rocksdb/table/get_context.cc

250 lines
8.3 KiB
C++
Raw Normal View History

// 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/get_context.h"
#include "db/merge_helper.h"
Introduce FullMergeV2 (eliminate memcpy from merge operators) Summary: This diff update the code to pin the merge operator operands while the merge operation is done, so that we can eliminate the memcpy cost, to do that we need a new public API for FullMerge that replace the std::deque<std::string> with std::vector<Slice> This diff is stacked on top of D56493 and D56511 In this diff we - Update FullMergeV2 arguments to be encapsulated in MergeOperationInput and MergeOperationOutput which will make it easier to add new arguments in the future - Replace std::deque<std::string> with std::vector<Slice> to pass operands - Replace MergeContext std::deque with std::vector (based on a simple benchmark I ran https://gist.github.com/IslamAbdelRahman/78fc86c9ab9f52b1df791e58943fb187) - Allow FullMergeV2 output to be an existing operand ``` [Everything in Memtable | 10K operands | 10 KB each | 1 operand per key] DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --merge_keys=10000 --num=10000 --disable_auto_compactions --value_size=10240 --write_buffer_size=1000000000 [FullMergeV2] readseq : 0.607 micros/op 1648235 ops/sec; 16121.2 MB/s readseq : 0.478 micros/op 2091546 ops/sec; 20457.2 MB/s readseq : 0.252 micros/op 3972081 ops/sec; 38850.5 MB/s readseq : 0.237 micros/op 4218328 ops/sec; 41259.0 MB/s readseq : 0.247 micros/op 4043927 ops/sec; 39553.2 MB/s [master] readseq : 3.935 micros/op 254140 ops/sec; 2485.7 MB/s readseq : 3.722 micros/op 268657 ops/sec; 2627.7 MB/s readseq : 3.149 micros/op 317605 ops/sec; 3106.5 MB/s readseq : 3.125 micros/op 320024 ops/sec; 3130.1 MB/s readseq : 4.075 micros/op 245374 ops/sec; 2400.0 MB/s ``` ``` [Everything in Memtable | 10K operands | 10 KB each | 10 operand per key] DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --merge_keys=1000 --num=10000 --disable_auto_compactions --value_size=10240 --write_buffer_size=1000000000 [FullMergeV2] readseq : 3.472 micros/op 288018 ops/sec; 2817.1 MB/s readseq : 2.304 micros/op 434027 ops/sec; 4245.2 MB/s readseq : 1.163 micros/op 859845 ops/sec; 8410.0 MB/s readseq : 1.192 micros/op 838926 ops/sec; 8205.4 MB/s readseq : 1.250 micros/op 800000 ops/sec; 7824.7 MB/s [master] readseq : 24.025 micros/op 41623 ops/sec; 407.1 MB/s readseq : 18.489 micros/op 54086 ops/sec; 529.0 MB/s readseq : 18.693 micros/op 53495 ops/sec; 523.2 MB/s readseq : 23.621 micros/op 42335 ops/sec; 414.1 MB/s readseq : 18.775 micros/op 53262 ops/sec; 521.0 MB/s ``` ``` [Everything in Block cache | 10K operands | 10 KB each | 1 operand per key] [FullMergeV2] $ DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --num=100000 --db="/dev/shm/merge-random-10K-10KB" --cache_size=1000000000 --use_existing_db --disable_auto_compactions readseq : 14.741 micros/op 67837 ops/sec; 663.5 MB/s readseq : 1.029 micros/op 971446 ops/sec; 9501.6 MB/s readseq : 0.974 micros/op 1026229 ops/sec; 10037.4 MB/s readseq : 0.965 micros/op 1036080 ops/sec; 10133.8 MB/s readseq : 0.943 micros/op 1060657 ops/sec; 10374.2 MB/s [master] readseq : 16.735 micros/op 59755 ops/sec; 584.5 MB/s readseq : 3.029 micros/op 330151 ops/sec; 3229.2 MB/s readseq : 3.136 micros/op 318883 ops/sec; 3119.0 MB/s readseq : 3.065 micros/op 326245 ops/sec; 3191.0 MB/s readseq : 3.014 micros/op 331813 ops/sec; 3245.4 MB/s ``` ``` [Everything in Block cache | 10K operands | 10 KB each | 10 operand per key] DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --num=100000 --db="/dev/shm/merge-random-10-operands-10K-10KB" --cache_size=1000000000 --use_existing_db --disable_auto_compactions [FullMergeV2] readseq : 24.325 micros/op 41109 ops/sec; 402.1 MB/s readseq : 1.470 micros/op 680272 ops/sec; 6653.7 MB/s readseq : 1.231 micros/op 812347 ops/sec; 7945.5 MB/s readseq : 1.091 micros/op 916590 ops/sec; 8965.1 MB/s readseq : 1.109 micros/op 901713 ops/sec; 8819.6 MB/s [master] readseq : 27.257 micros/op 36687 ops/sec; 358.8 MB/s readseq : 4.443 micros/op 225073 ops/sec; 2201.4 MB/s readseq : 5.830 micros/op 171526 ops/sec; 1677.7 MB/s readseq : 4.173 micros/op 239635 ops/sec; 2343.8 MB/s readseq : 4.150 micros/op 240963 ops/sec; 2356.8 MB/s ``` Test Plan: COMPILE_WITH_ASAN=1 make check -j64 Reviewers: yhchiang, andrewkr, sdong Reviewed By: sdong Subscribers: lovro, andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D57075
2016-07-20 16:49:03 +00:00
#include "db/pinned_iterators_manager.h"
#include "db/read_callback.h"
#include "monitoring/file_read_sample.h"
#include "monitoring/perf_context_imp.h"
#include "monitoring/statistics.h"
#include "rocksdb/env.h"
#include "rocksdb/merge_operator.h"
#include "rocksdb/statistics.h"
namespace rocksdb {
namespace {
void appendToReplayLog(std::string* replay_log, ValueType type, Slice value) {
#ifndef ROCKSDB_LITE
if (replay_log) {
if (replay_log->empty()) {
// Optimization: in the common case of only one operation in the
// log, we allocate the exact amount of space needed.
replay_log->reserve(1 + VarintLength(value.size()) + value.size());
}
replay_log->push_back(type);
PutLengthPrefixedSlice(replay_log, value);
}
#endif // ROCKSDB_LITE
}
} // namespace
GetContext::GetContext(const Comparator* ucmp,
const MergeOperator* merge_operator, Logger* logger,
Statistics* statistics, GetState init_state,
const Slice& user_key, PinnableSlice* pinnable_val,
bool* value_found, MergeContext* merge_context,
RangeDelAggregator* _range_del_agg, Env* env,
SequenceNumber* seq,
PinnedIteratorsManager* _pinned_iters_mgr,
ReadCallback* callback, bool* is_blob_index)
: ucmp_(ucmp),
merge_operator_(merge_operator),
logger_(logger),
statistics_(statistics),
state_(init_state),
user_key_(user_key),
pinnable_val_(pinnable_val),
value_found_(value_found),
merge_context_(merge_context),
range_del_agg_(_range_del_agg),
env_(env),
seq_(seq),
Introduce FullMergeV2 (eliminate memcpy from merge operators) Summary: This diff update the code to pin the merge operator operands while the merge operation is done, so that we can eliminate the memcpy cost, to do that we need a new public API for FullMerge that replace the std::deque<std::string> with std::vector<Slice> This diff is stacked on top of D56493 and D56511 In this diff we - Update FullMergeV2 arguments to be encapsulated in MergeOperationInput and MergeOperationOutput which will make it easier to add new arguments in the future - Replace std::deque<std::string> with std::vector<Slice> to pass operands - Replace MergeContext std::deque with std::vector (based on a simple benchmark I ran https://gist.github.com/IslamAbdelRahman/78fc86c9ab9f52b1df791e58943fb187) - Allow FullMergeV2 output to be an existing operand ``` [Everything in Memtable | 10K operands | 10 KB each | 1 operand per key] DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --merge_keys=10000 --num=10000 --disable_auto_compactions --value_size=10240 --write_buffer_size=1000000000 [FullMergeV2] readseq : 0.607 micros/op 1648235 ops/sec; 16121.2 MB/s readseq : 0.478 micros/op 2091546 ops/sec; 20457.2 MB/s readseq : 0.252 micros/op 3972081 ops/sec; 38850.5 MB/s readseq : 0.237 micros/op 4218328 ops/sec; 41259.0 MB/s readseq : 0.247 micros/op 4043927 ops/sec; 39553.2 MB/s [master] readseq : 3.935 micros/op 254140 ops/sec; 2485.7 MB/s readseq : 3.722 micros/op 268657 ops/sec; 2627.7 MB/s readseq : 3.149 micros/op 317605 ops/sec; 3106.5 MB/s readseq : 3.125 micros/op 320024 ops/sec; 3130.1 MB/s readseq : 4.075 micros/op 245374 ops/sec; 2400.0 MB/s ``` ``` [Everything in Memtable | 10K operands | 10 KB each | 10 operand per key] DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="mergerandom,readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --merge_keys=1000 --num=10000 --disable_auto_compactions --value_size=10240 --write_buffer_size=1000000000 [FullMergeV2] readseq : 3.472 micros/op 288018 ops/sec; 2817.1 MB/s readseq : 2.304 micros/op 434027 ops/sec; 4245.2 MB/s readseq : 1.163 micros/op 859845 ops/sec; 8410.0 MB/s readseq : 1.192 micros/op 838926 ops/sec; 8205.4 MB/s readseq : 1.250 micros/op 800000 ops/sec; 7824.7 MB/s [master] readseq : 24.025 micros/op 41623 ops/sec; 407.1 MB/s readseq : 18.489 micros/op 54086 ops/sec; 529.0 MB/s readseq : 18.693 micros/op 53495 ops/sec; 523.2 MB/s readseq : 23.621 micros/op 42335 ops/sec; 414.1 MB/s readseq : 18.775 micros/op 53262 ops/sec; 521.0 MB/s ``` ``` [Everything in Block cache | 10K operands | 10 KB each | 1 operand per key] [FullMergeV2] $ DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --num=100000 --db="/dev/shm/merge-random-10K-10KB" --cache_size=1000000000 --use_existing_db --disable_auto_compactions readseq : 14.741 micros/op 67837 ops/sec; 663.5 MB/s readseq : 1.029 micros/op 971446 ops/sec; 9501.6 MB/s readseq : 0.974 micros/op 1026229 ops/sec; 10037.4 MB/s readseq : 0.965 micros/op 1036080 ops/sec; 10133.8 MB/s readseq : 0.943 micros/op 1060657 ops/sec; 10374.2 MB/s [master] readseq : 16.735 micros/op 59755 ops/sec; 584.5 MB/s readseq : 3.029 micros/op 330151 ops/sec; 3229.2 MB/s readseq : 3.136 micros/op 318883 ops/sec; 3119.0 MB/s readseq : 3.065 micros/op 326245 ops/sec; 3191.0 MB/s readseq : 3.014 micros/op 331813 ops/sec; 3245.4 MB/s ``` ``` [Everything in Block cache | 10K operands | 10 KB each | 10 operand per key] DEBUG_LEVEL=0 make db_bench -j64 && ./db_bench --benchmarks="readseq,readseq,readseq,readseq,readseq" --merge_operator="max" --num=100000 --db="/dev/shm/merge-random-10-operands-10K-10KB" --cache_size=1000000000 --use_existing_db --disable_auto_compactions [FullMergeV2] readseq : 24.325 micros/op 41109 ops/sec; 402.1 MB/s readseq : 1.470 micros/op 680272 ops/sec; 6653.7 MB/s readseq : 1.231 micros/op 812347 ops/sec; 7945.5 MB/s readseq : 1.091 micros/op 916590 ops/sec; 8965.1 MB/s readseq : 1.109 micros/op 901713 ops/sec; 8819.6 MB/s [master] readseq : 27.257 micros/op 36687 ops/sec; 358.8 MB/s readseq : 4.443 micros/op 225073 ops/sec; 2201.4 MB/s readseq : 5.830 micros/op 171526 ops/sec; 1677.7 MB/s readseq : 4.173 micros/op 239635 ops/sec; 2343.8 MB/s readseq : 4.150 micros/op 240963 ops/sec; 2356.8 MB/s ``` Test Plan: COMPILE_WITH_ASAN=1 make check -j64 Reviewers: yhchiang, andrewkr, sdong Reviewed By: sdong Subscribers: lovro, andrewkr, dhruba Differential Revision: https://reviews.facebook.net/D57075
2016-07-20 16:49:03 +00:00
replay_log_(nullptr),
pinned_iters_mgr_(_pinned_iters_mgr),
callback_(callback),
is_blob_index_(is_blob_index) {
if (seq_) {
*seq_ = kMaxSequenceNumber;
}
sample_ = should_sample_file_read();
}
// Called from TableCache::Get and Table::Get when file/block in which
// key may exist are not there in TableCache/BlockCache respectively. In this
// case we can't guarantee that key does not exist and are not permitted to do
// IO to be certain.Set the status=kFound and value_found=false to let the
// caller know that key may exist but is not there in memory
void GetContext::MarkKeyMayExist() {
state_ = kFound;
if (value_found_ != nullptr) {
*value_found_ = false;
}
}
void GetContext::SaveValue(const Slice& value, SequenceNumber /*seq*/) {
assert(state_ == kNotFound);
appendToReplayLog(replay_log_, kTypeValue, value);
state_ = kFound;
if (LIKELY(pinnable_val_ != nullptr)) {
pinnable_val_->PinSelf(value);
}
}
void GetContext::RecordCounters(Tickers ticker, size_t val) {
if (ticker == Tickers::TICKER_ENUM_MAX) {
return;
}
tickers_value[ticker] += static_cast<uint64_t>(val);
}
bool GetContext::SaveValue(const ParsedInternalKey& parsed_key,
const Slice& value, bool* matched,
Cleanable* value_pinner) {
assert(matched);
assert((state_ != kMerge && parsed_key.type != kTypeMerge) ||
merge_context_ != nullptr);
if (ucmp_->Equal(parsed_key.user_key, user_key_)) {
*matched = true;
// If the value is not in the snapshot, skip it
if (!CheckCallback(parsed_key.sequence)) {
return true; // to continue to the next seq
}
appendToReplayLog(replay_log_, parsed_key.type, value);
if (seq_ != nullptr) {
// Set the sequence number if it is uninitialized
if (*seq_ == kMaxSequenceNumber) {
*seq_ = parsed_key.sequence;
}
}
auto type = parsed_key.type;
// Key matches. Process it
if ((type == kTypeValue || type == kTypeMerge || type == kTypeBlobIndex) &&
range_del_agg_ != nullptr && range_del_agg_->ShouldDelete(parsed_key)) {
type = kTypeRangeDeletion;
}
switch (type) {
case kTypeValue:
case kTypeBlobIndex:
assert(state_ == kNotFound || state_ == kMerge);
if (type == kTypeBlobIndex && is_blob_index_ == nullptr) {
// Blob value not supported. Stop.
state_ = kBlobIndex;
return false;
}
if (kNotFound == state_) {
state_ = kFound;
if (LIKELY(pinnable_val_ != nullptr)) {
if (LIKELY(value_pinner != nullptr)) {
// If the backing resources for the value are provided, pin them
pinnable_val_->PinSlice(value, value_pinner);
} else {
// Otherwise copy the value
pinnable_val_->PinSelf(value);
}
}
} else if (kMerge == state_) {
assert(merge_operator_ != nullptr);
state_ = kFound;
if (LIKELY(pinnable_val_ != nullptr)) {
Status merge_status = MergeHelper::TimedFullMerge(
merge_operator_, user_key_, &value,
merge_context_->GetOperands(), pinnable_val_->GetSelf(),
logger_, statistics_, env_);
pinnable_val_->PinSelf();
if (!merge_status.ok()) {
state_ = kCorrupt;
}
}
}
if (is_blob_index_ != nullptr) {
*is_blob_index_ = (type == kTypeBlobIndex);
}
return false;
case kTypeDeletion:
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
2015-09-17 18:42:56 +00:00
case kTypeSingleDeletion:
case kTypeRangeDeletion:
Support for SingleDelete() Summary: This patch fixes #7460559. It introduces SingleDelete as a new database operation. This operation can be used to delete keys that were never overwritten (no put following another put of the same key). If an overwritten key is single deleted the behavior is undefined. Single deletion of a non-existent key has no effect but multiple consecutive single deletions are not allowed (see limitations). In contrast to the conventional Delete() operation, the deletion entry is removed along with the value when the two are lined up in a compaction. Note: The semantics are similar to @igor's prototype that allowed to have this behavior on the granularity of a column family ( https://reviews.facebook.net/D42093 ). This new patch, however, is more aggressive when it comes to removing tombstones: It removes the SingleDelete together with the value whenever there is no snapshot between them while the older patch only did this when the sequence number of the deletion was older than the earliest snapshot. Most of the complex additions are in the Compaction Iterator, all other changes should be relatively straightforward. The patch also includes basic support for single deletions in db_stress and db_bench. Limitations: - Not compatible with cuckoo hash tables - Single deletions cannot be used in combination with merges and normal deletions on the same key (other keys are not affected by this) - Consecutive single deletions are currently not allowed (and older version of this patch supported this so it could be resurrected if needed) Test Plan: make all check Reviewers: yhchiang, sdong, rven, anthony, yoshinorim, igor Reviewed By: igor Subscribers: maykov, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D43179
2015-09-17 18:42:56 +00:00
// TODO(noetzli): Verify correctness once merge of single-deletes
// is supported
assert(state_ == kNotFound || state_ == kMerge);
if (kNotFound == state_) {
state_ = kDeleted;
} else if (kMerge == state_) {
state_ = kFound;
if (LIKELY(pinnable_val_ != nullptr)) {
Status merge_status = MergeHelper::TimedFullMerge(
merge_operator_, user_key_, nullptr,
merge_context_->GetOperands(), pinnable_val_->GetSelf(),
logger_, statistics_, env_);
pinnable_val_->PinSelf();
if (!merge_status.ok()) {
state_ = kCorrupt;
}
}
}
return false;
case kTypeMerge:
assert(state_ == kNotFound || state_ == kMerge);
state_ = kMerge;
// value_pinner is not set from plain_table_reader.cc for example.
if (pinned_iters_mgr() && pinned_iters_mgr()->PinningEnabled() &&
value_pinner != nullptr) {
value_pinner->DelegateCleanupsTo(pinned_iters_mgr());
merge_context_->PushOperand(value, true /*value_pinned*/);
} else {
merge_context_->PushOperand(value, false);
}
Introduce conditional merge-operator invocation in point lookups Summary: For every merge operand encountered for a key in the read path we now have the ability to decide whether to look further (to retrieve more merge operands for the key) or stop and invoke the merge operator to return the value. The user needs to override `ShouldMerge()` method with a condition to terminate search when true to avail this facility. This has a couple of advantages: 1. It helps in limiting the number of merge operands that are looked at to compute a value as part of a user Get operation. 2. It allows to peek at a merge key-value to see if further merge operands need to look at. Example: Limiting the number of merge operands that are looked at: Lets say you have 10 merge operands for a key spread over various levels. If you only want RocksDB to look at the latest two merge operands instead of all 10 to compute the value, it is now possible with this PR. You can set the condition in `ShouldMerge()` to return true when the size of the operand list is 2. Look at the example implementation in the unit test. Without this PR, a Get might look at all the 10 merge operands in different levels before invoking the merge-operator. Added a new unit test. Made sure that there is no perf regression by running benchmarks. Command line to Load data: ``` TEST_TMPDIR=/dev/shm ./db_bench --benchmarks="mergerandom" --merge_operator="uint64add" --num=10000000 ... mergerandom : 12.861 micros/op 77757 ops/sec; 8.6 MB/s ( updates:10000000) ``` **ReadRandomMergeRandom bechmark results:** Command line: ``` TEST_TMPDIR=/dev/shm ./db_bench --benchmarks="readrandommergerandom" --merge_operator="uint64add" --num=10000000 ``` Base -- Without this code change (on commit fc7476b): ``` readrandommergerandom : 38.586 micros/op 25916 ops/sec; (reads:3001599 merges:6998401 total:10000000 hits:842235 maxlength:8) ``` With this code change: ``` readrandommergerandom : 38.653 micros/op 25870 ops/sec; (reads:3001599 merges:6998401 total:10000000 hits:842235 maxlength:8) ``` Closes https://github.com/facebook/rocksdb/pull/2923 Differential Revision: D5898239 Pulled By: sagar0 fbshipit-source-id: daefa325019f77968639a75c851d46352c2303ef
2017-09-28 22:49:05 +00:00
if (merge_operator_ != nullptr &&
merge_operator_->ShouldMerge(merge_context_->GetOperands())) {
state_ = kFound;
if (LIKELY(pinnable_val_ != nullptr)) {
Status merge_status = MergeHelper::TimedFullMerge(
merge_operator_, user_key_, nullptr,
merge_context_->GetOperands(), pinnable_val_->GetSelf(),
logger_, statistics_, env_);
pinnable_val_->PinSelf();
if (!merge_status.ok()) {
state_ = kCorrupt;
}
}
return false;
}
return true;
default:
assert(false);
break;
}
}
// state_ could be Corrupt, merge or notfound
return false;
}
void replayGetContextLog(const Slice& replay_log, const Slice& user_key,
GetContext* get_context, Cleanable* value_pinner) {
#ifndef ROCKSDB_LITE
Slice s = replay_log;
while (s.size()) {
auto type = static_cast<ValueType>(*s.data());
s.remove_prefix(1);
Slice value;
bool ret = GetLengthPrefixedSlice(&s, &value);
assert(ret);
(void)ret;
bool dont_care __attribute__((__unused__));
// Since SequenceNumber is not stored and unknown, we will use
// kMaxSequenceNumber.
get_context->SaveValue(
ParsedInternalKey(user_key, kMaxSequenceNumber, type), value,
&dont_care, value_pinner);
}
#else // ROCKSDB_LITE
assert(false);
#endif // ROCKSDB_LITE
}
} // namespace rocksdb