hgwebdir: avoid systematic full garbage collection
Forcing a systematic full garbage collection upon each request
can serioulsy harm performance. This is reported as
https://bz.mercurial-scm.org/show_bug.cgi?id=6075
With this change we're performing the full collection according
to a new setting, `experimental.web.full-garbage-collection-rate`.
The default value is 1, which doesn't change the behavior and will
allow us to test on real use cases. If the value is 0, no full garbage
collection occurs.
Regardless of the value of the setting, a partial garbage collection
still occurs upon each request (not attempting to collect objects from
the oldest generation). This should be enough to take care of
reference cycles that have been created by the last request
(assessment of this requires changing the setting, not to be 1).
In my experience chasing memory leaks in Mercurial servers,
the full collection never reclaimed any memory, but this is with
Python 3 and biased towards small repositories.
On the other hand, as explained in the Python developer docs [1],
frequent full collections are very harmful in terms of performance if
lots of objects survive the collection, and hence stay in the
oldest generation. Note that `gc.collect()` is indeed trying to
collect the oldest generation [2]. This happens usually in two cases:
- unwanted lingering objects (i.e., an actual memory leak that
the GC cannot do anything about). Sadly, we have lots of those
these days.
- desireable long-term objects, typically in caches (not inner caches
carried by repositories, which should be collected with them). This
is a subject of interest for the Heptapod project.
In short, the flat rate that this change still permits is
probably a bad idea in most cases, and the default value can
be tweaked later on (or even be set to 0) according to experiments
in the wild.
The test is inspired from test-hgwebdir-paths.py
[1] https://devguide.python.org/garbage_collector/#collecting-the-oldest-generation
[2] https://docs.python.org/3/library/gc.html#gc.collect
Differential Revision: https://phab.mercurial-scm.org/D11204
# common patterns in test at can safely be replaced
from __future__ import absolute_import
import os
substitutions = [
# list of possible compressions
(br'(zstd,)?zlib,none,bzip2', br'$USUAL_COMPRESSIONS$'),
(br'=(zstd,)?zlib', br'=$BUNDLE2_COMPRESSIONS$'),
# capabilities sent through http
(
br'bundlecaps=HG20%2Cbundle2%3DHG20%250A'
br'bookmarks%250A'
br'changegroup%253D01%252C02%250A'
br'checkheads%253Drelated%250A'
br'digests%253Dmd5%252Csha1%252Csha512%250A'
br'error%253Dabort%252Cunsupportedcontent%252Cpushraced%252Cpushkey%250A'
br'hgtagsfnodes%250A'
br'listkeys%250A'
br'phases%253Dheads%250A'
br'pushkey%250A'
br'remote-changegroup%253Dhttp%252Chttps%250A'
br'stream%253Dv2',
# (the replacement patterns)
br'$USUAL_BUNDLE_CAPS$',
),
(
br'bundlecaps=HG20%2Cbundle2%3DHG20%250A'
br'bookmarks%250A'
br'changegroup%253D01%252C02%250A'
br'checkheads%3Drelated%0A'
br'digests%253Dmd5%252Csha1%252Csha512%250A'
br'error%253Dabort%252Cunsupportedcontent%252Cpushraced%252Cpushkey%250A'
br'hgtagsfnodes%250A'
br'listkeys%250A'
br'phases%253Dheads%250A'
br'pushkey%250A'
br'remote-changegroup%253Dhttp%252Chttps',
# (the replacement patterns)
br'$USUAL_BUNDLE_CAPS_SERVER$',
),
# bundle2 capabilities sent through ssh
(
br'bundle2=HG20%0A'
br'bookmarks%0A'
br'changegroup%3D01%2C02%0A'
br'checkheads%3Drelated%0A'
br'digests%3Dmd5%2Csha1%2Csha512%0A'
br'error%3Dabort%2Cunsupportedcontent%2Cpushraced%2Cpushkey%0A'
br'hgtagsfnodes%0A'
br'listkeys%0A'
br'phases%3Dheads%0A'
br'pushkey%0A'
br'remote-changegroup%3Dhttp%2Chttps%0A'
br'stream%3Dv2',
# (replacement patterns)
br'$USUAL_BUNDLE2_CAPS$',
),
# bundle2 capabilities advertised by the server
(
br'bundle2=HG20%0A'
br'bookmarks%0A'
br'changegroup%3D01%2C02%0A'
br'checkheads%3Drelated%0A'
br'digests%3Dmd5%2Csha1%2Csha512%0A'
br'error%3Dabort%2Cunsupportedcontent%2Cpushraced%2Cpushkey%0A'
br'hgtagsfnodes%0A'
br'listkeys%0A'
br'phases%3Dheads%0A'
br'pushkey%0A'
br'remote-changegroup%3Dhttp%2Chttps',
# (replacement patterns)
br'$USUAL_BUNDLE2_CAPS_SERVER$',
),
(
br'bundle2=HG20%0A'
br'bookmarks%0A'
br'changegroup%3D01%2C02%0A'
br'digests%3Dmd5%2Csha1%2Csha512%0A'
br'error%3Dabort%2Cunsupportedcontent%2Cpushraced%2Cpushkey%0A'
br'hgtagsfnodes%0A'
br'listkeys%0A'
br'pushkey%0A'
br'remote-changegroup%3Dhttp%2Chttps%0A'
br'stream%3Dv2',
# (replacement patterns)
br'$USUAL_BUNDLE2_CAPS_NO_PHASES$',
),
# HTTP access log dates
(
br' - - \[\d\d/.../2\d\d\d \d\d:\d\d:\d\d] "(GET|PUT|POST)',
lambda m: br' - - [$LOGDATE$] "' + m.group(1),
),
# HTTP error log dates
(
br' - - \[\d\d/.../2\d\d\d \d\d:\d\d:\d\d] (HG error:|Exception)',
lambda m: br' - - [$ERRDATE$] ' + m.group(1),
),
# HTTP header dates- RFC 1123
(
br'([Dd]ate): [A-Za-z]{3}, \d\d [A-Za-z]{3} \d{4} \d\d:\d\d:\d\d GMT',
lambda m: br'%s: $HTTP_DATE$' % m.group(1),
),
# LFS expiration value
(
br'"expires_at": "\d{4}-\d\d-\d\dT\d\d:\d\d:\d\dZ"',
br'"expires_at": "$ISO_8601_DATE_TIME$"',
),
# Windows has an extra '/' in the following lines that get globbed away:
# pushing to file:/*/$TESTTMP/r2 (glob)
# comparing with file:/*/$TESTTMP/r2 (glob)
# sub/maybelarge.dat: largefile 34..9c not available from
# file:/*/$TESTTMP/largefiles-repo (glob)
(
br'(.*file:/)/?(/\$TESTTMP.*)',
lambda m: m.group(1) + b'*' + m.group(2) + b' (glob)',
),
]
# Various platform error strings, keyed on a common replacement string
_errors = {
br'$ENOENT$': (
# IOError in Python does not have the same error message
# than in Rust, and automatic conversion is not possible
# because of module member privacy.
br'No such file or directory \(os error 2\)',
# strerror()
br'No such file or directory',
# FormatMessage(ERROR_FILE_NOT_FOUND)
br'The system cannot find the file specified',
),
br'$ENOTDIR$': (
# strerror()
br'Not a directory',
# FormatMessage(ERROR_PATH_NOT_FOUND)
br'The system cannot find the path specified',
),
br'$ECONNRESET$': (
# strerror()
br'Connection reset by peer',
# FormatMessage(WSAECONNRESET)
br'An existing connection was forcibly closed by the remote host',
),
br'$EADDRINUSE$': (
# strerror()
br'Address already in use',
# FormatMessage(WSAEADDRINUSE)
br'Only one usage of each socket address'
br' \(protocol/network address/port\) is normally permitted',
),
br'$EADDRNOTAVAIL$': (
# strerror()
br'Cannot assign requested address',
# FormatMessage(WSAEADDRNOTAVAIL)
),
}
for replace, msgs in _errors.items():
substitutions.extend((m, replace) for m in msgs)
# Output lines on Windows that can be autocorrected for '\' vs '/' path
# differences.
_winpathfixes = [
# cloning subrepo s\ss from $TESTTMP/t/s/ss
# cloning subrepo foo\bar from http://localhost:$HGPORT/foo/bar
br'(?m)^cloning subrepo \S+\\.*',
# pulling from $TESTTMP\issue1852a
br'(?m)^pulling from \$TESTTMP\\.*',
# pushing to $TESTTMP\a
br'(?m)^pushing to \$TESTTMP\\.*',
# pushing subrepo s\ss to $TESTTMP/t/s/ss
br'(?m)^pushing subrepo \S+\\\S+ to.*',
# moving d1\d11\a1 to d3/d11/a1
br'(?m)^moving \S+\\.*',
# d1\a: not recording move - dummy does not exist
br'\S+\\\S+: not recording move .+',
# reverting s\a
br'(?m)^reverting (?!subrepo ).*\\.*',
# saved backup bundle to
# $TESTTMP\test\.hg\strip-backup/443431ffac4f-2fc5398a-backup.hg
br'(?m)^saved backup bundle to \$TESTTMP.*\.hg',
# no changes made to subrepo s\ss since last push to ../tcc/s/ss
br'(?m)^no changes made to subrepo \S+\\\S+ since.*',
# changeset 5:9cc5aa7204f0: stuff/maybelarge.dat references missing
# $TESTTMP\largefiles-repo-hg\.hg\largefiles\76..38
br'(?m)^changeset .* references (corrupted|missing) \$TESTTMP\\.*',
# stuff/maybelarge.dat: largefile 76..38 not available from
# file:/*/$TESTTMP\largefiles-repo (glob)
br'.*: largefile \S+ not available from file:/\*/.+',
]
if os.name == 'nt':
substitutions.extend(
[
(s, lambda match: match.group().replace(b'\\', b'/'))
for s in _winpathfixes
]
)