view mercurial/revlogutils/__init__.py @ 48178:f12a19d03d2c

fix: reduce number of tool executions By grouping together (path, ctx) pairs according to the inputs they would provide to fixer tools, we can deduplicate executions of fixer tools to significantly reduce the amount of time spent running slow tools. This change does not handle clean files in the working copy, which could still be deduplicated against the files in the checked out commit. It's a little harder to do that because the filerev is not available in the workingfilectx (and it doesn't exist for added files). Anecdotally, this change makes some real uses cases at Google 10x faster. I think we were originally hesitant to do this because the benefits weren't obvious, and implementing it efficiently is kind of tricky. If we simply memoized the formatter execution function, we would be keeping tons of file content in memory. Also included is a regression test for a corner case that I broke with my first attempt at optimizing this code. Differential Revision: https://phab.mercurial-scm.org/D11280
author Danny Hooper <hooper@google.com>
date Thu, 02 Sep 2021 14:08:45 -0700
parents 34cc102c73f5
children 52034c42c09d
line wrap: on
line source

# mercurial.revlogutils -- basic utilities for revlog
#
# Copyright 2019 Pierre-Yves David <pierre-yves.david@octobus.net>
#
# 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

from ..thirdparty import attr
from ..interfaces import repository

# See mercurial.revlogutils.constants for doc
COMP_MODE_INLINE = 2


def offset_type(offset, type):
    if (type & ~repository.REVISION_FLAGS_KNOWN) != 0:
        raise ValueError(b'unknown revlog index flags: %d' % type)
    return int(int(offset) << 16 | type)


def entry(
    data_offset,
    data_compressed_length,
    data_delta_base,
    link_rev,
    parent_rev_1,
    parent_rev_2,
    node_id,
    flags=0,
    data_uncompressed_length=-1,
    data_compression_mode=COMP_MODE_INLINE,
    sidedata_offset=0,
    sidedata_compressed_length=0,
    sidedata_compression_mode=COMP_MODE_INLINE,
):
    """Build one entry from symbolic name

    This is useful to abstract the actual detail of how we build the entry
    tuple for caller who don't care about it.

    This should always be called using keyword arguments. Some arguments have
    default value, this match the value used by index version that does not store such data.
    """
    return (
        offset_type(data_offset, flags),
        data_compressed_length,
        data_uncompressed_length,
        data_delta_base,
        link_rev,
        parent_rev_1,
        parent_rev_2,
        node_id,
        sidedata_offset,
        sidedata_compressed_length,
        data_compression_mode,
        sidedata_compression_mode,
    )


@attr.s(slots=True, frozen=True)
class revisioninfo(object):
    """Information about a revision that allows building its fulltext
    node:       expected hash of the revision
    p1, p2:     parent revs of the revision
    btext:      built text cache consisting of a one-element list
    cachedelta: (baserev, uncompressed_delta) or None
    flags:      flags associated to the revision storage

    One of btext[0] or cachedelta must be set.
    """

    node = attr.ib()
    p1 = attr.ib()
    p2 = attr.ib()
    btext = attr.ib()
    textlen = attr.ib()
    cachedelta = attr.ib()
    flags = attr.ib()