tests/test-walkrepo.py

streamclone: also stream caches to the client

When stream clone is used over bundle2, relevant cache files are also streamed.
This is expected to be a massive performance win for clone since no important
cache will have to be recomputed.

Some performance numbers:

(All times are wall-clock times in seconds, 2 attempts per case.)

# Mozilla-Central

## Clone over ssh over lan
V1 streaming: 234.3 239.6
V2 streaming: 248.4 243.7

## Clone over ssh over Internet
V1 streaming: 175.5 110.9
V2 streaming: 109.1 111.0

## Clone over HTTP over lan
V1 streaming: 105.3 105.6
V2 streaming: 112.7 111.4

## Clone over HTTP over internet
V1 streaming: 105.6 114.6
V2 streaming: 226.7 225.9

## Hg tags
V1 streaming (no cache): 1.084 1.071
V2 streaming (cache):    0.312 0.325

## Hg branches
V1 streaming (no cache):   14.047 14.148
V2 streaming (with cache):  0.312  0.333

# Pypy

## Clone over ssh over internet
V1 streaming: 29.4 30.1
V2 streaming: 31.2 30.1

## Clone over http over internet
V1 streaming: 29.7 29.7
V2 streaming: 75.2 72.9

(since ssh and lan are not affected, there seems to be an issue with how we
read/write the http stream on connection with latency, unrelated to the format)

## Hg tags
V1 streaming (no cache):   1.752 1.664
V2 streaming (with cache): 0.274 0.260

## Hg branches
V1 streaming (no cache):   4.469 4.728
V2 streaming (with cache): 0.318 0.321

# Private repository:
    * 500K revision revisions
    * 11K topological heads
    * 28K branch heads

## hg tags
no cache:   1543.332
with cache:    4.900

## hg branches
no cache:   91.828
with cache:  2.955

from __future__ import absolute_import, print_function

import os

from mercurial import (
    hg,
    scmutil,
    ui as uimod,
    util,
)

chdir = os.chdir
mkdir = os.mkdir
pjoin = os.path.join

walkrepos = scmutil.walkrepos
checklink = util.checklink

u = uimod.ui.load()
sym = checklink('.')

hg.repository(u, 'top1', create=1)
mkdir('subdir')
chdir('subdir')
hg.repository(u, 'sub1', create=1)
mkdir('subsubdir')
chdir('subsubdir')
hg.repository(u, 'subsub1', create=1)
chdir(os.path.pardir)
if sym:
    os.symlink(os.path.pardir, 'circle')
    os.symlink(pjoin('subsubdir', 'subsub1'), 'subsub1')

def runtest():
    reposet = frozenset(walkrepos('.', followsym=True))
    if sym and (len(reposet) != 3):
        print("reposet = %r" % (reposet,))
        print(("Found %d repositories when I should have found 3"
               % (len(reposet),)))
    if (not sym) and (len(reposet) != 2):
        print("reposet = %r" % (reposet,))
        print(("Found %d repositories when I should have found 2"
               % (len(reposet),)))
    sub1set = frozenset((pjoin('.', 'sub1'),
                         pjoin('.', 'circle', 'subdir', 'sub1')))
    if len(sub1set & reposet) != 1:
        print("sub1set = %r" % (sub1set,))
        print("reposet = %r" % (reposet,))
        print("sub1set and reposet should have exactly one path in common.")
    sub2set = frozenset((pjoin('.', 'subsub1'),
                         pjoin('.', 'subsubdir', 'subsub1')))
    if len(sub2set & reposet) != 1:
        print("sub2set = %r" % (sub2set,))
        print("reposet = %r" % (reposet,))
        print("sub2set and reposet should have exactly one path in common.")
    sub3 = pjoin('.', 'circle', 'top1')
    if sym and sub3 not in reposet:
        print("reposet = %r" % (reposet,))
        print("Symbolic links are supported and %s is not in reposet" % (sub3,))

runtest()
if sym:
    # Simulate not having symlinks.
    del os.path.samestat
    sym = False
    runtest()