mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-30 04:41:49 +00:00
06e593376c
Summary: ## Context/Summary Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity. For that, this PR does the following: - Tag different write IOs by passing down and converting WriteOptions to IOOptions - Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS Some related code refactory to make implementation cleaner: - Blob stats - Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info. - Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write. - Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority - Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification - Build table - TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables - Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder. This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more - Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority ## Test ### db bench Flush ``` ./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100 rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 ``` compaction, db oopen ``` Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279 rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213 rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66 ``` blob stats - just to make sure they aren't broken by this PR ``` Integrated Blob DB Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600 rocksdb.blobdb.blob.file.synced COUNT : 1 rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same) ``` ``` Stacked Blob DB Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876 rocksdb.blobdb.blob.file.synced COUNT : 8 rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same) ``` ### Rehearsal CI stress test Trigger 3 full runs of all our CI stress tests ### Performance Flush ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark; enable_statistics = true Pre-pr: avg 507515519.3 ns 497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908, Post-pr: avg 511971266.5 ns, regressed 0.88% 502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408, ``` Compaction ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 495346098.30 ns 492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846 Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97% 502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007 ``` Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats) ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 3848.10 ns 3814,3838,3839,3848,3854,3854,3854,3860,3860,3860 Post-pr: avg 3874.20 ns, regressed 0.68% 3863,3867,3871,3874,3875,3877,3877,3877,3880,3881 ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910 Reviewed By: ajkr Differential Revision: D49788060 Pulled By: hx235 fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
460 lines
17 KiB
C++
460 lines
17 KiB
C++
// Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
//
|
|
// 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).
|
|
|
|
#include "db/version_builder.h"
|
|
|
|
#include "db/import_column_family_job.h"
|
|
|
|
#include <algorithm>
|
|
#include <cinttypes>
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
#include "db/version_edit.h"
|
|
#include "file/file_util.h"
|
|
#include "file/random_access_file_reader.h"
|
|
#include "logging/logging.h"
|
|
#include "table/merging_iterator.h"
|
|
#include "table/scoped_arena_iterator.h"
|
|
#include "table/sst_file_writer_collectors.h"
|
|
#include "table/table_builder.h"
|
|
#include "table/unique_id_impl.h"
|
|
#include "util/stop_watch.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
Status ImportColumnFamilyJob::Prepare(uint64_t next_file_number,
|
|
SuperVersion* sv) {
|
|
Status status;
|
|
std::vector<ColumnFamilyIngestFileInfo> cf_ingest_infos;
|
|
for (const auto& metadata_per_cf : metadatas_) {
|
|
// Read the information of files we are importing
|
|
ColumnFamilyIngestFileInfo cf_file_info;
|
|
InternalKey smallest, largest;
|
|
int num_files = 0;
|
|
std::vector<IngestedFileInfo> files_to_import_per_cf;
|
|
for (size_t i = 0; i < metadata_per_cf.size(); i++) {
|
|
auto file_metadata = *metadata_per_cf[i];
|
|
const auto file_path = file_metadata.db_path + "/" + file_metadata.name;
|
|
IngestedFileInfo file_to_import;
|
|
status = GetIngestedFileInfo(file_path, next_file_number++, sv,
|
|
file_metadata, &file_to_import);
|
|
if (!status.ok()) {
|
|
return status;
|
|
}
|
|
|
|
if (file_to_import.num_entries == 0) {
|
|
status = Status::InvalidArgument("File contain no entries");
|
|
return status;
|
|
}
|
|
|
|
if (!file_to_import.smallest_internal_key.Valid() ||
|
|
!file_to_import.largest_internal_key.Valid()) {
|
|
status = Status::Corruption("File has corrupted keys");
|
|
return status;
|
|
}
|
|
|
|
files_to_import_per_cf.push_back(file_to_import);
|
|
num_files++;
|
|
|
|
// Calculate the smallest and largest keys of all files in this CF
|
|
if (i == 0) {
|
|
smallest = file_to_import.smallest_internal_key;
|
|
largest = file_to_import.largest_internal_key;
|
|
} else {
|
|
if (cfd_->internal_comparator().Compare(
|
|
smallest, file_to_import.smallest_internal_key) < 0) {
|
|
smallest = file_to_import.smallest_internal_key;
|
|
}
|
|
if (cfd_->internal_comparator().Compare(
|
|
largest, file_to_import.largest_internal_key) > 0) {
|
|
largest = file_to_import.largest_internal_key;
|
|
}
|
|
}
|
|
}
|
|
|
|
if (num_files == 0) {
|
|
status = Status::InvalidArgument("The list of files is empty");
|
|
return status;
|
|
}
|
|
files_to_import_.push_back(files_to_import_per_cf);
|
|
cf_file_info.smallest_internal_key = smallest;
|
|
cf_file_info.largest_internal_key = largest;
|
|
cf_ingest_infos.push_back(cf_file_info);
|
|
}
|
|
|
|
std::sort(cf_ingest_infos.begin(), cf_ingest_infos.end(),
|
|
[this](const ColumnFamilyIngestFileInfo& info1,
|
|
const ColumnFamilyIngestFileInfo& info2) {
|
|
return cfd_->user_comparator()->Compare(
|
|
info1.smallest_internal_key.user_key(),
|
|
info2.smallest_internal_key.user_key()) < 0;
|
|
});
|
|
|
|
for (size_t i = 0; i + 1 < cf_ingest_infos.size(); i++) {
|
|
if (cfd_->user_comparator()->Compare(
|
|
cf_ingest_infos[i].largest_internal_key.user_key(),
|
|
cf_ingest_infos[i + 1].smallest_internal_key.user_key()) >= 0) {
|
|
status = Status::InvalidArgument("CFs have overlapping ranges");
|
|
return status;
|
|
}
|
|
}
|
|
|
|
// Copy/Move external files into DB
|
|
auto hardlink_files = import_options_.move_files;
|
|
|
|
for (auto& files_to_import_per_cf : files_to_import_) {
|
|
for (auto& f : files_to_import_per_cf) {
|
|
const auto path_outside_db = f.external_file_path;
|
|
const auto path_inside_db = TableFileName(
|
|
cfd_->ioptions()->cf_paths, f.fd.GetNumber(), f.fd.GetPathId());
|
|
|
|
if (hardlink_files) {
|
|
status = fs_->LinkFile(path_outside_db, path_inside_db, IOOptions(),
|
|
nullptr);
|
|
if (status.IsNotSupported()) {
|
|
// Original file is on a different FS, use copy instead of hard
|
|
// linking
|
|
hardlink_files = false;
|
|
ROCKS_LOG_INFO(db_options_.info_log,
|
|
"Try to link file %s but it's not supported : %s",
|
|
f.internal_file_path.c_str(),
|
|
status.ToString().c_str());
|
|
}
|
|
}
|
|
if (!hardlink_files) {
|
|
status =
|
|
CopyFile(fs_.get(), path_outside_db, path_inside_db, 0,
|
|
db_options_.use_fsync, io_tracer_, Temperature::kUnknown);
|
|
}
|
|
if (!status.ok()) {
|
|
break;
|
|
}
|
|
f.copy_file = !hardlink_files;
|
|
f.internal_file_path = path_inside_db;
|
|
}
|
|
if (!status.ok()) {
|
|
break;
|
|
}
|
|
}
|
|
|
|
if (!status.ok()) {
|
|
// We failed, remove all files that we copied into the db
|
|
for (auto& files_to_import_per_cf : files_to_import_) {
|
|
for (auto& f : files_to_import_per_cf) {
|
|
if (f.internal_file_path.empty()) {
|
|
break;
|
|
}
|
|
const auto s =
|
|
fs_->DeleteFile(f.internal_file_path, IOOptions(), nullptr);
|
|
if (!s.ok()) {
|
|
ROCKS_LOG_WARN(db_options_.info_log,
|
|
"AddFile() clean up for file %s failed : %s",
|
|
f.internal_file_path.c_str(), s.ToString().c_str());
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
return status;
|
|
}
|
|
|
|
// REQUIRES: we have become the only writer by entering both write_thread_ and
|
|
// nonmem_write_thread_
|
|
Status ImportColumnFamilyJob::Run() {
|
|
// We use the import time as the ancester time. This is the time the data
|
|
// is written to the database.
|
|
int64_t temp_current_time = 0;
|
|
uint64_t oldest_ancester_time = kUnknownOldestAncesterTime;
|
|
uint64_t current_time = kUnknownOldestAncesterTime;
|
|
if (clock_->GetCurrentTime(&temp_current_time).ok()) {
|
|
current_time = oldest_ancester_time =
|
|
static_cast<uint64_t>(temp_current_time);
|
|
}
|
|
|
|
// Recover files' epoch number using dummy VersionStorageInfo
|
|
VersionBuilder dummy_version_builder(
|
|
cfd_->current()->version_set()->file_options(), cfd_->ioptions(),
|
|
cfd_->table_cache(), cfd_->current()->storage_info(),
|
|
cfd_->current()->version_set(),
|
|
cfd_->GetFileMetadataCacheReservationManager());
|
|
VersionStorageInfo dummy_vstorage(
|
|
&cfd_->internal_comparator(), cfd_->user_comparator(),
|
|
cfd_->NumberLevels(), cfd_->ioptions()->compaction_style,
|
|
nullptr /* src_vstorage */, cfd_->ioptions()->force_consistency_checks,
|
|
EpochNumberRequirement::kMightMissing, cfd_->ioptions()->clock,
|
|
cfd_->GetLatestMutableCFOptions()->bottommost_file_compaction_delay,
|
|
cfd_->current()->version_set()->offpeak_time_option());
|
|
Status s;
|
|
|
|
for (size_t i = 0; s.ok() && i < files_to_import_.size(); ++i) {
|
|
for (size_t j = 0; s.ok() && j < files_to_import_[i].size(); ++j) {
|
|
const auto& f = files_to_import_[i][j];
|
|
const auto& file_metadata = *metadatas_[i][j];
|
|
|
|
uint64_t tail_size = 0;
|
|
bool contain_no_data_blocks = f.table_properties.num_entries > 0 &&
|
|
(f.table_properties.num_entries ==
|
|
f.table_properties.num_range_deletions);
|
|
if (f.table_properties.tail_start_offset > 0 || contain_no_data_blocks) {
|
|
uint64_t file_size = f.fd.GetFileSize();
|
|
assert(f.table_properties.tail_start_offset <= file_size);
|
|
tail_size = file_size - f.table_properties.tail_start_offset;
|
|
}
|
|
|
|
VersionEdit dummy_version_edit;
|
|
dummy_version_edit.AddFile(
|
|
file_metadata.level, f.fd.GetNumber(), f.fd.GetPathId(),
|
|
f.fd.GetFileSize(), f.smallest_internal_key, f.largest_internal_key,
|
|
file_metadata.smallest_seqno, file_metadata.largest_seqno, false,
|
|
file_metadata.temperature, kInvalidBlobFileNumber,
|
|
oldest_ancester_time, current_time, file_metadata.epoch_number,
|
|
kUnknownFileChecksum, kUnknownFileChecksumFuncName, f.unique_id, 0,
|
|
tail_size,
|
|
static_cast<bool>(
|
|
f.table_properties.user_defined_timestamps_persisted));
|
|
s = dummy_version_builder.Apply(&dummy_version_edit);
|
|
}
|
|
}
|
|
|
|
if (s.ok()) {
|
|
s = dummy_version_builder.SaveTo(&dummy_vstorage);
|
|
}
|
|
if (s.ok()) {
|
|
dummy_vstorage.RecoverEpochNumbers(cfd_);
|
|
}
|
|
|
|
// Record changes from this CF import in VersionEdit, including files with
|
|
// recovered epoch numbers
|
|
if (s.ok()) {
|
|
edit_.SetColumnFamily(cfd_->GetID());
|
|
|
|
for (int level = 0; level < dummy_vstorage.num_levels(); level++) {
|
|
for (FileMetaData* file_meta : dummy_vstorage.LevelFiles(level)) {
|
|
edit_.AddFile(level, *file_meta);
|
|
// If incoming sequence number is higher, update local sequence number.
|
|
if (file_meta->fd.largest_seqno > versions_->LastSequence()) {
|
|
versions_->SetLastAllocatedSequence(file_meta->fd.largest_seqno);
|
|
versions_->SetLastPublishedSequence(file_meta->fd.largest_seqno);
|
|
versions_->SetLastSequence(file_meta->fd.largest_seqno);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
// Release resources occupied by the dummy VersionStorageInfo
|
|
for (int level = 0; level < dummy_vstorage.num_levels(); level++) {
|
|
for (FileMetaData* file_meta : dummy_vstorage.LevelFiles(level)) {
|
|
file_meta->refs--;
|
|
if (file_meta->refs <= 0) {
|
|
delete file_meta;
|
|
}
|
|
}
|
|
}
|
|
return s;
|
|
}
|
|
|
|
void ImportColumnFamilyJob::Cleanup(const Status& status) {
|
|
if (!status.ok()) {
|
|
// We failed to add files to the database remove all the files we copied.
|
|
for (auto& files_to_import_per_cf : files_to_import_) {
|
|
for (auto& f : files_to_import_per_cf) {
|
|
const auto s =
|
|
fs_->DeleteFile(f.internal_file_path, IOOptions(), nullptr);
|
|
if (!s.ok()) {
|
|
ROCKS_LOG_WARN(db_options_.info_log,
|
|
"AddFile() clean up for file %s failed : %s",
|
|
f.internal_file_path.c_str(), s.ToString().c_str());
|
|
}
|
|
}
|
|
}
|
|
} else if (status.ok() && import_options_.move_files) {
|
|
// The files were moved and added successfully, remove original file links
|
|
for (auto& files_to_import_per_cf : files_to_import_) {
|
|
for (auto& f : files_to_import_per_cf) {
|
|
const auto s =
|
|
fs_->DeleteFile(f.external_file_path, IOOptions(), nullptr);
|
|
if (!s.ok()) {
|
|
ROCKS_LOG_WARN(
|
|
db_options_.info_log,
|
|
"%s was added to DB successfully but failed to remove original "
|
|
"file link : %s",
|
|
f.external_file_path.c_str(), s.ToString().c_str());
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
Status ImportColumnFamilyJob::GetIngestedFileInfo(
|
|
const std::string& external_file, uint64_t new_file_number,
|
|
SuperVersion* sv, const LiveFileMetaData& file_meta,
|
|
IngestedFileInfo* file_to_import) {
|
|
file_to_import->external_file_path = external_file;
|
|
Status status;
|
|
if (file_meta.size > 0) {
|
|
file_to_import->file_size = file_meta.size;
|
|
} else {
|
|
// Get external file size
|
|
status = fs_->GetFileSize(external_file, IOOptions(),
|
|
&file_to_import->file_size, nullptr);
|
|
if (!status.ok()) {
|
|
return status;
|
|
}
|
|
}
|
|
// Assign FD with number
|
|
file_to_import->fd =
|
|
FileDescriptor(new_file_number, 0, file_to_import->file_size);
|
|
|
|
// Create TableReader for external file
|
|
std::unique_ptr<TableReader> table_reader;
|
|
std::unique_ptr<FSRandomAccessFile> sst_file;
|
|
std::unique_ptr<RandomAccessFileReader> sst_file_reader;
|
|
|
|
status =
|
|
fs_->NewRandomAccessFile(external_file, env_options_, &sst_file, nullptr);
|
|
if (!status.ok()) {
|
|
return status;
|
|
}
|
|
sst_file_reader.reset(new RandomAccessFileReader(
|
|
std::move(sst_file), external_file, nullptr /*Env*/, io_tracer_));
|
|
|
|
// TODO(yuzhangyu): User-defined timestamps doesn't support importing column
|
|
// family. Pass in the correct `user_defined_timestamps_persisted` flag for
|
|
// creating `TableReaderOptions` when the support is there.
|
|
status = cfd_->ioptions()->table_factory->NewTableReader(
|
|
TableReaderOptions(
|
|
*cfd_->ioptions(), sv->mutable_cf_options.prefix_extractor,
|
|
env_options_, cfd_->internal_comparator(),
|
|
sv->mutable_cf_options.block_protection_bytes_per_key,
|
|
/*skip_filters*/ false, /*immortal*/ false,
|
|
/*force_direct_prefetch*/ false, /*level*/ -1,
|
|
/*block_cache_tracer*/ nullptr,
|
|
/*max_file_size_for_l0_meta_pin*/ 0, versions_->DbSessionId(),
|
|
/*cur_file_num*/ new_file_number),
|
|
std::move(sst_file_reader), file_to_import->file_size, &table_reader);
|
|
if (!status.ok()) {
|
|
return status;
|
|
}
|
|
|
|
// Get the external file properties
|
|
auto props = table_reader->GetTableProperties();
|
|
|
|
// Set original_seqno to 0.
|
|
file_to_import->original_seqno = 0;
|
|
|
|
// Get number of entries in table
|
|
file_to_import->num_entries = props->num_entries;
|
|
|
|
// If the importing files were exported with Checkpoint::ExportColumnFamily(),
|
|
// we cannot simply recompute smallest and largest used to truncate range
|
|
// tombstones from file content, and we expect smallest and largest populated
|
|
// in file_meta.
|
|
if (file_meta.smallest.empty()) {
|
|
assert(file_meta.largest.empty());
|
|
// TODO: plumb Env::IOActivity, Env::IOPriority
|
|
ReadOptions ro;
|
|
std::unique_ptr<InternalIterator> iter(table_reader->NewIterator(
|
|
ro, sv->mutable_cf_options.prefix_extractor.get(), /*arena=*/nullptr,
|
|
/*skip_filters=*/false, TableReaderCaller::kExternalSSTIngestion));
|
|
|
|
// Get first (smallest) key from file
|
|
iter->SeekToFirst();
|
|
bool bound_set = false;
|
|
if (iter->Valid()) {
|
|
file_to_import->smallest_internal_key.DecodeFrom(iter->key());
|
|
Slice largest;
|
|
if (strcmp(cfd_->ioptions()->table_factory->Name(), "PlainTable") == 0) {
|
|
// PlainTable iterator does not support SeekToLast().
|
|
largest = iter->key();
|
|
for (; iter->Valid(); iter->Next()) {
|
|
if (cfd_->internal_comparator().Compare(iter->key(), largest) > 0) {
|
|
largest = iter->key();
|
|
}
|
|
}
|
|
if (!iter->status().ok()) {
|
|
return iter->status();
|
|
}
|
|
} else {
|
|
iter->SeekToLast();
|
|
if (!iter->Valid()) {
|
|
if (iter->status().ok()) {
|
|
// The file contains at least 1 key since iter is valid after
|
|
// SeekToFirst().
|
|
return Status::Corruption("Can not find largest key in sst file");
|
|
} else {
|
|
return iter->status();
|
|
}
|
|
}
|
|
largest = iter->key();
|
|
}
|
|
file_to_import->largest_internal_key.DecodeFrom(largest);
|
|
bound_set = true;
|
|
} else if (!iter->status().ok()) {
|
|
return iter->status();
|
|
}
|
|
|
|
std::unique_ptr<InternalIterator> range_del_iter{
|
|
table_reader->NewRangeTombstoneIterator(ro)};
|
|
if (range_del_iter != nullptr) {
|
|
range_del_iter->SeekToFirst();
|
|
if (range_del_iter->Valid()) {
|
|
ParsedInternalKey key;
|
|
Status pik_status = ParseInternalKey(range_del_iter->key(), &key,
|
|
db_options_.allow_data_in_errors);
|
|
if (!pik_status.ok()) {
|
|
return Status::Corruption("Corrupted key in external file. ",
|
|
pik_status.getState());
|
|
}
|
|
RangeTombstone first_tombstone(key, range_del_iter->value());
|
|
InternalKey start_key = first_tombstone.SerializeKey();
|
|
const InternalKeyComparator* icmp = &cfd_->internal_comparator();
|
|
if (!bound_set ||
|
|
icmp->Compare(start_key, file_to_import->smallest_internal_key) <
|
|
0) {
|
|
file_to_import->smallest_internal_key = start_key;
|
|
}
|
|
|
|
range_del_iter->SeekToLast();
|
|
pik_status = ParseInternalKey(range_del_iter->key(), &key,
|
|
db_options_.allow_data_in_errors);
|
|
if (!pik_status.ok()) {
|
|
return Status::Corruption("Corrupted key in external file. ",
|
|
pik_status.getState());
|
|
}
|
|
RangeTombstone last_tombstone(key, range_del_iter->value());
|
|
InternalKey end_key = last_tombstone.SerializeEndKey();
|
|
if (!bound_set ||
|
|
icmp->Compare(end_key, file_to_import->largest_internal_key) > 0) {
|
|
file_to_import->largest_internal_key = end_key;
|
|
}
|
|
bound_set = true;
|
|
}
|
|
}
|
|
assert(bound_set);
|
|
} else {
|
|
assert(!file_meta.largest.empty());
|
|
file_to_import->smallest_internal_key.DecodeFrom(file_meta.smallest);
|
|
file_to_import->largest_internal_key.DecodeFrom(file_meta.largest);
|
|
}
|
|
|
|
file_to_import->cf_id = static_cast<uint32_t>(props->column_family_id);
|
|
|
|
file_to_import->table_properties = *props;
|
|
|
|
auto s = GetSstInternalUniqueId(props->db_id, props->db_session_id,
|
|
props->orig_file_number,
|
|
&(file_to_import->unique_id));
|
|
if (!s.ok()) {
|
|
ROCKS_LOG_WARN(db_options_.info_log,
|
|
"Failed to get SST unique id for file %s",
|
|
file_to_import->internal_file_path.c_str());
|
|
}
|
|
|
|
return status;
|
|
}
|
|
} // namespace ROCKSDB_NAMESPACE
|