempting to connect to PAPI to make requests:
            # read = 10 seconds

            # Timeout waiting for batch responses from PAPI:
            #
            # Note: Try raising this value if you see errors in logs like:
            #   WARN  - PAPI request worker PAPIQueryWorker-[...] terminated. 99 run creation requests, 0 status poll requests, and 0 abort requests will be reconsidered. If any of those succeeded in the cloud before the batch request failed, they might be run twice.
            #   ERROR - Read timed out
            # connect = 10 seconds
          }
        }
        filesystems {
          gcs {
            # A reference to a potentially different auth for manipulating files via engine functions.
            auth = "service-account"
            # Google project which will be billed for the requests
            project = "<project-id>"

            caching {
              # When a cache hit is found, the following duplication strategy will be followed to use the cached outputs
              # Possible values: "copy", "reference". Defaults to "copy"
              # "copy": Copy the output files
              # "reference": DO NOT copy the output files but point to the original output files instead.
              #              Will still make sure than all the original output files exist and are accessible before
              #              going forward with the cache hit.
              duplication-strategy = "copy"
            }
          }
        }

        default-runtime-attributes {
          cpu: 1
          failOnStderr: false
          continueOnReturnCode: 0
          memory: "2048 MB"
          bootDiskSizeGb: 10
          # Allowed to be a String, or a list of Strings
          disks: "local-disk 10 SSD"
          # Worker nodes will be created without External IP address, Private Google Access needs to be enabled to access
          # GCS and Cloud NAT needs to be configured to access Internet resources such as Docker HUB
          noAddress: true
          # Update to 1 to make PVM the default choice unless over-ridden in the task runtime-attribute
          preemptible: 0
          zones: ["us-central1-b", "us-central1-a"]
        }

        include "papi_v2_reference_image_manifest.conf"
      }
    }
  }
}

webservice {
  port = 8000
  interface = 0.0.0.0
  binding-timeout = 5s
  instance.name = "cromwell"
}

akka {
  # Allow longer timeout
  # https://gatkforums.broadinstitute.org/gatk/discussion/comment/41714#Comment_41714
  http {
    server {
      request-timeout = 600s
      idle-timeout = 600s
      }
    }
  }

database {
  # mysql example
  profile = "slick.jdbc.MySQLProfile$"
  db {
    driver = "com.mysql.jdbc.Driver"
    url = "jdbc:mysql://<db-ipaddress>/cromwell?rewriteBatchedStatements=true"
    # Updte Database user if other than root
    user = "root"
    password = "<db-password>"
    connectionTimeout = 5000
  }
}