contrib/phab-clean.py

clone: properly exclude rev-branch-cache from post clone cache warming

When adding "CACHE_REV_BRANCH" to "CACHES_ALL" in e51161b12c7e, I did not
expected it to impact the clone steps. However the "CACHES_POST_CLONE" set is
created rather creatively. (we should fix that, but not on stable)

The benchmark caught a quite significant slowdown one hardlink and ssh-stream
clones. Such slow down can be reduced to around ~5% by fully warming the cache
before the clone. However keeping this expensive step away from the clone
operation fully fix the slowdown and preserve the initial intend.


Example slowdow for hardlink clone

### benchmark.name                               = hg.command.clone
  # bin-env-vars.hg.flavor                       = default
  # bin-env-vars.hg.py-re2-module                = default
  # benchmark.variants.explicit-rev              = none
  # benchmark.variants.issue6528                 = default
  # benchmark.variants.protocol                  = local-hardlink
  # benchmark.variants.pulled-delta-reuse-policy = default
  # benchmark.variants.resource-usage            = default
  # benchmark.variants.validate                  = default
 ## data-env-vars.name = netbeans-2018-08-01-zstd-sparse-revlog
6.8.2:  19.799752
6.9rc0: 29.017493  (+46.55%, +9.22)
after:  19.929341

 ## data-env-vars.name = mercurial-public-2018-08-01-zstd-sparse-revlog
6.8.2:  0.468020
6.9rc0: 1.701294 (+263.51%, +1.23)
after:  0.471934

 ## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog
6.8.2:  2.397564
6.9rc0: 5.666641 (+137.41%, +3.28)
after:  2.428085

#!/usr/bin/env python3
#
# A small script to automatically reject idle Diffs
#
# you need to set the PHABBOT_USER and PHABBOT_TOKEN environment variable for authentication

import datetime
import os
import sys

import phabricator

MESSAGE = """There seems to have been no activities on this Diff for the past 3 Months.

By policy, we are automatically moving it out of the `need-review` state.

Please, move it back to `need-review` without hesitation if this diff should still be discussed.

:baymax:need-review-idle:
"""


PHAB_URL = "https://phab.mercurial-scm.org/api/"
USER = os.environ.get("PHABBOT_USER", "baymax")
TOKEN = os.environ.get("PHABBOT_TOKEN")


NOW = datetime.datetime.now()

# 3 months in seconds
DELAY = 60 * 60 * 24 * 30 * 3


def get_all_diff(phab):
    """Fetch all the diff that the need review"""
    return phab.differential.query(
        status="status-needs-review",
        order="order-modified",
        paths=[('HG', None)],
    )


def filter_diffs(diffs, older_than):
    """filter diffs to only keep the one unmodified sin <older_than> seconds"""
    olds = []
    for d in diffs:
        modified = int(d['dateModified'])
        modified = datetime.datetime.fromtimestamp(modified)
        d["idleFor"] = idle_for = NOW - modified
        if idle_for.total_seconds() > older_than:
            olds.append(d)
    return olds


def nudge_diff(phab, diff):
    """Comment on the idle diff and reject it"""
    diff_id = int(d['id'])
    phab.differential.createcomment(
        revision_id=diff_id, message=MESSAGE, action="reject"
    )


if not USER:
    print(
        "not user specified please set PHABBOT_USER and PHABBOT_TOKEN",
        file=sys.stderr,
    )
elif not TOKEN:
    print(
        "not api-token specified please set PHABBOT_USER and PHABBOT_TOKEN",
        file=sys.stderr,
    )
    sys.exit(1)

phab = phabricator.Phabricator(USER, host=PHAB_URL, token=TOKEN)
phab.connect()
phab.update_interfaces()
print('Hello "%s".' % phab.user.whoami()['realName'])

diffs = get_all_diff(phab)
print("Found %d Diffs" % len(diffs))
olds = filter_diffs(diffs, DELAY)
print("Found %d old Diffs" % len(olds))
for d in olds:
    diff_id = d['id']
    status = d['statusName']
    modified = int(d['dateModified'])
    idle_for = d["idleFor"]
    msg = 'nudging D%s in "%s" state for %s'
    print(msg % (diff_id, status, idle_for))
    # uncomment to actually affect phab
    nudge_diff(phab, d)