Added ReCreate. Also added try catch to api eval of rpc method.

[nodemanager.git] / accounts.py

diff --git a/accounts.py b/accounts.py
index 8363e7f..47e7af5 100644 (file)
--- a/accounts.py
+++ b/accounts.py
@@ -1,12 +1,14 @@
 """Functionality common to all account classes.
 
-Each subclass of Account must provide five methods: create(),
-destroy(), configure(), start(), and stop().  In addition, it must
+Each subclass of Account must provide five methods: create() and
+destroy(), which are static; configure(), start(), and stop(), which
+are not.  configure(), which takes a record as its only argument, does
+things like set up ssh keys.  In addition, an Account subclass must
 provide static member variables SHELL, which contains the unique shell
-that it uses; and TYPE, which contains a description of the type that
-it uses.  TYPE is divided hierarchically by periods; at the moment the
-only convention is that all sliver accounts have type that begins with
-sliver.
+that it uses; and TYPE, a string that is used by the account creation
+code.  For no particular reason, TYPE is divided hierarchically by
+periods; at the moment the only convention is that all sliver accounts
+have type that begins with sliver.
 
 There are any number of race conditions that may result from the fact
 that account names are not unique over time.  Moreover, it's a bad
@@ -27,6 +29,12 @@ import logger
 import tools
 
 
+# When this variable is true, start after any ensure_created
+Startingup = False
+# Cumulative delay for starts when Startingup is true
+csd_lock = threading.Lock()
+cumstartdelay = 0
+
 # shell path -> account class association
 shell_acct_class = {}
 # account type -> account class association
@@ -42,9 +50,12 @@ def register_class(acct_class):
 name_worker_lock = threading.Lock()
 name_worker = {}
 
+def allpwents():
+    return [pw_ent for pw_ent in pwd.getpwall() if pw_ent[6] in shell_acct_class]
+
 def all():
     """Return the names of all accounts on the system with recognized shells."""
-    return [pw_ent[0] for pw_ent in pwd.getpwall() if pw_ent[6] in shell_acct_class]
+    return [pw_ent[0] for pw_ent in allpwents()]
 
 def get(name):
     """Return the worker object for a particular username.  If no such object exists, create it first."""
@@ -59,10 +70,11 @@ class Account:
     def __init__(self, rec):
         self.name = rec['name']
         self.keys = ''
+        self.initscriptchanged = False
         self.configure(rec)
 
     @staticmethod
-    def create(name): abstract
+    def create(name, vref = None): abstract
     @staticmethod
     def destroy(name): abstract
 
@@ -74,11 +86,12 @@ class Account:
             dot_ssh = '/home/%s/.ssh' % self.name
             def do_installation():
                 if not os.access(dot_ssh, os.F_OK): os.mkdir(dot_ssh)
+                os.chmod(dot_ssh, 0700)
                 tools.write_file(dot_ssh + '/authorized_keys', lambda f: f.write(new_keys))
             logger.log('%s: installing ssh keys' % self.name)
             tools.fork_as(self.name, do_installation)
 
-    def start(self): pass
+    def start(self, delay=0): pass
     def stop(self): pass
 
 
@@ -98,25 +111,33 @@ class Worker:
 
     def ensure_created(self, rec):
         """Cause the account specified by <rec> to exist if it doesn't already."""
-        self._q.put((self._ensure_created, rec.copy()))
+        self._q.put((self._ensure_created, rec.copy(), Startingup))
 
-    def _ensure_created(self, rec):
+    def _ensure_created(self, rec, startingup):
         curr_class = self._get_class()
         next_class = type_acct_class[rec['type']]
         if next_class != curr_class:
             self._destroy(curr_class)
             self._create_sem.acquire()
-            try: next_class.create(self.name)
+            try: next_class.create(self.name, rec['vref'])
             finally: self._create_sem.release()
         if not isinstance(self._acct, next_class): self._acct = next_class(rec)
         else: self._acct.configure(rec)
-        if next_class != curr_class: self._acct.start()
+        if startingup:
+            csd_lock.acquire()
+            global cumstartdelay
+            delay = cumstartdelay
+            cumstartdelay += 2
+            csd_lock.release()
+            self._acct.start(delay=delay)
+        elif next_class != curr_class or self._acct.initscriptchanged:
+            self._acct.start()
 
     def ensure_destroyed(self): self._q.put((self._ensure_destroyed,))
     def _ensure_destroyed(self): self._destroy(self._get_class())
 
-    def start(self): self._q.put((self._start,))
-    def _start(self): self._acct.start()
+    def start(self, delay=0): self._q.put((self._start, delay))
+    def _start(self, d): self._acct.start(delay=d)
 
     def stop(self): self._q.put((self._stop,))
     def _stop(self): self._acct.stop()
@@ -134,8 +155,10 @@ class Worker:
         return shell_acct_class[shell]
 
     def _run(self):
+        """Repeatedly pull commands off the queue and execute.  If memory usage becomes an issue, it might be wise to terminate after a while."""
         while True:
             try:
                 cmd = self._q.get()
                 cmd[0](*cmd[1:])
-            except: logger.log_exc()
+            except:
+                logger.log_exc(self.name)