2016-02-10 00:12:00 +01:00
|
|
|
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
2017-07-16 01:03:42 +02:00
|
|
|
// 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).
|
2014-11-21 00:54:47 +01:00
|
|
|
//
|
|
|
|
// Copyright (c) 2012 Facebook.
|
|
|
|
// Use of this source code is governed by a BSD-style license that can be
|
|
|
|
// found in the LICENSE file.
|
|
|
|
|
|
|
|
#ifndef ROCKSDB_LITE
|
|
|
|
|
2017-04-24 23:57:27 +02:00
|
|
|
#include "utilities/checkpoint/checkpoint_impl.h"
|
2014-11-21 00:54:47 +01:00
|
|
|
|
2019-06-06 22:52:39 +02:00
|
|
|
#include <cinttypes>
|
2014-11-21 00:54:47 +01:00
|
|
|
#include <algorithm>
|
|
|
|
#include <string>
|
2017-04-24 23:57:27 +02:00
|
|
|
#include <vector>
|
|
|
|
|
2015-06-20 01:08:31 +02:00
|
|
|
#include "db/wal_manager.h"
|
2019-05-30 05:44:08 +02:00
|
|
|
#include "file/file_util.h"
|
|
|
|
#include "file/filename.h"
|
2017-04-04 03:27:24 +02:00
|
|
|
#include "port/port.h"
|
2014-11-21 00:54:47 +01:00
|
|
|
#include "rocksdb/db.h"
|
|
|
|
#include "rocksdb/env.h"
|
Export Import sst files (#5495)
Summary:
Refresh of the earlier change here - https://github.com/facebook/rocksdb/issues/5135
This is a review request for code change needed for - https://github.com/facebook/rocksdb/issues/3469
"Add support for taking snapshot of a column family and creating column family from a given CF snapshot"
We have an implementation for this that we have been testing internally. We have two new APIs that together provide this functionality.
(1) ExportColumnFamily() - This API is modelled after CreateCheckpoint() as below.
// Exports all live SST files of a specified Column Family onto export_dir,
// returning SST files information in metadata.
// - SST files will be created as hard links when the directory specified
// is in the same partition as the db directory, copied otherwise.
// - export_dir should not already exist and will be created by this API.
// - Always triggers a flush.
virtual Status ExportColumnFamily(ColumnFamilyHandle* handle,
const std::string& export_dir,
ExportImportFilesMetaData** metadata);
Internally, the API will DisableFileDeletions(), GetColumnFamilyMetaData(), Parse through
metadata, creating links/copies of all the sst files, EnableFileDeletions() and complete the call by
returning the list of file metadata.
(2) CreateColumnFamilyWithImport() - This API is modeled after IngestExternalFile(), but invoked only during a CF creation as below.
// CreateColumnFamilyWithImport() will create a new column family with
// column_family_name and import external SST files specified in metadata into
// this column family.
// (1) External SST files can be created using SstFileWriter.
// (2) External SST files can be exported from a particular column family in
// an existing DB.
// Option in import_options specifies whether the external files are copied or
// moved (default is copy). When option specifies copy, managing files at
// external_file_path is caller's responsibility. When option specifies a
// move, the call ensures that the specified files at external_file_path are
// deleted on successful return and files are not modified on any error
// return.
// On error return, column family handle returned will be nullptr.
// ColumnFamily will be present on successful return and will not be present
// on error return. ColumnFamily may be present on any crash during this call.
virtual Status CreateColumnFamilyWithImport(
const ColumnFamilyOptions& options, const std::string& column_family_name,
const ImportColumnFamilyOptions& import_options,
const ExportImportFilesMetaData& metadata,
ColumnFamilyHandle** handle);
Internally, this API creates a new CF, parses all the sst files and adds it to the specified column family, at the same level and with same sequence number as in the metadata. Also performs safety checks with respect to overlaps between the sst files being imported.
If incoming sequence number is higher than current local sequence number, local sequence
number is updated to reflect this.
Note, as the sst files is are being moved across Column Families, Column Family name in sst file
will no longer match the actual column family on destination DB. The API does not modify Column
Family name or id in the sst files being imported.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5495
Differential Revision: D16018881
fbshipit-source-id: 9ae2251025d5916d35a9fc4ea4d6707f6be16ff9
2019-07-17 21:22:21 +02:00
|
|
|
#include "rocksdb/metadata.h"
|
2015-06-20 01:08:31 +02:00
|
|
|
#include "rocksdb/transaction_log.h"
|
2017-04-24 23:57:27 +02:00
|
|
|
#include "rocksdb/utilities/checkpoint.h"
|
2019-05-30 20:21:38 +02:00
|
|
|
#include "test_util/sync_point.h"
|
2014-11-21 00:54:47 +01:00
|
|
|
|
|
|
|
namespace rocksdb {
|
|
|
|
|
|
|
|
Status Checkpoint::Create(DB* db, Checkpoint** checkpoint_ptr) {
|
|
|
|
*checkpoint_ptr = new CheckpointImpl(db);
|
|
|
|
return Status::OK();
|
|
|
|
}
|
|
|
|
|
2018-03-05 22:08:17 +01:00
|
|
|
Status Checkpoint::CreateCheckpoint(const std::string& /*checkpoint_dir*/,
|
|
|
|
uint64_t /*log_size_for_flush*/) {
|
2014-11-21 00:54:47 +01:00
|
|
|
return Status::NotSupported("");
|
|
|
|
}
|
|
|
|
|
2018-06-22 01:22:57 +02:00
|
|
|
void CheckpointImpl::CleanStagingDirectory(
|
|
|
|
const std::string& full_private_path, Logger* info_log) {
|
|
|
|
std::vector<std::string> subchildren;
|
|
|
|
Status s = db_->GetEnv()->FileExists(full_private_path);
|
|
|
|
if (s.IsNotFound()) {
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
ROCKS_LOG_INFO(info_log, "File exists %s -- %s",
|
|
|
|
full_private_path.c_str(), s.ToString().c_str());
|
|
|
|
db_->GetEnv()->GetChildren(full_private_path, &subchildren);
|
|
|
|
for (auto& subchild : subchildren) {
|
|
|
|
std::string subchild_path = full_private_path + "/" + subchild;
|
|
|
|
s = db_->GetEnv()->DeleteFile(subchild_path);
|
|
|
|
ROCKS_LOG_INFO(info_log, "Delete file %s -- %s",
|
|
|
|
subchild_path.c_str(), s.ToString().c_str());
|
|
|
|
}
|
|
|
|
// finally delete the private dir
|
|
|
|
s = db_->GetEnv()->DeleteDir(full_private_path);
|
|
|
|
ROCKS_LOG_INFO(info_log, "Delete dir %s -- %s",
|
|
|
|
full_private_path.c_str(), s.ToString().c_str());
|
|
|
|
}
|
|
|
|
|
Export Import sst files (#5495)
Summary:
Refresh of the earlier change here - https://github.com/facebook/rocksdb/issues/5135
This is a review request for code change needed for - https://github.com/facebook/rocksdb/issues/3469
"Add support for taking snapshot of a column family and creating column family from a given CF snapshot"
We have an implementation for this that we have been testing internally. We have two new APIs that together provide this functionality.
(1) ExportColumnFamily() - This API is modelled after CreateCheckpoint() as below.
// Exports all live SST files of a specified Column Family onto export_dir,
// returning SST files information in metadata.
// - SST files will be created as hard links when the directory specified
// is in the same partition as the db directory, copied otherwise.
// - export_dir should not already exist and will be created by this API.
// - Always triggers a flush.
virtual Status ExportColumnFamily(ColumnFamilyHandle* handle,
const std::string& export_dir,
ExportImportFilesMetaData** metadata);
Internally, the API will DisableFileDeletions(), GetColumnFamilyMetaData(), Parse through
metadata, creating links/copies of all the sst files, EnableFileDeletions() and complete the call by
returning the list of file metadata.
(2) CreateColumnFamilyWithImport() - This API is modeled after IngestExternalFile(), but invoked only during a CF creation as below.
// CreateColumnFamilyWithImport() will create a new column family with
// column_family_name and import external SST files specified in metadata into
// this column family.
// (1) External SST files can be created using SstFileWriter.
// (2) External SST files can be exported from a particular column family in
// an existing DB.
// Option in import_options specifies whether the external files are copied or
// moved (default is copy). When option specifies copy, managing files at
// external_file_path is caller's responsibility. When option specifies a
// move, the call ensures that the specified files at external_file_path are
// deleted on successful return and files are not modified on any error
// return.
// On error return, column family handle returned will be nullptr.
// ColumnFamily will be present on successful return and will not be present
// on error return. ColumnFamily may be present on any crash during this call.
virtual Status CreateColumnFamilyWithImport(
const ColumnFamilyOptions& options, const std::string& column_family_name,
const ImportColumnFamilyOptions& import_options,
const ExportImportFilesMetaData& metadata,
ColumnFamilyHandle** handle);
Internally, this API creates a new CF, parses all the sst files and adds it to the specified column family, at the same level and with same sequence number as in the metadata. Also performs safety checks with respect to overlaps between the sst files being imported.
If incoming sequence number is higher than current local sequence number, local sequence
number is updated to reflect this.
Note, as the sst files is are being moved across Column Families, Column Family name in sst file
will no longer match the actual column family on destination DB. The API does not modify Column
Family name or id in the sst files being imported.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5495
Differential Revision: D16018881
fbshipit-source-id: 9ae2251025d5916d35a9fc4ea4d6707f6be16ff9
2019-07-17 21:22:21 +02:00
|
|
|
Status Checkpoint::ExportColumnFamily(
|
|
|
|
ColumnFamilyHandle* /*handle*/, const std::string& /*export_dir*/,
|
|
|
|
ExportImportFilesMetaData** /*metadata*/) {
|
|
|
|
return Status::NotSupported("");
|
|
|
|
}
|
|
|
|
|
2014-11-21 00:54:47 +01:00
|
|
|
// Builds an openable snapshot of RocksDB
|
2017-03-22 01:53:21 +01:00
|
|
|
Status CheckpointImpl::CreateCheckpoint(const std::string& checkpoint_dir,
|
|
|
|
uint64_t log_size_for_flush) {
|
2016-12-29 03:38:20 +01:00
|
|
|
DBOptions db_options = db_->GetDBOptions();
|
2014-11-21 00:54:47 +01:00
|
|
|
|
2017-04-24 23:57:27 +02:00
|
|
|
Status s = db_->GetEnv()->FileExists(checkpoint_dir);
|
2015-07-21 02:20:40 +02:00
|
|
|
if (s.ok()) {
|
2014-11-21 00:54:47 +01:00
|
|
|
return Status::InvalidArgument("Directory exists");
|
2015-07-21 02:20:40 +02:00
|
|
|
} else if (!s.IsNotFound()) {
|
|
|
|
assert(s.IsIOError());
|
|
|
|
return s;
|
2014-11-21 00:54:47 +01:00
|
|
|
}
|
|
|
|
|
2017-04-24 23:57:27 +02:00
|
|
|
ROCKS_LOG_INFO(
|
|
|
|
db_options.info_log,
|
|
|
|
"Started the snapshot process -- creating snapshot in directory %s",
|
|
|
|
checkpoint_dir.c_str());
|
2018-01-30 05:59:59 +01:00
|
|
|
|
|
|
|
size_t final_nonslash_idx = checkpoint_dir.find_last_not_of('/');
|
|
|
|
if (final_nonslash_idx == std::string::npos) {
|
2018-02-21 01:42:06 +01:00
|
|
|
// npos means it's only slashes or empty. Non-empty means it's the root
|
|
|
|
// directory, but it shouldn't be because we verified above the directory
|
|
|
|
// doesn't exist.
|
|
|
|
assert(checkpoint_dir.empty());
|
2018-01-30 05:59:59 +01:00
|
|
|
return Status::InvalidArgument("invalid checkpoint directory name");
|
|
|
|
}
|
|
|
|
|
|
|
|
std::string full_private_path =
|
|
|
|
checkpoint_dir.substr(0, final_nonslash_idx + 1) + ".tmp";
|
|
|
|
ROCKS_LOG_INFO(
|
|
|
|
db_options.info_log,
|
|
|
|
"Snapshot process -- using temporary directory %s",
|
|
|
|
full_private_path.c_str());
|
2018-06-22 01:22:57 +02:00
|
|
|
CleanStagingDirectory(full_private_path, db_options.info_log.get());
|
2017-04-24 23:57:27 +02:00
|
|
|
// create snapshot directory
|
|
|
|
s = db_->GetEnv()->CreateDir(full_private_path);
|
|
|
|
uint64_t sequence_number = 0;
|
|
|
|
if (s.ok()) {
|
|
|
|
db_->DisableFileDeletions();
|
|
|
|
s = CreateCustomCheckpoint(
|
|
|
|
db_options,
|
|
|
|
[&](const std::string& src_dirname, const std::string& fname,
|
|
|
|
FileType) {
|
|
|
|
ROCKS_LOG_INFO(db_options.info_log, "Hard Linking %s", fname.c_str());
|
|
|
|
return db_->GetEnv()->LinkFile(src_dirname + fname,
|
|
|
|
full_private_path + fname);
|
|
|
|
} /* link_file_cb */,
|
|
|
|
[&](const std::string& src_dirname, const std::string& fname,
|
|
|
|
uint64_t size_limit_bytes, FileType) {
|
|
|
|
ROCKS_LOG_INFO(db_options.info_log, "Copying %s", fname.c_str());
|
|
|
|
return CopyFile(db_->GetEnv(), src_dirname + fname,
|
|
|
|
full_private_path + fname, size_limit_bytes,
|
|
|
|
db_options.use_fsync);
|
|
|
|
} /* copy_file_cb */,
|
|
|
|
[&](const std::string& fname, const std::string& contents, FileType) {
|
|
|
|
ROCKS_LOG_INFO(db_options.info_log, "Creating %s", fname.c_str());
|
2018-08-28 21:35:17 +02:00
|
|
|
return CreateFile(db_->GetEnv(), full_private_path + fname, contents,
|
|
|
|
db_options.use_fsync);
|
2017-04-24 23:57:27 +02:00
|
|
|
} /* create_file_cb */,
|
|
|
|
&sequence_number, log_size_for_flush);
|
|
|
|
// we copied all the files, enable file deletions
|
|
|
|
db_->EnableFileDeletions(false);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (s.ok()) {
|
|
|
|
// move tmp private backup to real snapshot directory
|
|
|
|
s = db_->GetEnv()->RenameFile(full_private_path, checkpoint_dir);
|
|
|
|
}
|
|
|
|
if (s.ok()) {
|
2018-11-09 20:17:34 +01:00
|
|
|
std::unique_ptr<Directory> checkpoint_directory;
|
2017-04-24 23:57:27 +02:00
|
|
|
db_->GetEnv()->NewDirectory(checkpoint_dir, &checkpoint_directory);
|
|
|
|
if (checkpoint_directory != nullptr) {
|
|
|
|
s = checkpoint_directory->Fsync();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (s.ok()) {
|
|
|
|
// here we know that we succeeded and installed the new snapshot
|
|
|
|
ROCKS_LOG_INFO(db_options.info_log, "Snapshot DONE. All is good");
|
|
|
|
ROCKS_LOG_INFO(db_options.info_log, "Snapshot sequence number: %" PRIu64,
|
|
|
|
sequence_number);
|
|
|
|
} else {
|
|
|
|
// clean all the files we might have created
|
|
|
|
ROCKS_LOG_INFO(db_options.info_log, "Snapshot failed -- %s",
|
|
|
|
s.ToString().c_str());
|
2018-06-22 01:22:57 +02:00
|
|
|
CleanStagingDirectory(full_private_path, db_options.info_log.get());
|
2017-04-24 23:57:27 +02:00
|
|
|
}
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
|
|
|
|
Status CheckpointImpl::CreateCustomCheckpoint(
|
|
|
|
const DBOptions& db_options,
|
|
|
|
std::function<Status(const std::string& src_dirname,
|
|
|
|
const std::string& src_fname, FileType type)>
|
|
|
|
link_file_cb,
|
|
|
|
std::function<Status(const std::string& src_dirname,
|
|
|
|
const std::string& src_fname,
|
|
|
|
uint64_t size_limit_bytes, FileType type)>
|
|
|
|
copy_file_cb,
|
|
|
|
std::function<Status(const std::string& fname, const std::string& contents,
|
|
|
|
FileType type)>
|
|
|
|
create_file_cb,
|
|
|
|
uint64_t* sequence_number, uint64_t log_size_for_flush) {
|
|
|
|
Status s;
|
|
|
|
std::vector<std::string> live_files;
|
|
|
|
uint64_t manifest_file_size = 0;
|
|
|
|
uint64_t min_log_num = port::kMaxUint64;
|
|
|
|
*sequence_number = db_->GetLatestSequenceNumber();
|
|
|
|
bool same_fs = true;
|
|
|
|
VectorLogPtr live_wal_files;
|
|
|
|
|
2017-03-22 01:53:21 +01:00
|
|
|
bool flush_memtable = true;
|
2014-11-21 00:54:47 +01:00
|
|
|
if (s.ok()) {
|
2017-03-22 01:53:21 +01:00
|
|
|
if (!db_options.allow_2pc) {
|
2017-04-24 23:57:27 +02:00
|
|
|
if (log_size_for_flush == port::kMaxUint64) {
|
|
|
|
flush_memtable = false;
|
|
|
|
} else if (log_size_for_flush > 0) {
|
|
|
|
// If out standing log files are small, we skip the flush.
|
|
|
|
s = db_->GetSortedWalFiles(live_wal_files);
|
2017-03-22 01:53:21 +01:00
|
|
|
|
2017-04-24 23:57:27 +02:00
|
|
|
if (!s.ok()) {
|
|
|
|
return s;
|
|
|
|
}
|
2017-03-22 01:53:21 +01:00
|
|
|
|
2017-04-24 23:57:27 +02:00
|
|
|
// Don't flush column families if total log size is smaller than
|
|
|
|
// log_size_for_flush. We copy the log files instead.
|
|
|
|
// We may be able to cover 2PC case too.
|
|
|
|
uint64_t total_wal_size = 0;
|
|
|
|
for (auto& wal : live_wal_files) {
|
|
|
|
total_wal_size += wal->SizeFileBytes();
|
|
|
|
}
|
|
|
|
if (total_wal_size < log_size_for_flush) {
|
|
|
|
flush_memtable = false;
|
|
|
|
}
|
|
|
|
live_wal_files.clear();
|
2017-03-22 01:53:21 +01:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-11-21 00:54:47 +01:00
|
|
|
// this will return live_files prefixed with "/"
|
2017-03-22 01:53:21 +01:00
|
|
|
s = db_->GetLiveFiles(live_files, &manifest_file_size, flush_memtable);
|
2016-12-28 20:53:29 +01:00
|
|
|
|
2016-12-29 03:38:20 +01:00
|
|
|
if (s.ok() && db_options.allow_2pc) {
|
2016-12-28 20:53:29 +01:00
|
|
|
// If 2PC is enabled, we need to get minimum log number after the flush.
|
|
|
|
// Need to refetch the live files to recapture the snapshot.
|
|
|
|
if (!db_->GetIntProperty(DB::Properties::kMinLogNumberToKeep,
|
|
|
|
&min_log_num)) {
|
|
|
|
return Status::InvalidArgument(
|
|
|
|
"2PC enabled but cannot fine the min log number to keep.");
|
|
|
|
}
|
|
|
|
// We need to refetch live files with flush to handle this case:
|
|
|
|
// A previous 000001.log contains the prepare record of transaction tnx1.
|
|
|
|
// The current log file is 000002.log, and sequence_number points to this
|
|
|
|
// file.
|
|
|
|
// After calling GetLiveFiles(), 000003.log is created.
|
|
|
|
// Then tnx1 is committed. The commit record is written to 000003.log.
|
|
|
|
// Now we fetch min_log_num, which will be 3.
|
|
|
|
// Then only 000002.log and 000003.log will be copied, and 000001.log will
|
|
|
|
// be skipped. 000003.log contains commit message of tnx1, but we don't
|
|
|
|
// have respective prepare record for it.
|
|
|
|
// In order to avoid this situation, we need to force flush to make sure
|
2017-04-24 23:57:27 +02:00
|
|
|
// all transactions committed before getting min_log_num will be flushed
|
2016-12-28 20:53:29 +01:00
|
|
|
// to SST files.
|
|
|
|
// We cannot get min_log_num before calling the GetLiveFiles() for the
|
|
|
|
// first time, because if we do that, all the logs files will be included,
|
|
|
|
// far more than needed.
|
2017-04-24 23:57:27 +02:00
|
|
|
s = db_->GetLiveFiles(live_files, &manifest_file_size, flush_memtable);
|
2016-12-28 20:53:29 +01:00
|
|
|
}
|
|
|
|
|
2016-03-17 18:07:21 +01:00
|
|
|
TEST_SYNC_POINT("CheckpointImpl::CreateCheckpoint:SavedLiveFiles1");
|
|
|
|
TEST_SYNC_POINT("CheckpointImpl::CreateCheckpoint:SavedLiveFiles2");
|
2018-03-27 01:16:59 +02:00
|
|
|
db_->FlushWAL(false /* sync */);
|
2014-11-21 00:54:47 +01:00
|
|
|
}
|
2015-06-20 01:08:31 +02:00
|
|
|
// if we have more than one column family, we need to also get WAL files
|
|
|
|
if (s.ok()) {
|
|
|
|
s = db_->GetSortedWalFiles(live_wal_files);
|
|
|
|
}
|
2014-11-21 00:54:47 +01:00
|
|
|
if (!s.ok()) {
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
|
2015-06-20 01:08:31 +02:00
|
|
|
size_t wal_size = live_wal_files.size();
|
2014-11-21 00:54:47 +01:00
|
|
|
|
|
|
|
// copy/hard link live_files
|
2016-03-17 18:07:21 +01:00
|
|
|
std::string manifest_fname, current_fname;
|
2014-11-21 00:54:47 +01:00
|
|
|
for (size_t i = 0; s.ok() && i < live_files.size(); ++i) {
|
|
|
|
uint64_t number;
|
|
|
|
FileType type;
|
|
|
|
bool ok = ParseFileName(live_files[i], &number, &type);
|
|
|
|
if (!ok) {
|
|
|
|
s = Status::Corruption("Can't parse file name. This is very bad");
|
|
|
|
break;
|
|
|
|
}
|
2016-06-10 04:03:10 +02:00
|
|
|
// we should only get sst, options, manifest and current files here
|
2014-11-21 00:54:47 +01:00
|
|
|
assert(type == kTableFile || type == kDescriptorFile ||
|
2016-06-10 04:03:10 +02:00
|
|
|
type == kCurrentFile || type == kOptionsFile);
|
2014-11-21 00:54:47 +01:00
|
|
|
assert(live_files[i].size() > 0 && live_files[i][0] == '/');
|
2016-03-17 18:07:21 +01:00
|
|
|
if (type == kCurrentFile) {
|
|
|
|
// We will craft the current file manually to ensure it's consistent with
|
|
|
|
// the manifest number. This is necessary because current's file contents
|
|
|
|
// can change during checkpoint creation.
|
|
|
|
current_fname = live_files[i];
|
|
|
|
continue;
|
|
|
|
} else if (type == kDescriptorFile) {
|
|
|
|
manifest_fname = live_files[i];
|
|
|
|
}
|
2014-11-21 00:54:47 +01:00
|
|
|
std::string src_fname = live_files[i];
|
|
|
|
|
|
|
|
// rules:
|
|
|
|
// * if it's kTableFile, then it's shared
|
|
|
|
// * if it's kDescriptorFile, limit the size to manifest_file_size
|
|
|
|
// * always copy if cross-device link
|
|
|
|
if ((type == kTableFile) && same_fs) {
|
2017-04-24 23:57:27 +02:00
|
|
|
s = link_file_cb(db_->GetName(), src_fname, type);
|
2014-11-21 00:54:47 +01:00
|
|
|
if (s.IsNotSupported()) {
|
|
|
|
same_fs = false;
|
|
|
|
s = Status::OK();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if ((type != kTableFile) || (!same_fs)) {
|
2017-04-24 23:57:27 +02:00
|
|
|
s = copy_file_cb(db_->GetName(), src_fname,
|
|
|
|
(type == kDescriptorFile) ? manifest_file_size : 0,
|
|
|
|
type);
|
2014-11-21 00:54:47 +01:00
|
|
|
}
|
|
|
|
}
|
2016-03-17 18:07:21 +01:00
|
|
|
if (s.ok() && !current_fname.empty() && !manifest_fname.empty()) {
|
2017-04-24 23:57:27 +02:00
|
|
|
create_file_cb(current_fname, manifest_fname.substr(1) + "\n",
|
|
|
|
kCurrentFile);
|
2016-03-17 18:07:21 +01:00
|
|
|
}
|
2017-03-16 03:22:52 +01:00
|
|
|
ROCKS_LOG_INFO(db_options.info_log, "Number of log files %" ROCKSDB_PRIszt,
|
|
|
|
live_wal_files.size());
|
2015-06-20 01:08:31 +02:00
|
|
|
|
|
|
|
// Link WAL files. Copy exact size of last one because it is the only one
|
|
|
|
// that has changes after the last flush.
|
|
|
|
for (size_t i = 0; s.ok() && i < wal_size; ++i) {
|
|
|
|
if ((live_wal_files[i]->Type() == kAliveLogFile) &&
|
2017-03-22 01:53:21 +01:00
|
|
|
(!flush_memtable ||
|
2017-04-24 23:57:27 +02:00
|
|
|
live_wal_files[i]->StartSequence() >= *sequence_number ||
|
2016-12-28 20:53:29 +01:00
|
|
|
live_wal_files[i]->LogNumber() >= min_log_num)) {
|
2015-06-20 01:08:31 +02:00
|
|
|
if (i + 1 == wal_size) {
|
2017-04-24 23:57:27 +02:00
|
|
|
s = copy_file_cb(db_options.wal_dir, live_wal_files[i]->PathName(),
|
|
|
|
live_wal_files[i]->SizeFileBytes(), kLogFile);
|
2015-06-20 01:08:31 +02:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (same_fs) {
|
|
|
|
// we only care about live log files
|
2017-04-24 23:57:27 +02:00
|
|
|
s = link_file_cb(db_options.wal_dir, live_wal_files[i]->PathName(),
|
|
|
|
kLogFile);
|
2015-06-20 01:08:31 +02:00
|
|
|
if (s.IsNotSupported()) {
|
|
|
|
same_fs = false;
|
|
|
|
s = Status::OK();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (!same_fs) {
|
2017-04-24 23:57:27 +02:00
|
|
|
s = copy_file_cb(db_options.wal_dir, live_wal_files[i]->PathName(), 0,
|
|
|
|
kLogFile);
|
2015-06-20 01:08:31 +02:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
2014-11-21 00:54:47 +01:00
|
|
|
|
|
|
|
return s;
|
|
|
|
}
|
2017-04-24 23:57:27 +02:00
|
|
|
|
Export Import sst files (#5495)
Summary:
Refresh of the earlier change here - https://github.com/facebook/rocksdb/issues/5135
This is a review request for code change needed for - https://github.com/facebook/rocksdb/issues/3469
"Add support for taking snapshot of a column family and creating column family from a given CF snapshot"
We have an implementation for this that we have been testing internally. We have two new APIs that together provide this functionality.
(1) ExportColumnFamily() - This API is modelled after CreateCheckpoint() as below.
// Exports all live SST files of a specified Column Family onto export_dir,
// returning SST files information in metadata.
// - SST files will be created as hard links when the directory specified
// is in the same partition as the db directory, copied otherwise.
// - export_dir should not already exist and will be created by this API.
// - Always triggers a flush.
virtual Status ExportColumnFamily(ColumnFamilyHandle* handle,
const std::string& export_dir,
ExportImportFilesMetaData** metadata);
Internally, the API will DisableFileDeletions(), GetColumnFamilyMetaData(), Parse through
metadata, creating links/copies of all the sst files, EnableFileDeletions() and complete the call by
returning the list of file metadata.
(2) CreateColumnFamilyWithImport() - This API is modeled after IngestExternalFile(), but invoked only during a CF creation as below.
// CreateColumnFamilyWithImport() will create a new column family with
// column_family_name and import external SST files specified in metadata into
// this column family.
// (1) External SST files can be created using SstFileWriter.
// (2) External SST files can be exported from a particular column family in
// an existing DB.
// Option in import_options specifies whether the external files are copied or
// moved (default is copy). When option specifies copy, managing files at
// external_file_path is caller's responsibility. When option specifies a
// move, the call ensures that the specified files at external_file_path are
// deleted on successful return and files are not modified on any error
// return.
// On error return, column family handle returned will be nullptr.
// ColumnFamily will be present on successful return and will not be present
// on error return. ColumnFamily may be present on any crash during this call.
virtual Status CreateColumnFamilyWithImport(
const ColumnFamilyOptions& options, const std::string& column_family_name,
const ImportColumnFamilyOptions& import_options,
const ExportImportFilesMetaData& metadata,
ColumnFamilyHandle** handle);
Internally, this API creates a new CF, parses all the sst files and adds it to the specified column family, at the same level and with same sequence number as in the metadata. Also performs safety checks with respect to overlaps between the sst files being imported.
If incoming sequence number is higher than current local sequence number, local sequence
number is updated to reflect this.
Note, as the sst files is are being moved across Column Families, Column Family name in sst file
will no longer match the actual column family on destination DB. The API does not modify Column
Family name or id in the sst files being imported.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5495
Differential Revision: D16018881
fbshipit-source-id: 9ae2251025d5916d35a9fc4ea4d6707f6be16ff9
2019-07-17 21:22:21 +02:00
|
|
|
// Exports all live SST files of a specified Column Family onto export_dir,
|
|
|
|
// returning SST files information in metadata.
|
|
|
|
Status CheckpointImpl::ExportColumnFamily(
|
|
|
|
ColumnFamilyHandle* handle, const std::string& export_dir,
|
|
|
|
ExportImportFilesMetaData** metadata) {
|
|
|
|
auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(handle);
|
|
|
|
const auto cf_name = cfh->GetName();
|
|
|
|
const auto db_options = db_->GetDBOptions();
|
|
|
|
|
|
|
|
assert(metadata != nullptr);
|
|
|
|
assert(*metadata == nullptr);
|
|
|
|
auto s = db_->GetEnv()->FileExists(export_dir);
|
|
|
|
if (s.ok()) {
|
|
|
|
return Status::InvalidArgument("Specified export_dir exists");
|
|
|
|
} else if (!s.IsNotFound()) {
|
|
|
|
assert(s.IsIOError());
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
|
|
|
|
const auto final_nonslash_idx = export_dir.find_last_not_of('/');
|
|
|
|
if (final_nonslash_idx == std::string::npos) {
|
|
|
|
return Status::InvalidArgument("Specified export_dir invalid");
|
|
|
|
}
|
|
|
|
ROCKS_LOG_INFO(db_options.info_log,
|
|
|
|
"[%s] export column family onto export directory %s",
|
|
|
|
cf_name.c_str(), export_dir.c_str());
|
|
|
|
|
|
|
|
// Create a temporary export directory.
|
|
|
|
const auto tmp_export_dir =
|
|
|
|
export_dir.substr(0, final_nonslash_idx + 1) + ".tmp";
|
|
|
|
s = db_->GetEnv()->CreateDir(tmp_export_dir);
|
|
|
|
|
|
|
|
if (s.ok()) {
|
|
|
|
s = db_->Flush(rocksdb::FlushOptions(), handle);
|
|
|
|
}
|
|
|
|
|
|
|
|
ColumnFamilyMetaData db_metadata;
|
|
|
|
if (s.ok()) {
|
|
|
|
// Export live sst files with file deletions disabled.
|
|
|
|
s = db_->DisableFileDeletions();
|
|
|
|
if (s.ok()) {
|
|
|
|
db_->GetColumnFamilyMetaData(handle, &db_metadata);
|
|
|
|
|
|
|
|
s = ExportFilesInMetaData(
|
|
|
|
db_options, db_metadata,
|
|
|
|
[&](const std::string& src_dirname, const std::string& fname) {
|
|
|
|
ROCKS_LOG_INFO(db_options.info_log, "[%s] HardLinking %s",
|
|
|
|
cf_name.c_str(), fname.c_str());
|
|
|
|
return db_->GetEnv()->LinkFile(src_dirname + fname,
|
|
|
|
tmp_export_dir + fname);
|
|
|
|
} /*link_file_cb*/,
|
|
|
|
[&](const std::string& src_dirname, const std::string& fname) {
|
|
|
|
ROCKS_LOG_INFO(db_options.info_log, "[%s] Copying %s",
|
|
|
|
cf_name.c_str(), fname.c_str());
|
|
|
|
return CopyFile(db_->GetEnv(), src_dirname + fname,
|
|
|
|
tmp_export_dir + fname, 0, db_options.use_fsync);
|
|
|
|
} /*copy_file_cb*/);
|
|
|
|
|
|
|
|
const auto enable_status = db_->EnableFileDeletions(false /*force*/);
|
|
|
|
if (s.ok()) {
|
|
|
|
s = enable_status;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
auto moved_to_user_specified_dir = false;
|
|
|
|
if (s.ok()) {
|
|
|
|
// Move temporary export directory to the actual export directory.
|
|
|
|
s = db_->GetEnv()->RenameFile(tmp_export_dir, export_dir);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (s.ok()) {
|
|
|
|
// Fsync export directory.
|
|
|
|
moved_to_user_specified_dir = true;
|
|
|
|
std::unique_ptr<Directory> dir_ptr;
|
|
|
|
s = db_->GetEnv()->NewDirectory(export_dir, &dir_ptr);
|
|
|
|
if (s.ok()) {
|
|
|
|
assert(dir_ptr != nullptr);
|
|
|
|
s = dir_ptr->Fsync();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (s.ok()) {
|
|
|
|
// Export of files succeeded. Fill in the metadata information.
|
|
|
|
auto result_metadata = new ExportImportFilesMetaData();
|
|
|
|
result_metadata->db_comparator_name = handle->GetComparator()->Name();
|
|
|
|
for (const auto& level_metadata : db_metadata.levels) {
|
|
|
|
for (const auto& file_metadata : level_metadata.files) {
|
|
|
|
LiveFileMetaData live_file_metadata;
|
|
|
|
live_file_metadata.size = file_metadata.size;
|
|
|
|
live_file_metadata.name = std::move(file_metadata.name);
|
|
|
|
live_file_metadata.db_path = export_dir;
|
|
|
|
live_file_metadata.smallest_seqno = file_metadata.smallest_seqno;
|
|
|
|
live_file_metadata.largest_seqno = file_metadata.largest_seqno;
|
|
|
|
live_file_metadata.smallestkey = std::move(file_metadata.smallestkey);
|
|
|
|
live_file_metadata.largestkey = std::move(file_metadata.largestkey);
|
|
|
|
live_file_metadata.level = level_metadata.level;
|
|
|
|
result_metadata->files.push_back(live_file_metadata);
|
|
|
|
}
|
|
|
|
*metadata = result_metadata;
|
|
|
|
}
|
|
|
|
ROCKS_LOG_INFO(db_options.info_log, "[%s] Export succeeded.",
|
|
|
|
cf_name.c_str());
|
|
|
|
} else {
|
|
|
|
// Failure: Clean up all the files/directories created.
|
|
|
|
ROCKS_LOG_INFO(db_options.info_log, "[%s] Export failed. %s",
|
|
|
|
cf_name.c_str(), s.ToString().c_str());
|
|
|
|
std::vector<std::string> subchildren;
|
|
|
|
const auto cleanup_dir =
|
|
|
|
moved_to_user_specified_dir ? export_dir : tmp_export_dir;
|
|
|
|
db_->GetEnv()->GetChildren(cleanup_dir, &subchildren);
|
|
|
|
for (const auto& subchild : subchildren) {
|
|
|
|
const auto subchild_path = cleanup_dir + "/" + subchild;
|
|
|
|
const auto status = db_->GetEnv()->DeleteFile(subchild_path);
|
|
|
|
if (!status.ok()) {
|
|
|
|
ROCKS_LOG_WARN(db_options.info_log, "Failed to cleanup file %s: %s",
|
|
|
|
subchild_path.c_str(), status.ToString().c_str());
|
|
|
|
}
|
|
|
|
}
|
|
|
|
const auto status = db_->GetEnv()->DeleteDir(cleanup_dir);
|
|
|
|
if (!status.ok()) {
|
|
|
|
ROCKS_LOG_WARN(db_options.info_log, "Failed to cleanup dir %s: %s",
|
|
|
|
cleanup_dir.c_str(), status.ToString().c_str());
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
|
|
|
|
Status CheckpointImpl::ExportFilesInMetaData(
|
|
|
|
const DBOptions& db_options, const ColumnFamilyMetaData& metadata,
|
|
|
|
std::function<Status(const std::string& src_dirname,
|
|
|
|
const std::string& src_fname)>
|
|
|
|
link_file_cb,
|
|
|
|
std::function<Status(const std::string& src_dirname,
|
|
|
|
const std::string& src_fname)>
|
|
|
|
copy_file_cb) {
|
|
|
|
Status s;
|
|
|
|
auto hardlink_file = true;
|
|
|
|
|
|
|
|
// Copy/hard link files in metadata.
|
|
|
|
size_t num_files = 0;
|
|
|
|
for (const auto& level_metadata : metadata.levels) {
|
|
|
|
for (const auto& file_metadata : level_metadata.files) {
|
|
|
|
uint64_t number;
|
|
|
|
FileType type;
|
|
|
|
const auto ok = ParseFileName(file_metadata.name, &number, &type);
|
|
|
|
if (!ok) {
|
|
|
|
s = Status::Corruption("Could not parse file name");
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
// We should only get sst files here.
|
|
|
|
assert(type == kTableFile);
|
|
|
|
assert(file_metadata.size > 0 && file_metadata.name[0] == '/');
|
|
|
|
const auto src_fname = file_metadata.name;
|
|
|
|
++num_files;
|
|
|
|
|
|
|
|
if (hardlink_file) {
|
|
|
|
s = link_file_cb(db_->GetName(), src_fname);
|
|
|
|
if (num_files == 1 && s.IsNotSupported()) {
|
|
|
|
// Fallback to copy if link failed due to cross-device directories.
|
|
|
|
hardlink_file = false;
|
|
|
|
s = Status::OK();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (!hardlink_file) {
|
|
|
|
s = copy_file_cb(db_->GetName(), src_fname);
|
|
|
|
}
|
|
|
|
if (!s.ok()) {
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
ROCKS_LOG_INFO(db_options.info_log, "Number of table files %" ROCKSDB_PRIszt,
|
|
|
|
num_files);
|
|
|
|
|
|
|
|
return s;
|
|
|
|
}
|
2014-11-21 00:54:47 +01:00
|
|
|
} // namespace rocksdb
|
|
|
|
|
|
|
|
#endif // ROCKSDB_LITE
|