Add a DB Session ID (#6959)

Summary:
Added DB::GetDbSessionId by using the same format and machinery as DB::GetDbIdentity.
The DB Session ID is generated (and therefore, updated) each time a DB object is opened. It is written to the LOG file right after the line of “DB SUMMARY”.
A test for the uniqueness, for different openings and during the same opening, is also added.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/6959

Test Plan: Passed make check

Reviewed By: zhichao-cao

Differential Revision: D21951721

Pulled By: gg814

fbshipit-source-id: 958a48a612db49a39998ea703cded45987d3fa8b
This commit is contained in:
Zitan Chen 2020-06-15 10:45:03 -07:00 committed by Facebook GitHub Bot
parent 9c24a5cb4d
commit 88db97b06d
9 changed files with 98 additions and 3 deletions

View File

@ -25,6 +25,7 @@
* `pin_l0_filter_and_index_blocks_in_cache` no longer applies to L0 files larger than `1.5 * write_buffer_size` to give more predictable memory usage. Such L0 files may exist due to intra-L0 compaction, external file ingestion, or user dynamically changing `write_buffer_size` (note, however, that files that are already pinned will continue being pinned, even after such a dynamic change).
* In point-in-time wal recovery mode, fail database recovery in case of IOError while reading the WAL to avoid data loss.
* A new method `Env::LowerThreadPoolCPUPriority(Priority, CpuPriority)` is added to `Env` to be able to lower to a specific priority such as `CpuPriority::kIdle`.
* `DB::GetDbSessionId(std::string& session_id)` is added. `session_id` stores a unique identifier that gets reset every time the DB is opened. This DB session ID should be unique among all open DB instances on all hosts, and should be unique among re-openings of the same or other DBs. This identifier is recorded in the `LOG` file on the line starting with `DB Session ID:`.
### New Features
* sst_dump to add a new --readahead_size argument. Users can specify read size when scanning the data. Sst_dump also tries to prefetch tail part of the SST files so usually some number of I/Os are saved there too.

View File

@ -41,6 +41,56 @@ TEST_F(DBBasicTest, OpenWhenOpen) {
delete db2;
}
TEST_F(DBBasicTest, UniqueSession) {
Options options = CurrentOptions();
std::string sid1, sid2, sid3, sid4;
db_->GetDbSessionId(sid1);
Reopen(options);
db_->GetDbSessionId(sid2);
ASSERT_OK(Put("foo", "v1"));
db_->GetDbSessionId(sid4);
Reopen(options);
db_->GetDbSessionId(sid3);
ASSERT_NE(sid1, sid2);
ASSERT_NE(sid1, sid3);
ASSERT_NE(sid2, sid3);
ASSERT_EQ(sid2, sid4);
#ifndef ROCKSDB_LITE
Close();
ASSERT_OK(ReadOnlyReopen(options));
db_->GetDbSessionId(sid1);
// Test uniqueness between readonly open (sid1) and regular open (sid3)
ASSERT_NE(sid1, sid3);
Close();
ASSERT_OK(ReadOnlyReopen(options));
db_->GetDbSessionId(sid2);
ASSERT_EQ("v1", Get("foo"));
db_->GetDbSessionId(sid3);
ASSERT_NE(sid1, sid2);
ASSERT_EQ(sid2, sid3);
#endif // ROCKSDB_LITE
CreateAndReopenWithCF({"goku"}, options);
db_->GetDbSessionId(sid1);
ASSERT_OK(Put("bar", "e1"));
db_->GetDbSessionId(sid2);
ASSERT_EQ("e1", Get("bar"));
db_->GetDbSessionId(sid3);
ReopenWithColumnFamilies({"default", "goku"}, options);
db_->GetDbSessionId(sid4);
ASSERT_EQ(sid1, sid2);
ASSERT_EQ(sid2, sid3);
ASSERT_NE(sid1, sid4);
}
#ifndef ROCKSDB_LITE
TEST_F(DBBasicTest, ReadOnlyDB) {
ASSERT_OK(Put("foo", "v1"));

View File

@ -249,7 +249,8 @@ DBImpl::DBImpl(const DBOptions& options, const std::string& dbname,
new ColumnFamilyMemTablesImpl(versions_->GetColumnFamilySet()));
DumpRocksDBBuildVersion(immutable_db_options_.info_log.get());
DumpDBFileSummary(immutable_db_options_, dbname_);
SetDbSessionId();
DumpDBFileSummary(immutable_db_options_, dbname_, db_session_id_);
immutable_db_options_.Dump(immutable_db_options_.info_log.get());
mutable_db_options_.Dump(immutable_db_options_.info_log.get());
DumpSupportInfo(immutable_db_options_.info_log.get());
@ -3601,6 +3602,21 @@ Status DBImpl::GetDbIdentityFromIdentityFile(std::string* identity) const {
return s;
}
Status DBImpl::GetDbSessionId(std::string& session_id) const {
session_id.assign(db_session_id_);
return Status::OK();
}
void DBImpl::SetDbSessionId() {
// GenerateUniqueId() generates an identifier
// that has a negligible probability of being duplicated
db_session_id_ = env_->GenerateUniqueId();
// Remove the extra '\n' at the end if there is one
if (!db_session_id_.empty() && db_session_id_.back() == '\n') {
db_session_id_.pop_back();
}
}
// Default implementation -- returns not supported status
Status DB::CreateColumnFamily(const ColumnFamilyOptions& /*cf_options*/,
const std::string& /*column_family_name*/,

View File

@ -350,6 +350,8 @@ class DBImpl : public DB {
virtual Status GetDbIdentityFromIdentityFile(std::string* identity) const;
virtual Status GetDbSessionId(std::string& session_id) const override;
ColumnFamilyHandle* DefaultColumnFamily() const override;
ColumnFamilyHandle* PersistentStatsColumnFamily() const;
@ -980,6 +982,9 @@ class DBImpl : public DB {
protected:
const std::string dbname_;
std::string db_id_;
// db_session_id_ is an identifier that gets reset
// every time the DB is opened
std::string db_session_id_;
std::unique_ptr<VersionSet> versions_;
// Flag to check whether we allocated and own the info log file
bool own_info_log_;
@ -1161,6 +1166,10 @@ class DBImpl : public DB {
// bump up the version set's next_file_number_ to be 1 + largest_file_number.
Status FinishBestEffortsRecovery();
// SetDbSessionId() should be called in the constuctor DBImpl()
// to ensure that db_session_id_ gets updated every time the DB is opened
void SetDbSessionId();
private:
friend class DB;
friend class ErrorHandler;

View File

@ -17,7 +17,8 @@
namespace ROCKSDB_NAMESPACE {
void DumpDBFileSummary(const ImmutableDBOptions& options,
const std::string& dbname) {
const std::string& dbname,
const std::string& session_id) {
if (options.info_log == nullptr) {
return;
}
@ -32,6 +33,8 @@ void DumpDBFileSummary(const ImmutableDBOptions& options,
std::string file_info, wal_info;
Header(options.info_log, "DB SUMMARY\n");
Header(options.info_log, "DB Session ID: %s\n", session_id.c_str());
// Get files in dbname dir
if (!env->GetChildren(dbname, &files).ok()) {
Error(options.info_log,

View File

@ -10,5 +10,6 @@
namespace ROCKSDB_NAMESPACE {
void DumpDBFileSummary(const ImmutableDBOptions& options,
const std::string& dbname);
const std::string& dbname,
const std::string& session_id = "");
} // namespace ROCKSDB_NAMESPACE

View File

@ -3031,6 +3031,10 @@ class ModelDB : public DB {
return Status::OK();
}
Status GetDbSessionId(std::string& /*session_id*/) const override {
return Status::OK();
}
SequenceNumber GetLatestSequenceNumber() const override { return 0; }
bool SetPreserveDeletesSequenceNumber(SequenceNumber /*seqnum*/) override {

View File

@ -1544,6 +1544,13 @@ class DB {
// Returns Status::OK if identity could be set properly
virtual Status GetDbIdentity(std::string& identity) const = 0;
// Return a unique identifier for each DB object that is opened
// This DB session ID should be unique among all open DB instances on all
// hosts, and should be unique among re-openings of the same or other DBs.
// (Two open DBs have the same identity from other function GetDbIdentity when
// one is physically copied from the other.)
virtual Status GetDbSessionId(std::string& session_id) const = 0;
// Returns default column family handle
virtual ColumnFamilyHandle* DefaultColumnFamily() const = 0;

View File

@ -400,6 +400,10 @@ class StackableDB : public DB {
return db_->GetDbIdentity(identity);
}
virtual Status GetDbSessionId(std::string& session_id) const override {
return db_->GetDbSessionId(session_id);
}
using DB::SetOptions;
virtual Status SetOptions(ColumnFamilyHandle* column_family_handle,
const std::unordered_map<std::string, std::string>&