bdiff: don't check border condition in loop
This is pretty much a copy of d500ddae7494, just to a different loop.
The condition `p == plast` (`plast == a + len - 1`) was only true on
the final iteration of the loop. So it was wasteful to check for it
on every iteration. We decrease the iteration count by 1 and add an
explicit check for `p == plast` after the loop.
Again, we see modest wins.
From the mozilla-unified repository:
$ perfbdiff -m 3041e4d59df2
! wall 0.035502 comb 0.040000 user 0.040000 sys 0.000000 (best of 100)
! wall 0.030480 comb 0.030000 user 0.030000 sys 0.000000 (best of 100)
$ perfbdiff 0e9928989e9c --alldata --count 100
! wall 4.097394 comb 4.100000 user 4.100000 sys 0.000000 (best of 3)
! wall 3.597798 comb 3.600000 user 3.600000 sys 0.000000 (best of 3)
The 2nd example throws a total of ~3.3GB of data at bdiff. This
change increases the throughput from ~811 MB/s to ~924 MB/s.
#!/usr/bin/env python
"""This does HTTP GET requests given a host:port and path and returns
a subset of the headers plus the body of the result."""
from __future__ import absolute_import, print_function
import json
import os
import sys
from mercurial import (
util,
)
httplib = util.httplib
try:
import msvcrt
msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
msvcrt.setmode(sys.stderr.fileno(), os.O_BINARY)
except ImportError:
pass
twice = False
if '--twice' in sys.argv:
sys.argv.remove('--twice')
twice = True
headeronly = False
if '--headeronly' in sys.argv:
sys.argv.remove('--headeronly')
headeronly = True
formatjson = False
if '--json' in sys.argv:
sys.argv.remove('--json')
formatjson = True
tag = None
def request(host, path, show):
assert not path.startswith('/'), path
global tag
headers = {}
if tag:
headers['If-None-Match'] = tag
conn = httplib.HTTPConnection(host)
conn.request("GET", '/' + path, None, headers)
response = conn.getresponse()
print(response.status, response.reason)
if show[:1] == ['-']:
show = sorted(h for h, v in response.getheaders()
if h.lower() not in show)
for h in [h.lower() for h in show]:
if response.getheader(h, None) is not None:
print("%s: %s" % (h, response.getheader(h)))
if not headeronly:
print()
data = response.read()
# Pretty print JSON. This also has the beneficial side-effect
# of verifying emitted JSON is well-formed.
if formatjson:
# json.dumps() will print trailing newlines. Eliminate them
# to make tests easier to write.
data = json.loads(data)
lines = json.dumps(data, sort_keys=True, indent=2).splitlines()
for line in lines:
print(line.rstrip())
else:
sys.stdout.write(data)
if twice and response.getheader('ETag', None):
tag = response.getheader('ETag')
return response.status
status = request(sys.argv[1], sys.argv[2], sys.argv[3:])
if twice:
status = request(sys.argv[1], sys.argv[2], sys.argv[3:])
if 200 <= status <= 305:
sys.exit(0)
sys.exit(1)