|
|
|
// 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) 2012 Facebook.
|
|
|
|
// Use of this source code is governed by a BSD-style license that can be
|
|
|
|
// found in the LICENSE file.
|
|
|
|
|
|
|
|
|
|
|
|
#include "utilities/checkpoint/checkpoint_impl.h"
|
|
|
|
|
|
|
|
#include <algorithm>
|
|
|
|
#include <cinttypes>
|
|
|
|
#include <string>
|
|
|
|
#include <tuple>
|
|
|
|
#include <unordered_set>
|
|
|
|
#include <vector>
|
|
|
|
|
|
|
|
#include "db/wal_manager.h"
|
|
|
|
#include "file/file_util.h"
|
|
|
|
#include "file/filename.h"
|
|
|
|
#include "logging/logging.h"
|
|
|
|
#include "port/port.h"
|
|
|
|
#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
6 years ago
|
|
|
#include "rocksdb/metadata.h"
|
|
|
|
#include "rocksdb/options.h"
|
|
|
|
#include "rocksdb/transaction_log.h"
|
|
|
|
#include "rocksdb/types.h"
|
|
|
|
#include "rocksdb/utilities/checkpoint.h"
|
|
|
|
#include "test_util/sync_point.h"
|
|
|
|
#include "util/cast_util.h"
|
|
|
|
#include "util/file_checksum_helper.h"
|
|
|
|
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
|
|
|
|
Status Checkpoint::Create(DB* db, Checkpoint** checkpoint_ptr) {
|
|
|
|
*checkpoint_ptr = new CheckpointImpl(db);
|
|
|
|
return Status::OK();
|
|
|
|
}
|
|
|
|
|
|
|
|
Status Checkpoint::CreateCheckpoint(const std::string& /*checkpoint_dir*/,
|
|
|
|
uint64_t /*log_size_for_flush*/,
|
|
|
|
uint64_t* /*sequence_number_ptr*/) {
|
|
|
|
return Status::NotSupported("");
|
|
|
|
}
|
|
|
|
|
|
|
|
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());
|
|
|
|
s = db_->GetEnv()->GetChildren(full_private_path, &subchildren);
|
|
|
|
if (s.ok()) {
|
|
|
|
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
6 years ago
|
|
|
Status Checkpoint::ExportColumnFamily(
|
|
|
|
ColumnFamilyHandle* /*handle*/, const std::string& /*export_dir*/,
|
|
|
|
ExportImportFilesMetaData** /*metadata*/) {
|
|
|
|
return Status::NotSupported("");
|
|
|
|
}
|
|
|
|
|
|
|
|
// Builds an openable snapshot of RocksDB
|
|
|
|
Status CheckpointImpl::CreateCheckpoint(const std::string& checkpoint_dir,
|
|
|
|
uint64_t log_size_for_flush,
|
|
|
|
uint64_t* sequence_number_ptr) {
|
|
|
|
DBOptions db_options = db_->GetDBOptions();
|
|
|
|
|
|
|
|
Status s = db_->GetEnv()->FileExists(checkpoint_dir);
|
|
|
|
if (s.ok()) {
|
|
|
|
return Status::InvalidArgument("Directory exists");
|
|
|
|
} else if (!s.IsNotFound()) {
|
|
|
|
assert(s.IsIOError());
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
|
|
|
|
ROCKS_LOG_INFO(
|
|
|
|
db_options.info_log,
|
|
|
|
"Started the snapshot process -- creating snapshot in directory %s",
|
|
|
|
checkpoint_dir.c_str());
|
|
|
|
|
|
|
|
size_t final_nonslash_idx = checkpoint_dir.find_last_not_of('/');
|
|
|
|
if (final_nonslash_idx == std::string::npos) {
|
|
|
|
// 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());
|
|
|
|
return Status::InvalidArgument("invalid checkpoint directory name");
|
|
|
|
}
|
|
|
|
|
|
|
|
std::string full_private_path =
|
|
|
|
checkpoint_dir.substr(0, final_nonslash_idx + 1) + ".tmp";
|
Checkpoint dir options fix (#8572)
Summary:
Originally the 2 options `db_log_dir` and `wal_dir` will be reused in a snapshot db since the options files are just copied. By default, if `wal_dir` was not set when a db was created, it is set to the db's dir. Therefore, the snapshot db will use the same WAL dir. If both the original db and the snapshot db write to or delete from the WAL dir, one may modify or delete files which belong to the other. The same applies to `db_log_dir` as well, but as info log files are not copied or linked, it is simpler for this option.
2 arguments are added to `Checkpoint::CreateCheckpoint()`, allowing to override these 2 options.
`wal_dir`: If the function argument `wal_dir` is empty, or set to the original db location, or the checkpoint location, the snapshot's `wal_dir` option will be updated to the checkpoint location. Otherwise, the absolute path specified in the argument will be used. During checkpointing, live WAL files will be copied or linked the new location, instead of the current WAL dir specified in the original db.
`db_log_dir`: Same as `wal_dir`, but no files will be copied or linked.
A new unit test was added: `CheckpointTest.CheckpointWithOptionsDirsTest`.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/8572
Test Plan:
New unit test
```
checkpoint_test --gtest_filter="CheckpointTest.CheckpointWithOptionsDirsTest"
```
Output
```
Note: Google Test filter = CheckpointTest.CheckpointWithOptionsDirsTest
[==========] Running 1 test from 1 test case.
[----------] Global test environment set-up.
[----------] 1 test from CheckpointTest
[ RUN ] CheckpointTest.CheckpointWithOptionsDirsTest
[ OK ] CheckpointTest.CheckpointWithOptionsDirsTest (11712 ms)
[----------] 1 test from CheckpointTest (11712 ms total)
[----------] Global test environment tear-down
[==========] 1 test from 1 test case ran. (11713 ms total)
[ PASSED ] 1 test.
```
This test will fail without this patch. Just modify the code to remove the 2 arguments introduced in this patch in `CreateCheckpoint()`.
Reviewed By: zhichao-cao
Differential Revision: D29832761
Pulled By: autopear
fbshipit-source-id: e6a639b4d674380df82998c0839e79cab695fe29
3 years ago
|
|
|
ROCKS_LOG_INFO(db_options.info_log,
|
|
|
|
"Snapshot process -- using temporary directory %s",
|
|
|
|
full_private_path.c_str());
|
|
|
|
CleanStagingDirectory(full_private_path, db_options.info_log.get());
|
|
|
|
// create snapshot directory
|
|
|
|
s = db_->GetEnv()->CreateDir(full_private_path);
|
|
|
|
uint64_t sequence_number = 0;
|
|
|
|
if (s.ok()) {
|
|
|
|
// enable file deletions
|
|
|
|
s = db_->DisableFileDeletions();
|
|
|
|
const bool disabled_file_deletions = s.ok();
|
|
|
|
|
|
|
|
if (s.ok() || s.IsNotSupported()) {
|
|
|
|
s = CreateCustomCheckpoint(
|
|
|
|
[&](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_->GetFileSystem()->LinkFile(
|
|
|
|
src_dirname + "/" + fname, full_private_path + "/" + fname,
|
|
|
|
IOOptions(), nullptr);
|
|
|
|
} /* link_file_cb */,
|
|
|
|
[&](const std::string& src_dirname, const std::string& fname,
|
|
|
|
uint64_t size_limit_bytes, FileType,
|
|
|
|
const std::string& /* checksum_func_name */,
|
|
|
|
const std::string& /* checksum_val */,
|
|
|
|
const Temperature temperature) {
|
|
|
|
ROCKS_LOG_INFO(db_options.info_log, "Copying %s", fname.c_str());
|
|
|
|
return CopyFile(db_->GetFileSystem(), src_dirname + "/" + fname,
|
|
|
|
full_private_path + "/" + fname, size_limit_bytes,
|
|
|
|
db_options.use_fsync, nullptr, temperature);
|
|
|
|
} /* copy_file_cb */,
|
|
|
|
[&](const std::string& fname, const std::string& contents, FileType) {
|
|
|
|
ROCKS_LOG_INFO(db_options.info_log, "Creating %s", fname.c_str());
|
|
|
|
return CreateFile(db_->GetFileSystem(),
|
|
|
|
full_private_path + "/" + fname, contents,
|
|
|
|
db_options.use_fsync);
|
|
|
|
} /* create_file_cb */,
|
|
|
|
&sequence_number, log_size_for_flush);
|
|
|
|
|
|
|
|
// we copied all the files, enable file deletions
|
|
|
|
if (disabled_file_deletions) {
|
|
|
|
Status ss = db_->EnableFileDeletions(false);
|
|
|
|
assert(ss.ok());
|
|
|
|
ss.PermitUncheckedError();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (s.ok()) {
|
|
|
|
// move tmp private backup to real snapshot directory
|
|
|
|
s = db_->GetEnv()->RenameFile(full_private_path, checkpoint_dir);
|
|
|
|
}
|
|
|
|
if (s.ok()) {
|
|
|
|
std::unique_ptr<FSDirectory> checkpoint_directory;
|
|
|
|
s = db_->GetFileSystem()->NewDirectory(checkpoint_dir, IOOptions(),
|
|
|
|
&checkpoint_directory, nullptr);
|
|
|
|
if (s.ok() && checkpoint_directory != nullptr) {
|
|
|
|
s = checkpoint_directory->FsyncWithDirOptions(
|
|
|
|
IOOptions(), nullptr,
|
|
|
|
DirFsyncOptions(DirFsyncOptions::FsyncReason::kDirRenamed));
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (s.ok()) {
|
|
|
|
if (sequence_number_ptr != nullptr) {
|
|
|
|
*sequence_number_ptr = sequence_number;
|
|
|
|
}
|
|
|
|
// 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());
|
|
|
|
CleanStagingDirectory(full_private_path, db_options.info_log.get());
|
|
|
|
}
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
|
|
|
|
Status CheckpointImpl::CreateCustomCheckpoint(
|
|
|
|
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,
|
|
|
|
const std::string& checksum_func_name,
|
|
|
|
const std::string& checksum_val, const Temperature temperature)>
|
|
|
|
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,
|
|
|
|
bool get_live_table_checksum) {
|
|
|
|
*sequence_number = db_->GetLatestSequenceNumber();
|
|
|
|
|
|
|
|
LiveFilesStorageInfoOptions opts;
|
|
|
|
opts.include_checksum_info = get_live_table_checksum;
|
|
|
|
opts.wal_size_for_flush = log_size_for_flush;
|
|
|
|
|
|
|
|
std::vector<LiveFileStorageInfo> infos;
|
|
|
|
{
|
|
|
|
Status s = db_->GetLiveFilesStorageInfo(opts, &infos);
|
|
|
|
if (!s.ok()) {
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
// Verify that everything except WAL files are in same directory
|
|
|
|
// (db_paths / cf_paths not supported)
|
|
|
|
std::unordered_set<std::string> dirs;
|
|
|
|
for (auto& info : infos) {
|
|
|
|
if (info.file_type != kWalFile) {
|
|
|
|
dirs.insert(info.directory);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (dirs.size() > 1) {
|
|
|
|
return Status::NotSupported(
|
|
|
|
"db_paths / cf_paths not supported for Checkpoint nor BackupEngine");
|
|
|
|
}
|
|
|
|
|
|
|
|
bool same_fs = true;
|
|
|
|
|
|
|
|
for (auto& info : infos) {
|
|
|
|
Status s;
|
|
|
|
if (!info.replacement_contents.empty()) {
|
|
|
|
// Currently should only be used for CURRENT file.
|
|
|
|
assert(info.file_type == kCurrentFile);
|
|
|
|
|
|
|
|
if (info.size != info.replacement_contents.size()) {
|
|
|
|
s = Status::Corruption("Inconsistent size metadata for " +
|
|
|
|
info.relative_filename);
|
|
|
|
} else {
|
|
|
|
s = create_file_cb(info.relative_filename, info.replacement_contents,
|
|
|
|
info.file_type);
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
if (same_fs && !info.trim_to_size) {
|
|
|
|
s = link_file_cb(info.directory, info.relative_filename,
|
|
|
|
info.file_type);
|
|
|
|
if (s.IsNotSupported()) {
|
|
|
|
same_fs = false;
|
|
|
|
s = Status::OK();
|
|
|
|
}
|
|
|
|
s.MustCheck();
|
|
|
|
}
|
|
|
|
if (!same_fs || info.trim_to_size) {
|
|
|
|
assert(info.file_checksum_func_name.empty() ==
|
|
|
|
!opts.include_checksum_info);
|
|
|
|
// no assertion on file_checksum because empty is used for both "not
|
|
|
|
// set" and "unknown"
|
|
|
|
if (opts.include_checksum_info) {
|
|
|
|
s = copy_file_cb(info.directory, info.relative_filename, info.size,
|
|
|
|
info.file_type, info.file_checksum_func_name,
|
|
|
|
info.file_checksum, info.temperature);
|
|
|
|
} else {
|
|
|
|
s = copy_file_cb(info.directory, info.relative_filename, info.size,
|
|
|
|
info.file_type, kUnknownFileChecksumFuncName,
|
|
|
|
kUnknownFileChecksum, info.temperature);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (!s.ok()) {
|
|
|
|
return s;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return Status::OK();
|
|
|
|
}
|
|
|
|
|
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
6 years ago
|
|
|
// 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 = static_cast_with_check<ColumnFamilyHandleImpl>(handle);
|
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
6 years ago
|
|
|
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_NAMESPACE::FlushOptions(), handle);
|
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
6 years ago
|
|
|
}
|
|
|
|
|
|
|
|
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());
|
Introduce a new storage specific Env API (#5761)
Summary:
The current Env API encompasses both storage/file operations, as well as OS related operations. Most of the APIs return a Status, which does not have enough metadata about an error, such as whether its retry-able or not, scope (i.e fault domain) of the error etc., that may be required in order to properly handle a storage error. The file APIs also do not provide enough control over the IO SLA, such as timeout, prioritization, hinting about placement and redundancy etc.
This PR separates out the file/storage APIs from Env into a new FileSystem class. The APIs are updated to return an IOStatus with metadata about the error, as well as to take an IOOptions structure as input in order to allow more control over the IO.
The user can set both ```options.env``` and ```options.file_system``` to specify that RocksDB should use the former for OS related operations and the latter for storage operations. Internally, a ```CompositeEnvWrapper``` has been introduced that inherits from ```Env``` and redirects individual methods to either an ```Env``` implementation or the ```FileSystem``` as appropriate. When options are sanitized during ```DB::Open```, ```options.env``` is replaced with a newly allocated ```CompositeEnvWrapper``` instance if both env and file_system have been specified. This way, the rest of the RocksDB code can continue to function as before.
This PR also ports PosixEnv to the new API by splitting it into two - PosixEnv and PosixFileSystem. PosixEnv is defined as a sub-class of CompositeEnvWrapper, and threading/time functions are overridden with Posix specific implementations in order to avoid an extra level of indirection.
The ```CompositeEnvWrapper``` translates ```IOStatus``` return code to ```Status```, and sets the severity to ```kSoftError``` if the io_status is retryable. The error handling code in RocksDB can then recover the DB automatically.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5761
Differential Revision: D18868376
Pulled By: anand1976
fbshipit-source-id: 39efe18a162ea746fabac6360ff529baba48486f
5 years ago
|
|
|
return CopyFile(db_->GetFileSystem(), src_dirname + fname,
|
|
|
|
tmp_export_dir + fname, 0, db_options.use_fsync,
|
|
|
|
nullptr, Temperature::kUnknown);
|
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
6 years ago
|
|
|
} /*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<FSDirectory> dir_ptr;
|
|
|
|
s = db_->GetFileSystem()->NewDirectory(export_dir, IOOptions(), &dir_ptr,
|
|
|
|
nullptr);
|
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
6 years ago
|
|
|
if (s.ok()) {
|
|
|
|
assert(dir_ptr != nullptr);
|
|
|
|
s = dir_ptr->FsyncWithDirOptions(
|
|
|
|
IOOptions(), nullptr,
|
|
|
|
DirFsyncOptions(DirFsyncOptions::FsyncReason::kDirRenamed));
|
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
6 years ago
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
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.file_number = file_metadata.file_number;
|
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
6 years ago
|
|
|
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.oldest_blob_file_number =
|
|
|
|
file_metadata.oldest_blob_file_number;
|
Sort L0 files by newly introduced epoch_num (#10922)
Summary:
**Context:**
Sorting L0 files by `largest_seqno` has at least two inconvenience:
- File ingestion and compaction involving ingested files can create files of overlapping seqno range with the existing files. `force_consistency_check=true` will catch such overlap seqno range even those harmless overlap.
- For example, consider the following sequence of events ("key@n" indicates key at seqno "n")
- insert k1@1 to memtable m1
- ingest file s1 with k2@2, ingest file s2 with k3@3
- insert k4@4 to m1
- compact files s1, s2 and result in new file s3 of seqno range [2, 3]
- flush m1 and result in new file s4 of seqno range [1, 4]. And `force_consistency_check=true` will think s4 and s3 has file reordering corruption that might cause retuning an old value of k1
- However such caught corruption is a false positive since s1, s2 will not have overlapped keys with k1 or whatever inserted into m1 before ingest file s1 by the requirement of file ingestion (otherwise the m1 will be flushed first before any of the file ingestion completes). Therefore there in fact isn't any file reordering corruption.
- Single delete can decrease a file's largest seqno and ordering by `largest_seqno` can introduce a wrong ordering hence file reordering corruption
- For example, consider the following sequence of events ("key@n" indicates key at seqno "n", Credit to ajkr for this example)
- an existing SST s1 contains only k1@1
- insert k1@2 to memtable m1
- ingest file s2 with k3@3, ingest file s3 with k4@4
- insert single delete k5@5 in m1
- flush m1 and result in new file s4 of seqno range [2, 5]
- compact s1, s2, s3 and result in new file s5 of seqno range [1, 4]
- compact s4 and result in new file s6 of seqno range [2] due to single delete
- By the last step, we have file ordering by largest seqno (">" means "newer") : s5 > s6 while s6 contains a newer version of the k1's value (i.e, k1@2) than s5, which is a real reordering corruption. While this can be caught by `force_consistency_check=true`, there isn't a good way to prevent this from happening if ordering by `largest_seqno`
Therefore, we are redesigning the sorting criteria of L0 files and avoid above inconvenience. Credit to ajkr , we now introduce `epoch_num` which describes the order of a file being flushed or ingested/imported (compaction output file will has the minimum `epoch_num` among input files'). This will avoid the above inconvenience in the following ways:
- In the first case above, there will no longer be overlap seqno range check in `force_consistency_check=true` but `epoch_number` ordering check. This will result in file ordering s1 < s2 < s4 (pre-compaction) and s3 < s4 (post-compaction) which won't trigger false positive corruption. See test class `DBCompactionTestL0FilesMisorderCorruption*` for more.
- In the second case above, this will result in file ordering s1 < s2 < s3 < s4 (pre-compacting s1, s2, s3), s5 < s4 (post-compacting s1, s2, s3), s5 < s6 (post-compacting s4), which are correct file ordering without causing any corruption.
**Summary:**
- Introduce `epoch_number` stored per `ColumnFamilyData` and sort CF's L0 files by their assigned `epoch_number` instead of `largest_seqno`.
- `epoch_number` is increased and assigned upon `VersionEdit::AddFile()` for flush (or similarly for WriteLevel0TableForRecovery) and file ingestion (except for allow_behind_true, which will always get assigned as the `kReservedEpochNumberForFileIngestedBehind`)
- Compaction output file is assigned with the minimum `epoch_number` among input files'
- Refit level: reuse refitted file's epoch_number
- Other paths needing `epoch_number` treatment:
- Import column families: reuse file's epoch_number if exists. If not, assign one based on `NewestFirstBySeqNo`
- Repair: reuse file's epoch_number if exists. If not, assign one based on `NewestFirstBySeqNo`.
- Assigning new epoch_number to a file and adding this file to LSM tree should be atomic. This is guaranteed by us assigning epoch_number right upon `VersionEdit::AddFile()` where this version edit will be apply to LSM tree shape right after by holding the db mutex (e.g, flush, file ingestion, import column family) or by there is only 1 ongoing edit per CF (e.g, WriteLevel0TableForRecovery, Repair).
- Assigning the minimum input epoch number to compaction output file won't misorder L0 files (even through later `Refit(target_level=0)`). It's due to for every key "k" in the input range, a legit compaction will cover a continuous epoch number range of that key. As long as we assign the key "k" the minimum input epoch number, it won't become newer or older than the versions of this key that aren't included in this compaction hence no misorder.
- Persist `epoch_number` of each file in manifest and recover `epoch_number` on db recovery
- Backward compatibility with old db without `epoch_number` support is guaranteed by assigning `epoch_number` to recovered files by `NewestFirstBySeqno` order. See `VersionStorageInfo::RecoverEpochNumbers()` for more
- Forward compatibility with manifest is guaranteed by flexibility of `NewFileCustomTag`
- Replace `force_consistent_check` on L0 with `epoch_number` and remove false positive check like case 1 with `largest_seqno` above
- Due to backward compatibility issue, we might encounter files with missing epoch number at the beginning of db recovery. We will still use old L0 sorting mechanism (`NewestFirstBySeqno`) to check/sort them till we infer their epoch number. See usages of `EpochNumberRequirement`.
- Remove fix https://github.com/facebook/rocksdb/pull/5958#issue-511150930 and their outdated tests to file reordering corruption because such fix can be replaced by this PR.
- Misc:
- update existing tests with `epoch_number` so make check will pass
- update https://github.com/facebook/rocksdb/pull/5958#issue-511150930 tests to verify corruption is fixed using `epoch_number` and cover universal/fifo compaction/CompactRange/CompactFile cases
- assert db_mutex is held for a few places before calling ColumnFamilyData::NewEpochNumber()
Pull Request resolved: https://github.com/facebook/rocksdb/pull/10922
Test Plan:
- `make check`
- New unit tests under `db/db_compaction_test.cc`, `db/db_test2.cc`, `db/version_builder_test.cc`, `db/repair_test.cc`
- Updated tests (i.e, `DBCompactionTestL0FilesMisorderCorruption*`) under https://github.com/facebook/rocksdb/pull/5958#issue-511150930
- [Ongoing] Compatibility test: manually run https://github.com/ajkr/rocksdb/commit/36a5686ec012f35a4371e409aa85c404ca1c210d (with file ingestion off for running the `.orig` binary to prevent this bug affecting upgrade/downgrade formality checking) for 1 hour on `simple black/white box`, `cf_consistency/txn/enable_ts with whitebox + test_best_efforts_recovery with blackbox`
- [Ongoing] normal db stress test
- [Ongoing] db stress test with aggressive value https://github.com/facebook/rocksdb/pull/10761
Reviewed By: ajkr
Differential Revision: D41063187
Pulled By: hx235
fbshipit-source-id: 826cb23455de7beaabe2d16c57682a82733a32a9
2 years ago
|
|
|
live_file_metadata.epoch_number = file_metadata.epoch_number;
|
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
6 years ago
|
|
|
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;
|
|
|
|
}
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|
|
|
|
|