mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-30 04:41:49 +00:00
937fbcbddc
Summary: Track per-SST user-defined timestamp information in MANIFEST https://github.com/facebook/rocksdb/issues/8957 Rockdb has supported user-defined timestamp feature. Application can specify a timestamp when writing each k-v pair. When data flush from memory to disk file called SST files, file creation activity will commit to MANIFEST. This commit is for tracking timestamp info in the MANIFEST for each file. The changes involved are as follows: 1) Track max/min timestamp in FileMetaData, and fix invoved codes. 2) Add NewFileCustomTag::kMinTimestamp and NewFileCustomTag::kMinTimestamp in NewFileCustomTag ( in the kNewFile4 part ), and support invoved codes such as VersionEdit Encode and Decode etc. 3) Add unit test code for VersionEdit EncodeDecodeNewFile4, and fix invoved test codes. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9092 Reviewed By: ajkr, akankshamahajan15 Differential Revision: D32252323 Pulled By: riversand963 fbshipit-source-id: d2642898d6e3ad1fef0eb866b98045408bd4e162
215 lines
7.1 KiB
C++
215 lines
7.1 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).
|
|
//
|
|
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
|
|
// Use of this source code is governed by a BSD-style license that can be
|
|
// found in the LICENSE file. See the AUTHORS file for names of contributors.
|
|
#include "db/dbformat.h"
|
|
|
|
#include <stdio.h>
|
|
|
|
#include <cinttypes>
|
|
|
|
#include "db/lookup_key.h"
|
|
#include "monitoring/perf_context_imp.h"
|
|
#include "port/port.h"
|
|
#include "util/coding.h"
|
|
#include "util/string_util.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
// kValueTypeForSeek defines the ValueType that should be passed when
|
|
// constructing a ParsedInternalKey object for seeking to a particular
|
|
// sequence number (since we sort sequence numbers in decreasing order
|
|
// and the value type is embedded as the low 8 bits in the sequence
|
|
// number in internal keys, we need to use the highest-numbered
|
|
// ValueType, not the lowest).
|
|
const ValueType kValueTypeForSeek = kTypeDeletionWithTimestamp;
|
|
const ValueType kValueTypeForSeekForPrev = kTypeDeletion;
|
|
const std::string kDisableUserTimestamp("");
|
|
|
|
EntryType GetEntryType(ValueType value_type) {
|
|
switch (value_type) {
|
|
case kTypeValue:
|
|
return kEntryPut;
|
|
case kTypeDeletion:
|
|
return kEntryDelete;
|
|
case kTypeDeletionWithTimestamp:
|
|
return kEntryDeleteWithTimestamp;
|
|
case kTypeSingleDeletion:
|
|
return kEntrySingleDelete;
|
|
case kTypeMerge:
|
|
return kEntryMerge;
|
|
case kTypeRangeDeletion:
|
|
return kEntryRangeDeletion;
|
|
case kTypeBlobIndex:
|
|
return kEntryBlobIndex;
|
|
default:
|
|
return kEntryOther;
|
|
}
|
|
}
|
|
|
|
void AppendInternalKey(std::string* result, const ParsedInternalKey& key) {
|
|
result->append(key.user_key.data(), key.user_key.size());
|
|
PutFixed64(result, PackSequenceAndType(key.sequence, key.type));
|
|
}
|
|
|
|
void AppendInternalKeyWithDifferentTimestamp(std::string* result,
|
|
const ParsedInternalKey& key,
|
|
const Slice& ts) {
|
|
assert(key.user_key.size() >= ts.size());
|
|
result->append(key.user_key.data(), key.user_key.size() - ts.size());
|
|
result->append(ts.data(), ts.size());
|
|
PutFixed64(result, PackSequenceAndType(key.sequence, key.type));
|
|
}
|
|
|
|
void AppendInternalKeyFooter(std::string* result, SequenceNumber s,
|
|
ValueType t) {
|
|
PutFixed64(result, PackSequenceAndType(s, t));
|
|
}
|
|
|
|
void AppendKeyWithMinTimestamp(std::string* result, const Slice& key,
|
|
size_t ts_sz) {
|
|
assert(ts_sz > 0);
|
|
const std::string kTsMin(ts_sz, static_cast<unsigned char>(0));
|
|
result->append(key.data(), key.size());
|
|
result->append(kTsMin.data(), ts_sz);
|
|
}
|
|
|
|
void AppendKeyWithMaxTimestamp(std::string* result, const Slice& key,
|
|
size_t ts_sz) {
|
|
assert(ts_sz > 0);
|
|
const std::string kTsMax(ts_sz, static_cast<unsigned char>(0xff));
|
|
result->append(key.data(), key.size());
|
|
result->append(kTsMax.data(), ts_sz);
|
|
}
|
|
|
|
std::string ParsedInternalKey::DebugString(bool log_err_key, bool hex) const {
|
|
std::string result = "'";
|
|
if (log_err_key) {
|
|
result += user_key.ToString(hex);
|
|
} else {
|
|
result += "<redacted>";
|
|
}
|
|
|
|
char buf[50];
|
|
snprintf(buf, sizeof(buf), "' seq:%" PRIu64 ", type:%d", sequence,
|
|
static_cast<int>(type));
|
|
|
|
result += buf;
|
|
return result;
|
|
}
|
|
|
|
std::string InternalKey::DebugString(bool hex) const {
|
|
std::string result;
|
|
ParsedInternalKey parsed;
|
|
if (ParseInternalKey(rep_, &parsed, false /* log_err_key */).ok()) {
|
|
result = parsed.DebugString(true /* log_err_key */, hex); // TODO
|
|
} else {
|
|
result = "(bad)";
|
|
result.append(EscapeString(rep_));
|
|
}
|
|
return result;
|
|
}
|
|
|
|
const char* InternalKeyComparator::Name() const {
|
|
if (name_.empty()) {
|
|
return "rocksdb.anonymous.InternalKeyComparator";
|
|
}
|
|
return name_.c_str();
|
|
}
|
|
|
|
int InternalKeyComparator::Compare(const ParsedInternalKey& a,
|
|
const ParsedInternalKey& b) const {
|
|
// Order by:
|
|
// increasing user key (according to user-supplied comparator)
|
|
// decreasing sequence number
|
|
// decreasing type (though sequence# should be enough to disambiguate)
|
|
int r = user_comparator_.Compare(a.user_key, b.user_key);
|
|
if (r == 0) {
|
|
if (a.sequence > b.sequence) {
|
|
r = -1;
|
|
} else if (a.sequence < b.sequence) {
|
|
r = +1;
|
|
} else if (a.type > b.type) {
|
|
r = -1;
|
|
} else if (a.type < b.type) {
|
|
r = +1;
|
|
}
|
|
}
|
|
return r;
|
|
}
|
|
|
|
void InternalKeyComparator::FindShortestSeparator(std::string* start,
|
|
const Slice& limit) const {
|
|
// Attempt to shorten the user portion of the key
|
|
Slice user_start = ExtractUserKey(*start);
|
|
Slice user_limit = ExtractUserKey(limit);
|
|
std::string tmp(user_start.data(), user_start.size());
|
|
user_comparator_.FindShortestSeparator(&tmp, user_limit);
|
|
if (tmp.size() <= user_start.size() &&
|
|
user_comparator_.Compare(user_start, tmp) < 0) {
|
|
// User key has become shorter physically, but larger logically.
|
|
// Tack on the earliest possible number to the shortened user key.
|
|
PutFixed64(&tmp,
|
|
PackSequenceAndType(kMaxSequenceNumber, kValueTypeForSeek));
|
|
assert(this->Compare(*start, tmp) < 0);
|
|
assert(this->Compare(tmp, limit) < 0);
|
|
start->swap(tmp);
|
|
}
|
|
}
|
|
|
|
void InternalKeyComparator::FindShortSuccessor(std::string* key) const {
|
|
Slice user_key = ExtractUserKey(*key);
|
|
std::string tmp(user_key.data(), user_key.size());
|
|
user_comparator_.FindShortSuccessor(&tmp);
|
|
if (tmp.size() <= user_key.size() &&
|
|
user_comparator_.Compare(user_key, tmp) < 0) {
|
|
// User key has become shorter physically, but larger logically.
|
|
// Tack on the earliest possible number to the shortened user key.
|
|
PutFixed64(&tmp,
|
|
PackSequenceAndType(kMaxSequenceNumber, kValueTypeForSeek));
|
|
assert(this->Compare(*key, tmp) < 0);
|
|
key->swap(tmp);
|
|
}
|
|
}
|
|
|
|
LookupKey::LookupKey(const Slice& _user_key, SequenceNumber s,
|
|
const Slice* ts) {
|
|
size_t usize = _user_key.size();
|
|
size_t ts_sz = (nullptr == ts) ? 0 : ts->size();
|
|
size_t needed = usize + ts_sz + 13; // A conservative estimate
|
|
char* dst;
|
|
if (needed <= sizeof(space_)) {
|
|
dst = space_;
|
|
} else {
|
|
dst = new char[needed];
|
|
}
|
|
start_ = dst;
|
|
// NOTE: We don't support users keys of more than 2GB :)
|
|
dst = EncodeVarint32(dst, static_cast<uint32_t>(usize + ts_sz + 8));
|
|
kstart_ = dst;
|
|
memcpy(dst, _user_key.data(), usize);
|
|
dst += usize;
|
|
if (nullptr != ts) {
|
|
memcpy(dst, ts->data(), ts_sz);
|
|
dst += ts_sz;
|
|
}
|
|
EncodeFixed64(dst, PackSequenceAndType(s, kValueTypeForSeek));
|
|
dst += 8;
|
|
end_ = dst;
|
|
}
|
|
|
|
void IterKey::EnlargeBuffer(size_t key_size) {
|
|
// If size is smaller than buffer size, continue using current buffer,
|
|
// or the static allocated one, as default
|
|
assert(key_size > buf_size_);
|
|
// Need to enlarge the buffer.
|
|
ResetBuffer();
|
|
buf_ = new char[key_size];
|
|
buf_size_ = key_size;
|
|
}
|
|
} // namespace ROCKSDB_NAMESPACE
|