threading.RLock acquire/release is very slow. A order of magnitude
higher than no reentrant threading.Lock:

"""
def RLockSpeed() :
  import time, threading
  t=time.time()
  result={}
  for i in xrange(1000000) :
    pass
  result["empty loop"]=time.time()-t
  l=threading.Lock()
  t=time.time()
  for i in xrange(1000000) :
    l.acquire()
    l.release()
  result["Lock"]=time.time()-t
  l=threading.RLock()
  t=time.time()
  for i in xrange(1000000) :
    l.acquire()
    l.release()
  result["RLock"]=time.time()-t
  return result

if __name__=="__main__" :
  print RLockSpeed()
"""

Result:
{'empty loop': 0.074212074279785156, 'RLock': 10.144084215164185,
'Lock': 1.2489800453186035}