Minimally working! We can run code on a remote dask worker.

eriknw · Jul 16, 2021 · 6648f10 · 6648f10
1 parent cae3682
commit 6648f10
Show file tree

Hide file tree

Showing 7 changed files with 202 additions and 92 deletions.
diff --git a/README.md b/README.md
@@ -8,25 +8,33 @@
 > _Robert A. Heinlein_
 <hr>
 
-`afar` explores new syntax around context managers.  For example:
+`afar` allows you to run code on a remote [Dask](https://dask.org/) [worker](https://distributed.dask.org/en/latest/) using context managers.  For example:
 ```python
 import afar
-with afar.run() as results, locally:
-    x = 1
-    y = x + 1
 
->>> results.x
-1
->>> results.y
-2
-```
-Soon, we will be able to run code on a remote [dask](https://dask.org/) worker with syntax like:
-```python
-with afar.run() as result, remotely:
+with afar.run, remotely:
     import dask_cudf
     df = dask_cudf.read_parquet("s3://...")
     result = df.sum().compute()
 ```
+`result` is a [Dask Future](https://docs.dask.org/en/latest/futures.html) whose data resides on a worker.  `result.result()` is necessary to copy the data locally.
+
+By default, only the last assignment is saved.  One can specify which variables to save:
+```python
+with afar.run("a", "b"), remotely:
+    a = 1
+    b = a + 1
+```
+`a` and `b` are now both Futures.  They can be used directly in other `afar.run` contexts:
+```python
+with afar.run as data, remotely:
+    c = a + b
+
+assert c.result() == 3
+assert data["c"].result() == 3
+```
+`data` is a dictionary of variable names to Futures.  It may be necessary at times to get the data from here.
+
 For motivation, see https://github.com/dask/distributed/issues/4003
 
-### *This code is highly experimental and magical!*
+### *This code is highly experimental and magical!*
diff --git a/afar/__init__.py b/afar/__init__.py
@@ -1,5 +1,6 @@
 from .core import run, remotely, locally  # noqa
 
 from ._version import get_versions
-__version__ = get_versions()['version']
+
+__version__ = get_versions()["version"]
 del get_versions
diff --git a/afar/_version.py b/afar/_version.py
@@ -1,4 +1,3 @@
-
 # This file helps to compute a version number in source trees obtained from
 # git-archive tarball (such as those provided by githubs download-from-tag
 # feature). Distribution tarballs (built by setup.py sdist) and build
@@ -58,28 +57,32 @@ class NotThisMethod(Exception):
 
 def register_vcs_handler(vcs, method):  # decorator
     """Create decorator to mark a method as the handler of a VCS."""
+
     def decorate(f):
         """Store f in HANDLERS[vcs][method]."""
         if vcs not in HANDLERS:
             HANDLERS[vcs] = {}
         HANDLERS[vcs][method] = f
         return f
+
     return decorate
 
 
-def run_command(commands, args, cwd=None, verbose=False, hide_stderr=False,
-                env=None):
+def run_command(commands, args, cwd=None, verbose=False, hide_stderr=False, env=None):
     """Call the given command(s)."""
     assert isinstance(commands, list)
     p = None
     for c in commands:
         try:
             dispcmd = str([c] + args)
             # remember shell=False, so use git.cmd on windows, not just git
-            p = subprocess.Popen([c] + args, cwd=cwd, env=env,
-                                 stdout=subprocess.PIPE,
-                                 stderr=(subprocess.PIPE if hide_stderr
-                                         else None))
+            p = subprocess.Popen(
+                [c] + args,
+                cwd=cwd,
+                env=env,
+                stdout=subprocess.PIPE,
+                stderr=(subprocess.PIPE if hide_stderr else None),
+            )
             break
         except EnvironmentError:
             e = sys.exc_info()[1]
@@ -114,16 +117,22 @@ def versions_from_parentdir(parentdir_prefix, root, verbose):
     for i in range(3):
         dirname = os.path.basename(root)
         if dirname.startswith(parentdir_prefix):
-            return {"version": dirname[len(parentdir_prefix):],
-                    "full-revisionid": None,
-                    "dirty": False, "error": None, "date": None}
+            return {
+                "version": dirname[len(parentdir_prefix) :],
+                "full-revisionid": None,
+                "dirty": False,
+                "error": None,
+                "date": None,
+            }
         else:
             rootdirs.append(root)
             root = os.path.dirname(root)  # up a level
 
     if verbose:
-        print("Tried directories %s but none started with prefix %s" %
-              (str(rootdirs), parentdir_prefix))
+        print(
+            "Tried directories %s but none started with prefix %s"
+            % (str(rootdirs), parentdir_prefix)
+        )
     raise NotThisMethod("rootdir doesn't start with parentdir_prefix")
 
 
@@ -183,7 +192,7 @@ def git_versions_from_keywords(keywords, tag_prefix, verbose):
     # starting in git-1.8.3, tags are listed as "tag: foo-1.0" instead of
     # just "foo-1.0". If we see a "tag: " prefix, prefer those.
     TAG = "tag: "
-    tags = set([r[len(TAG):] for r in refs if r.startswith(TAG)])
+    tags = set([r[len(TAG) :] for r in refs if r.startswith(TAG)])
     if not tags:
         # Either we're using git < 1.8.3, or there really are no tags. We use
         # a heuristic: assume all version tags have a digit. The old git %d
@@ -192,27 +201,34 @@ def git_versions_from_keywords(keywords, tag_prefix, verbose):
         # between branches and tags. By ignoring refnames without digits, we
         # filter out many common branch names like "release" and
         # "stabilization", as well as "HEAD" and "master".
-        tags = set([r for r in refs if re.search(r'\d', r)])
+        tags = set([r for r in refs if re.search(r"\d", r)])
         if verbose:
             print("discarding '%s', no digits" % ",".join(refs - tags))
     if verbose:
         print("likely tags: %s" % ",".join(sorted(tags)))
     for ref in sorted(tags):
         # sorting will prefer e.g. "2.0" over "2.0rc1"
         if ref.startswith(tag_prefix):
-            r = ref[len(tag_prefix):]
+            r = ref[len(tag_prefix) :]
             if verbose:
                 print("picking %s" % r)
-            return {"version": r,
-                    "full-revisionid": keywords["full"].strip(),
-                    "dirty": False, "error": None,
-                    "date": date}
+            return {
+                "version": r,
+                "full-revisionid": keywords["full"].strip(),
+                "dirty": False,
+                "error": None,
+                "date": date,
+            }
     # no suitable tags, so version is "0+unknown", but full hex is still there
     if verbose:
         print("no suitable tags, using unknown + full revision id")
-    return {"version": "0+unknown",
-            "full-revisionid": keywords["full"].strip(),
-            "dirty": False, "error": "no suitable tags", "date": None}
+    return {
+        "version": "0+unknown",
+        "full-revisionid": keywords["full"].strip(),
+        "dirty": False,
+        "error": "no suitable tags",
+        "date": None,
+    }
 
 
 @register_vcs_handler("git", "pieces_from_vcs")
@@ -227,19 +243,19 @@ def git_pieces_from_vcs(tag_prefix, root, verbose, run_command=run_command):
     if sys.platform == "win32":
         GITS = ["git.cmd", "git.exe"]
 
-    out, rc = run_command(GITS, ["rev-parse", "--git-dir"], cwd=root,
-                          hide_stderr=True)
+    out, rc = run_command(GITS, ["rev-parse", "--git-dir"], cwd=root, hide_stderr=True)
     if rc != 0:
         if verbose:
             print("Directory %s not under git control" % root)
         raise NotThisMethod("'git rev-parse --git-dir' returned error")
 
     # if there is a tag matching tag_prefix, this yields TAG-NUM-gHEX[-dirty]
     # if there isn't one, this yields HEX[-dirty] (no NUM)
-    describe_out, rc = run_command(GITS, ["describe", "--tags", "--dirty",
-                                          "--always", "--long",
-                                          "--match", "%s*" % tag_prefix],
-                                   cwd=root)
+    describe_out, rc = run_command(
+        GITS,
+        ["describe", "--tags", "--dirty", "--always", "--long", "--match", "%s*" % tag_prefix],
+        cwd=root,
+    )
     # --long was added in git-1.5.5
     if describe_out is None:
         raise NotThisMethod("'git describe' failed")
@@ -262,17 +278,16 @@ def git_pieces_from_vcs(tag_prefix, root, verbose, run_command=run_command):
     dirty = git_describe.endswith("-dirty")
     pieces["dirty"] = dirty
     if dirty:
-        git_describe = git_describe[:git_describe.rindex("-dirty")]
+        git_describe = git_describe[: git_describe.rindex("-dirty")]
 
     # now we have TAG-NUM-gHEX or HEX
 
     if "-" in git_describe:
         # TAG-NUM-gHEX
-        mo = re.search(r'^(.+)-(\d+)-g([0-9a-f]+)$', git_describe)
+        mo = re.search(r"^(.+)-(\d+)-g([0-9a-f]+)$", git_describe)
         if not mo:
             # unparseable. Maybe git-describe is misbehaving?
-            pieces["error"] = ("unable to parse git-describe output: '%s'"
-                               % describe_out)
+            pieces["error"] = "unable to parse git-describe output: '%s'" % describe_out
             return pieces
 
         # tag
@@ -281,10 +296,9 @@ def git_pieces_from_vcs(tag_prefix, root, verbose, run_command=run_command):
             if verbose:
                 fmt = "tag '%s' doesn't start with prefix '%s'"
                 print(fmt % (full_tag, tag_prefix))
-            pieces["error"] = ("tag '%s' doesn't start with prefix '%s'"
-                               % (full_tag, tag_prefix))
+            pieces["error"] = "tag '%s' doesn't start with prefix '%s'" % (full_tag, tag_prefix)
             return pieces
-        pieces["closest-tag"] = full_tag[len(tag_prefix):]
+        pieces["closest-tag"] = full_tag[len(tag_prefix) :]
 
         # distance: number of commits since tag
         pieces["distance"] = int(mo.group(2))
@@ -295,13 +309,11 @@ def git_pieces_from_vcs(tag_prefix, root, verbose, run_command=run_command):
     else:
         # HEX: no tags
         pieces["closest-tag"] = None
-        count_out, rc = run_command(GITS, ["rev-list", "HEAD", "--count"],
-                                    cwd=root)
+        count_out, rc = run_command(GITS, ["rev-list", "HEAD", "--count"], cwd=root)
         pieces["distance"] = int(count_out)  # total number of commits
 
     # commit date: see ISO-8601 comment in git_versions_from_keywords()
-    date = run_command(GITS, ["show", "-s", "--format=%ci", "HEAD"],
-                       cwd=root)[0].strip()
+    date = run_command(GITS, ["show", "-s", "--format=%ci", "HEAD"], cwd=root)[0].strip()
     # Use only the last line.  Previous lines may contain GPG signature
     # information.
     date = date.splitlines()[-1]
@@ -335,8 +347,7 @@ def render_pep440(pieces):
                 rendered += ".dirty"
     else:
         # exception #1
-        rendered = "0+untagged.%d.g%s" % (pieces["distance"],
-                                          pieces["short"])
+        rendered = "0+untagged.%d.g%s" % (pieces["distance"], pieces["short"])
         if pieces["dirty"]:
             rendered += ".dirty"
     return rendered
@@ -450,11 +461,13 @@ def render_git_describe_long(pieces):
 def render(pieces, style):
     """Render the given version pieces into the requested style."""
     if pieces["error"]:
-        return {"version": "unknown",
-                "full-revisionid": pieces.get("long"),
-                "dirty": None,
-                "error": pieces["error"],
-                "date": None}
+        return {
+            "version": "unknown",
+            "full-revisionid": pieces.get("long"),
+            "dirty": None,
+            "error": pieces["error"],
+            "date": None,
+        }
 
     if not style or style == "default":
         style = "pep440"  # the default
@@ -474,9 +487,13 @@ def render(pieces, style):
     else:
         raise ValueError("unknown style '%s'" % style)
 
-    return {"version": rendered, "full-revisionid": pieces["long"],
-            "dirty": pieces["dirty"], "error": None,
-            "date": pieces.get("date")}
+    return {
+        "version": rendered,
+        "full-revisionid": pieces["long"],
+        "dirty": pieces["dirty"],
+        "error": None,
+        "date": pieces.get("date"),
+    }
 
 
 def get_versions():
@@ -490,8 +507,7 @@ def get_versions():
     verbose = cfg.verbose
 
     try:
-        return git_versions_from_keywords(get_keywords(), cfg.tag_prefix,
-                                          verbose)
+        return git_versions_from_keywords(get_keywords(), cfg.tag_prefix, verbose)
     except NotThisMethod:
         pass
 
@@ -500,13 +516,16 @@ def get_versions():
         # versionfile_source is the relative path from the top of the source
         # tree (where the .git directory might live) to this file. Invert
         # this to find the root from __file__.
-        for i in cfg.versionfile_source.split('/'):
+        for i in cfg.versionfile_source.split("/"):
             root = os.path.dirname(root)
     except NameError:
-        return {"version": "0+unknown", "full-revisionid": None,
-                "dirty": None,
-                "error": "unable to find root of source tree",
-                "date": None}
+        return {
+            "version": "0+unknown",
+            "full-revisionid": None,
+            "dirty": None,
+            "error": "unable to find root of source tree",
+            "date": None,
+        }
 
     try:
         pieces = git_pieces_from_vcs(cfg.tag_prefix, root, verbose)
@@ -520,6 +539,10 @@ def get_versions():
     except NotThisMethod:
         pass
 
-    return {"version": "0+unknown", "full-revisionid": None,
-            "dirty": None,
-            "error": "unable to compute version", "date": None}
+    return {
+        "version": "0+unknown",
+        "full-revisionid": None,
+        "dirty": None,
+        "error": "unable to compute version",
+        "date": None,
+    }