EventLogger
Summary:
Here's my proposal for making our LOGs easier to read by machines.
The idea is to dump all events as JSON objects. JSON is easy to read by humans, but more importantly, it's easy to read by machines. That way, we can parse this, load into SQLite/mongo and then query or visualize.
I started with table_create and table_delete events, but if everybody agrees, I'll continue by adding more events (flush/compaction/etc etc)
Test Plan:
Ran db_bench. Observed:
2015/01/15-14:13:25.788019 1105ef000 EVENT_LOG_v1 {"time_micros": 1421360005788015, "event": "table_file_creation", "file_number": 12, "file_size": 1909699}
2015/01/15-14:13:25.956500 110740000 EVENT_LOG_v1 {"time_micros": 1421360005956498, "event": "table_file_deletion", "file_number": 12}
Reviewers: yhchiang, rven, dhruba, MarkCallaghan, lgalanis, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D31647
2015-03-13 17:15:54 +00:00
|
|
|
// Copyright (c) 2014, Facebook, Inc. All rights reserved.
|
|
|
|
// This source code is licensed under the BSD-style license found in the
|
|
|
|
// LICENSE file in the root directory of this source tree. An additional grant
|
|
|
|
// of patent rights can be found in the PATENTS file in the same directory.
|
|
|
|
|
|
|
|
#pragma once
|
|
|
|
|
|
|
|
#include <memory>
|
|
|
|
#include <sstream>
|
|
|
|
#include <string>
|
2015-03-13 17:29:32 +00:00
|
|
|
#include <chrono>
|
EventLogger
Summary:
Here's my proposal for making our LOGs easier to read by machines.
The idea is to dump all events as JSON objects. JSON is easy to read by humans, but more importantly, it's easy to read by machines. That way, we can parse this, load into SQLite/mongo and then query or visualize.
I started with table_create and table_delete events, but if everybody agrees, I'll continue by adding more events (flush/compaction/etc etc)
Test Plan:
Ran db_bench. Observed:
2015/01/15-14:13:25.788019 1105ef000 EVENT_LOG_v1 {"time_micros": 1421360005788015, "event": "table_file_creation", "file_number": 12, "file_size": 1909699}
2015/01/15-14:13:25.956500 110740000 EVENT_LOG_v1 {"time_micros": 1421360005956498, "event": "table_file_deletion", "file_number": 12}
Reviewers: yhchiang, rven, dhruba, MarkCallaghan, lgalanis, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D31647
2015-03-13 17:15:54 +00:00
|
|
|
|
|
|
|
#include "rocksdb/env.h"
|
Include bunch of more events into EventLogger
Summary:
Added these events:
* Recovery start, finish and also when recovery creates a file
* Trivial move
* Compaction start, finish and when compaction creates a file
* Flush start, finish
Also includes small fix to EventLogger
Also added option ROCKSDB_PRINT_EVENTS_TO_STDOUT which is useful when we debug things. I've spent far too much time chasing LOG files.
Still didn't get sst table properties in JSON. They are written very deeply into the stack. I'll address in separate diff.
TODO:
* Write specification. Let's first use this for a while and figure out what's good data to put here, too. After that we'll write spec
* Write tools that parse and analyze LOGs. This can be in python or go. Good intern task.
Test Plan: Ran db_bench with ROCKSDB_PRINT_EVENTS_TO_STDOUT. Here's the output: https://phabricator.fb.com/P19811976
Reviewers: sdong, yhchiang, rven, MarkCallaghan, kradhakrishnan, anthony
Reviewed By: anthony
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D37521
2015-04-27 22:20:02 +00:00
|
|
|
#include "util/log_buffer.h"
|
EventLogger
Summary:
Here's my proposal for making our LOGs easier to read by machines.
The idea is to dump all events as JSON objects. JSON is easy to read by humans, but more importantly, it's easy to read by machines. That way, we can parse this, load into SQLite/mongo and then query or visualize.
I started with table_create and table_delete events, but if everybody agrees, I'll continue by adding more events (flush/compaction/etc etc)
Test Plan:
Ran db_bench. Observed:
2015/01/15-14:13:25.788019 1105ef000 EVENT_LOG_v1 {"time_micros": 1421360005788015, "event": "table_file_creation", "file_number": 12, "file_size": 1909699}
2015/01/15-14:13:25.956500 110740000 EVENT_LOG_v1 {"time_micros": 1421360005956498, "event": "table_file_deletion", "file_number": 12}
Reviewers: yhchiang, rven, dhruba, MarkCallaghan, lgalanis, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D31647
2015-03-13 17:15:54 +00:00
|
|
|
|
|
|
|
namespace rocksdb {
|
|
|
|
|
|
|
|
// JSONWritter doesn't support objects in arrays yet. There wasn't a need for
|
|
|
|
// that.
|
|
|
|
class JSONWritter {
|
|
|
|
public:
|
|
|
|
JSONWritter() : state_(kExpectKey), first_element_(true) { stream_ << "{"; }
|
|
|
|
|
|
|
|
void AddKey(const std::string& key) {
|
|
|
|
assert(state_ == kExpectKey);
|
|
|
|
if (!first_element_) {
|
|
|
|
stream_ << ", ";
|
|
|
|
}
|
|
|
|
stream_ << "\"" << key << "\": ";
|
|
|
|
state_ = kExpectValue;
|
|
|
|
first_element_ = false;
|
|
|
|
}
|
|
|
|
|
|
|
|
void AddValue(const char* value) {
|
|
|
|
assert(state_ == kExpectValue || state_ == kInArray);
|
|
|
|
if (state_ == kInArray && !first_element_) {
|
|
|
|
stream_ << ", ";
|
|
|
|
}
|
|
|
|
stream_ << "\"" << value << "\"";
|
|
|
|
if (state_ != kInArray) {
|
|
|
|
state_ = kExpectKey;
|
|
|
|
}
|
|
|
|
first_element_ = false;
|
|
|
|
}
|
|
|
|
|
|
|
|
template <typename T>
|
|
|
|
void AddValue(const T& value) {
|
|
|
|
assert(state_ == kExpectValue || state_ == kInArray);
|
|
|
|
if (state_ == kInArray && !first_element_) {
|
|
|
|
stream_ << ", ";
|
|
|
|
}
|
|
|
|
stream_ << value;
|
|
|
|
if (state_ != kInArray) {
|
|
|
|
state_ = kExpectKey;
|
|
|
|
}
|
|
|
|
first_element_ = false;
|
|
|
|
}
|
|
|
|
|
|
|
|
void StartArray() {
|
Include bunch of more events into EventLogger
Summary:
Added these events:
* Recovery start, finish and also when recovery creates a file
* Trivial move
* Compaction start, finish and when compaction creates a file
* Flush start, finish
Also includes small fix to EventLogger
Also added option ROCKSDB_PRINT_EVENTS_TO_STDOUT which is useful when we debug things. I've spent far too much time chasing LOG files.
Still didn't get sst table properties in JSON. They are written very deeply into the stack. I'll address in separate diff.
TODO:
* Write specification. Let's first use this for a while and figure out what's good data to put here, too. After that we'll write spec
* Write tools that parse and analyze LOGs. This can be in python or go. Good intern task.
Test Plan: Ran db_bench with ROCKSDB_PRINT_EVENTS_TO_STDOUT. Here's the output: https://phabricator.fb.com/P19811976
Reviewers: sdong, yhchiang, rven, MarkCallaghan, kradhakrishnan, anthony
Reviewed By: anthony
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D37521
2015-04-27 22:20:02 +00:00
|
|
|
assert(state_ == kExpectValue);
|
EventLogger
Summary:
Here's my proposal for making our LOGs easier to read by machines.
The idea is to dump all events as JSON objects. JSON is easy to read by humans, but more importantly, it's easy to read by machines. That way, we can parse this, load into SQLite/mongo and then query or visualize.
I started with table_create and table_delete events, but if everybody agrees, I'll continue by adding more events (flush/compaction/etc etc)
Test Plan:
Ran db_bench. Observed:
2015/01/15-14:13:25.788019 1105ef000 EVENT_LOG_v1 {"time_micros": 1421360005788015, "event": "table_file_creation", "file_number": 12, "file_size": 1909699}
2015/01/15-14:13:25.956500 110740000 EVENT_LOG_v1 {"time_micros": 1421360005956498, "event": "table_file_deletion", "file_number": 12}
Reviewers: yhchiang, rven, dhruba, MarkCallaghan, lgalanis, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D31647
2015-03-13 17:15:54 +00:00
|
|
|
state_ = kInArray;
|
|
|
|
stream_ << "[";
|
|
|
|
first_element_ = true;
|
|
|
|
}
|
|
|
|
|
|
|
|
void EndArray() {
|
|
|
|
assert(state_ == kInArray);
|
|
|
|
state_ = kExpectKey;
|
|
|
|
stream_ << "]";
|
|
|
|
first_element_ = false;
|
|
|
|
}
|
|
|
|
|
|
|
|
void StartObject() {
|
|
|
|
assert(state_ == kExpectValue);
|
Add more table properties to EventLogger
Summary:
Example output:
{"time_micros": 1431463794310521, "job": 353, "event": "table_file_creation", "file_number": 387, "file_size": 86937, "table_info": {"data_size": "81801", "index_size": "9751", "filter_size": "0", "raw_key_size": "23448", "raw_average_key_size": "24.000000", "raw_value_size": "990571", "raw_average_value_size": "1013.890481", "num_data_blocks": "245", "num_entries": "977", "filter_policy_name": "", "kDeletedKeys": "0"}}
Also fixed a bug where BuildTable() in recovery was passing Env::IOHigh argument into paranoid_checks_file parameter.
Test Plan: make check + check out the output in the log
Reviewers: sdong, rven, yhchiang
Reviewed By: yhchiang
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D38343
2015-05-12 22:53:55 +00:00
|
|
|
state_ = kExpectKey;
|
EventLogger
Summary:
Here's my proposal for making our LOGs easier to read by machines.
The idea is to dump all events as JSON objects. JSON is easy to read by humans, but more importantly, it's easy to read by machines. That way, we can parse this, load into SQLite/mongo and then query or visualize.
I started with table_create and table_delete events, but if everybody agrees, I'll continue by adding more events (flush/compaction/etc etc)
Test Plan:
Ran db_bench. Observed:
2015/01/15-14:13:25.788019 1105ef000 EVENT_LOG_v1 {"time_micros": 1421360005788015, "event": "table_file_creation", "file_number": 12, "file_size": 1909699}
2015/01/15-14:13:25.956500 110740000 EVENT_LOG_v1 {"time_micros": 1421360005956498, "event": "table_file_deletion", "file_number": 12}
Reviewers: yhchiang, rven, dhruba, MarkCallaghan, lgalanis, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D31647
2015-03-13 17:15:54 +00:00
|
|
|
stream_ << "{";
|
|
|
|
first_element_ = true;
|
|
|
|
}
|
|
|
|
|
|
|
|
void EndObject() {
|
|
|
|
assert(state_ == kExpectKey);
|
|
|
|
stream_ << "}";
|
|
|
|
first_element_ = false;
|
|
|
|
}
|
|
|
|
|
|
|
|
std::string Get() const { return stream_.str(); }
|
|
|
|
|
|
|
|
JSONWritter& operator<<(const char* val) {
|
|
|
|
if (state_ == kExpectKey) {
|
|
|
|
AddKey(val);
|
|
|
|
} else {
|
|
|
|
AddValue(val);
|
|
|
|
}
|
|
|
|
return *this;
|
|
|
|
}
|
|
|
|
|
|
|
|
JSONWritter& operator<<(const std::string& val) {
|
|
|
|
return *this << val.c_str();
|
|
|
|
}
|
|
|
|
|
|
|
|
template <typename T>
|
|
|
|
JSONWritter& operator<<(const T& val) {
|
|
|
|
assert(state_ != kExpectKey);
|
|
|
|
AddValue(val);
|
|
|
|
return *this;
|
|
|
|
}
|
|
|
|
|
|
|
|
private:
|
|
|
|
enum JSONWritterState {
|
|
|
|
kExpectKey,
|
|
|
|
kExpectValue,
|
|
|
|
kInArray,
|
|
|
|
};
|
|
|
|
JSONWritterState state_;
|
|
|
|
bool first_element_;
|
|
|
|
std::ostringstream stream_;
|
|
|
|
};
|
|
|
|
|
|
|
|
class EventLoggerStream {
|
|
|
|
public:
|
|
|
|
template <typename T>
|
|
|
|
EventLoggerStream& operator<<(const T& val) {
|
|
|
|
MakeStream();
|
|
|
|
*json_writter_ << val;
|
|
|
|
return *this;
|
|
|
|
}
|
Include bunch of more events into EventLogger
Summary:
Added these events:
* Recovery start, finish and also when recovery creates a file
* Trivial move
* Compaction start, finish and when compaction creates a file
* Flush start, finish
Also includes small fix to EventLogger
Also added option ROCKSDB_PRINT_EVENTS_TO_STDOUT which is useful when we debug things. I've spent far too much time chasing LOG files.
Still didn't get sst table properties in JSON. They are written very deeply into the stack. I'll address in separate diff.
TODO:
* Write specification. Let's first use this for a while and figure out what's good data to put here, too. After that we'll write spec
* Write tools that parse and analyze LOGs. This can be in python or go. Good intern task.
Test Plan: Ran db_bench with ROCKSDB_PRINT_EVENTS_TO_STDOUT. Here's the output: https://phabricator.fb.com/P19811976
Reviewers: sdong, yhchiang, rven, MarkCallaghan, kradhakrishnan, anthony
Reviewed By: anthony
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D37521
2015-04-27 22:20:02 +00:00
|
|
|
|
|
|
|
void StartArray() { json_writter_->StartArray(); }
|
|
|
|
void EndArray() { json_writter_->EndArray(); }
|
|
|
|
void StartObject() { json_writter_->StartObject(); }
|
|
|
|
void EndObject() { json_writter_->EndObject(); }
|
|
|
|
|
EventLogger
Summary:
Here's my proposal for making our LOGs easier to read by machines.
The idea is to dump all events as JSON objects. JSON is easy to read by humans, but more importantly, it's easy to read by machines. That way, we can parse this, load into SQLite/mongo and then query or visualize.
I started with table_create and table_delete events, but if everybody agrees, I'll continue by adding more events (flush/compaction/etc etc)
Test Plan:
Ran db_bench. Observed:
2015/01/15-14:13:25.788019 1105ef000 EVENT_LOG_v1 {"time_micros": 1421360005788015, "event": "table_file_creation", "file_number": 12, "file_size": 1909699}
2015/01/15-14:13:25.956500 110740000 EVENT_LOG_v1 {"time_micros": 1421360005956498, "event": "table_file_deletion", "file_number": 12}
Reviewers: yhchiang, rven, dhruba, MarkCallaghan, lgalanis, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D31647
2015-03-13 17:15:54 +00:00
|
|
|
~EventLoggerStream();
|
|
|
|
|
|
|
|
private:
|
|
|
|
void MakeStream() {
|
|
|
|
if (!json_writter_) {
|
|
|
|
json_writter_ = new JSONWritter();
|
|
|
|
*this << "time_micros"
|
|
|
|
<< std::chrono::duration_cast<std::chrono::microseconds>(
|
|
|
|
std::chrono::system_clock::now().time_since_epoch()).count();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
friend class EventLogger;
|
|
|
|
explicit EventLoggerStream(Logger* logger);
|
Include bunch of more events into EventLogger
Summary:
Added these events:
* Recovery start, finish and also when recovery creates a file
* Trivial move
* Compaction start, finish and when compaction creates a file
* Flush start, finish
Also includes small fix to EventLogger
Also added option ROCKSDB_PRINT_EVENTS_TO_STDOUT which is useful when we debug things. I've spent far too much time chasing LOG files.
Still didn't get sst table properties in JSON. They are written very deeply into the stack. I'll address in separate diff.
TODO:
* Write specification. Let's first use this for a while and figure out what's good data to put here, too. After that we'll write spec
* Write tools that parse and analyze LOGs. This can be in python or go. Good intern task.
Test Plan: Ran db_bench with ROCKSDB_PRINT_EVENTS_TO_STDOUT. Here's the output: https://phabricator.fb.com/P19811976
Reviewers: sdong, yhchiang, rven, MarkCallaghan, kradhakrishnan, anthony
Reviewed By: anthony
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D37521
2015-04-27 22:20:02 +00:00
|
|
|
explicit EventLoggerStream(LogBuffer* log_buffer);
|
|
|
|
// exactly one is non-nullptr
|
|
|
|
Logger* const logger_;
|
|
|
|
LogBuffer* const log_buffer_;
|
EventLogger
Summary:
Here's my proposal for making our LOGs easier to read by machines.
The idea is to dump all events as JSON objects. JSON is easy to read by humans, but more importantly, it's easy to read by machines. That way, we can parse this, load into SQLite/mongo and then query or visualize.
I started with table_create and table_delete events, but if everybody agrees, I'll continue by adding more events (flush/compaction/etc etc)
Test Plan:
Ran db_bench. Observed:
2015/01/15-14:13:25.788019 1105ef000 EVENT_LOG_v1 {"time_micros": 1421360005788015, "event": "table_file_creation", "file_number": 12, "file_size": 1909699}
2015/01/15-14:13:25.956500 110740000 EVENT_LOG_v1 {"time_micros": 1421360005956498, "event": "table_file_deletion", "file_number": 12}
Reviewers: yhchiang, rven, dhruba, MarkCallaghan, lgalanis, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D31647
2015-03-13 17:15:54 +00:00
|
|
|
// ownership
|
|
|
|
JSONWritter* json_writter_;
|
|
|
|
};
|
|
|
|
|
|
|
|
// here is an example of the output that will show up in the LOG:
|
|
|
|
// 2015/01/15-14:13:25.788019 1105ef000 EVENT_LOG_v1 {"time_micros":
|
|
|
|
// 1421360005788015, "event": "table_file_creation", "file_number": 12,
|
|
|
|
// "file_size": 1909699}
|
|
|
|
class EventLogger {
|
|
|
|
public:
|
|
|
|
explicit EventLogger(Logger* logger) : logger_(logger) {}
|
|
|
|
EventLoggerStream Log() { return EventLoggerStream(logger_); }
|
Include bunch of more events into EventLogger
Summary:
Added these events:
* Recovery start, finish and also when recovery creates a file
* Trivial move
* Compaction start, finish and when compaction creates a file
* Flush start, finish
Also includes small fix to EventLogger
Also added option ROCKSDB_PRINT_EVENTS_TO_STDOUT which is useful when we debug things. I've spent far too much time chasing LOG files.
Still didn't get sst table properties in JSON. They are written very deeply into the stack. I'll address in separate diff.
TODO:
* Write specification. Let's first use this for a while and figure out what's good data to put here, too. After that we'll write spec
* Write tools that parse and analyze LOGs. This can be in python or go. Good intern task.
Test Plan: Ran db_bench with ROCKSDB_PRINT_EVENTS_TO_STDOUT. Here's the output: https://phabricator.fb.com/P19811976
Reviewers: sdong, yhchiang, rven, MarkCallaghan, kradhakrishnan, anthony
Reviewed By: anthony
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D37521
2015-04-27 22:20:02 +00:00
|
|
|
EventLoggerStream LogToBuffer(LogBuffer* log_buffer) {
|
|
|
|
return EventLoggerStream(log_buffer);
|
|
|
|
}
|
EventLogger
Summary:
Here's my proposal for making our LOGs easier to read by machines.
The idea is to dump all events as JSON objects. JSON is easy to read by humans, but more importantly, it's easy to read by machines. That way, we can parse this, load into SQLite/mongo and then query or visualize.
I started with table_create and table_delete events, but if everybody agrees, I'll continue by adding more events (flush/compaction/etc etc)
Test Plan:
Ran db_bench. Observed:
2015/01/15-14:13:25.788019 1105ef000 EVENT_LOG_v1 {"time_micros": 1421360005788015, "event": "table_file_creation", "file_number": 12, "file_size": 1909699}
2015/01/15-14:13:25.956500 110740000 EVENT_LOG_v1 {"time_micros": 1421360005956498, "event": "table_file_deletion", "file_number": 12}
Reviewers: yhchiang, rven, dhruba, MarkCallaghan, lgalanis, sdong
Reviewed By: sdong
Subscribers: dhruba, leveldb
Differential Revision: https://reviews.facebook.net/D31647
2015-03-13 17:15:54 +00:00
|
|
|
|
|
|
|
private:
|
|
|
|
Logger* logger_;
|
|
|
|
};
|
|
|
|
|
|
|
|
} // namespace rocksdb
|