rocksdb/table/block_test.cc
sdong 35ad531be3 Seperate InternalIterator from Iterator
Summary:
Separate a new class InternalIterator from class Iterator, when the look-up is done internally, which also means they operate on key with sequence ID and type.

This change will enable potential future optimizations but for now InternalIterator's functions are still the same as Iterator's.
At the same time, separate the cleanup function to a separate class and let both of InternalIterator and Iterator inherit from it.

Test Plan: Run all existing tests.

Reviewers: igor, yhchiang, anthony, kradhakrishnan, IslamAbdelRahman, rven

Reviewed By: rven

Subscribers: leveldb, dhruba

Differential Revision: https://reviews.facebook.net/D48549
2015-10-13 15:32:13 -07:00

243 lines
7.4 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 : public testing::Test {};
// block test
TEST_F(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(16);
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;
Block reader(std::move(contents));
// read contents of block sequentially
int count = 0;
InternalIterator *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 */));
// 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;
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
BlockContents contents_ref(contents.data, contents.cachable,
contents.compression_type);
Block reader1(std::move(contents));
Block reader2(std::move(contents_ref));
std::unique_ptr<const SliceTransform> prefix_extractor(
NewFixedPrefixTransform(prefix_size));
{
auto iter1 = reader1.NewIterator(nullptr);
auto iter2 = reader1.NewIterator(nullptr);
reader1.SetBlockHashIndex(CreateBlockHashIndexOnTheFly(
iter1, iter2, static_cast<uint32_t>(keys.size()), BytewiseComparator(),
prefix_extractor.get()));
delete iter1;
delete iter2;
}
std::unique_ptr<InternalIterator> hash_iter(
reader1.NewIterator(BytewiseComparator(), nullptr, false));
std::unique_ptr<InternalIterator> 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_F(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(std::move(contents), kMaxKey, keys, values);
}
TEST_F(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(std::move(contents), kMaxKey, keys, values);
}
} // namespace rocksdb
int main(int argc, char **argv) {
::testing::InitGoogleTest(&argc, argv);
return RUN_ALL_TESTS();
}