mirror of
https://github.com/facebook/rocksdb.git
synced 2024-12-03 14:52:53 +00:00
06e593376c
Summary: ## Context/Summary Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity. For that, this PR does the following: - Tag different write IOs by passing down and converting WriteOptions to IOOptions - Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS Some related code refactory to make implementation cleaner: - Blob stats - Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info. - Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write. - Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority - Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification - Build table - TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables - Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder. This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more - Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority ## Test ### db bench Flush ``` ./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100 rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 ``` compaction, db oopen ``` Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279 rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213 rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66 ``` blob stats - just to make sure they aren't broken by this PR ``` Integrated Blob DB Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600 rocksdb.blobdb.blob.file.synced COUNT : 1 rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same) ``` ``` Stacked Blob DB Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876 rocksdb.blobdb.blob.file.synced COUNT : 8 rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same) ``` ### Rehearsal CI stress test Trigger 3 full runs of all our CI stress tests ### Performance Flush ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark; enable_statistics = true Pre-pr: avg 507515519.3 ns 497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908, Post-pr: avg 511971266.5 ns, regressed 0.88% 502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408, ``` Compaction ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 495346098.30 ns 492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846 Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97% 502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007 ``` Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats) ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 3848.10 ns 3814,3838,3839,3848,3854,3854,3854,3860,3860,3860 Post-pr: avg 3874.20 ns, regressed 0.68% 3863,3867,3871,3874,3875,3877,3877,3877,3880,3881 ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910 Reviewed By: ajkr Differential Revision: D49788060 Pulled By: hx235 fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
721 lines
24 KiB
C++
721 lines
24 KiB
C++
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
|
// This source code is licensed under both the GPLv2 (found in the
|
|
// COPYING file in the root directory) and Apache 2.0 License
|
|
// (found in the LICENSE.Apache file in the root directory).
|
|
|
|
#include "table/block_based/data_block_hash_index.h"
|
|
|
|
#include <cstdlib>
|
|
#include <string>
|
|
#include <unordered_map>
|
|
|
|
#include "db/table_properties_collector.h"
|
|
#include "rocksdb/slice.h"
|
|
#include "table/block_based/block.h"
|
|
#include "table/block_based/block_based_table_reader.h"
|
|
#include "table/block_based/block_builder.h"
|
|
#include "table/get_context.h"
|
|
#include "table/table_builder.h"
|
|
#include "test_util/testharness.h"
|
|
#include "test_util/testutil.h"
|
|
#include "util/random.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
bool SearchForOffset(DataBlockHashIndex& index, const char* data,
|
|
uint16_t map_offset, const Slice& key,
|
|
uint8_t& restart_point) {
|
|
uint8_t entry = index.Lookup(data, map_offset, key);
|
|
if (entry == kCollision) {
|
|
return true;
|
|
}
|
|
|
|
if (entry == kNoEntry) {
|
|
return false;
|
|
}
|
|
|
|
return entry == restart_point;
|
|
}
|
|
|
|
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 += rnd->RandomString(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(rnd.RandomString(100));
|
|
}
|
|
}
|
|
}
|
|
|
|
TEST(DataBlockHashIndex, DataBlockHashTestSmall) {
|
|
DataBlockHashIndexBuilder builder;
|
|
builder.Initialize(0.75 /*util_ratio*/);
|
|
for (int j = 0; j < 5; j++) {
|
|
for (uint8_t i = 0; i < 2 + j; i++) {
|
|
std::string key("key" + std::to_string(i));
|
|
uint8_t restart_point = i;
|
|
builder.Add(key, restart_point);
|
|
}
|
|
|
|
size_t estimated_size = builder.EstimateSize();
|
|
|
|
std::string buffer("fake"), buffer2;
|
|
size_t original_size = buffer.size();
|
|
estimated_size += original_size;
|
|
builder.Finish(buffer);
|
|
|
|
ASSERT_EQ(buffer.size(), estimated_size);
|
|
|
|
buffer2 = buffer; // test for the correctness of relative offset
|
|
|
|
Slice s(buffer2);
|
|
DataBlockHashIndex index;
|
|
uint16_t map_offset;
|
|
index.Initialize(s.data(), static_cast<uint16_t>(s.size()), &map_offset);
|
|
|
|
// the additional hash map should start at the end of the buffer
|
|
ASSERT_EQ(original_size, map_offset);
|
|
for (uint8_t i = 0; i < 2; i++) {
|
|
std::string key("key" + std::to_string(i));
|
|
uint8_t restart_point = i;
|
|
ASSERT_TRUE(
|
|
SearchForOffset(index, s.data(), map_offset, key, restart_point));
|
|
}
|
|
builder.Reset();
|
|
}
|
|
}
|
|
|
|
TEST(DataBlockHashIndex, DataBlockHashTest) {
|
|
// bucket_num = 200, #keys = 100. 50% utilization
|
|
DataBlockHashIndexBuilder builder;
|
|
builder.Initialize(0.75 /*util_ratio*/);
|
|
|
|
for (uint8_t i = 0; i < 100; i++) {
|
|
std::string key("key" + std::to_string(i));
|
|
uint8_t restart_point = i;
|
|
builder.Add(key, restart_point);
|
|
}
|
|
|
|
size_t estimated_size = builder.EstimateSize();
|
|
|
|
std::string buffer("fake content"), buffer2;
|
|
size_t original_size = buffer.size();
|
|
estimated_size += original_size;
|
|
builder.Finish(buffer);
|
|
|
|
ASSERT_EQ(buffer.size(), estimated_size);
|
|
|
|
buffer2 = buffer; // test for the correctness of relative offset
|
|
|
|
Slice s(buffer2);
|
|
DataBlockHashIndex index;
|
|
uint16_t map_offset;
|
|
index.Initialize(s.data(), static_cast<uint16_t>(s.size()), &map_offset);
|
|
|
|
// the additional hash map should start at the end of the buffer
|
|
ASSERT_EQ(original_size, map_offset);
|
|
for (uint8_t i = 0; i < 100; i++) {
|
|
std::string key("key" + std::to_string(i));
|
|
uint8_t restart_point = i;
|
|
ASSERT_TRUE(
|
|
SearchForOffset(index, s.data(), map_offset, key, restart_point));
|
|
}
|
|
}
|
|
|
|
TEST(DataBlockHashIndex, DataBlockHashTestCollision) {
|
|
// bucket_num = 2. There will be intense hash collisions
|
|
DataBlockHashIndexBuilder builder;
|
|
builder.Initialize(0.75 /*util_ratio*/);
|
|
|
|
for (uint8_t i = 0; i < 100; i++) {
|
|
std::string key("key" + std::to_string(i));
|
|
uint8_t restart_point = i;
|
|
builder.Add(key, restart_point);
|
|
}
|
|
|
|
size_t estimated_size = builder.EstimateSize();
|
|
|
|
std::string buffer("some other fake content to take up space"), buffer2;
|
|
size_t original_size = buffer.size();
|
|
estimated_size += original_size;
|
|
builder.Finish(buffer);
|
|
|
|
ASSERT_EQ(buffer.size(), estimated_size);
|
|
|
|
buffer2 = buffer; // test for the correctness of relative offset
|
|
|
|
Slice s(buffer2);
|
|
DataBlockHashIndex index;
|
|
uint16_t map_offset;
|
|
index.Initialize(s.data(), static_cast<uint16_t>(s.size()), &map_offset);
|
|
|
|
// the additional hash map should start at the end of the buffer
|
|
ASSERT_EQ(original_size, map_offset);
|
|
for (uint8_t i = 0; i < 100; i++) {
|
|
std::string key("key" + std::to_string(i));
|
|
uint8_t restart_point = i;
|
|
ASSERT_TRUE(
|
|
SearchForOffset(index, s.data(), map_offset, key, restart_point));
|
|
}
|
|
}
|
|
|
|
TEST(DataBlockHashIndex, DataBlockHashTestLarge) {
|
|
DataBlockHashIndexBuilder builder;
|
|
builder.Initialize(0.75 /*util_ratio*/);
|
|
std::unordered_map<std::string, uint8_t> m;
|
|
|
|
for (uint8_t i = 0; i < 100; i++) {
|
|
if (i % 2) {
|
|
continue; // leave half of the keys out
|
|
}
|
|
std::string key = "key" + std::to_string(i);
|
|
uint8_t restart_point = i;
|
|
builder.Add(key, restart_point);
|
|
m[key] = restart_point;
|
|
}
|
|
|
|
size_t estimated_size = builder.EstimateSize();
|
|
|
|
std::string buffer("filling stuff"), buffer2;
|
|
size_t original_size = buffer.size();
|
|
estimated_size += original_size;
|
|
builder.Finish(buffer);
|
|
|
|
ASSERT_EQ(buffer.size(), estimated_size);
|
|
|
|
buffer2 = buffer; // test for the correctness of relative offset
|
|
|
|
Slice s(buffer2);
|
|
DataBlockHashIndex index;
|
|
uint16_t map_offset;
|
|
index.Initialize(s.data(), static_cast<uint16_t>(s.size()), &map_offset);
|
|
|
|
// the additional hash map should start at the end of the buffer
|
|
ASSERT_EQ(original_size, map_offset);
|
|
for (uint8_t i = 0; i < 100; i++) {
|
|
std::string key = "key" + std::to_string(i);
|
|
uint8_t restart_point = i;
|
|
if (m.count(key)) {
|
|
ASSERT_TRUE(m[key] == restart_point);
|
|
ASSERT_TRUE(
|
|
SearchForOffset(index, s.data(), map_offset, key, restart_point));
|
|
} else {
|
|
// we allow false positve, so don't test the nonexisting keys.
|
|
// when false positive happens, the search will continue to the
|
|
// restart intervals to see if the key really exist.
|
|
}
|
|
}
|
|
}
|
|
|
|
TEST(DataBlockHashIndex, RestartIndexExceedMax) {
|
|
DataBlockHashIndexBuilder builder;
|
|
builder.Initialize(0.75 /*util_ratio*/);
|
|
std::unordered_map<std::string, uint8_t> m;
|
|
|
|
for (uint8_t i = 0; i <= 253; i++) {
|
|
std::string key = "key" + std::to_string(i);
|
|
uint8_t restart_point = i;
|
|
builder.Add(key, restart_point);
|
|
}
|
|
ASSERT_TRUE(builder.Valid());
|
|
|
|
builder.Reset();
|
|
|
|
for (uint8_t i = 0; i <= 254; i++) {
|
|
std::string key = "key" + std::to_string(i);
|
|
uint8_t restart_point = i;
|
|
builder.Add(key, restart_point);
|
|
}
|
|
|
|
ASSERT_FALSE(builder.Valid());
|
|
|
|
builder.Reset();
|
|
ASSERT_TRUE(builder.Valid());
|
|
}
|
|
|
|
TEST(DataBlockHashIndex, BlockRestartIndexExceedMax) {
|
|
Options options = Options();
|
|
|
|
BlockBuilder builder(1 /* block_restart_interval */,
|
|
true /* use_delta_encoding */,
|
|
false /* use_value_delta_encoding */,
|
|
BlockBasedTableOptions::kDataBlockBinaryAndHash);
|
|
|
|
// #restarts <= 253. HashIndex is valid
|
|
for (int i = 0; i <= 253; i++) {
|
|
std::string ukey = "key" + std::to_string(i);
|
|
InternalKey ikey(ukey, 0, kTypeValue);
|
|
builder.Add(ikey.Encode().ToString(), "value");
|
|
}
|
|
|
|
{
|
|
// read serialized contents of the block
|
|
Slice rawblock = builder.Finish();
|
|
|
|
// create block reader
|
|
BlockContents contents;
|
|
contents.data = rawblock;
|
|
Block reader(std::move(contents));
|
|
|
|
ASSERT_EQ(reader.IndexType(),
|
|
BlockBasedTableOptions::kDataBlockBinaryAndHash);
|
|
}
|
|
|
|
builder.Reset();
|
|
|
|
// #restarts > 253. HashIndex is not used
|
|
for (int i = 0; i <= 254; i++) {
|
|
std::string ukey = "key" + std::to_string(i);
|
|
InternalKey ikey(ukey, 0, kTypeValue);
|
|
builder.Add(ikey.Encode().ToString(), "value");
|
|
}
|
|
|
|
{
|
|
// read serialized contents of the block
|
|
Slice rawblock = builder.Finish();
|
|
|
|
// create block reader
|
|
BlockContents contents;
|
|
contents.data = rawblock;
|
|
Block reader(std::move(contents));
|
|
|
|
ASSERT_EQ(reader.IndexType(),
|
|
BlockBasedTableOptions::kDataBlockBinarySearch);
|
|
}
|
|
}
|
|
|
|
TEST(DataBlockHashIndex, BlockSizeExceedMax) {
|
|
Options options = Options();
|
|
std::string ukey(10, 'k');
|
|
InternalKey ikey(ukey, 0, kTypeValue);
|
|
|
|
BlockBuilder builder(1 /* block_restart_interval */,
|
|
false /* use_delta_encoding */,
|
|
false /* use_value_delta_encoding */,
|
|
BlockBasedTableOptions::kDataBlockBinaryAndHash);
|
|
|
|
{
|
|
// insert a large value. The block size plus HashIndex is 65536.
|
|
std::string value(65502, 'v');
|
|
|
|
builder.Add(ikey.Encode().ToString(), value);
|
|
|
|
// read serialized contents of the block
|
|
Slice rawblock = builder.Finish();
|
|
ASSERT_LE(rawblock.size(), kMaxBlockSizeSupportedByHashIndex);
|
|
std::cerr << "block size: " << rawblock.size() << std::endl;
|
|
|
|
// create block reader
|
|
BlockContents contents;
|
|
contents.data = rawblock;
|
|
Block reader(std::move(contents));
|
|
|
|
ASSERT_EQ(reader.IndexType(),
|
|
BlockBasedTableOptions::kDataBlockBinaryAndHash);
|
|
}
|
|
|
|
builder.Reset();
|
|
|
|
{
|
|
// insert a large value. The block size plus HashIndex would be 65537.
|
|
// This excceed the max block size supported by HashIndex (65536).
|
|
// So when build finishes HashIndex will not be created for the block.
|
|
std::string value(65503, 'v');
|
|
|
|
builder.Add(ikey.Encode().ToString(), value);
|
|
|
|
// read serialized contents of the block
|
|
Slice rawblock = builder.Finish();
|
|
ASSERT_LE(rawblock.size(), kMaxBlockSizeSupportedByHashIndex);
|
|
std::cerr << "block size: " << rawblock.size() << std::endl;
|
|
|
|
// create block reader
|
|
BlockContents contents;
|
|
contents.data = rawblock;
|
|
Block reader(std::move(contents));
|
|
|
|
// the index type have fallen back to binary when build finish.
|
|
ASSERT_EQ(reader.IndexType(),
|
|
BlockBasedTableOptions::kDataBlockBinarySearch);
|
|
}
|
|
}
|
|
|
|
TEST(DataBlockHashIndex, BlockTestSingleKey) {
|
|
Options options = Options();
|
|
|
|
BlockBuilder builder(16 /* block_restart_interval */,
|
|
true /* use_delta_encoding */,
|
|
false /* use_value_delta_encoding */,
|
|
BlockBasedTableOptions::kDataBlockBinaryAndHash);
|
|
|
|
std::string ukey("gopher");
|
|
std::string value("gold");
|
|
InternalKey ikey(ukey, 10, kTypeValue);
|
|
builder.Add(ikey.Encode().ToString(), value /*value*/);
|
|
|
|
// read serialized contents of the block
|
|
Slice rawblock = builder.Finish();
|
|
|
|
// create block reader
|
|
BlockContents contents;
|
|
contents.data = rawblock;
|
|
Block reader(std::move(contents));
|
|
|
|
const InternalKeyComparator icmp(BytewiseComparator());
|
|
auto iter = reader.NewDataIterator(icmp.user_comparator(),
|
|
kDisableGlobalSequenceNumber);
|
|
bool may_exist;
|
|
// search in block for the key just inserted
|
|
{
|
|
InternalKey seek_ikey(ukey, 10, kValueTypeForSeek);
|
|
may_exist = iter->SeekForGet(seek_ikey.Encode().ToString());
|
|
ASSERT_TRUE(may_exist);
|
|
ASSERT_TRUE(iter->Valid());
|
|
ASSERT_EQ(
|
|
options.comparator->Compare(iter->key(), ikey.Encode().ToString()), 0);
|
|
ASSERT_EQ(iter->value(), value);
|
|
}
|
|
|
|
// search in block for the existing ukey, but with higher seqno
|
|
{
|
|
InternalKey seek_ikey(ukey, 20, kValueTypeForSeek);
|
|
|
|
// HashIndex should be able to set the iter correctly
|
|
may_exist = iter->SeekForGet(seek_ikey.Encode().ToString());
|
|
ASSERT_TRUE(may_exist);
|
|
ASSERT_TRUE(iter->Valid());
|
|
|
|
// user key should match
|
|
ASSERT_EQ(options.comparator->Compare(ExtractUserKey(iter->key()), ukey),
|
|
0);
|
|
|
|
// seek_key seqno number should be greater than that of iter result
|
|
ASSERT_GT(GetInternalKeySeqno(seek_ikey.Encode()),
|
|
GetInternalKeySeqno(iter->key()));
|
|
|
|
ASSERT_EQ(iter->value(), value);
|
|
}
|
|
|
|
// Search in block for the existing ukey, but with lower seqno
|
|
// in this case, hash can find the only occurrence of the user_key, but
|
|
// ParseNextDataKey() will skip it as it does not have a older seqno.
|
|
// In this case, GetForSeek() is effective to locate the user_key, and
|
|
// iter->Valid() == false indicates that we've reached to the end of
|
|
// the block and the caller should continue searching the next block.
|
|
{
|
|
InternalKey seek_ikey(ukey, 5, kValueTypeForSeek);
|
|
may_exist = iter->SeekForGet(seek_ikey.Encode().ToString());
|
|
ASSERT_TRUE(may_exist);
|
|
ASSERT_FALSE(iter->Valid()); // should have reached to the end of block
|
|
}
|
|
|
|
delete iter;
|
|
}
|
|
|
|
TEST(DataBlockHashIndex, BlockTestLarge) {
|
|
Random rnd(1019);
|
|
Options options = Options();
|
|
std::vector<std::string> keys;
|
|
std::vector<std::string> values;
|
|
|
|
BlockBuilder builder(16 /* block_restart_interval */,
|
|
true /* use_delta_encoding */,
|
|
false /* use_value_delta_encoding */,
|
|
BlockBasedTableOptions::kDataBlockBinaryAndHash);
|
|
int num_records = 500;
|
|
|
|
GenerateRandomKVs(&keys, &values, 0, num_records);
|
|
|
|
// Generate keys. Adding a trailing "1" to indicate existent keys.
|
|
// Later will Seeking for keys with a trailing "0" to test seeking
|
|
// non-existent keys.
|
|
for (int i = 0; i < num_records; i++) {
|
|
std::string ukey(keys[i] + "1" /* existing key marker */);
|
|
InternalKey ikey(ukey, 0, kTypeValue);
|
|
builder.Add(ikey.Encode().ToString(), values[i]);
|
|
}
|
|
|
|
// read serialized contents of the block
|
|
Slice rawblock = builder.Finish();
|
|
|
|
// create block reader
|
|
BlockContents contents;
|
|
contents.data = rawblock;
|
|
Block reader(std::move(contents));
|
|
const InternalKeyComparator icmp(BytewiseComparator());
|
|
|
|
// random seek existent keys
|
|
for (int i = 0; i < num_records; i++) {
|
|
auto iter = reader.NewDataIterator(icmp.user_comparator(),
|
|
kDisableGlobalSequenceNumber);
|
|
// find a random key in the lookaside array
|
|
int index = rnd.Uniform(num_records);
|
|
std::string ukey(keys[index] + "1" /* existing key marker */);
|
|
InternalKey ikey(ukey, 0, kTypeValue);
|
|
|
|
// search in block for this key
|
|
bool may_exist = iter->SeekForGet(ikey.Encode().ToString());
|
|
ASSERT_TRUE(may_exist);
|
|
ASSERT_TRUE(iter->Valid());
|
|
ASSERT_EQ(values[index], iter->value());
|
|
|
|
delete iter;
|
|
}
|
|
|
|
// random seek non-existent user keys
|
|
// In this case A), the user_key cannot be found in HashIndex. The key may
|
|
// exist in the next block. So the iter is set invalidated to tell the
|
|
// caller to search the next block. This test case belongs to this case A).
|
|
//
|
|
// Note that for non-existent keys, there is possibility of false positive,
|
|
// i.e. the key is still hashed into some restart interval.
|
|
// Two additional possible outcome:
|
|
// B) linear seek the restart interval and not found, the iter stops at the
|
|
// starting of the next restart interval. The key does not exist
|
|
// anywhere.
|
|
// C) linear seek the restart interval and not found, the iter stops at the
|
|
// the end of the block, i.e. restarts_. The key may exist in the next
|
|
// block.
|
|
// So these combinations are possible when searching non-existent user_key:
|
|
//
|
|
// case# may_exist iter->Valid()
|
|
// A true false
|
|
// B false true
|
|
// C true false
|
|
|
|
for (int i = 0; i < num_records; i++) {
|
|
auto iter = reader.NewDataIterator(icmp.user_comparator(),
|
|
kDisableGlobalSequenceNumber);
|
|
// find a random key in the lookaside array
|
|
int index = rnd.Uniform(num_records);
|
|
std::string ukey(keys[index] + "0" /* non-existing key marker */);
|
|
InternalKey ikey(ukey, 0, kTypeValue);
|
|
|
|
// search in block for this key
|
|
bool may_exist = iter->SeekForGet(ikey.Encode().ToString());
|
|
if (!may_exist) {
|
|
ASSERT_TRUE(iter->Valid());
|
|
}
|
|
if (!iter->Valid()) {
|
|
ASSERT_TRUE(may_exist);
|
|
}
|
|
|
|
delete iter;
|
|
}
|
|
}
|
|
|
|
// helper routine for DataBlockHashIndex.BlockBoundary
|
|
void TestBoundary(InternalKey& ik1, std::string& v1, InternalKey& ik2,
|
|
std::string& v2, InternalKey& seek_ikey,
|
|
GetContext& get_context, Options& options) {
|
|
std::unique_ptr<WritableFileWriter> file_writer;
|
|
std::unique_ptr<RandomAccessFileReader> file_reader;
|
|
std::unique_ptr<TableReader> table_reader;
|
|
int level_ = -1;
|
|
|
|
std::vector<std::string> keys;
|
|
const ImmutableOptions ioptions(options);
|
|
const MutableCFOptions moptions(options);
|
|
const InternalKeyComparator internal_comparator(options.comparator);
|
|
|
|
EnvOptions soptions;
|
|
|
|
soptions.use_mmap_reads = ioptions.allow_mmap_reads;
|
|
test::StringSink* sink = new test::StringSink();
|
|
std::unique_ptr<FSWritableFile> f(sink);
|
|
file_writer.reset(
|
|
new WritableFileWriter(std::move(f), "" /* don't care */, FileOptions()));
|
|
std::unique_ptr<TableBuilder> builder;
|
|
IntTblPropCollectorFactories int_tbl_prop_collector_factories;
|
|
std::string column_family_name;
|
|
const ReadOptions read_options;
|
|
const WriteOptions write_options;
|
|
builder.reset(ioptions.table_factory->NewTableBuilder(
|
|
TableBuilderOptions(
|
|
ioptions, moptions, read_options, write_options, internal_comparator,
|
|
&int_tbl_prop_collector_factories, options.compression,
|
|
CompressionOptions(),
|
|
TablePropertiesCollectorFactory::Context::kUnknownColumnFamily,
|
|
column_family_name, level_),
|
|
file_writer.get()));
|
|
|
|
builder->Add(ik1.Encode().ToString(), v1);
|
|
builder->Add(ik2.Encode().ToString(), v2);
|
|
EXPECT_TRUE(builder->status().ok());
|
|
|
|
Status s = builder->Finish();
|
|
ASSERT_OK(file_writer->Flush(IOOptions()));
|
|
EXPECT_TRUE(s.ok()) << s.ToString();
|
|
|
|
EXPECT_EQ(sink->contents().size(), builder->FileSize());
|
|
|
|
// Open the table
|
|
test::StringSource* source = new test::StringSource(
|
|
sink->contents(), 0 /*uniq_id*/, ioptions.allow_mmap_reads);
|
|
std::unique_ptr<FSRandomAccessFile> file(source);
|
|
file_reader.reset(new RandomAccessFileReader(std::move(file), "test"));
|
|
const bool kSkipFilters = true;
|
|
const bool kImmortal = true;
|
|
ASSERT_OK(ioptions.table_factory->NewTableReader(
|
|
TableReaderOptions(ioptions, moptions.prefix_extractor, soptions,
|
|
internal_comparator,
|
|
0 /* block_protection_bytes_per_key */, !kSkipFilters,
|
|
!kImmortal, level_),
|
|
std::move(file_reader), sink->contents().size(), &table_reader));
|
|
// Search using Get()
|
|
ReadOptions ro;
|
|
|
|
ASSERT_OK(table_reader->Get(ro, seek_ikey.Encode().ToString(), &get_context,
|
|
moptions.prefix_extractor.get()));
|
|
}
|
|
|
|
TEST(DataBlockHashIndex, BlockBoundary) {
|
|
BlockBasedTableOptions table_options;
|
|
table_options.data_block_index_type =
|
|
BlockBasedTableOptions::kDataBlockBinaryAndHash;
|
|
table_options.block_restart_interval = 1;
|
|
table_options.block_size = 4096;
|
|
|
|
Options options;
|
|
options.comparator = BytewiseComparator();
|
|
|
|
options.table_factory.reset(NewBlockBasedTableFactory(table_options));
|
|
|
|
// insert two large k/v pair. Given that the block_size is 4096, one k/v
|
|
// pair will take up one block.
|
|
// [ k1/v1 ][ k2/v2 ]
|
|
// [ Block N ][ Block N+1 ]
|
|
|
|
{
|
|
// [ "aab"@100 ][ "axy"@10 ]
|
|
// | Block N ][ Block N+1 ]
|
|
// seek for "axy"@60
|
|
std::string uk1("aab");
|
|
InternalKey ik1(uk1, 100, kTypeValue);
|
|
std::string v1(4100, '1'); // large value
|
|
|
|
std::string uk2("axy");
|
|
InternalKey ik2(uk2, 10, kTypeValue);
|
|
std::string v2(4100, '2'); // large value
|
|
|
|
PinnableSlice value;
|
|
std::string seek_ukey("axy");
|
|
InternalKey seek_ikey(seek_ukey, 60, kTypeValue);
|
|
GetContext get_context(options.comparator, nullptr, nullptr, nullptr,
|
|
GetContext::kNotFound, seek_ukey, &value, nullptr,
|
|
nullptr, nullptr, true, nullptr, nullptr);
|
|
|
|
TestBoundary(ik1, v1, ik2, v2, seek_ikey, get_context, options);
|
|
ASSERT_EQ(get_context.State(), GetContext::kFound);
|
|
ASSERT_EQ(value, v2);
|
|
value.Reset();
|
|
}
|
|
|
|
{
|
|
// [ "axy"@100 ][ "axy"@10 ]
|
|
// | Block N ][ Block N+1 ]
|
|
// seek for "axy"@60
|
|
std::string uk1("axy");
|
|
InternalKey ik1(uk1, 100, kTypeValue);
|
|
std::string v1(4100, '1'); // large value
|
|
|
|
std::string uk2("axy");
|
|
InternalKey ik2(uk2, 10, kTypeValue);
|
|
std::string v2(4100, '2'); // large value
|
|
|
|
PinnableSlice value;
|
|
std::string seek_ukey("axy");
|
|
InternalKey seek_ikey(seek_ukey, 60, kTypeValue);
|
|
GetContext get_context(options.comparator, nullptr, nullptr, nullptr,
|
|
GetContext::kNotFound, seek_ukey, &value, nullptr,
|
|
nullptr, nullptr, true, nullptr, nullptr);
|
|
|
|
TestBoundary(ik1, v1, ik2, v2, seek_ikey, get_context, options);
|
|
ASSERT_EQ(get_context.State(), GetContext::kFound);
|
|
ASSERT_EQ(value, v2);
|
|
value.Reset();
|
|
}
|
|
|
|
{
|
|
// [ "axy"@100 ][ "axy"@10 ]
|
|
// | Block N ][ Block N+1 ]
|
|
// seek for "axy"@120
|
|
std::string uk1("axy");
|
|
InternalKey ik1(uk1, 100, kTypeValue);
|
|
std::string v1(4100, '1'); // large value
|
|
|
|
std::string uk2("axy");
|
|
InternalKey ik2(uk2, 10, kTypeValue);
|
|
std::string v2(4100, '2'); // large value
|
|
|
|
PinnableSlice value;
|
|
std::string seek_ukey("axy");
|
|
InternalKey seek_ikey(seek_ukey, 120, kTypeValue);
|
|
GetContext get_context(options.comparator, nullptr, nullptr, nullptr,
|
|
GetContext::kNotFound, seek_ukey, &value, nullptr,
|
|
nullptr, nullptr, true, nullptr, nullptr);
|
|
|
|
TestBoundary(ik1, v1, ik2, v2, seek_ikey, get_context, options);
|
|
ASSERT_EQ(get_context.State(), GetContext::kFound);
|
|
ASSERT_EQ(value, v1);
|
|
value.Reset();
|
|
}
|
|
|
|
{
|
|
// [ "axy"@100 ][ "axy"@10 ]
|
|
// | Block N ][ Block N+1 ]
|
|
// seek for "axy"@5
|
|
std::string uk1("axy");
|
|
InternalKey ik1(uk1, 100, kTypeValue);
|
|
std::string v1(4100, '1'); // large value
|
|
|
|
std::string uk2("axy");
|
|
InternalKey ik2(uk2, 10, kTypeValue);
|
|
std::string v2(4100, '2'); // large value
|
|
|
|
PinnableSlice value;
|
|
std::string seek_ukey("axy");
|
|
InternalKey seek_ikey(seek_ukey, 5, kTypeValue);
|
|
GetContext get_context(options.comparator, nullptr, nullptr, nullptr,
|
|
GetContext::kNotFound, seek_ukey, &value, nullptr,
|
|
nullptr, nullptr, true, nullptr, nullptr);
|
|
|
|
TestBoundary(ik1, v1, ik2, v2, seek_ikey, get_context, options);
|
|
ASSERT_EQ(get_context.State(), GetContext::kNotFound);
|
|
value.Reset();
|
|
}
|
|
}
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|
|
|
|
int main(int argc, char** argv) {
|
|
ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
|
|
::testing::InitGoogleTest(&argc, argv);
|
|
return RUN_ALL_TESTS();
|
|
}
|