Improve the memory utilization (and speed) of functools.lru_cache().

diff --git a/Lib/functools.py b/Lib/functools.py
index 092b1ab8682956e5f3c362056f8291a42425a303..66067428adc4e6d3fd96025794bf47e64c5a6059 100644 (file)
--- a/Lib/functools.py
+++ b/Lib/functools.py
@@ -12,7 +12,7 @@ __all__ = ['update_wrapper', 'wraps', 'WRAPPER_ASSIGNMENTS', 'WRAPPER_UPDATES',
            'total_ordering', 'cmp_to_key', 'lru_cache', 'reduce', 'partial']
 
 from _functools import partial, reduce
-from collections import OrderedDict, namedtuple
+from collections import namedtuple
 try:
     from _thread import allocate_lock as Lock
 except:
@@ -147,17 +147,20 @@ def lru_cache(maxsize=100, typed=False):
     # to allow the implementation to change (including a possible C version).
 
     def decorating_function(user_function,
-            *, tuple=tuple, sorted=sorted, map=map, len=len, type=type, KeyError=KeyError):
+            *, tuple=tuple, sorted=sorted, map=map, len=len, type=type):
 
+        cache = dict()
         hits = misses = 0
+        cache_get = cache.get           # bound method for fast lookup
         kwd_mark = (object(),)          # separates positional and keyword args
-        lock = Lock()                   # needed because OrderedDict isn't threadsafe
+        lock = Lock()                   # needed because linkedlist isn't threadsafe
+        root = []                       # root of circular doubly linked list
+        root[:] = [root, root, None, None]      # initialize by pointing to self
 
         if maxsize is None:
-            cache = dict()              # simple cache without ordering or size limit
-
             @wraps(user_function)
             def wrapper(*args, **kwds):
+                # simple caching without ordering or size limit
                 nonlocal hits, misses
                 key = args
                 if kwds:
@@ -167,23 +170,18 @@ def lru_cache(maxsize=100, typed=False):
                     key += tuple(map(type, args))
                     if kwds:
                         key += tuple(type(v) for k, v in sorted_items)
-                try:
-                    result = cache[key]
+                result = cache_get(key)
+                if result is not None:
                     hits += 1
                     return result
-                except KeyError:
-                    pass
                 result = user_function(*args, **kwds)
                 cache[key] = result
                 misses += 1
                 return result
         else:
-            cache = OrderedDict()           # ordered least recent to most recent
-            cache_popitem = cache.popitem
-            cache_renew = cache.move_to_end
-
             @wraps(user_function)
             def wrapper(*args, **kwds):
+                # size limited caching that tracks accesses by recency
                 nonlocal hits, misses
                 key = args
                 if kwds:
@@ -193,20 +191,33 @@ def lru_cache(maxsize=100, typed=False):
                     key += tuple(map(type, args))
                     if kwds:
                         key += tuple(type(v) for k, v in sorted_items)
+                PREV, NEXT = 0, 1               # names of link fields
                 with lock:
-                    try:
-                        result = cache[key]
-                        cache_renew(key)    # record recent use of this key
+                    link = cache_get(key)
+                    if link is not None:
+                        link = cache[key]
+                        # record recent use of the key by moving it to the front of the list
+                        link_prev, link_next, key, result = link
+                        link_prev[NEXT] = link_next
+                        link_next[PREV] = link_prev
+                        last = root[PREV]
+                        last[NEXT] = root[PREV] = link
+                        link[PREV] = last
+                        link[NEXT] = root
                         hits += 1
                         return result
-                    except KeyError:
-                        pass
                 result = user_function(*args, **kwds)
                 with lock:
-                    cache[key] = result     # record recent use of this key
-                    misses += 1
+                    last = root[PREV]
+                    link = [last, root, key, result]
+                    cache[key] = last[NEXT] = root[PREV] = link
                     if len(cache) > maxsize:
-                        cache_popitem(0)    # purge least recently used cache entry
+                        # purge least recently used cache entry
+                        old_prev, old_next, old_key, old_result = root[NEXT]
+                        root[NEXT] = old_next
+                        old_next[PREV] = root
+                        del cache[old_key]
+                    misses += 1
                 return result
 
         def cache_info():

diff --git a/Misc/NEWS b/Misc/NEWS
index 1c4c2155041e1ed4f14fc3a4b012ded651538c99..2f424e6e26e6ec0323882addf213b996c8d1ef7b 100644 (file)
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -26,6 +26,8 @@ Library
 
 - Issue #11199: Fix the with urllib which hangs on particular ftp urls.
 
+- Improve the memory utilization and speed of functools.lru_cache.
+
 - Issue #14222: Use the new time.steady() function instead of time.time() for
   timeout in queue and threading modules to not be affected of system time
   update.