我正面臨以下問題。我試圖並行化一個更新文件的函數,但由於OSError: [Errno 12] Cannot allocate memory
,我無法啓動Pool()
。我已經開始在服務器上四處查看了,這並不像我使用的是舊的,弱的/不是實際的內存。 見htop
: 此外,
free -m
顯示我有足夠的可用RAM除了交換內存〜7GB: 我試圖與之合作的文件並不大任。我將在下面粘貼我的代碼(和堆棧跟蹤),那裏的大小如下:Python多處理 - 調試OSError:[Errno 12]無法分配內存
predictionmatrix
數據幀佔用了約ca. 80MB根據pandasdataframe.memory_usage()
文件geo.geojson
是2MB
我該如何去調試呢?我可以檢查什麼以及如何?感謝您提供任何提示/技巧!
代碼:
def parallelUpdateJSON(paramMatch, predictionmatrix, data):
for feature in data['features']:
currentfeature = predictionmatrix[(predictionmatrix['SId']==feature['properties']['cellId']) & paramMatch]
if (len(currentfeature) > 0):
feature['properties'].update({"style": {"opacity": currentfeature.AllActivity.item()}})
else:
feature['properties'].update({"style": {"opacity": 0}})
def writeGeoJSON(weekdaytopredict, hourtopredict, predictionmatrix):
with open('geo.geojson') as f:
data = json.load(f)
paramMatch = (predictionmatrix['Hour']==hourtopredict) & (predictionmatrix['Weekday']==weekdaytopredict)
pool = Pool()
func = partial(parallelUpdateJSON, paramMatch, predictionmatrix)
pool.map(func, data)
pool.close()
pool.join()
with open('output.geojson', 'w') as outfile:
json.dump(data, outfile)
堆棧跟蹤:
---------------------------------------------------------------------------
OSError Traceback (most recent call last)
<ipython-input-428-d6121ed2750b> in <module>()
----> 1 writeGeoJSON(6, 15, baseline)
<ipython-input-427-973b7a5a8acc> in writeGeoJSON(weekdaytopredict, hourtopredict, predictionmatrix)
14 print("Start loop")
15 paramMatch = (predictionmatrix['Hour']==hourtopredict) & (predictionmatrix['Weekday']==weekdaytopredict)
---> 16 pool = Pool(2)
17 func = partial(parallelUpdateJSON, paramMatch, predictionmatrix)
18 print(predictionmatrix.memory_usage())
/usr/lib/python3.5/multiprocessing/context.py in Pool(self, processes, initializer, initargs, maxtasksperchild)
116 from .pool import Pool
117 return Pool(processes, initializer, initargs, maxtasksperchild,
--> 118 context=self.get_context())
119
120 def RawValue(self, typecode_or_type, *args):
/usr/lib/python3.5/multiprocessing/pool.py in __init__(self, processes, initializer, initargs, maxtasksperchild, context)
166 self._processes = processes
167 self._pool = []
--> 168 self._repopulate_pool()
169
170 self._worker_handler = threading.Thread(
/usr/lib/python3.5/multiprocessing/pool.py in _repopulate_pool(self)
231 w.name = w.name.replace('Process', 'PoolWorker')
232 w.daemon = True
--> 233 w.start()
234 util.debug('added worker')
235
/usr/lib/python3.5/multiprocessing/process.py in start(self)
103 'daemonic processes are not allowed to have children'
104 _cleanup()
--> 105 self._popen = self._Popen(self)
106 self._sentinel = self._popen.sentinel
107 _children.add(self)
/usr/lib/python3.5/multiprocessing/context.py in _Popen(process_obj)
265 def _Popen(process_obj):
266 from .popen_fork import Popen
--> 267 return Popen(process_obj)
268
269 class SpawnProcess(process.BaseProcess):
/usr/lib/python3.5/multiprocessing/popen_fork.py in __init__(self, process_obj)
18 sys.stderr.flush()
19 self.returncode = None
---> 20 self._launch(process_obj)
21
22 def duplicate_for_child(self, fd):
/usr/lib/python3.5/multiprocessing/popen_fork.py in _launch(self, process_obj)
65 code = 1
66 parent_r, child_w = os.pipe()
---> 67 self.pid = os.fork()
68 if self.pid == 0:
69 try:
OSError: [Errno 12] Cannot allocate memory
UPDATE
據@ robyschek的解決方案,我已經更新了我的代碼:
global g_predictionmatrix
def worker_init(predictionmatrix):
global g_predictionmatrix
g_predictionmatrix = predictionmatrix
def parallelUpdateJSON(paramMatch, data_item):
for feature in data_item['features']:
currentfeature = predictionmatrix[(predictionmatrix['SId']==feature['properties']['cellId']) & paramMatch]
if (len(currentfeature) > 0):
feature['properties'].update({"style": {"opacity": currentfeature.AllActivity.item()}})
else:
feature['properties'].update({"style": {"opacity": 0}})
def use_the_pool(data, paramMatch, predictionmatrix):
pool = Pool(initializer=worker_init, initargs=(predictionmatrix,))
func = partial(parallelUpdateJSON, paramMatch)
pool.map(func, data)
pool.close()
pool.join()
def writeGeoJSON(weekdaytopredict, hourtopredict, predictionmatrix):
with open('geo.geojson') as f:
data = json.load(f)
paramMatch = (predictionmatrix['Hour']==hourtopredict) & (predictionmatrix['Weekday']==weekdaytopredict)
use_the_pool(data, paramMatch, predictionmatrix)
with open('trentino-grid.geojson', 'w') as outfile:
json.dump(data, outfile)
我仍然遇到同樣的錯誤。另外,根據documentation,map()
應該將我的data
分成塊,所以我不認爲它應該複製我80MB的rownum時間。我可能是錯的,雖然... :) 另外我注意到,如果我使用較小的輸入(~11MB而不是80MB),我不會收到錯誤。所以我想我試圖使用太多的內存,但我無法想象它是如何從80MB到16GB的內存無法處理的。
對不起,我是懶得看的堆棧跟蹤,並沒有注意到,在'OS出現錯誤.fork'。 另外,我看了一下多處理源,發現 我關於重複'predictionmatrix'的理論只與 相關,而'Pool.imap'只有很小的'chunksize',Pool.map默認不受影響。 我刪除了我的答案。 – robyschek