util: increase filechunkiter size to 128k
util.filechunkiter has been using a chunk size of 64k for more than 10 years,
also in years where Moore's law still was a law. It is probably ok to bump it
now and perhaps get a slight win in some cases.
Also, largefiles have been using 128k for a long time. Specifying that size
multiple times (or forgetting to do it) seems a bit stupid. Decreasing it to
64k also seems unfortunate.
Thus, we will set the default chunksize to 128k and use the default everywhere.
--- a/hgext/largefiles/lfutil.py Wed Oct 12 12:22:18 2016 +0200
+++ b/hgext/largefiles/lfutil.py Fri Oct 14 01:53:15 2016 +0200
@@ -372,7 +372,7 @@
return ''
hasher = hashlib.sha1('')
with open(file, 'rb') as fd:
- for data in util.filechunkiter(fd, 128 * 1024):
+ for data in util.filechunkiter(fd):
hasher.update(data)
return hasher.hexdigest()
--- a/hgext/largefiles/overrides.py Wed Oct 12 12:22:18 2016 +0200
+++ b/hgext/largefiles/overrides.py Fri Oct 14 01:53:15 2016 +0200
@@ -1356,7 +1356,7 @@
'downloaded') % lf)
path = lfutil.usercachepath(repo.ui, hash)
with open(path, "rb") as fpin:
- for chunk in util.filechunkiter(fpin, 128 * 1024):
+ for chunk in util.filechunkiter(fpin):
fp.write(chunk)
err = 0
return err
--- a/hgext/largefiles/proto.py Wed Oct 12 12:22:18 2016 +0200
+++ b/hgext/largefiles/proto.py Fri Oct 14 01:53:15 2016 +0200
@@ -134,7 +134,7 @@
length))
# SSH streams will block if reading more than length
- for chunk in util.filechunkiter(stream, 128 * 1024, length):
+ for chunk in util.filechunkiter(stream, limit=length):
yield chunk
# HTTP streams must hit the end to process the last empty
# chunk of Chunked-Encoding so the connection can be reused.
--- a/mercurial/util.py Wed Oct 12 12:22:18 2016 +0200
+++ b/mercurial/util.py Fri Oct 14 01:53:15 2016 +0200
@@ -1684,9 +1684,9 @@
return ''.join(buf)
-def filechunkiter(f, size=65536, limit=None):
+def filechunkiter(f, size=131072, limit=None):
"""Create a generator that produces the data in the file size
- (default 65536) bytes at a time, up to optional limit (default is
+ (default 131072) bytes at a time, up to optional limit (default is
to read all data). Chunks may be less than size bytes if the
chunk is the last chunk in the file, or the file is a socket or
some other type of file that sometimes reads less data than is
--- a/tests/test-largefiles-small-disk.t Wed Oct 12 12:22:18 2016 +0200
+++ b/tests/test-largefiles-small-disk.t Fri Oct 14 01:53:15 2016 +0200
@@ -11,7 +11,7 @@
> shutil.copyfileobj = copyfileobj
> #
> # this makes the rewritten code abort:
- > def filechunkiter(f, size=65536, limit=None):
+ > def filechunkiter(f, size=131072, limit=None):
> yield f.read(4)
> raise IOError(errno.ENOSPC, os.strerror(errno.ENOSPC))
> util.filechunkiter = filechunkiter