annotate hgext/fastannotate/support.py @ 42044:bb271ec2fbfb

compression: introduce a `storage.revlog.zstd.level` configuration

This option control the zstd compression level used when compressing revlog
chunk. The usage of zstd for revlog compression has not graduated from
experimental yet, but we intend to fix that soon.

The option name for the compression level is more straight forward to pick, so
this changesets comes first.  Having a dedicated option for each compression
engine is useful because they don't support the same range of values.

I ran the same measurement as for the zlib compression level (in the parent
changesets). The variation in repository size is stay mostly in the same (small)
range. The "read/write" performance see smallish variation, but are overall much
better than zlib. Write performance show the same tend of having better write
performance for when reaching high-end compression.

Again, we don't intend to change the default zstd compression level (currently:
3) in this series. However this is worth investigating in the future.

The Performance comparison of zlib vs zstd is quite impressive. The repository
size stay in the same range, but the performance are much better in all
situations.

Comparison summary
==================

We are looking at:
- performance range for zlib
- performance range for zstd
- comparison of default zstd (level-3) to default zlib (level 6)
- comparison of the slowest zstd time to the fastest zlib time

Read performance:
-----------------
          |           zlib          |           zstd          | cmp | f2s
mercurial |   0.170159 -   0.189219 |   0.144127 -   0.149624 | 80% | 88%
pypy      |   2.679217 -   2.768691 |   1.532317 -   1.705044 | 60% | 63%
netbeans  | 122.477027 - 141.620281 |  72.996346 -  89.731560 | 58% | 73%
mozilla   | 147.867662 - 170.572118 |  91.700995 - 105.853099 | 56% | 71%

Write performance:
------------------
          |           zlib          |           zstd          | cmp | f2s
mercurial |  53.250304 - 56.2936129 |  40.877025 -  45.677286 | 75% | 86%
pypy      | 460.721984 - 476.589918 | 270.545409 - 301.002219 | 63% | 65%
netbeans  | 520.560316 - 715.930400 | 370.356311 - 428.329652 | 55% | 82%
mozilla   | 739.803002 - 987.056093 | 505.152906 - 591.930683 | 57% | 80%

Raw data
--------

repo      alg lvl  .hg/store size  00manifest.d read       write

mercurial zlib  1      49,402,813     5,963,475   0.170159  53.250304
mercurial zlib  6      47,197,397     5,875,730   0.182820  56.264320
mercurial zlib  9      47,121,596     5,849,781   0.189219  56.293612

mercurial zstd  1      49,737,084     5,966,355   0.144127  40.877025
mercurial zstd  3      48,961,867     5,895,208   0.146376  42.268142
mercurial zstd  5      48,200,592     5,938,676   0.149624  43.162875
mercurial zstd 10      47,833,520     5,913,353   0.145185  44.012489
mercurial zstd 15      47,314,604     5,728,679   0.147686  45.677286
mercurial zstd 20      47,330,502     5,830,539   0.145789  45.025407
mercurial zstd 22      47,330,076     5,830,539   0.143996  44.690460


pypy      zlib  1     370,830,572    28,462,425   2.679217 460.721984
pypy      zlib  6     340,112,317    27,648,747   2.768691 467.537158
pypy      zlib  9     338,360,736    27,639,003   2.763495 476.589918

pypy      zstd  1     362,377,479    27,916,214   1.532317 270.545409
pypy      zstd  3     354,137,693    27,905,988   1.686718 294.951509
pypy      zstd  5     342,640,043    27,655,774   1.705044 301.002219
pypy      zstd 10     334,224,327    27,164,493   1.567287 285.186239
pypy      zstd 15     329,000,363    26,645,965   1.637729 299.561332
pypy      zstd 20     324,534,039    26,199,547   1.526813 302.149827
pypy      zstd 22     324,530,595    26,198,932   1.525718 307.821218


netbeans  zlib  1   1,281,847,810   165,495,457 122.477027 520.560316
netbeans  zlib  6   1,205,284,353   159,161,207 139.876147 715.930400
netbeans  zlib  9   1,197,135,671   155,034,586 141.620281 678.297064

netbeans  zstd  1   1,259,581,737   160,840,613  72.996346 370.356311
netbeans  zstd  3   1,232,978,122   157,691,551  81.622317 396.733087
netbeans  zstd  5   1,208,034,075   160,246,880  83.080549 364.342626
netbeans  zstd 10   1,188,624,176   156,083,417  79.323935 403.594602
netbeans  zstd 15   1,176,973,589   153,859,477  89.731560 428.329652
netbeans  zstd 20   1,162,958,258   151,147,535  82.842667 392.335349
netbeans  zstd 22   1,162,707,029   151,150,220  82.565695 402.840655


mozilla   zlib  1   2,775,497,186   298,527,987 147.867662 751.263721
mozilla   zlib  6   2,596,856,420   286,597,671 170.572118 987.056093
mozilla   zlib  9   2,587,542,494   287,018,264 163.622338 739.803002

mozilla   zstd  1   2,723,159,348   286,617,532  91.700995 570.042751
mozilla   zstd  3   2,665,055,001   286,152,013  95.240155 561.412805
mozilla   zstd  5   2,607,819,817   288,060,030 101.978048 505.152906
mozilla   zstd 10   2,558,761,085   283,967,648 104.113481 497.771202
mozilla   zstd 15   2,526,216,060   275,581,300 105.853099 591.930683
mozilla   zstd 20   2,485,114,806   266,478,859  95.268795 576.515389
mozilla   zstd 22   2,484,869,080   266,456,505  94.429282 572.785537

# Copyright 2016-present Facebook. All Rights Reserved.
#
# support: fastannotate support for hgweb, and filectx
#
# 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 mercurial import (
    context as hgcontext,
    dagop,
    extensions,
    hgweb,
    patch,
    util,
)

from . import (
    context,
    revmap,
)

class _lazyfctx(object):
    """delegates to fctx but do not construct fctx when unnecessary"""

    def __init__(self, repo, node, path):
        self._node = node
        self._path = path
        self._repo = repo

    def node(self):
        return self._node

    def path(self):
        return self._path

    @util.propertycache
    def _fctx(self):
        return context.resolvefctx(self._repo, self._node, self._path)

    def __getattr__(self, name):
        return getattr(self._fctx, name)

def _convertoutputs(repo, annotated, contents):
    """convert fastannotate outputs to vanilla annotate format"""
    # fastannotate returns: [(nodeid, linenum, path)], [linecontent]
    # convert to what fctx.annotate returns: [annotateline]
    results = []
    fctxmap = {}
    annotateline = dagop.annotateline
    for i, (hsh, linenum, path) in enumerate(annotated):
        if (hsh, path) not in fctxmap:
            fctxmap[(hsh, path)] = _lazyfctx(repo, hsh, path)
        # linenum: the user wants 1-based, we have 0-based.
        lineno = linenum + 1
        fctx = fctxmap[(hsh, path)]
        line = contents[i]
        results.append(annotateline(fctx=fctx, lineno=lineno, text=line))
    return results

def _getmaster(fctx):
    """(fctx) -> str"""
    return fctx._repo.ui.config('fastannotate', 'mainbranch') or 'default'

def _doannotate(fctx, follow=True, diffopts=None):
    """like the vanilla fctx.annotate, but do it via fastannotate, and make
    the output format compatible with the vanilla fctx.annotate.
    may raise Exception, and always return line numbers.
    """
    master = _getmaster(fctx)
    annotated = contents = None

    with context.fctxannotatecontext(fctx, follow, diffopts) as ac:
        try:
            annotated, contents = ac.annotate(fctx.rev(), master=master,
                                              showpath=True, showlines=True)
        except Exception:
            ac.rebuild() # try rebuild once
            fctx._repo.ui.debug('fastannotate: %s: rebuilding broken cache\n'
                                % fctx._path)
            try:
                annotated, contents = ac.annotate(fctx.rev(), master=master,
                                                  showpath=True, showlines=True)
            except Exception:
                raise

    assert annotated and contents
    return _convertoutputs(fctx._repo, annotated, contents)

def _hgwebannotate(orig, fctx, ui):
    diffopts = patch.difffeatureopts(ui, untrusted=True,
                                     section='annotate', whitespace=True)
    return _doannotate(fctx, diffopts=diffopts)

def _fctxannotate(orig, self, follow=False, linenumber=False, skiprevs=None,
                  diffopts=None):
    if skiprevs:
        # skiprevs is not supported yet
        return orig(self, follow, linenumber, skiprevs=skiprevs,
                    diffopts=diffopts)
    try:
        return _doannotate(self, follow, diffopts)
    except Exception as ex:
        self._repo.ui.debug('fastannotate: falling back to the vanilla '
                            'annotate: %r\n' % ex)
        return orig(self, follow=follow, skiprevs=skiprevs,
                    diffopts=diffopts)

def _remotefctxannotate(orig, self, follow=False, skiprevs=None, diffopts=None):
    # skipset: a set-like used to test if a fctx needs to be downloaded
    with context.fctxannotatecontext(self, follow, diffopts) as ac:
        skipset = revmap.revmap(ac.revmappath)
    return orig(self, follow, skiprevs=skiprevs, diffopts=diffopts,
                prefetchskip=skipset)

def replacehgwebannotate():
    extensions.wrapfunction(hgweb.webutil, 'annotate', _hgwebannotate)

def replacefctxannotate():
    extensions.wrapfunction(hgcontext.basefilectx, 'annotate', _fctxannotate)