# HG changeset patch # User Pierre-Yves David # Date 1553708127 -3600 # Node ID 1fac9b931d4617f1ea6bc76a9c25fd3d4308ad29 # Parent aaececb4b0668d5750be70cdea9f44681c8ba6e9 compression: introduce a `storage.revlog.zlib.level` configuration This option control the zlib compression level used when compression revlog chunk. This is also a good excuse to pave the way for a similar configuration option for the zstd compression engine. Having a dedicated option for each compression algorithm is useful because they don't support the same range of values. Using a higher zlib compression impact CPU consumption at compression time, but does not directly affected decompression time. However dealing with small compressed chunk can directly help decompression and indirectly help other revlog logic. I ran some basic test on repositories using different level. I am using the mercurial, pypy, netbeans and mozilla-central clone from our benchmark suite. All tested repository use sparse-revlog and got all their delta recomputed. The different compression level has a small effect on the repository size (about 10% variation in the total range). My quick analysis is that revlog mostly store small delta, that are not affected by the compression level much. So the variation probably mostly comes from better compression of the snapshots revisions, and snapshot revision only represent a small portion of the repository content. I also made some basic timings measurements. The "read" timings are gathered using simple run of `hg perfrevlogrevisions`, the "write" timings using `hg perfrevlogwrite` (restricted to the last 5000 revisions for netbeans and mozilla central). The timings are gathered on a generic machine, (not one of our performance locked machine), so small variation might not be meaningful. However large trend remains relevant. Keep in mind that these numbers are not pure compression/decompression time. They also involve the full revlog logic. In particular the difference in chunk size has an impact on the delta chain structure, affecting performance when writing or reading them. On read/write performance, the compression level has a bigger impact. Counter-intuitively, the higher compression levels improve "write" performance for the large repositories in our tested setting. Maybe because the last 5000 delta chain end up having a very different shape in this specific spot? Or maybe because of a more general trend of better delta chains thanks to the smaller chunk and snapshot. This series does not intend to change the default compression level. However, these result call for a deeper analysis of this performance difference in the future. Full data ========= repo level .hg/store size 00manifest.d read write ---------------------------------------------------------------- mercurial 1 49,402,813 5,963,475 0.170159 53.250304 mercurial 6 47,197,397 5,875,730 0.182820 56.264320 mercurial 9 47,121,596 5,849,781 0.189219 56.293612 pypy 1 370,830,572 28,462,425 2.679217 460.721984 pypy 6 340,112,317 27,648,747 2.768691 467.537158 pypy 9 338,360,736 27,639,003 2.763495 476.589918 netbeans 1 1,281,847,810 165,495,457 122.477027 520.560316 netbeans 6 1,205,284,353 159,161,207 139.876147 715.930400 netbeans 9 1,197,135,671 155,034,586 141.620281 678.297064 mozilla 1 2,775,497,186 298,527,987 147.867662 751.263721 mozilla 6 2,596,856,420 286,597,671 170.572118 987.056093 mozilla 9 2,587,542,494 287,018,264 163.622338 739.803002 diff -r aaececb4b066 -r 1fac9b931d46 mercurial/configitems.py --- a/mercurial/configitems.py Wed Mar 27 19:34:10 2019 +0100 +++ b/mercurial/configitems.py Wed Mar 27 18:35:27 2019 +0100 @@ -992,6 +992,9 @@ coreconfigitem('storage', 'revlog.reuse-external-delta-parent', default=None, ) +coreconfigitem('storage', 'revlog.zlib.level', + default=None, +) coreconfigitem('server', 'bookmarks-pushkey-compat', default=True, ) diff -r aaececb4b066 -r 1fac9b931d46 mercurial/help/config.txt --- a/mercurial/help/config.txt Wed Mar 27 19:34:10 2019 +0100 +++ b/mercurial/help/config.txt Wed Mar 27 18:35:27 2019 +0100 @@ -1881,6 +1881,11 @@ This option is enabled by default. When disabled, it also disables the related ``storage.revlog.reuse-external-delta-parent`` option. +``revlog.zlib.level`` + Zlib compression level used when storing data into the repository. Accepted + Value range from 1 (lowest compression) to 9 (highest compression). Zlib + default value is 6. + ``server`` ---------- diff -r aaececb4b066 -r 1fac9b931d46 mercurial/localrepo.py --- a/mercurial/localrepo.py Wed Mar 27 19:34:10 2019 +0100 +++ b/mercurial/localrepo.py Wed Mar 27 18:35:27 2019 +0100 @@ -797,6 +797,12 @@ if r.startswith(b'exp-compression-'): options[b'compengine'] = r[len(b'exp-compression-'):] + options[b'zlib.level'] = ui.configint(b'storage', b'revlog.zlib.level') + if options[b'zlib.level'] is not None: + if not (0 <= options[b'zlib.level'] <= 9): + msg = _('invalid value for `storage.revlog.zlib.level` config: %d') + raise error.Abort(msg % options[b'zlib.level']) + if repository.NARROW_REQUIREMENT in requirements: options[b'enableellipsis'] = True diff -r aaececb4b066 -r 1fac9b931d46 mercurial/revlog.py --- a/mercurial/revlog.py Wed Mar 27 19:34:10 2019 +0100 +++ b/mercurial/revlog.py Wed Mar 27 18:35:27 2019 +0100 @@ -371,6 +371,7 @@ self._nodecache = {nullid: nullrev} self._nodepos = None self._compengine = 'zlib' + self._compengineopts = {} self._maxdeltachainspan = -1 self._withsparseread = False self._sparserevlog = False @@ -416,6 +417,8 @@ self._lazydeltabase = bool(opts.get('lazydeltabase', False)) if 'compengine' in opts: self._compengine = opts['compengine'] + if 'zlib.level' in opts: + self._compengineopts['zlib.level'] = opts['zlib.level'] if 'maxdeltachainspan' in opts: self._maxdeltachainspan = opts['maxdeltachainspan'] if self._mmaplargeindex and 'mmapindexthreshold' in opts: @@ -526,7 +529,8 @@ @util.propertycache def _compressor(self): - return util.compengines[self._compengine].revlogcompressor() + engine = util.compengines[self._compengine] + return engine.revlogcompressor(self._compengineopts) def _indexfp(self, mode='r'): """file object for the revlog's index file""" @@ -1981,7 +1985,7 @@ except KeyError: try: engine = util.compengines.forrevlogheader(t) - compressor = engine.revlogcompressor() + compressor = engine.revlogcompressor(self._compengineopts) self._decompressors[t] = compressor except KeyError: raise error.RevlogError(_('unknown compression type %r') % t) diff -r aaececb4b066 -r 1fac9b931d46 mercurial/utils/compression.py --- a/mercurial/utils/compression.py Wed Mar 27 19:34:10 2019 +0100 +++ b/mercurial/utils/compression.py Wed Mar 27 18:35:27 2019 +0100 @@ -505,7 +505,10 @@ stringutil.forcebytestr(e)) def revlogcompressor(self, opts=None): - return self.zlibrevlogcompressor() + level = None + if opts is not None: + level = opts.get('zlib.level') + return self.zlibrevlogcompressor(level) compengines.register(_zlibengine()) diff -r aaececb4b066 -r 1fac9b931d46 tests/test-repo-compengines.t --- a/tests/test-repo-compengines.t Wed Mar 27 19:34:10 2019 +0100 +++ b/tests/test-repo-compengines.t Wed Mar 27 18:35:27 2019 +0100 @@ -82,3 +82,59 @@ 0x78 (x) : 199 (100.00%) #endif + +checking zlib options +===================== + + $ hg init zlib-level-default + $ hg init zlib-level-1 + $ cat << EOF >> zlib-level-1/.hg/hgrc + > [storage] + > revlog.zlib.level=1 + > EOF + $ hg init zlib-level-9 + $ cat << EOF >> zlib-level-9/.hg/hgrc + > [storage] + > revlog.zlib.level=9 + > EOF + + + $ commitone() { + > repo=$1 + > cp $RUNTESTDIR/bundles/issue4438-r1.hg $repo/a + > hg -R $repo add $repo/a + > hg -R $repo commit -m some-commit + > } + + $ for repo in zlib-level-default zlib-level-1 zlib-level-9; do + > commitone $repo + > done + + $ $RUNTESTDIR/f -s */.hg/store/data/* + zlib-level-1/.hg/store/data/a.i: size=4146 + zlib-level-9/.hg/store/data/a.i: size=4138 + zlib-level-default/.hg/store/data/a.i: size=4138 + +Test error cases + + $ hg init zlib-level-invalid + $ cat << EOF >> zlib-level-invalid/.hg/hgrc + > [storage] + > revlog.zlib.level=foobar + > EOF + $ commitone zlib-level-invalid + abort: storage.revlog.zlib.level is not a valid integer ('foobar') + abort: storage.revlog.zlib.level is not a valid integer ('foobar') + [255] + + $ hg init zlib-level-out-of-range + $ cat << EOF >> zlib-level-out-of-range/.hg/hgrc + > [storage] + > revlog.zlib.level=42 + > EOF + + $ commitone zlib-level-out-of-range + abort: invalid value for `storage.revlog.zlib.level` config: 42 + abort: invalid value for `storage.revlog.zlib.level` config: 42 + [255] +