view mercurial/peer.py @ 26379:39d643252b9f

revlog: use existing file handle when reading during _addrevision

_addrevision() may need to read from revlogs as part of computing
deltas. Previously, we would flush existing file handles and open
a new, short-lived file handle to perform the reading.

If we have an existing file handle, it seems logical to reuse it
for reading instead of opening a new file handle. This patch
makes that the new behavior.

After this patch, revlog files are only reopened when adding
revisions if the revlog is switched from inline to non-inline.

On Linux when unbundling a bundle of the mozilla-central repo, this
patch has the following impact on system call counts:

Call     Before     After       Delta
write    827,639    673,390   -154,249
open     700,103    684,089    -16,014
read      74,489     74,489          0
fstat    493,924    461,896    -32,028
close    249,131    233,117    -16,014
stat     242,001    242,001          0
lstat     18,676     18,676          0
lseek     20,268     20,268          0
ioctl     14,652     13,173     -1,479
TOTAL  3,180,758  2,930,679   -250,079

It's worth noting that many of the open() calls fail due to missing
files. That's why there are many more open() calls than close().

Despite the significant system call reduction, this change does not
seem to have a significant performance impact on Linux.

On Windows 10 (not a VM, on a SSD), this patch appears to reduce
unbundle time for mozilla-central from ~960s to ~920s. This isn't
as significant as I was hoping. But a decrease it is nonetheless.
Still, Windows unbundle performance is still >2x slower than Linux.

Despite the lack of significant gains, fewer system calls is fewer
system calls. If nothing else, this will narrow the focus of potential
areas to optimize in the future.

# peer.py - repository base classes for mercurial
#
# Copyright 2005, 2006 Matt Mackall <[e-mail]>
# Copyright 2006 Vadim Gelfer <[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

from .i18n import _
from . import (
    error,
    util,
)

# abstract batching support

class future(object):
    '''placeholder for a value to be set later'''
    def set(self, value):
        if util.safehasattr(self, 'value'):
            raise error.RepoError("future is already set")
        self.value = value

class batcher(object):
    '''base class for batches of commands submittable in a single request

    All methods invoked on instances of this class are simply queued and
    return a a future for the result. Once you call submit(), all the queued
    calls are performed and the results set in their respective futures.
    '''
    def __init__(self):
        self.calls = []
    def __getattr__(self, name):
        def call(*args, **opts):
            resref = future()
            self.calls.append((name, args, opts, resref,))
            return resref
        return call
    def submit(self):
        pass

class localbatch(batcher):
    '''performs the queued calls directly'''
    def __init__(self, local):
        batcher.__init__(self)
        self.local = local
    def submit(self):
        for name, args, opts, resref in self.calls:
            resref.set(getattr(self.local, name)(*args, **opts))

def batchable(f):
    '''annotation for batchable methods

    Such methods must implement a coroutine as follows:

    @batchable
    def sample(self, one, two=None):
        # Handle locally computable results first:
        if not one:
            yield "a local result", None
        # Build list of encoded arguments suitable for your wire protocol:
        encargs = [('one', encode(one),), ('two', encode(two),)]
        # Create future for injection of encoded result:
        encresref = future()
        # Return encoded arguments and future:
        yield encargs, encresref
        # Assuming the future to be filled with the result from the batched
        # request now. Decode it:
        yield decode(encresref.value)

    The decorator returns a function which wraps this coroutine as a plain
    method, but adds the original method as an attribute called "batchable",
    which is used by remotebatch to split the call into separate encoding and
    decoding phases.
    '''
    def plain(*args, **opts):
        batchable = f(*args, **opts)
        encargsorres, encresref = batchable.next()
        if not encresref:
            return encargsorres # a local result in this case
        self = args[0]
        encresref.set(self._submitone(f.func_name, encargsorres))
        return batchable.next()
    setattr(plain, 'batchable', f)
    return plain

class peerrepository(object):

    def batch(self):
        return localbatch(self)

    def capable(self, name):
        '''tell whether repo supports named capability.
        return False if not supported.
        if boolean capability, return True.
        if string capability, return string.'''
        caps = self._capabilities()
        if name in caps:
            return True
        name_eq = name + '='
        for cap in caps:
            if cap.startswith(name_eq):
                return cap[len(name_eq):]
        return False

    def requirecap(self, name, purpose):
        '''raise an exception if the given capability is not present'''
        if not self.capable(name):
            raise error.CapabilityError(
                _('cannot %s; remote repository does not '
                  'support the %r capability') % (purpose, name))

    def local(self):
        '''return peer as a localrepo, or None'''
        return None

    def peer(self):
        return self

    def canpush(self):
        return True

    def close(self):
        pass