rocksdb/db/blob_index.h
Levi Tamasi fdc1cb43a6 Support decoding blob indexes in sst_dump (#5926)
Summary:
The patch adds a new command line parameter --decode_blob_index to sst_dump.
If this switch is specified, sst_dump prints blob indexes in a human readable format,
printing the blob file number, offset, size, and expiration (if applicable) for blob
references, and the blob value (and expiration) for inlined blobs.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5926

Test Plan:
Used db_bench's BlobDB mode to generate SST files containing blob references with
and without expiration, as well as inlined blobs with and without expiration (note: the
latter are stored as plain values), and confirmed sst_dump correctly prints all four types
of records.

Differential Revision: D17939077

Pulled By: ltamasi

fbshipit-source-id: edc5f58fee94ba35f6699c6a042d5758f5b3963d
2019-10-17 19:36:54 -07:00

180 lines
5.4 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).
#pragma once
#ifndef ROCKSDB_LITE
#include <sstream>
#include <string>
#include "rocksdb/options.h"
#include "util/coding.h"
#include "util/string_util.h"
namespace rocksdb {
// BlobIndex is a pointer to the blob and metadata of the blob. The index is
// stored in base DB as ValueType::kTypeBlobIndex.
// There are three types of blob index:
//
// kInlinedTTL:
// +------+------------+---------------+
// | type | expiration | value |
// +------+------------+---------------+
// | char | varint64 | variable size |
// +------+------------+---------------+
//
// kBlob:
// +------+-------------+----------+----------+-------------+
// | type | file number | offset | size | compression |
// +------+-------------+----------+----------+-------------+
// | char | varint64 | varint64 | varint64 | char |
// +------+-------------+----------+----------+-------------+
//
// kBlobTTL:
// +------+------------+-------------+----------+----------+-------------+
// | type | expiration | file number | offset | size | compression |
// +------+------------+-------------+----------+----------+-------------+
// | char | varint64 | varint64 | varint64 | varint64 | char |
// +------+------------+-------------+----------+----------+-------------+
//
// There isn't a kInlined (without TTL) type since we can store it as a plain
// value (i.e. ValueType::kTypeValue).
class BlobIndex {
public:
enum class Type : unsigned char {
kInlinedTTL = 0,
kBlob = 1,
kBlobTTL = 2,
kUnknown = 3,
};
BlobIndex() : type_(Type::kUnknown) {}
bool IsInlined() const { return type_ == Type::kInlinedTTL; }
bool HasTTL() const {
return type_ == Type::kInlinedTTL || type_ == Type::kBlobTTL;
}
uint64_t expiration() const {
assert(HasTTL());
return expiration_;
}
const Slice& value() const {
assert(IsInlined());
return value_;
}
uint64_t file_number() const {
assert(!IsInlined());
return file_number_;
}
uint64_t offset() const {
assert(!IsInlined());
return offset_;
}
uint64_t size() const {
assert(!IsInlined());
return size_;
}
Status DecodeFrom(Slice slice) {
static const std::string kErrorMessage = "Error while decoding blob index";
assert(slice.size() > 0);
type_ = static_cast<Type>(*slice.data());
if (type_ >= Type::kUnknown) {
return Status::Corruption(
kErrorMessage,
"Unknown blob index type: " + ToString(static_cast<char>(type_)));
}
slice = Slice(slice.data() + 1, slice.size() - 1);
if (HasTTL()) {
if (!GetVarint64(&slice, &expiration_)) {
return Status::Corruption(kErrorMessage, "Corrupted expiration");
}
}
if (IsInlined()) {
value_ = slice;
} else {
if (GetVarint64(&slice, &file_number_) && GetVarint64(&slice, &offset_) &&
GetVarint64(&slice, &size_) && slice.size() == 1) {
compression_ = static_cast<CompressionType>(*slice.data());
} else {
return Status::Corruption(kErrorMessage, "Corrupted blob offset");
}
}
return Status::OK();
}
std::string DebugString(bool output_hex) {
std::ostringstream oss;
if (IsInlined()) {
oss << "[inlined blob] value:" << value_.ToString(output_hex);
} else {
oss << "[blob ref] file:" << file_number_ << " offset:" << offset_
<< " size:" << size_;
}
if (HasTTL()) {
oss << " exp:" << expiration_;
}
return oss.str();
}
static void EncodeInlinedTTL(std::string* dst, uint64_t expiration,
const Slice& value) {
assert(dst != nullptr);
dst->clear();
dst->reserve(1 + kMaxVarint64Length + value.size());
dst->push_back(static_cast<char>(Type::kInlinedTTL));
PutVarint64(dst, expiration);
dst->append(value.data(), value.size());
}
static void EncodeBlob(std::string* dst, uint64_t file_number,
uint64_t offset, uint64_t size,
CompressionType compression) {
assert(dst != nullptr);
dst->clear();
dst->reserve(kMaxVarint64Length * 3 + 2);
dst->push_back(static_cast<char>(Type::kBlob));
PutVarint64(dst, file_number);
PutVarint64(dst, offset);
PutVarint64(dst, size);
dst->push_back(static_cast<char>(compression));
}
static void EncodeBlobTTL(std::string* dst, uint64_t expiration,
uint64_t file_number, uint64_t offset,
uint64_t size, CompressionType compression) {
assert(dst != nullptr);
dst->clear();
dst->reserve(kMaxVarint64Length * 4 + 2);
dst->push_back(static_cast<char>(Type::kBlobTTL));
PutVarint64(dst, expiration);
PutVarint64(dst, file_number);
PutVarint64(dst, offset);
PutVarint64(dst, size);
dst->push_back(static_cast<char>(compression));
}
private:
Type type_ = Type::kUnknown;
uint64_t expiration_ = 0;
Slice value_;
uint64_t file_number_ = 0;
uint64_t offset_ = 0;
uint64_t size_ = 0;
CompressionType compression_ = kNoCompression;
};
} // namespace rocksdb
#endif // ROCKSDB_LITE