使用python 看门狗文件系统事件监视库,我注意到在Windows 2003下使用时,它进入了“轮询模式”,从而停止使用异步OS通知,因此,在大量文件更改的情况下,严重降低了系统性能。
我将问题追溯到watchdog/observers/winapi.py
文件,其中使用了CancelIoEx
系统调用,以便在用户希望停止监视监视的目录或文件时停止ReadDirectoryChangesW
调用锁:
(winapi.py)
CancelIoEx = ctypes.windll.kernel32.CancelIoEx
CancelIoEx.restype = ctypes.wintypes.BOOL
CancelIoEx.errcheck = _errcheck_bool
CancelIoEx.argtypes = (
ctypes.wintypes.HANDLE, # hObject
ctypes.POINTER(OVERLAPPED) # lpOverlapped
)
...
...
...
def close_directory_handle(handle):
try:
CancelIoEx(handle, None) # force ReadDirectoryChangesW to return
except WindowsError:
return
CancelIoEx
调用的问题是直到Windows 2008:http://msdn.microsoft.com/en-us/library/windows/desktop/aa363792(v=vs.85).aspx才可用
一种可能的选择是更改close_directory_handle
,使其在受监视的目录中创建一个模拟文件,从而打开等待ReadDirectoryChangesW
返回的线程。
但是,我注意到Windows 2003中的CancelIo
系统调用是事实上是可用的:
取消由调用线程为指定文件发出的所有挂起的输入和输出(I/O)操作。该函数不会取消其他线程为文件句柄发出的I/O操作。要取消来自另一个线程的I/O操作,请使用CancelIoEx函数。
但是调用CancelIo
不会影响等待线程。
你知道如何解决这个问题吗?可以使用threading.enumerate()
,发出一个信号,由每个被这些处理程序调用的CancelIo
处理的线程处理?
发布于 2014-09-15 07:47:04
自然的方法是实现一个完成例程,并使用其重叠模式调用ReadDirectoryChangesW
。下面的示例演示了实现此操作的方法:
RDCW_CALLBACK_F = ctypes.WINFUNCTYPE(None, ctypes.wintypes.DWORD, ctypes.wintypes.DWORD, ctypes.POINTER(OVERLAPPED))
首先,创建一个WINFUNCTYPE工厂,它将用于从python方法生成类似于C的函数(可从Windows调用)。在这种情况下,没有返回值和对应于
VOID CALLBACK FileIOCompletionRoutine(
_In_ DWORD dwErrorCode,
_In_ DWORD dwNumberOfBytesTransfered,
_Inout_ LPOVERLAPPED lpOverlapped
);
FileIOCompletionRoutine标头
回调引用和重叠结构需要添加到ReadDirectoryChangesW
参数列表中:
ReadDirectoryChangesW = ctypes.windll.kernel32.ReadDirectoryChangesW
ReadDirectoryChangesW.restype = ctypes.wintypes.BOOL
ReadDirectoryChangesW.errcheck = _errcheck_bool
ReadDirectoryChangesW.argtypes = (
ctypes.wintypes.HANDLE, # hDirectory
LPVOID, # lpBuffer
ctypes.wintypes.DWORD, # nBufferLength
ctypes.wintypes.BOOL, # bWatchSubtree
ctypes.wintypes.DWORD, # dwNotifyFilter
ctypes.POINTER(ctypes.wintypes.DWORD), # lpBytesReturned
ctypes.POINTER(OVERLAPPED), # lpOverlapped
RDCW_CALLBACK_F # FileIOCompletionRoutine # lpCompletionRoutine
)
从这里开始,我们准备执行重叠的系统调用。这是一个简单的调用-- bacl只是用来测试一切是否正常:
def dir_change_callback(dwErrorCode,dwNumberOfBytesTransfered,p):
print("dir_change_callback! PID:" + str(os.getpid()))
print("CALLBACK THREAD: " + str(threading.currentThread()))
准备并执行呼叫:
event_buffer = ctypes.create_string_buffer(BUFFER_SIZE)
nbytes = ctypes.wintypes.DWORD()
overlapped_read_dir = OVERLAPPED()
call2pass = RDCW_CALLBACK_F(dir_change_callback)
hand = get_directory_handle(os.path.abspath("/test/"))
def docall():
ReadDirectoryChangesW(hand, ctypes.byref(event_buffer),
len(event_buffer), False,
WATCHDOG_FILE_NOTIFY_FLAGS,
ctypes.byref(nbytes),
ctypes.byref(overlapped_read_dir), call2pass)
print("Waiting!")
docall()
如果将所有这些代码加载并执行到DreamPie交互式shell中,则可以检查系统调用是否完成,回调是否执行,从而在c:\test
目录下完成第一次更改后打印线程和pid编号。此外,您还会注意到它们与主线程和进程相同:尽管事件是由分离的线程引发的,回调运行在与我们的主程序相同的进程和线程中,从而提供了一种不想要的行为:
lck = threading.Lock()
def dir_change_callback(dwErrorCode,dwNumberOfBytesTransfered,p):
print("dir_change_callback! PID:" + str(os.getpid()))
print("CALLBACK THREAD: " + str(threading.currentThread()))
...
...
...
lck.acquire()
print("Waiting!")
docall()
lck.acquire()
此程序将锁定主线程,回调将永远不会执行。我尝试了许多同步工具,甚至Windows信号量总是具有相同的行为,因此,最后,我决定在使用ReadDirectoryChangesW
库管理和同步的单独进程中使用multiprocessing
的同步配置来实现异步调用:
对get_directory_handle
的调用不会返回由windows提供的句柄号,而是返回一个由winapi
库管理的句柄号,为此,我实现了句柄生成器:
class FakeHandleFactory():
_hl = threading.Lock()
_next = 0
@staticmethod
def next():
FakeHandleFactory._hl.acquire()
ret = FakeHandleFactory._next
FakeHandleFactory._next += 1
FakeHandleFactory._hl.release()
return ret
每个生成的句柄必须与文件系统路径全局关联:
handle2file = {}
现在,每次对read_directory_changes
的调用都将生成ReadDirectoryRequest
(从multiprocessing.Process
派生)对象:
class ReadDirectoryRequest(multiprocessing.Process):
def _perform_and_wait4request(self, path, recursive, event_buffer, nbytes):
hdl = CreateFileW(path, FILE_LIST_DIRECTORY, WATCHDOG_FILE_SHARE_FLAGS,
None, OPEN_EXISTING, WATCHDOG_FILE_FLAGS, None)
#print("path: " + path)
aux_buffer = ctypes.create_string_buffer(BUFFER_SIZE)
aux_n = ctypes.wintypes.DWORD()
#print("_perform_and_wait4request! PID:" + str(os.getpid()))
#print("CALLBACK THREAD: " + str(threading.currentThread()) + "\n----------")
try:
ReadDirectoryChangesW(hdl, ctypes.byref(aux_buffer),
len(event_buffer), recursive,
WATCHDOG_FILE_NOTIFY_FLAGS,
ctypes.byref(aux_n), None, None)
except WindowsError as e:
print("!" + str(e))
if e.winerror == ERROR_OPERATION_ABORTED:
nbytes = 0
event_buffer = []
else:
nbytes = 0
event_buffer = []
# Python 2/3 compat
nbytes.value = aux_n.value
for i in xrange(self.int_class(aux_n.value)):
event_buffer[i] = aux_buffer[i]
CloseHandle(hdl)
try:
self.lck.release()
except:
pass
def __init__(self, handle, recursive):
buffer = ctypes.create_string_buffer(BUFFER_SIZE)
self.event_buffer = multiprocessing.Array(ctypes.c_char, buffer)
self.nbytes = multiprocessing.Value(ctypes.wintypes.DWORD, 0)
targetPath = handle2file.get(handle, None)
super(ReadDirectoryRequest, self).__init__(target=self._perform_and_wait4request, args=(targetPath, recursive, self.event_buffer, self.nbytes))
self.daemon = True
self.lck = multiprocessing.Lock()
self.result = None
try:
self.int_class = long
except NameError:
self.int_class = int
if targetPath is None:
self.result = ([], -1)
def CancelIo(self):
try:
self.result = ([], 0)
self.lck.release()
except:
pass
def read_changes(self):
#print("read_changes! PID:" + str(os.getpid()))
#print("CALLBACK THREAD: " + str(threading.currentThread()) + "\n----------")
if self.result is not None:
raise Exception("ReadDirectoryRequest object can be used only once!")
self.lck.acquire()
self.start()
self.lck.acquire()
self.result = (self.event_buffer, self.int_class(self.nbytes.value))
return self.result
该类指定Process
,提供执行系统调用并等待(或)的进程:
ReadDirectoryRequest
对象CancelIo
方法来取消请求。请注意:
角色现在负责管理请求。为此,需要线程锁和辅助数据结构:
rqIndexLck = threading.Lock() # Protects the access to `rqIndex`
rqIndex = {} # Maps handles to request objects sets.
get_directory_handle
def get_directory_handle(path):
rqIndexLck.acquire()
ret = FakeHandleFactory.next()
handle2file[ret] = path
rqIndexLck.release()
return ret
close_directory_handle
def close_directory_handle(handle):
rqIndexLck.acquire()
rqset4handle = rqIndex.get(handle, None)
if rqset4handle is not None:
for rq in rqset4handle:
rq.CancelIo()
del rqIndex[handle]
if handle in handle2file:
del handle2file[handle]
rqIndexLck.release()
最后但并非最不重要的是:read_directory_changes
def read_directory_changes(handle, recursive):
rqIndexLck.acquire()
rq = ReadDirectoryRequest(handle, recursive)
set4handle = None
if handle in rqIndex:
set4handle = rqIndex[handle]
else:
set4handle = set()
rqIndex[handle] = set4handle
set4handle.add(rq)
rqIndexLck.release()
ret = rq.read_changes()
rqIndexLck.acquire()
if rq in set4handle:
set4handle.remove(rq)
rqIndexLck.release()
return ret
https://stackoverflow.com/questions/25669139
复制相似问题