hgweb: tweak zlib chunking behavior

When doing streaming compression with zlib, zlib appears to emit chunks
with data after ~20-30kb on average is available. In other words, most
calls to compress() return an empty string. On the mozilla-unified repo,
only 48,433 of 921,167 (5.26%) of calls to compress() returned data.
In other words, we were sending hundreds of thousands of empty chunks
via a generator where they touched who knows how many frames (my guess
is millions). Filtering out the empty chunks from the generator
cuts down on overhead.

In addition, we were previously feeding 8kb chunks into zlib
compression. Since this function tends to emit *compressed* data after
20-30kb is available, it would take several calls before data was
produced. We increase the amount of data fed in at a time to 32kb.
This reduces the number of calls to compress() from 921,167 to
115,146. It also reduces the number of output chunks from 48,433 to
31,377. This does increase the average output chunk size by a little.
But I don't think this will matter in most scenarios.

The combination of these 2 changes appears to shave ~6s CPU time
or ~3% from a server serving the mozilla-unified repo.

mercurial/hgweb/protocol.py

@@ -1,120 +1,124 b''
 #
 # Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import cgi
 import zlib
 
 from .common import (
     HTTP_OK,
 )
 
 from .. import (
     util,
     wireproto,
 )
 stringio = util.stringio
 
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 HGTYPE = 'application/mercurial-0.1'
 HGERRTYPE = 'application/hg-error'
 
 class webproto(wireproto.abstractserverproto):
     def __init__(self, req, ui):
         self.req = req
         self.response = ''
         self.ui = ui
     def getargs(self, args):
         knownargs = self._args()
         data = {}
         keys = args.split()
         for k in keys:
             if k == '*':
                 star = {}
                 for key in knownargs.keys():
                     if key != 'cmd' and key not in keys:
                         star[key] = knownargs[key][0]
                 data['*'] = star
             else:
                 data[k] = knownargs[k][0]
         return [data[k] for k in keys]
     def _args(self):
         args = self.req.form.copy()
         postlen = int(self.req.env.get('HTTP_X_HGARGS_POST', 0))
         if postlen:
             args.update(cgi.parse_qs(
                 self.req.read(postlen), keep_blank_values=True))
             return args
         chunks = []
         i = 1
         while True:
             h = self.req.env.get('HTTP_X_HGARG_' + str(i))
             if h is None:
                 break
             chunks += [h]
             i += 1
         args.update(cgi.parse_qs(''.join(chunks), keep_blank_values=True))
         return args
     def getfile(self, fp):
         length = int(self.req.env['CONTENT_LENGTH'])
         for s in util.filechunkiter(self.req, limit=length):
             fp.write(s)
     def redirect(self):
         self.oldio = self.ui.fout, self.ui.ferr
         self.ui.ferr = self.ui.fout = stringio()
     def restore(self):
         val = self.ui.fout.getvalue()
         self.ui.ferr, self.ui.fout = self.oldio
         return val
     def groupchunks(self, cg):
         # Don't allow untrusted settings because disabling compression or
         # setting a very high compression level could lead to flooding
         # the server's network or CPU.
         z = zlib.compressobj(self.ui.configint('server', 'zliblevel', -1))
         while True:
-            chunk = cg.read(4096)
+            chunk = cg.read(32768)
             if not chunk:
                 break
-            yield z.compress(chunk)
+            data = z.compress(chunk)
+            # Not all calls to compress() emit data. It is cheaper to inspect
+            # that here than to send it via the generator.
+            if data:
+                yield data
         yield z.flush()
     def _client(self):
         return 'remote:%s:%s:%s' % (
             self.req.env.get('wsgi.url_scheme') or 'http',
             urlreq.quote(self.req.env.get('REMOTE_HOST', '')),
             urlreq.quote(self.req.env.get('REMOTE_USER', '')))
 
 def iscmd(cmd):
     return cmd in wireproto.commands
 
 def call(repo, req, cmd):
     p = webproto(req, repo.ui)
     rsp = wireproto.dispatch(repo, p, cmd)
     if isinstance(rsp, str):
         req.respond(HTTP_OK, HGTYPE, body=rsp)
         return []
     elif isinstance(rsp, wireproto.streamres):
         req.respond(HTTP_OK, HGTYPE)
         return rsp.gen
     elif isinstance(rsp, wireproto.pushres):
         val = p.restore()
         rsp = '%d\n%s' % (rsp.res, val)
         req.respond(HTTP_OK, HGTYPE, body=rsp)
         return []
     elif isinstance(rsp, wireproto.pusherr):
         # drain the incoming bundle
         req.drain()
         p.restore()
         rsp = '0\n%s\n' % rsp.res
         req.respond(HTTP_OK, HGTYPE, body=rsp)
         return []
     elif isinstance(rsp, wireproto.ooberror):
         rsp = rsp.message
         req.respond(HTTP_OK, HGERRTYPE, body=rsp)
         return []