Mercurial > hg
view mercurial/statichttprepo.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
author | Pierre-Yves David <pierre-yves.david@octobus.net> |
---|---|
date | Wed, 27 Mar 2019 18:35:59 +0100 |
parents | 328ca3b9e545 |
children | d345627d104b |
line wrap: on
line source
# statichttprepo.py - simple http repository class for mercurial # # This provides read-only repo access to repositories exported via static http # # Copyright 2005-2007 Matt Mackall <mpm@selenic.com> # # 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 import errno from .i18n import _ from . import ( branchmap, changelog, error, localrepo, manifest, namespaces, pathutil, pycompat, url, util, vfs as vfsmod, ) urlerr = util.urlerr urlreq = util.urlreq class httprangereader(object): def __init__(self, url, opener): # we assume opener has HTTPRangeHandler self.url = url self.pos = 0 self.opener = opener self.name = url def __enter__(self): return self def __exit__(self, exc_type, exc_value, traceback): self.close() def seek(self, pos): self.pos = pos def read(self, bytes=None): req = urlreq.request(pycompat.strurl(self.url)) end = '' if bytes: end = self.pos + bytes - 1 if self.pos or end: req.add_header(r'Range', r'bytes=%d-%s' % (self.pos, end)) try: f = self.opener.open(req) data = f.read() code = f.code except urlerr.httperror as inst: num = inst.code == 404 and errno.ENOENT or None raise IOError(num, inst) except urlerr.urlerror as inst: raise IOError(None, inst.reason) if code == 200: # HTTPRangeHandler does nothing if remote does not support # Range headers and returns the full entity. Let's slice it. if bytes: data = data[self.pos:self.pos + bytes] else: data = data[self.pos:] elif bytes: data = data[:bytes] self.pos += len(data) return data def readlines(self): return self.read().splitlines(True) def __iter__(self): return iter(self.readlines()) def close(self): pass # _RangeError and _HTTPRangeHandler were originally in byterange.py, # which was itself extracted from urlgrabber. See the last version of # byterange.py from history if you need more information. class _RangeError(IOError): """Error raised when an unsatisfiable range is requested.""" class _HTTPRangeHandler(urlreq.basehandler): """Handler that enables HTTP Range headers. This was extremely simple. The Range header is a HTTP feature to begin with so all this class does is tell urllib2 that the "206 Partial Content" response from the HTTP server is what we expected. """ def http_error_206(self, req, fp, code, msg, hdrs): # 206 Partial Content Response r = urlreq.addinfourl(fp, hdrs, req.get_full_url()) r.code = code r.msg = msg return r def http_error_416(self, req, fp, code, msg, hdrs): # HTTP's Range Not Satisfiable error raise _RangeError('Requested Range Not Satisfiable') def build_opener(ui, authinfo): # urllib cannot handle URLs with embedded user or passwd urlopener = url.opener(ui, authinfo) urlopener.add_handler(_HTTPRangeHandler()) class statichttpvfs(vfsmod.abstractvfs): def __init__(self, base): self.base = base def __call__(self, path, mode='r', *args, **kw): if mode not in ('r', 'rb'): raise IOError('Permission denied') f = "/".join((self.base, urlreq.quote(path))) return httprangereader(f, urlopener) def join(self, path): if path: return pathutil.join(self.base, path) else: return self.base return statichttpvfs class statichttppeer(localrepo.localpeer): def local(self): return None def canpush(self): return False class statichttprepository(localrepo.localrepository, localrepo.revlogfilestorage): supported = localrepo.localrepository._basesupported def __init__(self, ui, path): self._url = path self.ui = ui self.root = path u = util.url(path.rstrip('/') + "/.hg") self.path, authinfo = u.authinfo() vfsclass = build_opener(ui, authinfo) self.vfs = vfsclass(self.path) self.cachevfs = vfsclass(self.vfs.join('cache')) self._phasedefaults = [] self.names = namespaces.namespaces() self.filtername = None try: requirements = set(self.vfs.read(b'requires').splitlines()) except IOError as inst: if inst.errno != errno.ENOENT: raise requirements = set() # check if it is a non-empty old-style repository try: fp = self.vfs("00changelog.i") fp.read(1) fp.close() except IOError as inst: if inst.errno != errno.ENOENT: raise # we do not care about empty old-style repositories here msg = _("'%s' does not appear to be an hg repository") % path raise error.RepoError(msg) supportedrequirements = localrepo.gathersupportedrequirements(ui) localrepo.ensurerequirementsrecognized(requirements, supportedrequirements) localrepo.ensurerequirementscompatible(ui, requirements) # setup store self.store = localrepo.makestore(requirements, self.path, vfsclass) self.spath = self.store.path self.svfs = self.store.opener self.sjoin = self.store.join self._filecache = {} self.requirements = requirements rootmanifest = manifest.manifestrevlog(self.svfs) self.manifestlog = manifest.manifestlog(self.svfs, self, rootmanifest, self.narrowmatch()) self.changelog = changelog.changelog(self.svfs) self._tags = None self.nodetagscache = None self._branchcaches = branchmap.BranchMapCache() self._revbranchcache = None self.encodepats = None self.decodepats = None self._transref = None def _restrictcapabilities(self, caps): caps = super(statichttprepository, self)._restrictcapabilities(caps) return caps.difference(["pushkey"]) def url(self): return self._url def local(self): return False def peer(self): return statichttppeer(self) def wlock(self, wait=True): raise error.LockUnavailable(0, _('lock not available'), 'lock', _('cannot lock static-http repository')) def lock(self, wait=True): raise error.Abort(_('cannot lock static-http repository')) def _writecaches(self): pass # statichttprepository are read only def instance(ui, path, create, intents=None, createopts=None): if create: raise error.Abort(_('cannot create new static-http repository')) return statichttprepository(ui, path[7:])