Mercurial > hg
view mercurial/namespaces.py @ 30212:260af19891f2
changegroup: increase write buffer size to 128k
By default, Python defers to the operating system for choosing the
default buffer size on opened files. On my Linux machine, the default
is 4k, which is really small for 2016.
This patch bumps the write buffer size when writing
changegroups/bundles to 128k. This matches the 128k read buffer
we already use on revlogs.
It's worth noting that this only impacts when writing to an explicit
file (such as during `hg bundle`). Buffers when writing to bundle
files via the repo vfs or to a temporary file are not impacted.
When producing a none-v2 bundle file of the mozilla-unified repository,
this change caused the number of write() system calls to drop from
952,449 to 29,788. After this change, the most frequent system
calls are fstat(), read(), lseek(), and open(). There were
2,523,672 system calls after this patch (so a net decrease of
~950k is statistically significant).
This change shows no performance change on my system. But I have a
high-end system with a fast SSD. It is quite possible this change
will have a significant impact on network file systems, where
extra network round trips due to excessive I/O system calls could
introduce significant latency.
author | Gregory Szorc <gregory.szorc@gmail.com> |
---|---|
date | Sun, 16 Oct 2016 13:35:23 -0700 |
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))