Merge branch '2411-check-copyright'

[arvados.git] / sdk / cwl / arvados_cwl / arv-cwl-schema.yml

diff --git a/sdk/cwl/arvados_cwl/arv-cwl-schema.yml b/sdk/cwl/arvados_cwl/arv-cwl-schema.yml
index 44b1b06a1a09b11848119743f9f48f5a63e3240a..7ae2239e2e81dd4f9345e4b2a47743eb585987e9 100644 (file)
--- a/sdk/cwl/arvados_cwl/arv-cwl-schema.yml
+++ b/sdk/cwl/arvados_cwl/arv-cwl-schema.yml
@@ -1,7 +1,36 @@
+# Copyright (C) The Arvados Authors. All rights reserved.
+#
+# SPDX-License-Identifier: Apache-2.0
+
 $base: "http://arvados.org/cwl#"
+$namespaces:
+  cwl: "https://w3id.org/cwl/cwl#"
+  cwltool: "http://commonwl.org/cwltool#"
 $graph:
+- $import: https://w3id.org/cwl/CommonWorkflowLanguage.yml
+
+- name: cwltool:LoadListingRequirement
+  type: record
+  extends: cwl:ProcessRequirement
+  inVocab: false
+  fields:
+    class:
+      type: string
+      doc: "Always 'LoadListingRequirement'"
+      jsonldPredicate:
+        "_id": "@type"
+        "_type": "@vocab"
+    loadListing:
+      type:
+        - "null"
+        - type: enum
+          name: LoadListingEnum
+          symbols: [no_listing, shallow_listing, deep_listing]
+
 - name: RunInSingleContainer
   type: record
+  extends: cwl:ProcessRequirement
+  inVocab: false
   doc: |
     Indicates that a subworkflow should run in a single container
     and not be scheduled as separate steps.
@@ -13,8 +42,33 @@ $graph:
         _id: "@type"
         _type: "@vocab"
 
+- name: OutputDirType
+  type: enum
+  symbols:
+    - local_output_dir
+    - keep_output_dir
+  doc:
+    - |
+      local_output_dir: Use regular file system local to the compute node.
+      There must be sufficient local scratch space to store entire output;
+      specify this with `outdirMin` of `ResourceRequirement`.  Files are
+      batch uploaded to Keep when the process completes.  Most compatible, but
+      upload step can be time consuming for very large files.
+    - |
+      keep_output_dir: Use writable Keep mount.  Files are streamed to Keep as
+      they are written.  Does not consume local scratch space, but does consume
+      RAM for output buffers (up to 192 MiB per file simultaneously open for
+      writing.)  Best suited to processes which produce sequential output of
+      large files (non-sequential writes may produced fragmented file
+      manifests).  Supports regular files and directories, does not support
+      special files such as symlinks, hard links, named pipes, named sockets,
+      or device nodes.
+
+
 - name: RuntimeConstraints
   type: record
+  extends: cwl:ProcessRequirement
+  inVocab: false
   doc: |
     Set Arvados-specific runtime hints.
   fields:
@@ -31,9 +85,34 @@ $graph:
         MiB. Increase this to reduce cache thrashing in situations such as
         accessing multiple large (64+ MiB) files at the same time, or
         performing random access on a large file.
+    - name: outputDirType
+      type: OutputDirType?
+      doc: |
+        Preferred backing store for output staging.  If not specified, the
+        system may choose which one to use.
+
+- name: PartitionRequirement
+  type: record
+  extends: cwl:ProcessRequirement
+  inVocab: false
+  doc: |
+    Select preferred compute partitions on which to run jobs.
+  fields:
+    - name: class
+      type: string
+      doc: "Always 'arv:PartitionRequirement'"
+      jsonldPredicate:
+        _id: "@type"
+        _type: "@vocab"
+    - name: partition
+      type:
+        - string
+        - string[]
 
 - name: APIRequirement
   type: record
+  extends: cwl:ProcessRequirement
+  inVocab: false
   doc: |
     Indicates that process wants to access to the Arvados API.  Will be granted
     limited network access and have ARVADOS_API_HOST and ARVADOS_API_TOKEN set
@@ -45,3 +124,48 @@ $graph:
       jsonldPredicate:
         _id: "@type"
         _type: "@vocab"
+
+- name: IntermediateOutput
+  type: record
+  extends: cwl:ProcessRequirement
+  inVocab: false
+  doc: |
+    Specify desired handling of intermediate output collections.
+  fields:
+    class:
+      type: string
+      doc: "Always 'arv:IntermediateOutput'"
+      jsonldPredicate:
+        _id: "@type"
+        _type: "@vocab"
+    outputTTL:
+      type: int
+      doc: |
+        If the value is greater than zero, consider intermediate output
+        collections to be temporary and should be automatically
+        trashed. Temporary collections will be trashed `outputTTL` seconds
+        after creation.  A value of zero means intermediate output should be
+        retained indefinitely (this is the default behavior).
+
+        Note: arvados-cwl-runner currently does not take workflow dependencies
+        into account when setting the TTL on an intermediate output
+        collection. If the TTL is too short, it is possible for a collection to
+        be trashed before downstream steps that consume it are started.  The
+        recommended minimum value for TTL is the expected duration of the
+        entire the workflow.
+
+- name: ReuseRequirement
+  type: record
+  extends: cwl:ProcessRequirement
+  inVocab: false
+  doc: |
+    Enable/disable work reuse for current process.  Default true (work reuse enabled).
+  fields:
+    - name: class
+      type: string
+      doc: "Always 'arv:ReuseRequirement'"
+      jsonldPredicate:
+        _id: "@type"
+        _type: "@vocab"
+    - name: enableReuse
+      type: boolean