view contrib/fuzz/mpatch.cc @ 38956:a3cabe9415e1

dirstate: use visitchildrenset in traverse This speeds up `hg status` a fair amount when there is a very large directory and narrow is in use. Timing numbers according to command: hyperfine --warmup 1 'hg status' HGRCPATH points to a file with the following contents: [extensions] narrow = mozilla-unified (called m-u below) was at revision #468856. regular hash: eb39298e432d treemanifests hash: 0553b7f29eaf large-dir-repo (called l-d-r below) was generated with the following script: #!/bin/bash hg init large-dir-repo mkdir -p large-dir-repo/third_party/rust/log touch large-dir-repo/third_party/rust/log/foo.txt for i in $(seq 1 30000); do d=$(mktemp -d large-dir-repo/third_party/XXXXXXXXX) touch $d/file.txt done hg -R large-dir-repo ci -Am 'rev0' --user test --date '0 0' for repos that use narrow, the narrowspec was this: [includes] rootfilesin:third_party/rust/log [excludes] This narrowspec was chosen due to the size of the third_party/rust directory; this directory was *not* modified in revision #468856 in mozilla-unified. Importantly, when using narrow, these repos had everything checked out (in the case of large-dir-repo, that means all 30,001 directories), *before* adding the narrowspec. This is to simulate the behavior when using a virtual filesystem that shows everything for the user even if they haven't added it to the narrowspec yet. This is not a supported configuration, and `hg update` will not really do the "correct" thing, but non-mutating commands should behave correctly. There are two repos below that do not follow the setup above, 'citc1' and 'citc2', which are using a virtual filesystem and can not be reproduced upstream; these numbers are here mostly to indicate that these performance improvements are not hypothetical, and show the benefits we're hoping to achieve on our real workloads. 'citc1' is closest to large-dir-repo with one of our pathological cases, 'citc2' is an arbitrary repo and closer to "average". I'm not claiming anything less than a 5% speed win as improvements due to this change; these are probably eiter measurement artifacts or constant time improvements. The numbers that aren't changing are shown primarily to prove that this doesn't make anything worse in any case I plan on testing during this series. 'before' is hg from commit c83ad576. 'N' indicates narrow in use, 'T' indicates treemanifest in use. hg status: repo | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before ------+---+---+------------------------+-----------------------+------------ m-u | | | 2.284 s +- 0.022 s | 2.274 s +- 0.021 s | 99.6% m-u | | x | 2.289 s +- 0.008 s | 2.284 s +- 0.028 s | 99.8% m-u | x | | 430.8 ms +- 3.1 ms | 424.5 ms +- 3.2 ms | 98.5% m-u | x | x | 429.8 ms +- 2.5 ms | 425.8 ms +- 3.7 ms | 99.1% l-d-r | | | 681.3 ms +- 5.5 ms | 689.6 ms +- 8.0 ms | 101.2% l-d-r | | x | 666.8 ms +- 21.8 ms | 672.5 ms +- 14.9 ms | 100.9% l-d-r | x | | 282.6 ms +- 1.8 ms | 203.0 ms +- 1.2 ms | 71.8% <-- l-d-r | x | x | 275.2 ms +- 3.9 ms | 199.3 ms +- 3.5 ms | 72.4% <-- citc1 | x | x | 1.023 s +- 0.011 s | 398.6 ms +- 9.2 ms | 39.0% <-- citc2 | x | x | 297.9 ms +- 4.4 ms | 289.6 ms +- 4.2 ms | 97.2% hg status --change .: repo | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before ------+---+---+------------------------+-----------------------+------------ m-u | | | 478.2 ms +- 2.0 ms | 476.9 ms +- 3.7 ms | 99.7% m-u | | x | 169.5 ms +- 2.7 ms | 169.5 ms +- 2.5 ms | 100.0% m-u | x | | 477.0 ms +- 2.4 ms | 476.1 ms +- 1.4 ms | 99.8% m-u | x | x | 124.7 ms +- 1.9 ms | 124.2 ms +- 3.3 ms | 99.6% l-d-r | | | 97.4 ms +- 1.2 ms | 96.5 ms +- 1.2 ms | 99.1% l-d-r | | x | 4.778 s +- 0.018 s | 4.774 s +- 0.011 s | 99.9% l-d-r | x | | 99.9 ms +- 1.1 ms | 98.8 ms +- 1.3 ms | 98.9% l-d-r | x | x | 848.7 ms +- 7.1 ms | 849.4 ms +- 6.5 ms | 100.1% citc1 | x | x | 4.250 s +- 0.051 s | 4.283 s +- 0.042 s | 100.8% citc2 | x | x | 341.5 ms +- 4.7 ms | 341.5 ms +- 4.1 ms | 100.0% hg update $rev^; hg update $rev: repo | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before ------+---+---+------------------------+-----------------------+------------ m-u | | | 4.357 s +- 0.032 s | 4.312 s +- 0.093 s | 99.0% m-u | | x | 3.599 s +- 0.061 s | 3.592 s +- 0.071 s | 99.8% m-u | x | | 1.815 s +- 0.012 s | 1.816 s +- 0.013 s | 100.1% m-u | x | x | 1.110 s +- 0.009 s | 1.106 s +- 0.005 s | 99.6% l-d-r | | | 527.1 ms +- 7.8 ms | 523.3 ms +- 6.5 ms | 99.3% l-d-r | | x | 8.835 s +- 0.067 s | 8.825 s +- 0.064 s | 99.9% l-d-r | x | | 313.0 ms +- 2.2 ms | 312.1 ms +- 1.2 ms | 99.7% l-d-r | x | x | 1.780 s +- 0.011 s | 1.799 s +- 0.013 s | 101.1% citc1 | x | x | 6.825 s +- 0.262 s | 6.707 s +- 0.353 s | 98.3% citc2 | x | x | 776.4 ms +- 4.5 ms | 781.3 ms +- 6.3 ms | 100.6% hg diff: repo | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before ------+---+---+------------------------+-----------------------+------------ m-u | | | 1.519 s +- 0.015 s | 1.525 s +- 0.017 s | 100.4% m-u | | x | 1.512 s +- 0.010 s | 1.517 s +- 0.027 s | 100.3% m-u | x | | 420.0 ms +- 3.2 ms | 417.1 ms +- 1.9 ms | 99.3% m-u | x | x | 415.0 ms +- 3.8 ms | 415.7 ms +- 2.7 ms | 100.2% l-d-r | | | 220.8 ms +- 4.0 ms | 220.8 ms +- 3.7 ms | 100.0% l-d-r | | x | 216.6 ms +- 7.5 ms | 211.4 ms +- 2.1 ms | 97.6% l-d-r | x | | 111.9 ms +- 1.8 ms | 112.0 ms +- 1.5 ms | 100.1% l-d-r | x | x | 111.4 ms +- 1.4 ms | 110.2 ms +- 1.0 ms | 98.9% citc1 | x | x | 268.7 ms +- 2.3 ms | 269.6 ms +- 2.8 ms | 100.3% citc2 | x | x | 273.5 ms +- 5.5 ms | 273.9 ms +- 3.7 ms | 100.1% hg diff -c .: repo | N | T | before (mean +- stdev) | after (mean +- stdev) | % of before ------+---+---+--------------------------+-----------------------+---------- m-u | | | 497.1 ms +- 1.4 ms | 500.1 ms +- 2.4 ms | 100.6% m-u | | x | 195.3 ms +- 13.2 ms | 191.6 ms +- 3.0 ms | 98.1% m-u | x | | 476.8 ms +- 1.9 ms | 476.7 ms +- 2.3 ms | 100.0% m-u | x | x | 122.8 ms +- 2.1 ms | 122.9 ms +- 2.0 ms | 100.1% l-d-r | | | 99.3 ms +- 2.3 ms | 98.8 ms +- 1.7 ms | 99.5% l-d-r | | x | 4.875 s +- 0.041 s | 4.847 s +- 0.038 s | 99.4% l-d-r | x | | 98.5 ms +- 1.2 ms | 98.9 ms +- 1.3 ms | 100.4% l-d-r | x | x | 864.6 ms +- 7.4 ms | 855.4 ms +- 6.6 ms | 98.9% citc1 | x | x | 4.505 s +- 0.060 s | 4.466 s +- 0.036 s | 99.1% citc2 | x | x | 368.0 ms +- 4.0 ms | 365.5 ms +- 6.3 ms | 99.3% Differential Revision: https://phab.mercurial-scm.org/D4131
author Kyle Lippincott <spectral@google.com>
date Tue, 31 Jul 2018 16:47:43 -0700
parents 46dcb9f14900
children 51a99e09c54b
line wrap: on
line source

/*
 * mpatch.cc - fuzzer harness for mpatch.c
 *
 * Copyright 2018, Google Inc.
 *
 * This software may be used and distributed according to the terms of
 * the GNU General Public License, incorporated herein by reference.
 */
#include <iostream>
#include <memory>
#include <stdint.h>
#include <stdlib.h>
#include <vector>

#include "fuzzutil.h"

// To avoid having too many OOMs from the fuzzer infrastructure, we'll
// skip patch application if the resulting fulltext would be bigger
// than 10MiB.
#define MAX_OUTPUT_SIZE 10485760

extern "C" {
#include "bitmanipulation.h"
#include "mpatch.h"

struct mpatchbin {
	std::unique_ptr<char[]> data;
	size_t len;
};

static mpatch_flist *getitem(void *vbins, ssize_t pos)
{
	std::vector<mpatchbin> *bins = (std::vector<mpatchbin> *)vbins;
	const mpatchbin &bin = bins->at(pos + 1);
	struct mpatch_flist *res;
	LOG(2) << "mpatch_decode " << bin.len << std::endl;
	if (mpatch_decode(bin.data.get(), bin.len, &res) < 0)
		return NULL;
	return res;
}

// input format:
// u8 number of inputs
// one u16 for each input, its length
// the inputs
int LLVMFuzzerTestOneInput(const uint8_t *Data, size_t Size)
{
	if (!Size) {
		return 0;
	}
	// First byte of data is how many texts we expect, first text
	// being the base the rest being the deltas.
	ssize_t numtexts = Data[0];
	if (numtexts < 2) {
		// No point if we don't have at least a base text and a delta...
		return 0;
	}
	// Each text will be described by a byte for how long it
	// should be, so give up if we don't have enough.
	if ((Size - 1) < (numtexts * 2)) {
		return 0;
	}
	size_t consumed = 1 + (numtexts * 2);
	LOG(2) << "input contains " << Size << std::endl;
	LOG(2) << numtexts << " texts, consuming " << consumed << std::endl;
	std::vector<mpatchbin> bins;
	bins.reserve(numtexts);
	for (int i = 0; i < numtexts; ++i) {
		mpatchbin bin;
		size_t nthsize = getbeuint16((char *)Data + 1 + (2 * i));
		LOG(2) << "text " << i << " is " << nthsize << std::endl;
		char *start = (char *)Data + consumed;
		consumed += nthsize;
		if (consumed > Size) {
			LOG(2) << "ran out of data, consumed " << consumed
			       << " of " << Size << std::endl;
			return 0;
		}
		bin.len = nthsize;
		bin.data.reset(new char[nthsize]);
		memcpy(bin.data.get(), start, nthsize);
		bins.push_back(std::move(bin));
	}
	LOG(2) << "mpatch_flist" << std::endl;
	struct mpatch_flist *patch =
	    mpatch_fold(&bins, getitem, 0, numtexts - 1);
	if (!patch) {
		return 0;
	}
	LOG(2) << "mpatch_calcsize" << std::endl;
	ssize_t outlen = mpatch_calcsize(bins[0].len, patch);
	LOG(2) << "outlen " << outlen << std::endl;
	if (outlen < 0 || outlen > MAX_OUTPUT_SIZE) {
		goto cleanup;
	}
	{
		char *dest = (char *)malloc(outlen);
		LOG(2) << "expecting " << outlen << " total bytes at "
		       << (void *)dest << std::endl;
		mpatch_apply(dest, bins[0].data.get(), bins[0].len, patch);
		free(dest);
		LOG(1) << "applied a complete patch" << std::endl;
	}
cleanup:
	mpatch_lfree(patch);
	return 0;
}

#ifdef HG_FUZZER_INCLUDE_MAIN
int main(int argc, char **argv)
{
	// One text, one patch.
	const char data[] = "\x02\x00\0x1\x00\x0d"
	                    // base text
	                    "a"
	                    // binary delta that will append a single b
	                    "\x00\x00\x00\x01\x00\x00\x00\x01\x00\x00\x00\x01b";
	return LLVMFuzzerTestOneInput((const uint8_t *)data, 19);
}
#endif

} // extern "C"