view tests/test-commandserver.py @ 16120:47ee41fcf42b

largefiles: optimize update speed by only updating changed largefiles

Historically, during 'hg update', every largefile in the working copy was
hashed (which is a very expensive operation on big files) and any
largefiles that did not have a hash that matched their standin were
updated.

This patch optimizes 'hg update' by keeping track of what standins have
changed between the old and new revisions, and only updating the largefiles
that have changed.  This saves a lot of time by avoiding the unecessary
calculation of a list of sha1 hashes for big files.

With this patch, the time 'hg update' takes to complete is a function of
how many largefiles need to be updated and what their size is.

Performance tests on a repository with about 80 largefiles ranging from
a few MB to about 97 MB are shown below.  The tests show how long it takes
to run 'hg update' with no changes actually being updated.

Mercurial 2.1 release:

$ time hg update
0 files updated, 0 files merged, 0 files removed, 0 files unresolved
getting changed largefiles
0 largefiles updated, 0 removed

real    0m10.045s
user    0m9.367s
sys    0m0.674s

With this patch:

$ time hg update
0 files updated, 0 files merged, 0 files removed, 0 files unresolved

real    0m0.965s
user    0m0.845s
sys    0m0.115s

The same repsoitory, without the largefiles extension enabled:

$ time hg update
0 files updated, 0 files merged, 0 files removed, 0 files unresolved

real    0m0.799s
user    0m0.684s
sys    0m0.111s

So before the patch, 'hg update' with no changes was approximately 9.25s
slower with largefiles enabled.  With this patch, it is approximately 0.165s
slower.

import sys, os, struct, subprocess, cStringIO, re, shutil

def connect(path=None):
    cmdline = ['hg', 'serve', '--cmdserver', 'pipe']
    if path:
        cmdline += ['-R', path]

    server = subprocess.Popen(cmdline, stdin=subprocess.PIPE,
                              stdout=subprocess.PIPE)

    return server

def writeblock(server, data):
    server.stdin.write(struct.pack('>I', len(data)))
    server.stdin.write(data)
    server.stdin.flush()

def readchannel(server):
    data = server.stdout.read(5)
    if not data:
        raise EOFError()
    channel, length = struct.unpack('>cI', data)
    if channel in 'IL':
        return channel, length
    else:
        return channel, server.stdout.read(length)

def runcommand(server, args, output=sys.stdout, error=sys.stderr, input=None):
    print ' runcommand', ' '.join(args)
    server.stdin.write('runcommand\n')
    writeblock(server, '\0'.join(args))

    if not input:
        input = cStringIO.StringIO()

    while True:
        ch, data = readchannel(server)
        if ch == 'o':
            output.write(data)
            output.flush()
        elif ch == 'e':
            error.write(data)
            error.flush()
        elif ch == 'I':
            writeblock(server, input.read(data))
        elif ch == 'L':
            writeblock(server, input.readline(data))
        elif ch == 'r':
            return struct.unpack('>i', data)[0]
        else:
            print "unexpected channel %c: %r" % (ch, data)
            if ch.isupper():
                return

def check(func, repopath=None):
    print
    print 'testing %s:' % func.__name__
    print
    server = connect(repopath)
    try:
        return func(server)
    finally:
        server.stdin.close()
        server.wait()

def unknowncommand(server):
    server.stdin.write('unknowncommand\n')

def hellomessage(server):
    ch, data = readchannel(server)
    # escaping python tests output not supported
    print '%c, %r' % (ch, re.sub('encoding: [a-zA-Z0-9-]+', 'encoding: ***', data))

    # run an arbitrary command to make sure the next thing the server sends
    # isn't part of the hello message
    runcommand(server, ['id'])

def checkruncommand(server):
    # hello block
    readchannel(server)

    # no args
    runcommand(server, [])

    # global options
    runcommand(server, ['id', '--quiet'])

    # make sure global options don't stick through requests
    runcommand(server, ['id'])

    # --config
    runcommand(server, ['id', '--config', 'ui.quiet=True'])

    # make sure --config doesn't stick
    runcommand(server, ['id'])

def inputeof(server):
    readchannel(server)
    server.stdin.write('runcommand\n')
    # close stdin while server is waiting for input
    server.stdin.close()

    # server exits with 1 if the pipe closed while reading the command
    print 'server exit code =', server.wait()

def serverinput(server):
    readchannel(server)

    patch = """
# HG changeset patch
# User test
# Date 0 0
# Node ID c103a3dec114d882c98382d684d8af798d09d857
# Parent  0000000000000000000000000000000000000000
1

diff -r 000000000000 -r c103a3dec114 a
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/a	Thu Jan 01 00:00:00 1970 +0000
@@ -0,0 +1,1 @@
+1
"""

    runcommand(server, ['import', '-'], input=cStringIO.StringIO(patch))
    runcommand(server, ['log'])

def cwd(server):
    """ check that --cwd doesn't persist between requests """
    readchannel(server)
    os.mkdir('foo')
    f = open('foo/bar', 'wb')
    f.write('a')
    f.close()
    runcommand(server, ['--cwd', 'foo', 'st', 'bar'])
    runcommand(server, ['st', 'foo/bar'])
    os.remove('foo/bar')

def localhgrc(server):
    """ check that local configs for the cached repo aren't inherited when -R
    is used """
    readchannel(server)

    # the cached repo local hgrc contains ui.foo=bar, so showconfig should show it
    runcommand(server, ['showconfig'])

    # but not for this repo
    runcommand(server, ['init', 'foo'])
    runcommand(server, ['-R', 'foo', 'showconfig', 'ui', 'defaults'])
    shutil.rmtree('foo')

def hook(**args):
    print 'hook talking'
    print 'now try to read something: %r' % sys.stdin.read()

def hookoutput(server):
    readchannel(server)
    runcommand(server, ['--config',
                        'hooks.pre-identify=python:test-commandserver.hook', 'id'],
               input=cStringIO.StringIO('some input'))

def outsidechanges(server):
    readchannel(server)
    f = open('a', 'ab')
    f.write('a\n')
    f.close()
    os.system('hg ci -Am2')
    runcommand(server, ['tip'])

def bookmarks(server):
    readchannel(server)
    runcommand(server, ['bookmarks'])

    # changes .hg/bookmarks
    os.system('hg bookmark -i bm1')
    os.system('hg bookmark -i bm2')
    runcommand(server, ['bookmarks'])

    # changes .hg/bookmarks.current
    os.system('hg upd bm1 -q')
    runcommand(server, ['bookmarks'])

def tagscache(server):
    readchannel(server)
    runcommand(server, ['id', '-t', '-r', '0'])
    os.system('hg tag -r 0 foo')
    runcommand(server, ['id', '-t', '-r', '0'])

def setphase(server):
    readchannel(server)
    runcommand(server, ['phase', '-r', '.'])
    os.system('hg phase -r . -p')
    runcommand(server, ['phase', '-r', '.'])

if __name__ == '__main__':
    os.system('hg init')

    check(hellomessage)
    check(unknowncommand)
    check(checkruncommand)
    check(inputeof)
    check(serverinput)
    check(cwd)

    hgrc = open('.hg/hgrc', 'a')
    hgrc.write('[ui]\nfoo=bar\n')
    hgrc.close()
    check(localhgrc)
    check(hookoutput)
    check(outsidechanges)
    check(bookmarks)
    check(tagscache)
    check(setphase)