Push- instead of pull-model for managing Write stalls
Summary:
Introducing WriteController, which is a source of truth about per-DB write delays. Let's define an DB epoch as a period where there are no flushes and compactions (i.e. new epoch is started when flush or compaction finishes). Each epoch can either:
* proceed with all writes without delay
* delay all writes by fixed time
* stop all writes
The three modes are recomputed at each epoch change (flush, compaction), rather than on every write (which is currently the case).
When we have a lot of column families, our current pull behavior adds a big overhead, since we need to loop over every column family for every write. With new push model, overhead on Write code-path is minimal.
This is just the start. Next step is to also take care of stalls introduced by slow memtable flushes. The final goal is to eliminate function MakeRoomForWrite(), which currently needs to be called for every column family by every write.
Test Plan: make check for now. I'll add some unit tests later. Also, perf test.
Reviewers: dhruba, yhchiang, MarkCallaghan, sdong, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D22791
10 years ago
|
|
|
// Copyright (c) 2013, 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.
|
|
|
|
|
//
|
|
|
|
|
#include "db/write_controller.h"
|
|
|
|
|
|
|
|
|
|
#include "util/testharness.h"
|
|
|
|
|
|
|
|
|
|
namespace rocksdb {
|
|
|
|
|
|
|
|
|
|
class WriteControllerTest : public testing::Test {};
|
Push- instead of pull-model for managing Write stalls
Summary:
Introducing WriteController, which is a source of truth about per-DB write delays. Let's define an DB epoch as a period where there are no flushes and compactions (i.e. new epoch is started when flush or compaction finishes). Each epoch can either:
* proceed with all writes without delay
* delay all writes by fixed time
* stop all writes
The three modes are recomputed at each epoch change (flush, compaction), rather than on every write (which is currently the case).
When we have a lot of column families, our current pull behavior adds a big overhead, since we need to loop over every column family for every write. With new push model, overhead on Write code-path is minimal.
This is just the start. Next step is to also take care of stalls introduced by slow memtable flushes. The final goal is to eliminate function MakeRoomForWrite(), which currently needs to be called for every column family by every write.
Test Plan: make check for now. I'll add some unit tests later. Also, perf test.
Reviewers: dhruba, yhchiang, MarkCallaghan, sdong, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D22791
10 years ago
|
|
|
|
|
|
|
|
TEST_F(WriteControllerTest, SanityTest) {
|
Push- instead of pull-model for managing Write stalls
Summary:
Introducing WriteController, which is a source of truth about per-DB write delays. Let's define an DB epoch as a period where there are no flushes and compactions (i.e. new epoch is started when flush or compaction finishes). Each epoch can either:
* proceed with all writes without delay
* delay all writes by fixed time
* stop all writes
The three modes are recomputed at each epoch change (flush, compaction), rather than on every write (which is currently the case).
When we have a lot of column families, our current pull behavior adds a big overhead, since we need to loop over every column family for every write. With new push model, overhead on Write code-path is minimal.
This is just the start. Next step is to also take care of stalls introduced by slow memtable flushes. The final goal is to eliminate function MakeRoomForWrite(), which currently needs to be called for every column family by every write.
Test Plan: make check for now. I'll add some unit tests later. Also, perf test.
Reviewers: dhruba, yhchiang, MarkCallaghan, sdong, ljin
Reviewed By: ljin
Subscribers: leveldb
Differential Revision: https://reviews.facebook.net/D22791
10 years ago
|
|
|
WriteController controller;
|
|
|
|
|
auto stop_token_1 = controller.GetStopToken();
|
|
|
|
|
auto stop_token_2 = controller.GetStopToken();
|
|
|
|
|
|
|
|
|
|
ASSERT_EQ(true, controller.IsStopped());
|
|
|
|
|
stop_token_1.reset();
|
|
|
|
|
ASSERT_EQ(true, controller.IsStopped());
|
|
|
|
|
stop_token_2.reset();
|
|
|
|
|
ASSERT_EQ(false, controller.IsStopped());
|
|
|
|
|
|
|
|
|
|
auto delay_token_1 = controller.GetDelayToken(5);
|
|
|
|
|
ASSERT_EQ(static_cast<uint64_t>(5), controller.GetDelay());
|
|
|
|
|
auto delay_token_2 = controller.GetDelayToken(8);
|
|
|
|
|
ASSERT_EQ(static_cast<uint64_t>(13), controller.GetDelay());
|
|
|
|
|
|
|
|
|
|
delay_token_2.reset();
|
|
|
|
|
ASSERT_EQ(static_cast<uint64_t>(5), controller.GetDelay());
|
|
|
|
|
delay_token_1.reset();
|
|
|
|
|
ASSERT_EQ(static_cast<uint64_t>(0), controller.GetDelay());
|
|
|
|
|
delay_token_1.reset();
|
|
|
|
|
ASSERT_EQ(false, controller.IsStopped());
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
} // namespace rocksdb
|
|
|
|
|
|
|
|
|
|
int main(int argc, char** argv) {
|
|
|
|
|
::testing::InitGoogleTest(&argc, argv);
|
|
|
|
|
return RUN_ALL_TESTS();
|
|
|
|
|
}
|
