Parallelize file uploads in fs cp command.

NEXT_CHANGELOG.md

@@ -6,6 +6,9 @@
 
 ### CLI
 
+* Improve performance of `databricks fs cp` command by parallelizing file uploads when
+  copying directories with the `--recursive` flag.
+
 ### Bundles
 * engine/direct: Fix dependency-ordered deletion by persisting depends_on in state ([#4105](https://github.com/databricks/cli/pull/4105))
 * Pass SYSTEM_ACCESSTOKEN from env to the Terraform provider ([#4135](https://github.com/databricks/cli/pull/4135)

acceptance/cmd/fs/cp/dir-to-dir/output.txt

@@ -0,0 +1,2 @@
+localdir/file1.txt -> dbfs:/Volumes/main/default/data/uploaded-dir/file1.txt
+localdir/file2.txt -> dbfs:/Volumes/main/default/data/uploaded-dir/file2.txt

acceptance/cmd/fs/cp/dir-to-dir/script

@@ -0,0 +1,6 @@
+mkdir -p localdir
+echo -n "file1 content" > localdir/file1.txt
+echo -n "file2 content" > localdir/file2.txt
+
+# Recursive directory copy (output sorted for deterministic ordering).
+$CLI fs cp -r localdir dbfs:/Volumes/main/default/data/uploaded-dir 2>&1 | sort

acceptance/cmd/fs/cp/dir-to-dir/test.toml

@@ -0,0 +1,20 @@
+Local = true
+Cloud = false
+Ignore = ["localdir"]
+
+# Recursive copy: localdir/ -> uploaded-dir/.
+[[Server]]
+Pattern = "PUT /api/2.0/fs/directories/Volumes/main/default/data/uploaded-dir"
+Response.StatusCode = 200
+
+[[Server]]
+Pattern = "HEAD /api/2.0/fs/directories/Volumes/main/default/data/uploaded-dir"
+Response.StatusCode = 200
+
+[[Server]]
+Pattern = "PUT /api/2.0/fs/files/Volumes/main/default/data/uploaded-dir/file1.txt"
+Response.StatusCode = 200
+
+[[Server]]
+Pattern = "PUT /api/2.0/fs/files/Volumes/main/default/data/uploaded-dir/file2.txt"
+Response.StatusCode = 200

acceptance/cmd/fs/cp/file-to-dir/output.txt

@@ -0,0 +1,3 @@
+
+>>> [CLI] fs cp local.txt dbfs:/Volumes/main/default/data/mydir/
+local.txt -> dbfs:/Volumes/main/default/data/mydir/local.txt

acceptance/cmd/fs/cp/file-to-dir/script

@@ -0,0 +1,4 @@
+echo -n "hello world!" > local.txt
+
+# Copy file into a directory (trailing slash indicates directory target).
+trace $CLI fs cp local.txt dbfs:/Volumes/main/default/data/mydir/

acceptance/cmd/fs/cp/file-to-dir/test.toml

@@ -0,0 +1,12 @@
+Local = true
+Cloud = false
+Ignore = ["local.txt"]
+
+# Copy file into existing directory: local.txt -> mydir/local.txt.
+[[Server]]
+Pattern = "HEAD /api/2.0/fs/directories/Volumes/main/default/data/mydir"
+Response.StatusCode = 200
+
+[[Server]]
+Pattern = "PUT /api/2.0/fs/files/Volumes/main/default/data/mydir/local.txt"
+Response.StatusCode = 200

acceptance/cmd/fs/cp/file-to-file/output.txt

@@ -0,0 +1,7 @@
+
+>>> [CLI] fs cp local.txt dbfs:/Volumes/main/default/data/uploaded.txt
+local.txt -> dbfs:/Volumes/main/default/data/uploaded.txt
+
+>>> [CLI] fs cp dbfs:/Volumes/main/default/data/remote.txt downloaded.txt
+dbfs:/Volumes/main/default/data/remote.txt -> downloaded.txt
+content from volume

acceptance/cmd/fs/cp/file-to-file/script

@@ -0,0 +1,9 @@
+echo -n "hello world!" > local.txt
+
+# Upload local file to volume.
+trace $CLI fs cp local.txt dbfs:/Volumes/main/default/data/uploaded.txt
+
+# Download file from volume to local.
+trace $CLI fs cp dbfs:/Volumes/main/default/data/remote.txt downloaded.txt
+
+cat downloaded.txt

acceptance/cmd/fs/cp/file-to-file/test.toml

@@ -0,0 +1,34 @@
+Local = true
+Cloud = false
+Ignore = ["local.txt", "downloaded.txt"]
+
+# Upload: local.txt -> dbfs:/Volumes/.../uploaded.txt.
+[[Server]]
+Pattern = "HEAD /api/2.0/fs/directories/Volumes/main/default/data/uploaded.txt"
+Response.StatusCode = 404
+
+[[Server]]
+Pattern = "HEAD /api/2.0/fs/files/Volumes/main/default/data/uploaded.txt"
+Response.StatusCode = 404
+
+[[Server]]
+Pattern = "HEAD /api/2.0/fs/directories/Volumes/main/default/data"
+Response.StatusCode = 200
+
+[[Server]]
+Pattern = "PUT /api/2.0/fs/files/Volumes/main/default/data/uploaded.txt"
+Response.StatusCode = 200
+
+# Download: dbfs:/Volumes/.../remote.txt -> downloaded.txt.
+[[Server]]
+Pattern = "HEAD /api/2.0/fs/directories/Volumes/main/default/data/remote.txt"
+Response.StatusCode = 404
+
+[[Server]]
+Pattern = "HEAD /api/2.0/fs/files/Volumes/main/default/data/remote.txt"
+Response.StatusCode = 200
+
+[[Server]]
+Pattern = "GET /api/2.0/fs/files/Volumes/main/default/data/remote.txt"
+Response.StatusCode = 200
+Response.Body = "content from volume"

acceptance/cmd/fs/cp/input-validation/output.txt

@@ -0,0 +1,10 @@
+
+>>> errcode [CLI] fs cp src dst --concurrency -1
+Error: --concurrency must be at least 1
+
+Exit code: 1
+
+>>> errcode [CLI] fs cp src dst --concurrency 0
+Error: --concurrency must be at least 1
+
+Exit code: 1

acceptance/cmd/fs/cp/input-validation/script

@@ -0,0 +1,3 @@
+# Invalid concurrency values should fail.
+trace errcode $CLI fs cp src dst --concurrency -1
+trace errcode $CLI fs cp src dst --concurrency 0

acceptance/cmd/fs/cp/input-validation/test.toml

@@ -0,0 +1,2 @@
+Local = true
+Cloud = false