##// END OF EJS Templates
manifest: persist the manifestfulltext cache...
manifest: persist the manifestfulltext cache Reconstructing the manifest from the revlog takes time, so much so that there already is a LRU cache to avoid having to load a manifest multiple times. This patch persists that LRU cache in the .hg/cache directory, so we can re-use this cache across hg commands. Commit benchmark (run on Macos 10.13 on a 2017-model Macbook Pro with Core i7 2.9GHz and flash drive), testing without and with patch run 5 times, baseline is r2a227782e754: * committing to an existing file, against the mozilla-central repository. Baseline real time average 1.9692, with patch 1.3786. A new debugcommand "hg debugmanifestfulltextcache" lets you inspect the cache, clear it, or add specific manifest nodeids to it. When calling repo.updatecaches(), the manifest(s) for the working copy parents are added to the cache. The hg perfmanifest command has an additional --clear-disk switch to clear this cache when testing manifest loading performance. Using this command to test performance on the firefox repository for revision f947d902ed91, whose manifest has a delta chain length of 60540, we see: $ hg perfmanifest f947d902ed91 --clear-disk ! wall 0.972253 comb 0.970000 user 0.850000 sys 0.120000 (best of 10) $ hg debugmanifestfulltextcache -a `hg log --debug -r f947d902ed91 | grep manifest | cut -d: -f3` Cache contains 1 manifest entries, in order of most to least recent: id: 0294517df4aad07c70701db43bc7ff24c3ce7dbc, size 25.6 MB Total cache data size 25.6 MB, on-disk 0 bytes $ hg perfmanifest f947d902ed91 ! wall 0.036748 comb 0.040000 user 0.020000 sys 0.020000 (best of 100) Worst-case scenario: a manifest text loaded from a single delta; in the firefox repository manifest node 9a1246ff762e is the chain base for the manifest attached to revision f947d902ed91. Loading this from a full cache file is just as fast as without the cache; the extra node ids ensure a big full cache: $ for node in 9a1246ff762e 1a1922c14a3e 54a31d11a36a 0294517df4aa; do > hgd debugmanifestfulltextcache -a $node > /dev/null > done $ hgd perfmanifest -m 9a1246ff762e ! wall 0.077513 comb 0.080000 user 0.030000 sys 0.050000 (best of 100) $ hgd perfmanifest -m 9a1246ff762e --clear-disk ! wall 0.078547 comb 0.080000 user 0.070000 sys 0.010000 (best of 100)

File last commit:

r37743:3ea8323d default
r38803:0a57945a default
Show More
wireprotov2peer.py
201 lines | 5.8 KiB | text/x-python | PythonLexer
# wireprotov2peer.py - client side code for wire protocol version 2
#
# Copyright 2018 Gregory Szorc <gregory.szorc@gmail.com>
#
# 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
from .i18n import _
from .thirdparty import (
cbor,
)
from . import (
encoding,
error,
util,
wireprotoframing,
)
def formatrichmessage(atoms):
"""Format an encoded message from the framing protocol."""
chunks = []
for atom in atoms:
msg = _(atom[b'msg'])
if b'args' in atom:
msg = msg % atom[b'args']
chunks.append(msg)
return b''.join(chunks)
class commandresponse(object):
"""Represents the response to a command request."""
def __init__(self, requestid, command):
self.requestid = requestid
self.command = command
self.b = util.bytesio()
def cborobjects(self):
"""Obtain decoded CBOR objects from this response."""
size = self.b.tell()
self.b.seek(0)
decoder = cbor.CBORDecoder(self.b)
while self.b.tell() < size:
yield decoder.decode()
class clienthandler(object):
"""Object to handle higher-level client activities.
The ``clientreactor`` is used to hold low-level state about the frame-based
protocol, such as which requests and streams are active. This type is used
for higher-level operations, such as reading frames from a socket, exposing
and managing a higher-level primitive for representing command responses,
etc. This class is what peers should probably use to bridge wire activity
with the higher-level peer API.
"""
def __init__(self, ui, clientreactor):
self._ui = ui
self._reactor = clientreactor
self._requests = {}
self._futures = {}
self._responses = {}
def callcommand(self, command, args, f):
"""Register a request to call a command.
Returns an iterable of frames that should be sent over the wire.
"""
request, action, meta = self._reactor.callcommand(command, args)
if action != 'noop':
raise error.ProgrammingError('%s not yet supported' % action)
rid = request.requestid
self._requests[rid] = request
self._futures[rid] = f
self._responses[rid] = commandresponse(rid, command)
return iter(())
def flushcommands(self):
"""Flush all queued commands.
Returns an iterable of frames that should be sent over the wire.
"""
action, meta = self._reactor.flushcommands()
if action != 'sendframes':
raise error.ProgrammingError('%s not yet supported' % action)
return meta['framegen']
def readframe(self, fh):
"""Attempt to read and process a frame.
Returns None if no frame was read. Presumably this means EOF.
"""
frame = wireprotoframing.readframe(fh)
if frame is None:
# TODO tell reactor?
return
self._ui.note(_('received %r\n') % frame)
self._processframe(frame)
return True
def _processframe(self, frame):
"""Process a single read frame."""
action, meta = self._reactor.onframerecv(frame)
if action == 'error':
e = error.RepoError(meta['message'])
if frame.requestid in self._futures:
self._futures[frame.requestid].set_exception(e)
else:
raise e
if frame.requestid not in self._requests:
raise error.ProgrammingError(
'received frame for unknown request; this is either a bug in '
'the clientreactor not screening for this or this instance was '
'never told about this request: %r' % frame)
response = self._responses[frame.requestid]
if action == 'responsedata':
response.b.write(meta['data'])
if meta['eos']:
# If the command has a decoder, resolve the future to the
# decoded value. Otherwise resolve to the rich response object.
decoder = COMMAND_DECODERS.get(response.command)
# TODO consider always resolving the overall status map.
if decoder:
objs = response.cborobjects()
overall = next(objs)
if overall['status'] == 'ok':
self._futures[frame.requestid].set_result(decoder(objs))
else:
e = error.RepoError(
formatrichmessage(overall['error']['message']))
self._futures[frame.requestid].set_exception(e)
else:
self._futures[frame.requestid].set_result(response)
del self._requests[frame.requestid]
del self._futures[frame.requestid]
else:
raise error.ProgrammingError(
'unhandled action from clientreactor: %s' % action)
def decodebranchmap(objs):
# Response should be a single CBOR map of branch name to array of nodes.
bm = next(objs)
return {encoding.tolocal(k): v for k, v in bm.items()}
def decodeheads(objs):
# Array of node bytestrings.
return next(objs)
def decodeknown(objs):
# Bytestring where each byte is a 0 or 1.
raw = next(objs)
return [True if c == '1' else False for c in raw]
def decodelistkeys(objs):
# Map with bytestring keys and values.
return next(objs)
def decodelookup(objs):
return next(objs)
def decodepushkey(objs):
return next(objs)
COMMAND_DECODERS = {
'branchmap': decodebranchmap,
'heads': decodeheads,
'known': decodeknown,
'listkeys': decodelistkeys,
'lookup': decodelookup,
'pushkey': decodepushkey,
}