bpo-36050: optimize HTTPResponse.read() (GH-12698)

* No need to chunking for now.
* No need to partial read caused by EINTR for now.

diff --git a/Lib/http/client.py b/Lib/http/client.py
index 1de151c38e92f1bdda963bf098d4cd37c1a8ea7a..5a2225276b1acd630de0bcd2df249edcfa6c8d0e 100644 (file)
--- a/Lib/http/client.py
+++ b/Lib/http/client.py
@@ -105,9 +105,6 @@ globals().update(http.HTTPStatus.__members__)
 # Mapping status codes to official W3C names
 responses = {v: v.phrase for v in http.HTTPStatus.__members__.values()}
 
-# maximal amount of data to read at one time in _safe_read
-MAXAMOUNT = 1048576
-
 # maximal line length when calling readline().
 _MAXLINE = 65536
 _MAXHEADERS = 100
@@ -592,43 +589,24 @@ class HTTPResponse(io.BufferedIOBase):
             raise IncompleteRead(bytes(b[0:total_bytes]))
 
     def _safe_read(self, amt):
-        """Read the number of bytes requested, compensating for partial reads.
-
-        Normally, we have a blocking socket, but a read() can be interrupted
-        by a signal (resulting in a partial read).
-
-        Note that we cannot distinguish between EOF and an interrupt when zero
-        bytes have been read. IncompleteRead() will be raised in this
-        situation.
+        """Read the number of bytes requested.
 
         This function should be used when <amt> bytes "should" be present for
         reading. If the bytes are truly not available (due to EOF), then the
         IncompleteRead exception can be used to detect the problem.
         """
-        s = []
-        while amt > 0:
-            chunk = self.fp.read(min(amt, MAXAMOUNT))
-            if not chunk:
-                raise IncompleteRead(b''.join(s), amt)
-            s.append(chunk)
-            amt -= len(chunk)
-        return b"".join(s)
+        data = self.fp.read(amt)
+        if len(data) < amt:
+            raise IncompleteRead(data, amt-len(data))
+        return data
 
     def _safe_readinto(self, b):
         """Same as _safe_read, but for reading into a buffer."""
-        total_bytes = 0
-        mvb = memoryview(b)
-        while total_bytes < len(b):
-            if MAXAMOUNT < len(mvb):
-                temp_mvb = mvb[0:MAXAMOUNT]
-                n = self.fp.readinto(temp_mvb)
-            else:
-                n = self.fp.readinto(mvb)
-            if not n:
-                raise IncompleteRead(bytes(mvb[0:total_bytes]), len(b))
-            mvb = mvb[n:]
-            total_bytes += n
-        return total_bytes
+        amt = len(b)
+        n = self.fp.readinto(b)
+        if n < amt:
+            raise IncompleteRead(bytes(b[:n]), amt-n)
+        return n
 
     def read1(self, n=-1):
         """Read with at most one underlying system call.  If at least one

diff --git a/Misc/NEWS.d/next/Library/2019-04-05-21-29-53.bpo-36050.x9DRKE.rst b/Misc/NEWS.d/next/Library/2019-04-05-21-29-53.bpo-36050.x9DRKE.rst
new file mode 100644 (file)
index 0000000..92318f8
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2019-04-05-21-29-53.bpo-36050.x9DRKE.rst
@@ -0,0 +1,2 @@
+Optimized ``http.client.HTTPResponse.read()`` for large response. Patch by
+Inada Naoki.