##// END OF EJS Templates
util: optimize cost auditing on insert...
util: optimize cost auditing on insert Calling popoldest() on insert with cost auditing enabled introduces significant overhead. The primary reason for this overhead is that popoldest() needs to walk the linked list to find the first non-empty node. When we call popoldest() within a loop, this can become quadratic. The performance impact is more pronounced on caches with large capacities. This commit effectively inlines the popoldest() call into _enforcecostlimit(). By doing so, we only do the backwards walk to find the first empty node once. However, we still may still perform this work on insert when the cache is near cost capacity. So this is only a partial performance win. $ hg perflrucachedict --size 4 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 100 ! gets w/ cost limit ! wall 0.598737 comb 0.590000 user 0.590000 sys 0.000000 (best of 17) ! inserts w/ cost limit ! wall 1.694282 comb 1.700000 user 1.700000 sys 0.000000 (best of 6) ! wall 1.659181 comb 1.650000 user 1.650000 sys 0.000000 (best of 7) ! mixed w/ cost limit ! wall 1.157655 comb 1.150000 user 1.150000 sys 0.000000 (best of 9) ! wall 1.139955 comb 1.140000 user 1.140000 sys 0.000000 (best of 9) $ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 10000 ! gets w/ cost limit ! wall 0.598526 comb 0.600000 user 0.600000 sys 0.000000 (best of 17) ! wall 0.601993 comb 0.600000 user 0.600000 sys 0.000000 (best of 17) ! inserts w/ cost limit ! wall 37.838315 comb 37.840000 user 37.840000 sys 0.000000 (best of 3) ! wall 25.105273 comb 25.080000 user 25.080000 sys 0.000000 (best of 3) ! mixed w/ cost limit ! wall 18.060198 comb 18.060000 user 18.060000 sys 0.000000 (best of 3) ! wall 12.104470 comb 12.070000 user 12.070000 sys 0.000000 (best of 3) $ hg perflrucachedict --size 1000 --gets 1000000 --sets 1000000 --mixed 1000000 --costlimit 10000 --mixedgetfreq 90 ! gets w/ cost limit ! wall 0.600024 comb 0.600000 user 0.600000 sys 0.000000 (best of 17) ! wall 0.614439 comb 0.620000 user 0.620000 sys 0.000000 (best of 17) ! inserts w/ cost limit ! wall 37.154547 comb 37.120000 user 37.120000 sys 0.000000 (best of 3) ! wall 25.963028 comb 25.960000 user 25.960000 sys 0.000000 (best of 3) ! mixed w/ cost limit ! wall 4.381602 comb 4.380000 user 4.370000 sys 0.010000 (best of 3) ! wall 3.174256 comb 3.170000 user 3.170000 sys 0.000000 (best of 4) Differential Revision: https://phab.mercurial-scm.org/D4504

File last commit:

r39482:5bfab940 default
r39605:cc23c09b default
Show More
state.py
87 lines | 2.8 KiB | text/x-python | PythonLexer
# state.py - writing and reading state files in Mercurial
#
# Copyright 2018 Pulkit Goyal <pulkitmgoyal@gmail.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
"""
This file contains class to wrap the state for commands and other
related logic.
All the data related to the command state is stored as dictionary in the object.
The class has methods using which the data can be stored to disk in a file under
.hg/ directory.
We store the data on disk in cbor, for which we use the third party cbor library
to serialize and deserialize data.
"""
from __future__ import absolute_import
from . import (
error,
util,
)
from .utils import (
cborutil,
)
class cmdstate(object):
"""a wrapper class to store the state of commands like `rebase`, `graft`,
`histedit`, `shelve` etc. Extensions can also use this to write state files.
All the data for the state is stored in the form of key-value pairs in a
dictionary.
The class object can write all the data to a file in .hg/ directory and
can populate the object data reading that file.
Uses cbor to serialize and deserialize data while writing and reading from
disk.
"""
def __init__(self, repo, fname):
""" repo is the repo object
fname is the file name in which data should be stored in .hg directory
"""
self._repo = repo
self.fname = fname
def read(self):
"""read the existing state file and return a dict of data stored"""
return self._read()
def save(self, version, data):
"""write all the state data stored to .hg/<filename> file
we use third-party library cbor to serialize data to write in the file.
"""
if not isinstance(version, int):
raise error.ProgrammingError("version of state file should be"
" an integer")
with self._repo.vfs(self.fname, 'wb', atomictemp=True) as fp:
fp.write('%d\n' % version)
for chunk in cborutil.streamencode(data):
fp.write(chunk)
def _read(self):
"""reads the state file and returns a dictionary which contain
data in the same format as it was before storing"""
with self._repo.vfs(self.fname, 'rb') as fp:
try:
int(fp.readline())
except ValueError:
raise error.CorruptedState("unknown version of state file"
" found")
return cborutil.decodeall(fp.read())[0]
def delete(self):
"""drop the state file if exists"""
util.unlinkpath(self._repo.vfs.join(self.fname), ignoremissing=True)
def exists(self):
"""check whether the state file exists or not"""
return self._repo.vfs.exists(self.fname)