own pid-file checks

setup.py

@@ -138,6 +138,9 @@ install_requires = [
     "treq",
     "cbor2",
     "pycddl",
+
+    # for pid-file support
+    "psutil",
 ]
 
 setup_requires = [

src/allmydata/scripts/tahoe_run.py

@@ -19,6 +19,7 @@ import os, sys
 from allmydata.scripts.common import BasedirOptions
 from twisted.scripts import twistd
 from twisted.python import usage
+from twisted.python.filepath import FilePath
 from twisted.python.reflect import namedAny
 from twisted.internet.defer import maybeDeferred
 from twisted.application.service import Service
@@ -27,6 +28,11 @@ from allmydata.scripts.default_nodedir import _default_nodedir
 from allmydata.util.encodingutil import listdir_unicode, quote_local_unicode_path
 from allmydata.util.configutil import UnknownConfigError
 from allmydata.util.deferredutil import HookMixin
+from allmydata.util.pid import (
+    check_pid_process,
+    cleanup_pidfile,
+    ProcessInTheWay,
+)
 from allmydata.storage.crawler import (
     MigratePickleFileError,
 )
@@ -35,28 +41,31 @@ from allmydata.node import (
     PrivacyError,
 )
 
+
 def get_pidfile(basedir):
     """
     Returns the path to the PID file.
     :param basedir: the node's base directory
     :returns: the path to the PID file
     """
-    return os.path.join(basedir, u"twistd.pid")
+    return os.path.join(basedir, u"running.process")
+
 
 def get_pid_from_pidfile(pidfile):
     """
     Tries to read and return the PID stored in the node's PID file
-    (twistd.pid).
+
     :param pidfile: try to read this PID file
     :returns: A numeric PID on success, ``None`` if PID file absent or
               inaccessible, ``-1`` if PID file invalid.
     """
     try:
         with open(pidfile, "r") as f:
-            pid = f.read()
+            data = f.read().strip()
     except EnvironmentError:
         return None
 
+    pid, _ = data.split()
     try:
         pid = int(pid)
     except ValueError:
@@ -64,6 +73,7 @@ def get_pid_from_pidfile(pidfile):
 
     return pid
 
+
 def identify_node_type(basedir):
     """
     :return unicode: None or one of: 'client' or 'introducer'.
@@ -227,10 +237,8 @@ def run(config, runApp=twistd.runApp):
         print("%s is not a recognizable node directory" % quoted_basedir, file=err)
         return 1
 
-    twistd_args = ["--nodaemon", "--rundir", basedir]
+    # we turn off Twisted's pid-file to use our own
-    if sys.platform != "win32":
+    twistd_args = ["--pidfile", None, "--nodaemon", "--rundir", basedir]
-        pidfile = get_pidfile(basedir)
-        twistd_args.extend(["--pidfile", pidfile])
     twistd_args.extend(config.twistd_args)
     twistd_args.append("DaemonizeTahoeNode") # point at our DaemonizeTahoeNodePlugin
 
@@ -246,12 +254,16 @@ def run(config, runApp=twistd.runApp):
         return 1
     twistd_config.loadedPlugins = {"DaemonizeTahoeNode": DaemonizeTahoeNodePlugin(nodetype, basedir)}
 
-    # handle invalid PID file (twistd might not start otherwise)
+    # before we try to run, check against our pidfile -- this will
-    if sys.platform != "win32" and get_pid_from_pidfile(pidfile) == -1:
+    # raise an exception if there appears to be a running process "in
-        print("found invalid PID file in %s - deleting it" % basedir, file=err)
+    # the way"
-        os.remove(pidfile)
+    pidfile = FilePath(get_pidfile(config['basedir']))
+    try:
+        check_pid_process(pidfile)
+    except ProcessInTheWay as e:
+        print("ERROR: {}".format(e))
+        return 1
 
     # We always pass --nodaemon so twistd.runApp does not daemonize.
-    print("running node in %s" % (quoted_basedir,), file=out)
     runApp(twistd_config)
     return 0

src/allmydata/util/pid.py

@@ -0,0 +1,72 @@
+import os
+import psutil
+
+
+class ProcessInTheWay(Exception):
+    """
+    our pidfile points at a running process
+    """
+
+
+def check_pid_process(pidfile, find_process=None):
+    """
+    If another instance appears to be running already, raise an
+    exception.  Otherwise, write our PID + start time to the pidfile
+    and arrange to delete it upon exit.
+
+    :param FilePath pidfile: the file to read/write our PID from.
+
+    :param Callable find_process: None, or a custom way to get a
+        Process objet (usually for tests)
+
+    :raises ProcessInTheWay: if a running process exists at our PID
+    """
+    find_process = psutil.Process if find_process is None else find_process
+    # check if we have another instance running already
+    if pidfile.exists():
+        with pidfile.open("r") as f:
+            content = f.read().decode("utf8").strip()
+        pid, starttime = content.split()
+        pid = int(pid)
+        starttime = float(starttime)
+        try:
+            # if any other process is running at that PID, let the
+            # user decide if this is another magic-older
+            # instance. Automated programs may use the start-time to
+            # help decide this (if the PID is merely recycled, the
+            # start-time won't match).
+            proc = find_process(pid)
+            raise ProcessInTheWay(
+                "A process is already running as PID {}".format(pid)
+            )
+        except psutil.NoSuchProcess:
+            print(
+                "'{pidpath}' refers to {pid} that isn't running".format(
+                    pidpath=pidfile.path,
+                    pid=pid,
+                )
+            )
+            # nothing is running at that PID so it must be a stale file
+            pidfile.remove()
+
+    # write our PID + start-time to the pid-file
+    pid = os.getpid()
+    starttime = find_process(pid).create_time()
+    with pidfile.open("w") as f:
+        f.write("{} {}\n".format(pid, starttime).encode("utf8"))
+
+
+def cleanup_pidfile(pidfile):
+    """
+    Safely remove the given pidfile
+    """
+
+    try:
+        pidfile.remove()
+    except Exception as e:
+        print(
+            "Couldn't remove '{pidfile}': {err}.".format(
+                pidfile=pidfile.path,
+                err=e,
+            )
+        )