rocksdb/table/block_test.cc
Kai Liu 22f396798e Enable hash index for block-based table
Summary: Based on previous patches, this diff eventually provides the end-to-end mechanism for users to specify the hash-index.

Test Plan: Wrote several new unit tests.

Reviewers: sdong, haobo, dhruba

Reviewed By: sdong

CC: leveldb

Differential Revision: https://reviews.facebook.net/D16539

Use shorten index key for hash-index
Summary:
I was wrong about the "index builder", right now since we create index
by scanning both whole table and index, there is not need to preserve
the whole key as the index key.

I switch back to original way index which is both space efficient and
able to supprot in-fly construction of hash index.

IN this patch, I made minimal change since I'm not sure if we still need
the "pluggable index builder", under current circumstance it is of no use
and kind of over-engineered. But I'm not sure if we can still exploit its
usefulness in the future; otherwise I think I can just burn them with great
vengeance.

Test Plan: unit tests

Reviewers: sdong, haobo

CC: leveldb

Differential Revision: https://reviews.facebook.net/D17745

Conflicts:
	table/block_based_table_reader.cc
	table/block_based_table_reader.h
2014-04-15 20:13:34 -07:00

243 lines
7.3 KiB
C++

// Copyright (c) 2013, Facebook, Inc. All rights reserved.
// This source code is licensed under the BSD-style license found in the
// LICENSE file in the root directory of this source tree. An additional grant
// of patent rights can be found in the PATENTS file in the same directory.
//
#include <stdio.h>
#include <string>
#include <vector>
#include "db/dbformat.h"
#include "db/memtable.h"
#include "db/write_batch_internal.h"
#include "rocksdb/db.h"
#include "rocksdb/env.h"
#include "rocksdb/iterator.h"
#include "rocksdb/table.h"
#include "rocksdb/slice_transform.h"
#include "table/block.h"
#include "table/block_builder.h"
#include "table/format.h"
#include "table/block_hash_index.h"
#include "util/random.h"
#include "util/testharness.h"
#include "util/testutil.h"
namespace rocksdb {
static std::string RandomString(Random* rnd, int len) {
std::string r;
test::RandomString(rnd, len, &r);
return r;
}
std::string GenerateKey(int primary_key, int secondary_key, int padding_size,
Random *rnd) {
char buf[50];
char *p = &buf[0];
snprintf(buf, sizeof(buf), "%6d%4d", primary_key, secondary_key);
std::string k(p);
if (padding_size) {
k += RandomString(rnd, padding_size);
}
return k;
}
// Generate random key value pairs.
// The generated key will be sorted. You can tune the parameters to generated
// different kinds of test key/value pairs for different scenario.
void GenerateRandomKVs(std::vector<std::string> *keys,
std::vector<std::string> *values, const int from,
const int len, const int step = 1,
const int padding_size = 0,
const int keys_share_prefix = 1) {
Random rnd(302);
// generate different prefix
for (int i = from; i < from + len; i += step) {
// generating keys that shares the prefix
for (int j = 0; j < keys_share_prefix; ++j) {
keys->emplace_back(GenerateKey(i, j, padding_size, &rnd));
// 100 bytes values
values->emplace_back(RandomString(&rnd, 100));
}
}
}
class BlockTest {};
// block test
TEST(BlockTest, SimpleTest) {
Random rnd(301);
Options options = Options();
std::unique_ptr<InternalKeyComparator> ic;
ic.reset(new test::PlainInternalKeyComparator(options.comparator));
std::vector<std::string> keys;
std::vector<std::string> values;
BlockBuilder builder(options, ic.get());
int num_records = 100000;
GenerateRandomKVs(&keys, &values, 0, num_records);
// add a bunch of records to a block
for (int i = 0; i < num_records; i++) {
builder.Add(keys[i], values[i]);
}
// read serialized contents of the block
Slice rawblock = builder.Finish();
// create block reader
BlockContents contents;
contents.data = rawblock;
contents.cachable = false;
contents.heap_allocated = false;
Block reader(contents);
// read contents of block sequentially
int count = 0;
Iterator* iter = reader.NewIterator(options.comparator);
for (iter->SeekToFirst();iter->Valid(); count++, iter->Next()) {
// read kv from block
Slice k = iter->key();
Slice v = iter->value();
// compare with lookaside array
ASSERT_EQ(k.ToString().compare(keys[count]), 0);
ASSERT_EQ(v.ToString().compare(values[count]), 0);
}
delete iter;
// read block contents randomly
iter = reader.NewIterator(options.comparator);
for (int i = 0; i < num_records; i++) {
// find a random key in the lookaside array
int index = rnd.Uniform(num_records);
Slice k(keys[index]);
// search in block for this key
iter->Seek(k);
ASSERT_TRUE(iter->Valid());
Slice v = iter->value();
ASSERT_EQ(v.ToString().compare(values[index]), 0);
}
delete iter;
}
// return the block contents
BlockContents GetBlockContents(std::unique_ptr<BlockBuilder> *builder,
const std::vector<std::string> &keys,
const std::vector<std::string> &values,
const int prefix_group_size = 1) {
builder->reset(
new BlockBuilder(1 /* restart interval */, BytewiseComparator()));
// Add only half of the keys
for (size_t i = 0; i < keys.size(); ++i) {
(*builder)->Add(keys[i], values[i]);
}
Slice rawblock = (*builder)->Finish();
BlockContents contents;
contents.data = rawblock;
contents.cachable = false;
contents.heap_allocated = false;
return contents;
}
void CheckBlockContents(BlockContents contents, const int max_key,
const std::vector<std::string> &keys,
const std::vector<std::string> &values) {
const size_t prefix_size = 6;
// create block reader
Block reader1(contents);
Block reader2(contents);
std::unique_ptr<const SliceTransform> prefix_extractor(
NewFixedPrefixTransform(prefix_size));
{
auto iter1 = reader1.NewIterator(nullptr);
auto iter2 = reader1.NewIterator(nullptr);
reader1.SetBlockHashIndex(CreateBlockHashIndex(iter1, iter2, keys.size(),
BytewiseComparator(),
prefix_extractor.get()));
delete iter1;
delete iter2;
}
std::unique_ptr<Iterator> hash_iter(
reader1.NewIterator(BytewiseComparator()));
std::unique_ptr<Iterator> regular_iter(
reader2.NewIterator(BytewiseComparator()));
// Seek existent keys
for (size_t i = 0; i < keys.size(); i++) {
hash_iter->Seek(keys[i]);
ASSERT_OK(hash_iter->status());
ASSERT_TRUE(hash_iter->Valid());
Slice v = hash_iter->value();
ASSERT_EQ(v.ToString().compare(values[i]), 0);
}
// Seek non-existent keys.
// For hash index, if no key with a given prefix is not found, iterator will
// simply be set as invalid; whereas the binary search based iterator will
// return the one that is closest.
for (int i = 1; i < max_key - 1; i += 2) {
auto key = GenerateKey(i, 0, 0, nullptr);
hash_iter->Seek(key);
ASSERT_TRUE(!hash_iter->Valid());
regular_iter->Seek(key);
ASSERT_TRUE(regular_iter->Valid());
}
}
// In this test case, no two key share same prefix.
TEST(BlockTest, SimpleIndexHash) {
const int kMaxKey = 100000;
std::vector<std::string> keys;
std::vector<std::string> values;
GenerateRandomKVs(&keys, &values, 0 /* first key id */,
kMaxKey /* last key id */, 2 /* step */,
8 /* padding size (8 bytes randomly generated suffix) */);
std::unique_ptr<BlockBuilder> builder;
auto contents = GetBlockContents(&builder, keys, values);
CheckBlockContents(contents, kMaxKey, keys, values);
}
TEST(BlockTest, IndexHashWithSharedPrefix) {
const int kMaxKey = 100000;
// for each prefix, there will be 5 keys starts with it.
const int kPrefixGroup = 5;
std::vector<std::string> keys;
std::vector<std::string> values;
// Generate keys with same prefix.
GenerateRandomKVs(&keys, &values, 0, // first key id
kMaxKey, // last key id
2, // step
10, // padding size,
kPrefixGroup);
std::unique_ptr<BlockBuilder> builder;
auto contents = GetBlockContents(&builder, keys, values, kPrefixGroup);
CheckBlockContents(contents, kMaxKey, keys, values);
}
} // namespace rocksdb
int main(int argc, char** argv) {
return rocksdb::test::RunAllTests();
}