Mercurial > hg
view mercurial/namespaces.py @ 30895:c32454d69b85
zstd: vendor python-zstandard 0.7.0
Commit 3054ae3a66112970a091d3939fee32c2d0c1a23e from
https://github.com/indygreg/python-zstandard is imported without
modifications (other than removing unwanted files).
The vendored zstd library within has been upgraded from 1.1.2 to
1.1.3. This version introduced new APIs for threads, thread
pools, multi-threaded compression, and a new dictionary
builder (COVER). These features are not yet used by
python-zstandard (or Mercurial for that matter). However,
that will likely change in the next python-zstandard release
(and I think there are opportunities for Mercurial to take
advantage of the multi-threaded APIs).
Relevant to Mercurial, the CFFI bindings are now fully
implemented. This means zstd should "just work" with PyPy
(although I haven't tried). The python-zstandard test suite also
runs all tests against both the C extension and CFFI bindings to
ensure feature parity.
There is also a "decompress_content_dict_chain()" API. This was
derived from discussions with Yann Collet on list about alternate
ways of encoding delta chains.
The change most relevant to Mercurial is a performance enhancement in
the simple decompression API to reuse a data structure across
operations. This makes decompression of multiple inputs significantly
faster. (This scenario occurs when reading revlog delta chains, for
example.)
Using python-zstandard's bench.py to measure the performance
difference...
On changelog chunks in the mozilla-unified repo:
decompress discrete decompress() reuse zctx
1.262243 wall; 1.260000 CPU; 1.260000 user; 0.000000 sys 170.43 MB/s (best of 3)
0.949106 wall; 0.950000 CPU; 0.950000 user; 0.000000 sys 226.66 MB/s (best of 4)
decompress discrete dict decompress() reuse zctx
0.692170 wall; 0.690000 CPU; 0.690000 user; 0.000000 sys 310.80 MB/s (best of 5)
0.437088 wall; 0.440000 CPU; 0.440000 user; 0.000000 sys 492.17 MB/s (best of 7)
On manifest chunks in the mozilla-unified repo:
decompress discrete decompress() reuse zctx
1.367284 wall; 1.370000 CPU; 1.370000 user; 0.000000 sys 274.01 MB/s (best of 3)
1.086831 wall; 1.080000 CPU; 1.080000 user; 0.000000 sys 344.72 MB/s (best of 3)
decompress discrete dict decompress() reuse zctx
0.993272 wall; 0.990000 CPU; 0.990000 user; 0.000000 sys 377.19 MB/s (best of 3)
0.678651 wall; 0.680000 CPU; 0.680000 user; 0.000000 sys 552.06 MB/s (best of 5)
That should make reads on zstd revlogs a bit faster ;)
# no-check-commit
author | Gregory Szorc <gregory.szorc@gmail.com> |
---|---|
date | Tue, 07 Feb 2017 23:24:47 -0800 |
parents | ca52512ac709 |
children | bd872f64a8ba |
line wrap: on
line source
from __future__ import absolute_import from .i18n import _ from . import ( templatekw, util, ) def tolist(val): """ a convenience method to return an empty list instead of None """ if val is None: return [] else: return [val] class namespaces(object): """provides an interface to register and operate on multiple namespaces. See the namespace class below for details on the namespace object. """ _names_version = 0 def __init__(self): self._names = util.sortdict() # we need current mercurial named objects (bookmarks, tags, and # branches) to be initialized somewhere, so that place is here bmknames = lambda repo: repo._bookmarks.keys() bmknamemap = lambda repo, name: tolist(repo._bookmarks.get(name)) bmknodemap = lambda repo, node: repo.nodebookmarks(node) n = namespace("bookmarks", templatename="bookmark", # i18n: column positioning for "hg log" logfmt=_("bookmark: %s\n"), listnames=bmknames, namemap=bmknamemap, nodemap=bmknodemap) self.addnamespace(n) tagnames = lambda repo: [t for t, n in repo.tagslist()] tagnamemap = lambda repo, name: tolist(repo._tagscache.tags.get(name)) tagnodemap = lambda repo, node: repo.nodetags(node) n = namespace("tags", templatename="tag", # i18n: column positioning for "hg log" logfmt=_("tag: %s\n"), listnames=tagnames, namemap=tagnamemap, nodemap=tagnodemap, deprecated=set(['tip'])) self.addnamespace(n) bnames = lambda repo: repo.branchmap().keys() bnamemap = lambda repo, name: tolist(repo.branchtip(name, True)) bnodemap = lambda repo, node: [repo[node].branch()] n = namespace("branches", templatename="branch", # i18n: column positioning for "hg log" logfmt=_("branch: %s\n"), listnames=bnames, namemap=bnamemap, nodemap=bnodemap) self.addnamespace(n) def __getitem__(self, namespace): """returns the namespace object""" return self._names[namespace] def __iter__(self): return self._names.__iter__() def iteritems(self): return self._names.iteritems() def addnamespace(self, namespace, order=None): """register a namespace namespace: the name to be registered (in plural form) order: optional argument to specify the order of namespaces (e.g. 'branches' should be listed before 'bookmarks') """ if order is not None: self._names.insert(order, namespace.name, namespace) else: self._names[namespace.name] = namespace # we only generate a template keyword if one does not already exist if namespace.name not in templatekw.keywords: def generatekw(**args): return templatekw.shownames(namespace.name, **args) templatekw.keywords[namespace.name] = generatekw def singlenode(self, repo, name): """ Return the 'best' node for the given name. Best means the first node in the first nonempty list returned by a name-to-nodes mapping function in the defined precedence order. Raises a KeyError if there is no such node. """ for ns, v in self._names.iteritems(): n = v.namemap(repo, name) if n: # return max revision number if len(n) > 1: cl = repo.changelog maxrev = max(cl.rev(node) for node in n) return cl.node(maxrev) return n[0] raise KeyError(_('no such name: %s') % name) class namespace(object): """provides an interface to a namespace Namespaces are basically generic many-to-many mapping between some (namespaced) names and nodes. The goal here is to control the pollution of jamming things into tags or bookmarks (in extension-land) and to simplify internal bits of mercurial: log output, tab completion, etc. More precisely, we define a mapping of names to nodes, and a mapping from nodes to names. Each mapping returns a list. Furthermore, each name mapping will be passed a name to lookup which might not be in its domain. In this case, each method should return an empty list and not raise an error. This namespace object will define the properties we need: 'name': the namespace (plural form) 'templatename': name to use for templating (usually the singular form of the plural namespace name) 'listnames': list of all names in the namespace (usually the keys of a dictionary) 'namemap': function that takes a name and returns a list of nodes 'nodemap': function that takes a node and returns a list of names 'deprecated': set of names to be masked for ordinary use """ def __init__(self, name, templatename=None, logname=None, colorname=None, logfmt=None, listnames=None, namemap=None, nodemap=None, deprecated=None): """create a namespace name: the namespace to be registered (in plural form) templatename: the name to use for templating logname: the name to use for log output; if not specified templatename is used colorname: the name to use for colored log output; if not specified logname is used logfmt: the format to use for (i18n-ed) log output; if not specified it is composed from logname listnames: function to list all names namemap: function that inputs a name, output node(s) nodemap: function that inputs a node, output name(s) deprecated: set of names to be masked for ordinary use """ self.name = name self.templatename = templatename self.logname = logname self.colorname = colorname self.logfmt = logfmt self.listnames = listnames self.namemap = namemap self.nodemap = nodemap # if logname is not specified, use the template name as backup if self.logname is None: self.logname = self.templatename # if colorname is not specified, just use the logname as a backup if self.colorname is None: self.colorname = self.logname # if logfmt is not specified, compose it from logname as backup if self.logfmt is None: # i18n: column positioning for "hg log" self.logfmt = ("%s:" % self.logname).ljust(13) + "%s\n" if deprecated is None: self.deprecated = set() else: self.deprecated = deprecated def names(self, repo, node): """method that returns a (sorted) list of names in a namespace that match a given node""" return sorted(self.nodemap(repo, node)) def nodes(self, repo, name): """method that returns a list of nodes in a namespace that match a given name. """ return sorted(self.namemap(repo, name))