Maintain the set of linked SSTs in BlobFileMetaData (#6945)

Summary:
The `FileMetaData` objects associated with table files already contain the
number of the oldest blob file referenced by the SST in question. This patch
adds the inverse mapping to `BlobFileMetaData`, namely the set of table file
numbers for which the oldest blob file link points to the given blob file (these
are referred to as *linked SSTs*). This mapping will be used by the GC logic.

Implementation-wise, the patch builds on the `BlobFileMetaDataDelta`
functionality introduced in https://github.com/facebook/rocksdb/pull/6835: newly linked/unlinked SSTs are
accumulated in `BlobFileMetaDataDelta`, and the changes to the linked SST set
are applied in one shot when the new `Version` is saved. The patch also reworks
the blob file related consistency checks in `VersionBuilder` so they validate the
consistency of the forward table file -> blob file links and the backward blob file ->
table file links for blob files that are part of the `Version`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6945

Test Plan: `make check`

Reviewed By: riversand963

Differential Revision: D21912228

Pulled By: ltamasi

fbshipit-source-id: c5bc7acf6e729a8fccbb12672dd5cd00f6f000f8
main
Levi Tamasi 4 years ago committed by Facebook GitHub Bot
parent 717749f4c0
commit 83833637c1
  1. 9
      db/blob/blob_file_meta.cc
  2. 22
      db/blob/blob_file_meta.h
  3. 219
      db/version_builder.cc
  4. 261
      db/version_builder_test.cc

@ -38,8 +38,15 @@ std::string BlobFileMetaData::DebugString() const {
std::ostream& operator<<(std::ostream& os, const BlobFileMetaData& meta) {
const auto& shared_meta = meta.GetSharedMeta();
assert(shared_meta);
os << (*shared_meta);
os << (*shared_meta) << " garbage_blob_count: " << meta.GetGarbageBlobCount()
os << " linked_ssts: {";
for (uint64_t file_number : meta.GetLinkedSsts()) {
os << ' ' << file_number;
}
os << " }";
os << " garbage_blob_count: " << meta.GetGarbageBlobCount()
<< " garbage_blob_bytes: " << meta.GetGarbageBlobBytes();
return os;

@ -5,12 +5,13 @@
#pragma once
#include "rocksdb/rocksdb_namespace.h"
#include <cassert>
#include <iosfwd>
#include <memory>
#include <string>
#include <unordered_set>
#include "rocksdb/rocksdb_namespace.h"
namespace ROCKSDB_NAMESPACE {
@ -90,11 +91,15 @@ std::ostream& operator<<(std::ostream& os,
class BlobFileMetaData {
public:
using LinkedSsts = std::unordered_set<uint64_t>;
static std::shared_ptr<BlobFileMetaData> Create(
std::shared_ptr<SharedBlobFileMetaData> shared_meta,
uint64_t garbage_blob_count, uint64_t garbage_blob_bytes) {
return std::shared_ptr<BlobFileMetaData>(new BlobFileMetaData(
std::move(shared_meta), garbage_blob_count, garbage_blob_bytes));
LinkedSsts linked_ssts, uint64_t garbage_blob_count,
uint64_t garbage_blob_bytes) {
return std::shared_ptr<BlobFileMetaData>(
new BlobFileMetaData(std::move(shared_meta), std::move(linked_ssts),
garbage_blob_count, garbage_blob_bytes));
}
BlobFileMetaData(const BlobFileMetaData&) = delete;
@ -128,6 +133,8 @@ class BlobFileMetaData {
return shared_meta_->GetChecksumValue();
}
const LinkedSsts& GetLinkedSsts() const { return linked_ssts_; }
uint64_t GetGarbageBlobCount() const { return garbage_blob_count_; }
uint64_t GetGarbageBlobBytes() const { return garbage_blob_bytes_; }
@ -135,8 +142,10 @@ class BlobFileMetaData {
private:
BlobFileMetaData(std::shared_ptr<SharedBlobFileMetaData> shared_meta,
uint64_t garbage_blob_count, uint64_t garbage_blob_bytes)
LinkedSsts linked_ssts, uint64_t garbage_blob_count,
uint64_t garbage_blob_bytes)
: shared_meta_(std::move(shared_meta)),
linked_ssts_(std::move(linked_ssts)),
garbage_blob_count_(garbage_blob_count),
garbage_blob_bytes_(garbage_blob_bytes) {
assert(shared_meta_);
@ -145,6 +154,7 @@ class BlobFileMetaData {
}
std::shared_ptr<SharedBlobFileMetaData> shared_meta_;
LinkedSsts linked_ssts_;
uint64_t garbage_blob_count_;
uint64_t garbage_blob_bytes_;
};

@ -90,7 +90,8 @@ class VersionBuilder::Rep {
public:
bool IsEmpty() const {
return !shared_meta_ && !additional_garbage_count_ &&
!additional_garbage_bytes_;
!additional_garbage_bytes_ && newly_linked_ssts_.empty() &&
newly_unlinked_ssts_.empty();
}
std::shared_ptr<SharedBlobFileMetaData> GetSharedMeta() const {
@ -105,6 +106,14 @@ class VersionBuilder::Rep {
return additional_garbage_bytes_;
}
const std::unordered_set<uint64_t>& GetNewlyLinkedSsts() const {
return newly_linked_ssts_;
}
const std::unordered_set<uint64_t>& GetNewlyUnlinkedSsts() const {
return newly_unlinked_ssts_;
}
void SetSharedMeta(std::shared_ptr<SharedBlobFileMetaData> shared_meta) {
assert(!shared_meta_);
assert(shared_meta);
@ -117,10 +126,44 @@ class VersionBuilder::Rep {
additional_garbage_bytes_ += bytes;
}
void LinkSst(uint64_t sst_file_number) {
assert(newly_linked_ssts_.find(sst_file_number) ==
newly_linked_ssts_.end());
// Reconcile with newly unlinked SSTs on the fly. (Note: an SST can be
// linked to and unlinked from the same blob file in the case of a trivial
// move.)
auto it = newly_unlinked_ssts_.find(sst_file_number);
if (it != newly_unlinked_ssts_.end()) {
newly_unlinked_ssts_.erase(it);
} else {
newly_linked_ssts_.emplace(sst_file_number);
}
}
void UnlinkSst(uint64_t sst_file_number) {
assert(newly_unlinked_ssts_.find(sst_file_number) ==
newly_unlinked_ssts_.end());
// Reconcile with newly linked SSTs on the fly. (Note: an SST can be
// linked to and unlinked from the same blob file in the case of a trivial
// move.)
auto it = newly_linked_ssts_.find(sst_file_number);
if (it != newly_linked_ssts_.end()) {
newly_linked_ssts_.erase(it);
} else {
newly_unlinked_ssts_.emplace(sst_file_number);
}
}
private:
std::shared_ptr<SharedBlobFileMetaData> shared_meta_;
uint64_t additional_garbage_count_ = 0;
uint64_t additional_garbage_bytes_ = 0;
std::unordered_set<uint64_t> newly_linked_ssts_;
std::unordered_set<uint64_t> newly_unlinked_ssts_;
};
const FileOptions& file_options_;
@ -212,29 +255,19 @@ class VersionBuilder::Rep {
return false;
}
Status CheckConsistencyOfOldestBlobFileReference(
const VersionStorageInfo* vstorage, uint64_t blob_file_number) const {
assert(vstorage);
using ExpectedLinkedSsts =
std::unordered_map<uint64_t, BlobFileMetaData::LinkedSsts>;
// TODO: remove this check once we actually start recoding metadata for
// blob files in the MANIFEST.
if (vstorage->GetBlobFiles().empty()) {
return Status::OK();
}
static void UpdateExpectedLinkedSsts(
uint64_t table_file_number, uint64_t blob_file_number,
ExpectedLinkedSsts* expected_linked_ssts) {
assert(expected_linked_ssts);
if (blob_file_number == kInvalidBlobFileNumber) {
return Status::OK();
return;
}
if (!IsBlobFileInVersion(blob_file_number)) {
std::ostringstream oss;
oss << "Blob file #" << blob_file_number
<< " is not part of this version";
return Status::Corruption("VersionBuilder", oss.str());
}
return Status::OK();
(*expected_linked_ssts)[blob_file_number].emplace(table_file_number);
}
Status CheckConsistency(VersionStorageInfo* vstorage) {
@ -245,9 +278,13 @@ class VersionBuilder::Rep {
return Status::OK();
}
#endif
// Make sure the files are sorted correctly and that the oldest blob file
// reference for each table file points to a valid blob file in this
// version.
// Make sure the files are sorted correctly and that the links between
// table files and blob files are consistent. The latter is checked using
// the following mapping, which is built using the forward links
// (table file -> blob file), and is subsequently compared with the inverse
// mapping stored in the BlobFileMetaData objects.
ExpectedLinkedSsts expected_linked_ssts;
for (int level = 0; level < num_levels_; level++) {
auto& level_files = vstorage->LevelFiles(level);
@ -256,19 +293,14 @@ class VersionBuilder::Rep {
}
assert(level_files[0]);
Status s = CheckConsistencyOfOldestBlobFileReference(
vstorage, level_files[0]->oldest_blob_file_number);
if (!s.ok()) {
return s;
}
UpdateExpectedLinkedSsts(level_files[0]->fd.GetNumber(),
level_files[0]->oldest_blob_file_number,
&expected_linked_ssts);
for (size_t i = 1; i < level_files.size(); i++) {
assert(level_files[i]);
s = CheckConsistencyOfOldestBlobFileReference(
vstorage, level_files[i]->oldest_blob_file_number);
if (!s.ok()) {
return s;
}
UpdateExpectedLinkedSsts(level_files[i]->fd.GetNumber(),
level_files[i]->oldest_blob_file_number,
&expected_linked_ssts);
auto f1 = level_files[i - 1];
auto f2 = level_files[i];
@ -328,17 +360,27 @@ class VersionBuilder::Rep {
// Make sure that all blob files in the version have non-garbage data.
const auto& blob_files = vstorage->GetBlobFiles();
for (const auto& pair : blob_files) {
const uint64_t blob_file_number = pair.first;
const auto& blob_file_meta = pair.second;
assert(blob_file_meta);
if (blob_file_meta->GetGarbageBlobCount() >=
blob_file_meta->GetTotalBlobCount()) {
std::ostringstream oss;
oss << "Blob file #" << blob_file_meta->GetBlobFileNumber()
oss << "Blob file #" << blob_file_number
<< " consists entirely of garbage";
return Status::Corruption("VersionBuilder", oss.str());
}
if (blob_file_meta->GetLinkedSsts() !=
expected_linked_ssts[blob_file_number]) {
std::ostringstream oss;
oss << "Links are inconsistent between table files and blob file #"
<< blob_file_number;
return Status::Corruption("VersionBuilder", oss.str());
}
}
Status ret_s;
@ -430,6 +472,28 @@ class VersionBuilder::Rep {
return base_vstorage_->GetFileLocation(file_number).GetLevel();
}
uint64_t GetOldestBlobFileNumberForTableFile(int level,
uint64_t file_number) const {
assert(level < num_levels_);
const auto& added_files = levels_[level].added_files;
auto it = added_files.find(file_number);
if (it != added_files.end()) {
const FileMetaData* const meta = it->second;
assert(meta);
return meta->oldest_blob_file_number;
}
assert(base_vstorage_);
const FileMetaData* const meta =
base_vstorage_->GetFileMetaDataByNumber(file_number);
assert(meta);
return meta->oldest_blob_file_number;
}
Status ApplyFileDeletion(int level, uint64_t file_number) {
assert(level != VersionStorageInfo::FileLocation::Invalid().GetLevel());
@ -463,6 +527,14 @@ class VersionBuilder::Rep {
return Status::OK();
}
const uint64_t blob_file_number =
GetOldestBlobFileNumberForTableFile(level, file_number);
if (blob_file_number != kInvalidBlobFileNumber &&
IsBlobFileInVersion(blob_file_number)) {
blob_file_meta_deltas_[blob_file_number].UnlinkSst(file_number);
}
auto& level_state = levels_[level];
auto& add_files = level_state.added_files;
@ -523,6 +595,13 @@ class VersionBuilder::Rep {
assert(add_files.find(file_number) == add_files.end());
add_files.emplace(file_number, f);
const uint64_t blob_file_number = f->oldest_blob_file_number;
if (blob_file_number != kInvalidBlobFileNumber &&
IsBlobFileInVersion(blob_file_number)) {
blob_file_meta_deltas_[blob_file_number].LinkSst(file_number);
}
table_file_levels_[file_number] = level;
return Status::OK();
@ -537,7 +616,27 @@ class VersionBuilder::Rep {
}
}
// Delete files
// Note: we process the blob file related changes first because the
// table file addition/deletion logic depends on the blob files
// already being there.
// Add new blob files
for (const auto& blob_file_addition : edit->GetBlobFileAdditions()) {
const Status s = ApplyBlobFileAddition(blob_file_addition);
if (!s.ok()) {
return s;
}
}
// Increase the amount of garbage for blob files affected by GC
for (const auto& blob_file_garbage : edit->GetBlobFileGarbages()) {
const Status s = ApplyBlobFileGarbage(blob_file_garbage);
if (!s.ok()) {
return s;
}
}
// Delete table files
for (const auto& deleted_file : edit->GetDeletedFiles()) {
const int level = deleted_file.first;
const uint64_t file_number = deleted_file.second;
@ -548,7 +647,7 @@ class VersionBuilder::Rep {
}
}
// Add new files
// Add new table files
for (const auto& new_file : edit->GetNewFiles()) {
const int level = new_file.first;
const FileMetaData& meta = new_file.second;
@ -559,23 +658,28 @@ class VersionBuilder::Rep {
}
}
// Add new blob files
for (const auto& blob_file_addition : edit->GetBlobFileAdditions()) {
const Status s = ApplyBlobFileAddition(blob_file_addition);
if (!s.ok()) {
return s;
}
return Status::OK();
}
static BlobFileMetaData::LinkedSsts ApplyLinkedSstChanges(
const BlobFileMetaData::LinkedSsts& base,
const std::unordered_set<uint64_t>& newly_linked,
const std::unordered_set<uint64_t>& newly_unlinked) {
BlobFileMetaData::LinkedSsts result(base);
for (uint64_t sst_file_number : newly_unlinked) {
assert(result.find(sst_file_number) != result.end());
result.erase(sst_file_number);
}
// Increase the amount of garbage for blob files affected by GC
for (const auto& blob_file_garbage : edit->GetBlobFileGarbages()) {
const Status s = ApplyBlobFileGarbage(blob_file_garbage);
if (!s.ok()) {
return s;
}
for (uint64_t sst_file_number : newly_linked) {
assert(result.find(sst_file_number) == result.end());
result.emplace(sst_file_number);
}
return Status::OK();
return result;
}
static std::shared_ptr<BlobFileMetaData> CreateMetaDataForNewBlobFile(
@ -583,9 +687,11 @@ class VersionBuilder::Rep {
auto shared_meta = delta.GetSharedMeta();
assert(shared_meta);
auto meta = BlobFileMetaData::Create(std::move(shared_meta),
delta.GetAdditionalGarbageCount(),
delta.GetAdditionalGarbageBytes());
assert(delta.GetNewlyUnlinkedSsts().empty());
auto meta = BlobFileMetaData::Create(
std::move(shared_meta), delta.GetNewlyLinkedSsts(),
delta.GetAdditionalGarbageCount(), delta.GetAdditionalGarbageBytes());
return meta;
}
@ -604,8 +710,12 @@ class VersionBuilder::Rep {
auto shared_meta = base_meta->GetSharedMeta();
assert(shared_meta);
auto linked_ssts = ApplyLinkedSstChanges(base_meta->GetLinkedSsts(),
delta.GetNewlyLinkedSsts(),
delta.GetNewlyUnlinkedSsts());
auto meta = BlobFileMetaData::Create(
std::move(shared_meta),
std::move(shared_meta), std::move(linked_ssts),
base_meta->GetGarbageBlobCount() + delta.GetAdditionalGarbageCount(),
base_meta->GetGarbageBlobBytes() + delta.GetAdditionalGarbageBytes());
@ -618,7 +728,8 @@ class VersionBuilder::Rep {
assert(vstorage);
assert(meta);
if (meta->GetGarbageBlobCount() < meta->GetTotalBlobCount()) {
if (meta->GetGarbageBlobCount() < meta->GetTotalBlobCount() ||
!meta->GetLinkedSsts().empty()) {
vstorage->AddBlobFile(meta);
}
}

@ -4,8 +4,11 @@
// (found in the LICENSE.Apache file in the root directory).
#include <cstring>
#include <iomanip>
#include <memory>
#include <sstream>
#include <string>
#include "db/version_edit.h"
#include "db/version_set.h"
#include "logging/logging.h"
@ -80,13 +83,15 @@ class VersionBuilderTest : public testing::Test {
void AddBlob(uint64_t blob_file_number, uint64_t total_blob_count,
uint64_t total_blob_bytes, std::string checksum_method,
std::string checksum_value, uint64_t garbage_blob_count,
uint64_t garbage_blob_bytes) {
std::string checksum_value,
BlobFileMetaData::LinkedSsts linked_ssts,
uint64_t garbage_blob_count, uint64_t garbage_blob_bytes) {
auto shared_meta = SharedBlobFileMetaData::Create(
blob_file_number, total_blob_count, total_blob_bytes,
std::move(checksum_method), std::move(checksum_value));
auto meta = BlobFileMetaData::Create(
std::move(shared_meta), garbage_blob_count, garbage_blob_bytes);
auto meta =
BlobFileMetaData::Create(std::move(shared_meta), std::move(linked_ssts),
garbage_blob_count, garbage_blob_bytes);
vstorage_.AddBlobFile(std::move(meta));
}
@ -642,6 +647,7 @@ TEST_F(VersionBuilderTest, ApplyBlobFileAddition) {
ASSERT_EQ(new_meta->GetTotalBlobBytes(), total_blob_bytes);
ASSERT_EQ(new_meta->GetChecksumMethod(), checksum_method);
ASSERT_EQ(new_meta->GetChecksumValue(), checksum_value);
ASSERT_TRUE(new_meta->GetLinkedSsts().empty());
ASSERT_EQ(new_meta->GetGarbageBlobCount(), 0);
ASSERT_EQ(new_meta->GetGarbageBlobBytes(), 0);
}
@ -658,7 +664,8 @@ TEST_F(VersionBuilderTest, ApplyBlobFileAdditionAlreadyInBase) {
constexpr uint64_t garbage_blob_bytes = 456789;
AddBlob(blob_file_number, total_blob_count, total_blob_bytes, checksum_method,
checksum_value, garbage_blob_count, garbage_blob_bytes);
checksum_value, BlobFileMetaData::LinkedSsts(), garbage_blob_count,
garbage_blob_bytes);
EnvOptions env_options;
constexpr TableCache* table_cache = nullptr;
@ -717,7 +724,8 @@ TEST_F(VersionBuilderTest, ApplyBlobFileGarbageFileInBase) {
constexpr uint64_t garbage_blob_bytes = 456789;
AddBlob(blob_file_number, total_blob_count, total_blob_bytes, checksum_method,
checksum_value, garbage_blob_count, garbage_blob_bytes);
checksum_value, BlobFileMetaData::LinkedSsts(), garbage_blob_count,
garbage_blob_bytes);
const auto meta =
GetBlobFileMetaData(vstorage_.GetBlobFiles(), blob_file_number);
@ -759,6 +767,7 @@ TEST_F(VersionBuilderTest, ApplyBlobFileGarbageFileInBase) {
ASSERT_EQ(new_meta->GetTotalBlobBytes(), total_blob_bytes);
ASSERT_EQ(new_meta->GetChecksumMethod(), checksum_method);
ASSERT_EQ(new_meta->GetChecksumValue(), checksum_value);
ASSERT_TRUE(new_meta->GetLinkedSsts().empty());
ASSERT_EQ(new_meta->GetGarbageBlobCount(),
garbage_blob_count + new_garbage_blob_count);
ASSERT_EQ(new_meta->GetGarbageBlobBytes(),
@ -816,6 +825,7 @@ TEST_F(VersionBuilderTest, ApplyBlobFileGarbageFileAdditionApplied) {
ASSERT_EQ(new_meta->GetTotalBlobBytes(), total_blob_bytes);
ASSERT_EQ(new_meta->GetChecksumMethod(), checksum_method);
ASSERT_EQ(new_meta->GetChecksumValue(), checksum_value);
ASSERT_TRUE(new_meta->GetLinkedSsts().empty());
ASSERT_EQ(new_meta->GetGarbageBlobCount(), garbage_blob_count);
ASSERT_EQ(new_meta->GetGarbageBlobBytes(), garbage_blob_bytes);
}
@ -856,8 +866,8 @@ TEST_F(VersionBuilderTest, SaveBlobFilesTo) {
AddBlob(blob_file_number, total_blob_count, total_blob_bytes,
/* checksum_method */ std::string(),
/* checksum_value */ std::string(), garbage_blob_count,
garbage_blob_bytes);
/* checksum_value */ std::string(), BlobFileMetaData::LinkedSsts(),
garbage_blob_count, garbage_blob_bytes);
}
EnvOptions env_options;
@ -946,7 +956,7 @@ TEST_F(VersionBuilderTest, CheckConsistencyForBlobFiles) {
AddBlob(/* blob_file_number */ 16, /* total_blob_count */ 1000,
/* total_blob_bytes */ 1000000,
/* checksum_method */ std::string(),
/* checksum_value */ std::string(),
/* checksum_value */ std::string(), BlobFileMetaData::LinkedSsts{1},
/* garbage_blob_count */ 500, /* garbage_blob_bytes */ 300000);
UpdateVersionStorageInfo();
@ -995,9 +1005,9 @@ TEST_F(VersionBuilderTest, CheckConsistencyForBlobFiles) {
UnrefFilesInVersion(&new_vstorage);
}
TEST_F(VersionBuilderTest, CheckConsistencyForBlobFilesNotInVersion) {
// Initialize base version. The table file points to a blob file that is
// not in this version.
TEST_F(VersionBuilderTest, CheckConsistencyForBlobFilesInconsistentLinks) {
// Initialize base version. Links between the table file and the blob file
// are inconsistent.
Add(/* level */ 1, /* file_number */ 1, /* smallest */ "150",
/* largest */ "200", /* file_size */ 100,
@ -1009,7 +1019,7 @@ TEST_F(VersionBuilderTest, CheckConsistencyForBlobFilesNotInVersion) {
AddBlob(/* blob_file_number */ 16, /* total_blob_count */ 1000,
/* total_blob_bytes */ 1000000,
/* checksum_method */ std::string(),
/* checksum_value */ std::string(),
/* checksum_value */ std::string(), BlobFileMetaData::LinkedSsts{1},
/* garbage_blob_count */ 500, /* garbage_blob_bytes */ 300000);
UpdateVersionStorageInfo();
@ -1029,8 +1039,9 @@ TEST_F(VersionBuilderTest, CheckConsistencyForBlobFilesNotInVersion) {
const Status s = builder.SaveTo(&new_vstorage);
ASSERT_TRUE(s.IsCorruption());
ASSERT_TRUE(
std::strstr(s.getState(), "Blob file #256 is not part of this version"));
ASSERT_TRUE(std::strstr(
s.getState(),
"Links are inconsistent between table files and blob file #16"));
UnrefFilesInVersion(&new_vstorage);
}
@ -1049,7 +1060,7 @@ TEST_F(VersionBuilderTest, CheckConsistencyForBlobFilesAllGarbage) {
AddBlob(/* blob_file_number */ 16, /* total_blob_count */ 1000,
/* total_blob_bytes */ 1000000,
/* checksum_method */ std::string(),
/* checksum_value */ std::string(),
/* checksum_value */ std::string(), BlobFileMetaData::LinkedSsts{1},
/* garbage_blob_count */ 1000, /* garbage_blob_bytes */ 1000000);
UpdateVersionStorageInfo();
@ -1075,6 +1086,224 @@ TEST_F(VersionBuilderTest, CheckConsistencyForBlobFilesAllGarbage) {
UnrefFilesInVersion(&new_vstorage);
}
TEST_F(VersionBuilderTest, CheckConsistencyForBlobFilesAllGarbageLinkedSsts) {
// Initialize base version, with a table file pointing to a blob file
// that has no garbage at this point.
Add(/* level */ 1, /* file_number */ 1, /* smallest */ "150",
/* largest */ "200", /* file_size */ 100,
/* path_id */ 0, /* smallest_seq */ 100, /* largest_seq */ 100,
/* num_entries */ 0, /* num_deletions */ 0,
/* sampled */ false, /* smallest_seqno */ 100, /* largest_seqno */ 100,
/* oldest_blob_file_number */ 16);
AddBlob(/* blob_file_number */ 16, /* total_blob_count */ 1000,
/* total_blob_bytes */ 1000000,
/* checksum_method */ std::string(),
/* checksum_value */ std::string(), BlobFileMetaData::LinkedSsts{1},
/* garbage_blob_count */ 0, /* garbage_blob_bytes */ 0);
UpdateVersionStorageInfo();
// Mark the entire blob file garbage but do not remove the linked SST.
EnvOptions env_options;
constexpr TableCache* table_cache = nullptr;
constexpr VersionSet* version_set = nullptr;
VersionBuilder builder(env_options, &ioptions_, table_cache, &vstorage_,
version_set);
VersionEdit edit;
edit.AddBlobFileGarbage(/* blob_file_number */ 16,
/* garbage_blob_count */ 1000,
/* garbage_blob_bytes */ 1000000);
ASSERT_OK(builder.Apply(&edit));
// Save to a new version in order to trigger consistency checks.
constexpr bool force_consistency_checks = true;
VersionStorageInfo new_vstorage(&icmp_, ucmp_, options_.num_levels,
kCompactionStyleLevel, &vstorage_,
force_consistency_checks);
const Status s = builder.SaveTo(&new_vstorage);
ASSERT_TRUE(s.IsCorruption());
ASSERT_TRUE(
std::strstr(s.getState(), "Blob file #16 consists entirely of garbage"));
UnrefFilesInVersion(&new_vstorage);
}
TEST_F(VersionBuilderTest, MaintainLinkedSstsForBlobFiles) {
// Initialize base version. Table files 1..10 are linked to blob files 1..5,
// while table files 11..20 are not linked to any blob files.
for (uint64_t i = 1; i <= 10; ++i) {
std::ostringstream oss;
oss << std::setw(2) << std::setfill('0') << i;
const std::string key = oss.str();
Add(/* level */ 1, /* file_number */ i, /* smallest */ key.c_str(),
/* largest */ key.c_str(), /* file_size */ 100,
/* path_id */ 0, /* smallest_seq */ i * 100, /* largest_seq */ i * 100,
/* num_entries */ 0, /* num_deletions */ 0,
/* sampled */ false, /* smallest_seqno */ i * 100,
/* largest_seqno */ i * 100,
/* oldest_blob_file_number */ ((i - 1) % 5) + 1);
}
for (uint64_t i = 1; i <= 5; ++i) {
AddBlob(/* blob_file_number */ i, /* total_blob_count */ 2000,
/* total_blob_bytes */ 2000000,
/* checksum_method */ std::string(),
/* checksum_value */ std::string(),
BlobFileMetaData::LinkedSsts{i, i + 5},
/* garbage_blob_count */ 1000, /* garbage_blob_bytes */ 1000000);
}
for (uint64_t i = 11; i <= 20; ++i) {
std::ostringstream oss;
oss << std::setw(2) << std::setfill('0') << i;
const std::string key = oss.str();
Add(/* level */ 1, /* file_number */ i, /* smallest */ key.c_str(),
/* largest */ key.c_str(), /* file_size */ 100,
/* path_id */ 0, /* smallest_seq */ i * 100, /* largest_seq */ i * 100,
/* num_entries */ 0, /* num_deletions */ 0,
/* sampled */ false, /* smallest_seqno */ i * 100,
/* largest_seqno */ i * 100, kInvalidBlobFileNumber);
}
UpdateVersionStorageInfo();
{
const auto& blob_files = vstorage_.GetBlobFiles();
ASSERT_EQ(blob_files.size(), 5);
const std::vector<BlobFileMetaData::LinkedSsts> expected_linked_ssts{
{1, 6}, {2, 7}, {3, 8}, {4, 9}, {5, 10}};
for (size_t i = 0; i < 5; ++i) {
const auto meta =
GetBlobFileMetaData(blob_files, /* blob_file_number */ i + 1);
ASSERT_NE(meta, nullptr);
ASSERT_EQ(meta->GetLinkedSsts(), expected_linked_ssts[i]);
}
}
VersionEdit edit;
// Add an SST that references a blob file.
edit.AddFile(
/* level */ 1, /* file_number */ 21, /* path_id */ 0,
/* file_size */ 100, /* smallest */ GetInternalKey("21", 2100),
/* largest */ GetInternalKey("21", 2100), /* smallest_seqno */ 2100,
/* largest_seqno */ 2100, /* marked_for_compaction */ false,
/* oldest_blob_file_number */ 1, kUnknownOldestAncesterTime,
kUnknownFileCreationTime, kUnknownFileChecksum,
kUnknownFileChecksumFuncName);
// Add an SST that does not reference any blob files.
edit.AddFile(
/* level */ 1, /* file_number */ 22, /* path_id */ 0,
/* file_size */ 100, /* smallest */ GetInternalKey("22", 2200),
/* largest */ GetInternalKey("22", 2200), /* smallest_seqno */ 2200,
/* largest_seqno */ 2200, /* marked_for_compaction */ false,
kInvalidBlobFileNumber, kUnknownOldestAncesterTime,
kUnknownFileCreationTime, kUnknownFileChecksum,
kUnknownFileChecksumFuncName);
// Delete a file that references a blob file.
edit.DeleteFile(/* level */ 1, /* file_number */ 6);
// Delete a file that does not reference any blob files.
edit.DeleteFile(/* level */ 1, /* file_number */ 16);
// Trivially move a file that references a blob file. Note that we save
// the original BlobFileMetaData object so we can check that no new object
// gets created.
auto meta3 =
GetBlobFileMetaData(vstorage_.GetBlobFiles(), /* blob_file_number */ 3);
edit.DeleteFile(/* level */ 1, /* file_number */ 3);
edit.AddFile(/* level */ 2, /* file_number */ 3, /* path_id */ 0,
/* file_size */ 100, /* smallest */ GetInternalKey("03", 300),
/* largest */ GetInternalKey("03", 300),
/* smallest_seqno */ 300,
/* largest_seqno */ 300, /* marked_for_compaction */ false,
/* oldest_blob_file_number */ 3, kUnknownOldestAncesterTime,
kUnknownFileCreationTime, kUnknownFileChecksum,
kUnknownFileChecksumFuncName);
// Trivially move a file that does not reference any blob files.
edit.DeleteFile(/* level */ 1, /* file_number */ 13);
edit.AddFile(/* level */ 2, /* file_number */ 13, /* path_id */ 0,
/* file_size */ 100, /* smallest */ GetInternalKey("13", 1300),
/* largest */ GetInternalKey("13", 1300),
/* smallest_seqno */ 1300,
/* largest_seqno */ 1300, /* marked_for_compaction */ false,
kInvalidBlobFileNumber, kUnknownOldestAncesterTime,
kUnknownFileCreationTime, kUnknownFileChecksum,
kUnknownFileChecksumFuncName);
// Add one more SST file that references a blob file, then promptly
// delete it in a second version edit before the new version gets saved.
// This file should not show up as linked to the blob file in the new version.
edit.AddFile(/* level */ 1, /* file_number */ 23, /* path_id */ 0,
/* file_size */ 100, /* smallest */ GetInternalKey("23", 2300),
/* largest */ GetInternalKey("23", 2300),
/* smallest_seqno */ 2300,
/* largest_seqno */ 2300, /* marked_for_compaction */ false,
/* oldest_blob_file_number */ 5, kUnknownOldestAncesterTime,
kUnknownFileCreationTime, kUnknownFileChecksum,
kUnknownFileChecksumFuncName);
VersionEdit edit2;
edit2.DeleteFile(/* level */ 1, /* file_number */ 23);
EnvOptions env_options;
constexpr TableCache* table_cache = nullptr;
constexpr VersionSet* version_set = nullptr;
VersionBuilder builder(env_options, &ioptions_, table_cache, &vstorage_,
version_set);
ASSERT_OK(builder.Apply(&edit));
ASSERT_OK(builder.Apply(&edit2));
constexpr bool force_consistency_checks = true;
VersionStorageInfo new_vstorage(&icmp_, ucmp_, options_.num_levels,
kCompactionStyleLevel, &vstorage_,
force_consistency_checks);
ASSERT_OK(builder.SaveTo(&new_vstorage));
{
const auto& blob_files = new_vstorage.GetBlobFiles();
ASSERT_EQ(blob_files.size(), 5);
const std::vector<BlobFileMetaData::LinkedSsts> expected_linked_ssts{
{1, 21}, {2, 7}, {3, 8}, {4, 9}, {5, 10}};
for (size_t i = 0; i < 5; ++i) {
const auto meta =
GetBlobFileMetaData(blob_files, /* blob_file_number */ i + 1);
ASSERT_NE(meta, nullptr);
ASSERT_EQ(meta->GetLinkedSsts(), expected_linked_ssts[i]);
}
// Make sure that no new BlobFileMetaData got created for the blob file
// affected by the trivial move.
ASSERT_EQ(GetBlobFileMetaData(blob_files, /* blob_file_number */ 3), meta3);
}
UnrefFilesInVersion(&new_vstorage);
}
TEST_F(VersionBuilderTest, CheckConsistencyForFileDeletedTwice) {
Add(0, 1U, "150", "200", 100U);
UpdateVersionStorageInfo();

Loading…
Cancel
Save