rocksdb/monitoring/thread_status_updater.h

234 lines
8.5 KiB
C
Raw Normal View History

// 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).
//
// The implementation of ThreadStatus.
//
// Note that we make get and set access to ThreadStatusData lockless.
// As a result, ThreadStatusData as a whole is not atomic. However,
// we guarantee consistent ThreadStatusData all the time whenever
// user call GetThreadList(). This consistency guarantee is done
// by having the following constraint in the internal implementation
// of set and get order:
//
// 1. When reset any information in ThreadStatusData, always start from
// clearing up the lower-level information first.
// 2. When setting any information in ThreadStatusData, always start from
// setting the higher-level information.
// 3. When returning ThreadStatusData to the user, fields are fetched from
// higher-level to lower-level. In addition, where there's a nullptr
// in one field, then all fields that has lower-level than that field
// should be ignored.
//
// The high to low level information would be:
// thread_id > thread_type > db > cf > operation > state
//
// This means user might not always get full information, but whenever
// returned by the GetThreadList() is guaranteed to be consistent.
#pragma once
#include <atomic>
#include <list>
#include <memory>
#include <mutex>
#include <string>
#include <unordered_map>
#include <unordered_set>
#include <vector>
#include "rocksdb/status.h"
#include "rocksdb/thread_status.h"
#include "port/port.h"
#include "util/thread_operation.h"
namespace rocksdb {
class ColumnFamilyHandle;
// The structure that keeps constant information about a column family.
struct ConstantColumnFamilyInfo {
#ifdef ROCKSDB_USING_THREAD_STATUS
public:
ConstantColumnFamilyInfo(
const void* _db_key,
const std::string& _db_name,
const std::string& _cf_name) :
db_key(_db_key), db_name(_db_name), cf_name(_cf_name) {}
const void* db_key;
const std::string db_name;
const std::string cf_name;
#endif // ROCKSDB_USING_THREAD_STATUS
};
// the internal data-structure that is used to reflect the current
// status of a thread using a set of atomic pointers.
struct ThreadStatusData {
#ifdef ROCKSDB_USING_THREAD_STATUS
explicit ThreadStatusData() : enable_tracking(false) {
thread_id.store(0);
thread_type.store(ThreadStatus::USER);
cf_key.store(nullptr);
operation_type.store(ThreadStatus::OP_UNKNOWN);
op_start_time.store(0);
state_type.store(ThreadStatus::STATE_UNKNOWN);
}
// A flag to indicate whether the thread tracking is enabled
// in the current thread. This value will be updated based on whether
// the associated Options::enable_thread_tracking is set to true
// in ThreadStatusUtil::SetColumnFamily().
//
// If set to false, then SetThreadOperation and SetThreadState
// will be no-op.
bool enable_tracking;
std::atomic<uint64_t> thread_id;
std::atomic<ThreadStatus::ThreadType> thread_type;
std::atomic<void*> cf_key;
std::atomic<ThreadStatus::OperationType> operation_type;
Report elapsed time in micros in ThreadStatus instead of start time. Summary: Report elapsed time of a thread operation in micros in ThreadStatus instead of start time of a thread operation in seconds since the Epoch, 1970-01-01 00:00:00 (UTC). Test Plan: ./db_bench --benchmarks=fillrandom --num=100000 --threads=40 \ --max_background_compactions=10 --max_background_flushes=3 \ --thread_status_per_interval=1000 --key_size=16 --value_size=1000 \ --num_column_families=10 Sample Output: ThreadID ThreadType cfName Operation ElapsedTime Stage State 140667724562496 High Pri column_family_name_000002 Flush 772.419 ms FlushJob::WriteLevel0Table 140667728756800 High Pri default Flush 617.845 ms FlushJob::WriteLevel0Table 140667732951104 High Pri column_family_name_000005 Flush 772.078 ms FlushJob::WriteLevel0Table 140667875557440 Low Pri column_family_name_000008 Compaction 1409.216 ms CompactionJob::Install 140667737145408 Low Pri 140667749728320 Low Pri 140667816837184 Low Pri column_family_name_000007 Compaction 1071.815 ms CompactionJob::ProcessKeyValueCompaction 140667787477056 Low Pri column_family_name_000009 Compaction 772.516 ms CompactionJob::ProcessKeyValueCompaction 140667741339712 Low Pri 140667758116928 Low Pri column_family_name_000004 Compaction 620.739 ms CompactionJob::ProcessKeyValueCompaction 140667753922624 Low Pri 140667842003008 Low Pri column_family_name_000006 Compaction 1260.079 ms CompactionJob::ProcessKeyValueCompaction 140667745534016 Low Pri Reviewers: sdong, igor, rven Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D35769
2015-03-23 23:35:04 +00:00
std::atomic<uint64_t> op_start_time;
Allow GetThreadList() to report operation stage. Summary: Allow GetThreadList() to report operation stage. Test Plan: ./thread_list_test ./db_bench --benchmarks=fillrandom --num=100000 --threads=40 \ --max_background_compactions=10 --max_background_flushes=3 \ --thread_status_per_interval=1000 --key_size=16 --value_size=1000 \ --num_column_families=10 export ROCKSDB_TESTS=ThreadStatus ./db_test Sample output ThreadID ThreadType cfName Operation OP_StartTime ElapsedTime Stage State 140116265861184 Low Pri 140116270055488 Low Pri 140116274249792 High Pri column_family_name_000005 Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116400078912 Low Pri column_family_name_000004 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116358135872 Low Pri column_family_name_000006 Compaction 2015/03/10-14:58:10 1 us CompactionJob::FinishCompactionOutputFile 140116341358656 Low Pri 140116295221312 High Pri default Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116324581440 Low Pri column_family_name_000009 Compaction 2015/03/10-14:58:11 0 us CompactionJob::ProcessKeyValueCompaction 140116278444096 Low Pri 140116299415616 Low Pri column_family_name_000008 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116291027008 High Pri column_family_name_000001 Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116286832704 Low Pri column_family_name_000002 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116282638400 Low Pri Reviewers: rven, igor, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D34683
2015-03-13 17:45:40 +00:00
std::atomic<ThreadStatus::OperationStage> operation_stage;
Allow GetThreadList() to report basic compaction operation properties. Summary: Now we're able to show more details about a compaction in GetThreadList() :) This patch allows GetThreadList() to report basic compaction operation properties. Basic compaction properties include: 1. job id 2. compaction input / output level 3. compaction property flags (is_manual, is_deletion, .. etc) 4. total input bytes 5. the number of bytes has been read currently. 6. the number of bytes has been written currently. Flush operation properties will be done in a seperate diff. Test Plan: /db_bench --threads=30 --num=1000000 --benchmarks=fillrandom --thread_status_per_interval=1 Sample output of tracking same job: ThreadID ThreadType cfName Operation ElapsedTime Stage State OperationProperties 140664171987072 Low Pri default Compaction 31.357 ms CompactionJob::FinishCompactionOutputFile BaseInputLevel 1 | BytesRead 2264663 | BytesWritten 1934241 | IsDeletion 0 | IsManual 0 | IsTrivialMove 0 | JobID 277 | OutputLevel 2 | TotalInputBytes 3964158 | ThreadID ThreadType cfName Operation ElapsedTime Stage State OperationProperties 140664171987072 Low Pri default Compaction 59.440 ms CompactionJob::FinishCompactionOutputFile BaseInputLevel 1 | BytesRead 2264663 | BytesWritten 1934241 | IsDeletion 0 | IsManual 0 | IsTrivialMove 0 | JobID 277 | OutputLevel 2 | TotalInputBytes 3964158 | ThreadID ThreadType cfName Operation ElapsedTime Stage State OperationProperties 140664171987072 Low Pri default Compaction 226.375 ms CompactionJob::Install BaseInputLevel 1 | BytesRead 3958013 | BytesWritten 3621940 | IsDeletion 0 | IsManual 0 | IsTrivialMove 0 | JobID 277 | OutputLevel 2 | TotalInputBytes 3964158 | Reviewers: sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D37653
2015-05-07 05:50:35 +00:00
std::atomic<uint64_t> op_properties[ThreadStatus::kNumOperationProperties];
std::atomic<ThreadStatus::StateType> state_type;
#endif // ROCKSDB_USING_THREAD_STATUS
};
// The class that stores and updates the status of the current thread
// using a thread-local ThreadStatusData.
//
// In most of the case, you should use ThreadStatusUtil to update
// the status of the current thread instead of using ThreadSatusUpdater
// directly.
//
// @see ThreadStatusUtil
class ThreadStatusUpdater {
public:
ThreadStatusUpdater() {}
// Releases all ThreadStatusData of all active threads.
virtual ~ThreadStatusUpdater() {}
// Unregister the current thread.
void UnregisterThread();
// Reset the status of the current thread. This includes resetting
// ColumnFamilyInfoKey, ThreadOperation, and ThreadState.
void ResetThreadStatus();
// Set the id of the current thread.
void SetThreadID(uint64_t thread_id);
// Register the current thread for tracking.
void RegisterThread(ThreadStatus::ThreadType ttype, uint64_t thread_id);
// Update the column-family info of the current thread by setting
// its thread-local pointer of ThreadStateInfo to the correct entry.
void SetColumnFamilyInfoKey(const void* cf_key);
// returns the column family info key.
const void* GetColumnFamilyInfoKey();
// Update the thread operation of the current thread.
void SetThreadOperation(const ThreadStatus::OperationType type);
Report elapsed time in micros in ThreadStatus instead of start time. Summary: Report elapsed time of a thread operation in micros in ThreadStatus instead of start time of a thread operation in seconds since the Epoch, 1970-01-01 00:00:00 (UTC). Test Plan: ./db_bench --benchmarks=fillrandom --num=100000 --threads=40 \ --max_background_compactions=10 --max_background_flushes=3 \ --thread_status_per_interval=1000 --key_size=16 --value_size=1000 \ --num_column_families=10 Sample Output: ThreadID ThreadType cfName Operation ElapsedTime Stage State 140667724562496 High Pri column_family_name_000002 Flush 772.419 ms FlushJob::WriteLevel0Table 140667728756800 High Pri default Flush 617.845 ms FlushJob::WriteLevel0Table 140667732951104 High Pri column_family_name_000005 Flush 772.078 ms FlushJob::WriteLevel0Table 140667875557440 Low Pri column_family_name_000008 Compaction 1409.216 ms CompactionJob::Install 140667737145408 Low Pri 140667749728320 Low Pri 140667816837184 Low Pri column_family_name_000007 Compaction 1071.815 ms CompactionJob::ProcessKeyValueCompaction 140667787477056 Low Pri column_family_name_000009 Compaction 772.516 ms CompactionJob::ProcessKeyValueCompaction 140667741339712 Low Pri 140667758116928 Low Pri column_family_name_000004 Compaction 620.739 ms CompactionJob::ProcessKeyValueCompaction 140667753922624 Low Pri 140667842003008 Low Pri column_family_name_000006 Compaction 1260.079 ms CompactionJob::ProcessKeyValueCompaction 140667745534016 Low Pri Reviewers: sdong, igor, rven Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D35769
2015-03-23 23:35:04 +00:00
// The start time of the current thread operation. It is in the format
// of micro-seconds since some fixed point in time.
void SetOperationStartTime(const uint64_t start_time);
Allow GetThreadList() to report basic compaction operation properties. Summary: Now we're able to show more details about a compaction in GetThreadList() :) This patch allows GetThreadList() to report basic compaction operation properties. Basic compaction properties include: 1. job id 2. compaction input / output level 3. compaction property flags (is_manual, is_deletion, .. etc) 4. total input bytes 5. the number of bytes has been read currently. 6. the number of bytes has been written currently. Flush operation properties will be done in a seperate diff. Test Plan: /db_bench --threads=30 --num=1000000 --benchmarks=fillrandom --thread_status_per_interval=1 Sample output of tracking same job: ThreadID ThreadType cfName Operation ElapsedTime Stage State OperationProperties 140664171987072 Low Pri default Compaction 31.357 ms CompactionJob::FinishCompactionOutputFile BaseInputLevel 1 | BytesRead 2264663 | BytesWritten 1934241 | IsDeletion 0 | IsManual 0 | IsTrivialMove 0 | JobID 277 | OutputLevel 2 | TotalInputBytes 3964158 | ThreadID ThreadType cfName Operation ElapsedTime Stage State OperationProperties 140664171987072 Low Pri default Compaction 59.440 ms CompactionJob::FinishCompactionOutputFile BaseInputLevel 1 | BytesRead 2264663 | BytesWritten 1934241 | IsDeletion 0 | IsManual 0 | IsTrivialMove 0 | JobID 277 | OutputLevel 2 | TotalInputBytes 3964158 | ThreadID ThreadType cfName Operation ElapsedTime Stage State OperationProperties 140664171987072 Low Pri default Compaction 226.375 ms CompactionJob::Install BaseInputLevel 1 | BytesRead 3958013 | BytesWritten 3621940 | IsDeletion 0 | IsManual 0 | IsTrivialMove 0 | JobID 277 | OutputLevel 2 | TotalInputBytes 3964158 | Reviewers: sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D37653
2015-05-07 05:50:35 +00:00
// Set the "i"th property of the current operation.
//
// NOTE: Our practice here is to set all the thread operation properties
// and stage before we set thread operation, and thread operation
// will be set in std::memory_order_release. This is to ensure
// whenever a thread operation is not OP_UNKNOWN, we will always
// have a consistent information on its properties.
void SetThreadOperationProperty(
int i, uint64_t value);
// Increase the "i"th property of the current operation with
// the specified delta.
void IncreaseThreadOperationProperty(
int i, uint64_t delta);
Allow GetThreadList() to report operation stage. Summary: Allow GetThreadList() to report operation stage. Test Plan: ./thread_list_test ./db_bench --benchmarks=fillrandom --num=100000 --threads=40 \ --max_background_compactions=10 --max_background_flushes=3 \ --thread_status_per_interval=1000 --key_size=16 --value_size=1000 \ --num_column_families=10 export ROCKSDB_TESTS=ThreadStatus ./db_test Sample output ThreadID ThreadType cfName Operation OP_StartTime ElapsedTime Stage State 140116265861184 Low Pri 140116270055488 Low Pri 140116274249792 High Pri column_family_name_000005 Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116400078912 Low Pri column_family_name_000004 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116358135872 Low Pri column_family_name_000006 Compaction 2015/03/10-14:58:10 1 us CompactionJob::FinishCompactionOutputFile 140116341358656 Low Pri 140116295221312 High Pri default Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116324581440 Low Pri column_family_name_000009 Compaction 2015/03/10-14:58:11 0 us CompactionJob::ProcessKeyValueCompaction 140116278444096 Low Pri 140116299415616 Low Pri column_family_name_000008 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116291027008 High Pri column_family_name_000001 Flush 2015/03/10-14:58:11 0 us FlushJob::WriteLevel0Table 140116286832704 Low Pri column_family_name_000002 Compaction 2015/03/10-14:58:11 0 us CompactionJob::FinishCompactionOutputFile 140116282638400 Low Pri Reviewers: rven, igor, sdong Reviewed By: sdong Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D34683
2015-03-13 17:45:40 +00:00
// Update the thread operation stage of the current thread.
ThreadStatus::OperationStage SetThreadOperationStage(
const ThreadStatus::OperationStage stage);
// Clear thread operation of the current thread.
void ClearThreadOperation();
Allow GetThreadList() to report basic compaction operation properties. Summary: Now we're able to show more details about a compaction in GetThreadList() :) This patch allows GetThreadList() to report basic compaction operation properties. Basic compaction properties include: 1. job id 2. compaction input / output level 3. compaction property flags (is_manual, is_deletion, .. etc) 4. total input bytes 5. the number of bytes has been read currently. 6. the number of bytes has been written currently. Flush operation properties will be done in a seperate diff. Test Plan: /db_bench --threads=30 --num=1000000 --benchmarks=fillrandom --thread_status_per_interval=1 Sample output of tracking same job: ThreadID ThreadType cfName Operation ElapsedTime Stage State OperationProperties 140664171987072 Low Pri default Compaction 31.357 ms CompactionJob::FinishCompactionOutputFile BaseInputLevel 1 | BytesRead 2264663 | BytesWritten 1934241 | IsDeletion 0 | IsManual 0 | IsTrivialMove 0 | JobID 277 | OutputLevel 2 | TotalInputBytes 3964158 | ThreadID ThreadType cfName Operation ElapsedTime Stage State OperationProperties 140664171987072 Low Pri default Compaction 59.440 ms CompactionJob::FinishCompactionOutputFile BaseInputLevel 1 | BytesRead 2264663 | BytesWritten 1934241 | IsDeletion 0 | IsManual 0 | IsTrivialMove 0 | JobID 277 | OutputLevel 2 | TotalInputBytes 3964158 | ThreadID ThreadType cfName Operation ElapsedTime Stage State OperationProperties 140664171987072 Low Pri default Compaction 226.375 ms CompactionJob::Install BaseInputLevel 1 | BytesRead 3958013 | BytesWritten 3621940 | IsDeletion 0 | IsManual 0 | IsTrivialMove 0 | JobID 277 | OutputLevel 2 | TotalInputBytes 3964158 | Reviewers: sdong, rven, igor Reviewed By: igor Subscribers: dhruba, leveldb Differential Revision: https://reviews.facebook.net/D37653
2015-05-07 05:50:35 +00:00
// Reset all thread-operation-properties to 0.
void ClearThreadOperationProperties();
// Update the thread state of the current thread.
void SetThreadState(const ThreadStatus::StateType type);
// Clear the thread state of the current thread.
void ClearThreadState();
// Obtain the status of all active registered threads.
Status GetThreadList(
std::vector<ThreadStatus>* thread_list);
// Create an entry in the global ColumnFamilyInfo table for the
// specified column family. This function should be called only
// when the current thread does not hold db_mutex.
void NewColumnFamilyInfo(
const void* db_key, const std::string& db_name,
const void* cf_key, const std::string& cf_name);
// Erase all ConstantColumnFamilyInfo that is associated with the
// specified db instance. This function should be called only when
// the current thread does not hold db_mutex.
void EraseDatabaseInfo(const void* db_key);
// Erase the ConstantColumnFamilyInfo that is associated with the
// specified ColumnFamilyData. This function should be called only
// when the current thread does not hold db_mutex.
void EraseColumnFamilyInfo(const void* cf_key);
// Verifies whether the input ColumnFamilyHandles matches
// the information stored in the current cf_info_map.
void TEST_VerifyColumnFamilyInfoMap(
const std::vector<ColumnFamilyHandle*>& handles,
bool check_exist);
protected:
#ifdef ROCKSDB_USING_THREAD_STATUS
// The thread-local variable for storing thread status.
static __thread ThreadStatusData* thread_status_data_;
// Returns the pointer to the thread status data only when the
// thread status data is non-null and has enable_tracking == true.
ThreadStatusData* GetLocalThreadStatus();
// Directly returns the pointer to thread_status_data_ without
// checking whether enabling_tracking is true of not.
ThreadStatusData* Get() {
return thread_status_data_;
}
// The mutex that protects cf_info_map and db_key_map.
std::mutex thread_list_mutex_;
// The current status data of all active threads.
std::unordered_set<ThreadStatusData*> thread_data_set_;
// A global map that keeps the column family information. It is stored
// globally instead of inside DB is to avoid the situation where DB is
// closing while GetThreadList function already get the pointer to its
// CopnstantColumnFamilyInfo.
std::unordered_map<const void*, ConstantColumnFamilyInfo> cf_info_map_;
// A db_key to cf_key map that allows erasing elements in cf_info_map
// associated to the same db_key faster.
std::unordered_map<
const void*, std::unordered_set<const void*>> db_key_map_;
#else
static ThreadStatusData* thread_status_data_;
#endif // ROCKSDB_USING_THREAD_STATUS
};
} // namespace rocksdb