view contrib/dumprevlog @ 31397:8f5ed8fa39f8

perf: perform a garbage collection before each iteration

Currently, no explicit garbage collection is performed when running
the microbenchmarks in `hg perf`. I think this is wrong because
garbage collection can have a significant impact on execution times.
And, if gc is triggered via the default heuristics, it will
fire effectively randomly during subsequent benchmark iterations
due to variable amount of garbage left over from previous runs.

Running a gc before invoking the measured function will help ensure
state is more consistent across all iterations.

#!/usr/bin/env python
# Dump revlogs as raw data stream
# $ find .hg/store/ -name "*.i" | xargs dumprevlog > repo.dump

from __future__ import absolute_import, print_function

import sys
from mercurial import (
    node,
    revlog,
    util,
)

for fp in (sys.stdin, sys.stdout, sys.stderr):
    util.setbinary(fp)

for f in sys.argv[1:]:
    binopen = lambda fn: open(fn, 'rb')
    r = revlog.revlog(binopen, f)
    print("file:", f)
    for i in r:
        n = r.node(i)
        p = r.parents(n)
        d = r.revision(n)
        print("node:", node.hex(n))
        print("linkrev:", r.linkrev(i))
        print("parents:", node.hex(p[0]), node.hex(p[1]))
        print("length:", len(d))
        print("-start-")
        print(d)
        print("-end-")