mercurial/revlogutils/sidedata.py

copies: avoid instancing more changectx to access parent revisions

We just need to know the revision numbers of the parents, creating full context
is needlessly expensive.

This provide a small, but noticeable performance boost.

revision: large amount; added files: large amount; rename small amount; c3b14617fbd7 9ba6ab77fd29
before: ! wall 2.885636 comb 2.900000 user 2.870000 sys 0.030000 (median of 10)
after:  ! wall 2.702270 comb 2.710000 user 2.690000 sys 0.020000 (median of 10)
revision: large amount; added files: small amount; rename small amount; c3b14617fbd7 f650a9b140d2
before: ! wall 4.298271 comb 4.290000 user 4.240000 sys 0.050000 (median of 10)
after:  ! wall 3.976610 comb 3.970000 user 3.920000 sys 0.050000 (median of 10)
revision: large amount; added files: large amount; rename large amount; 08ea3258278e d9fa043f30c0
before: ! wall 0.773397 comb 0.770000 user 0.770000 sys 0.000000 (median of 11)
after:  ! wall 0.701634 comb 0.700000 user 0.700000 sys 0.000000 (median of 13)
revision: small amount; added files: large amount; rename large amount; df6f7a526b60 a83dc6a2d56f
before: ! wall 0.013585 comb 0.010000 user 0.010000 sys 0.000000 (median of 217)
after:  ! wall 0.013550 comb 0.010000 user 0.010000 sys 0.000000 (median of 218)
revision: small amount; added files: large amount; rename small amount; 4aa4e1f8e19a 169138063d63
before: ! wall 0.003202 comb 0.000000 user 0.000000 sys 0.000000 (median of 929)
after:  ! wall 0.002993 comb 0.010000 user 0.010000 sys 0.000000 (median of 992)
revision: small amount; added files: small amount; rename small amount; 4bc173b045a6 964879152e2e
before: ! wall 0.000077 comb 0.000000 user 0.000000 sys 0.000000 (median of 12060)
after:  ! wall 0.000072 comb 0.000000 user 0.000000 sys 0.000000 (median of 12804)
revision: medium amount; added files: large amount; rename medium amount; c95f1ced15f2 2c68e87c3efe
before: ! wall 0.510614 comb 0.500000 user 0.500000 sys 0.000000 (median of 18)
after:  ! wall 0.473681 comb 0.470000 user 0.470000 sys 0.000000 (median of 20)
revision: medium amount; added files: medium amount; rename small amount; d343da0c55a8 d7746d32bf9d
before: ! wall 0.126552 comb 0.130000 user 0.130000 sys 0.000000 (median of 77)
after:  ! wall 0.115240 comb 0.110000 user 0.110000 sys 0.000000 (median of 85)

Differential Revision: https://phab.mercurial-scm.org/D7122

# sidedata.py - Logic around store extra data alongside revlog revisions
#
# Copyright 2019 Pierre-Yves David <[e-mail])
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
"""core code for "sidedata" support

The "sidedata" are stored alongside the revision without actually being part of
its content and not affecting its hash. It's main use cases is to cache
important information related to a changesets.

The current implementation is experimental and subject to changes. Do not rely
on it in production.

Sidedata are stored in the revlog itself, withing the revision rawtext. They
are inserted, removed from it using the flagprocessors mechanism. The following
format is currently used::

    initial header:
        <number of sidedata; 2 bytes>
    sidedata (repeated N times):
        <sidedata-key; 2 bytes>
        <sidedata-entry-length: 4 bytes>
        <sidedata-content-sha1-digest: 20 bytes>
        <sidedata-content; X bytes>
    normal raw text:
        <all bytes remaining in the rawtext>

This is a simple and effective format. It should be enought to experiment with
the concept.
"""

from __future__ import absolute_import

import hashlib
import struct

from .. import error

## sidedata type constant
# reserve a block for testing purposes.
SD_TEST1 = 1
SD_TEST2 = 2
SD_TEST3 = 3
SD_TEST4 = 4
SD_TEST5 = 5
SD_TEST6 = 6
SD_TEST7 = 7

# key to store copies related information
SD_P1COPIES = 8
SD_P2COPIES = 9
SD_FILESADDED = 10
SD_FILESREMOVED = 11

# internal format constant
SIDEDATA_HEADER = struct.Struct(r'>H')
SIDEDATA_ENTRY = struct.Struct(r'>HL20s')


def sidedatawriteprocessor(rl, text, sidedata):
    sidedata = list(sidedata.items())
    sidedata.sort()
    rawtext = [SIDEDATA_HEADER.pack(len(sidedata))]
    for key, value in sidedata:
        digest = hashlib.sha1(value).digest()
        rawtext.append(SIDEDATA_ENTRY.pack(key, len(value), digest))
    for key, value in sidedata:
        rawtext.append(value)
    rawtext.append(bytes(text))
    return b''.join(rawtext), False


def sidedatareadprocessor(rl, text):
    sidedata = {}
    offset = 0
    (nbentry,) = SIDEDATA_HEADER.unpack(text[: SIDEDATA_HEADER.size])
    offset += SIDEDATA_HEADER.size
    dataoffset = SIDEDATA_HEADER.size + (SIDEDATA_ENTRY.size * nbentry)
    for i in range(nbentry):
        nextoffset = offset + SIDEDATA_ENTRY.size
        key, size, storeddigest = SIDEDATA_ENTRY.unpack(text[offset:nextoffset])
        offset = nextoffset
        # read the data associated with that entry
        nextdataoffset = dataoffset + size
        entrytext = text[dataoffset:nextdataoffset]
        readdigest = hashlib.sha1(entrytext).digest()
        if storeddigest != readdigest:
            raise error.SidedataHashError(key, storeddigest, readdigest)
        sidedata[key] = entrytext
        dataoffset = nextdataoffset
    text = text[dataoffset:]
    return text, True, sidedata


def sidedatarawprocessor(rl, text):
    # side data modifies rawtext and prevent rawtext hash validation
    return False


processors = (
    sidedatareadprocessor,
    sidedatawriteprocessor,
    sidedatarawprocessor,
)