240c4126fd
Summary: Context: An extra IO_USER priority in rate limiter allows users to optionally charge WAL writes / SST reads to rate limiter at this priority level, which then has higher priority than IO_HIGH and IO_LOW. With an extra IO_USER priority, it allows users to better specify the relative urgency/importance among different requests in rate limiter. As a consequence, IO resource management can better prioritize and limit resource based on user's need. The IO_USER is implemented as superior priority in GenericRateLimiter, in the sense that its request queue will always be iterated first without being constrained to fairness. The reason is that the notion of fairness is only meaningful in helping lower priorities in background IO (i.e, IO_HIGH/MID/LOW) to gain some fair chance to run so that it does not block foreground IO (i.e, the ones that are charged at the level of IO_USER). As we can see, the ultimate goal here is to not blocking foreground IO at IO_USER level, which justifies the superiority of IO_USER. Similar benefits exist for IO_MID priority. - Rewrote the logic of deciding the order of iterating request queues of high/low priorities to include the extra user/mid priority w/o affecting the existing behavior (see PR's [comment](https://github.com/facebook/rocksdb/pull/8595/files#r678749331)) - Included the request queue of user-pri/mid-pri in the code path of next-leader-candidate signaling and GenericRateLimiter's destructor - Included the extra user/mid-pri in bookkeeping data structures: total_bytes_through_ and total_requests_ - Re-written the previous impl of explicitly iterating priorities with a loop from Env::IO_LOW to Env::IO_TOTAL Pull Request resolved: https://github.com/facebook/rocksdb/pull/8595 Test Plan: - passed existing rate_limiter_test.cc - passed added unit tests in rate_limiter_test.cc - run performance test to verify performance with only high/low requests is not affected by this change - Set-up command: `TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=fillrandom --duration=5 --compression_type=none --num=100000000 --disable_auto_compactions=true --write_buffer_size=1048576 --writable_file_max_buffer_size=65536 --target_file_size_base=1048576 --max_bytes_for_level_base=4194304 --level0_slowdown_writes_trigger=$(((1 << 31) - 1)) --level0_stop_writes_trigger=$(((1 << 31) - 1))` - Test command: `TEST_TMPDIR=/dev/shm ./db_bench --benchmarks=overwrite --use_existing_db=true --disable_wal=true --duration=30 --compression_type=none --num=100000000 --write_buffer_size=1048576 --writable_file_max_buffer_size=65536 --target_file_size_base=1048576 --max_bytes_for_level_base=4194304 --level0_slowdown_writes_trigger=$(((1 << 31) - 1)) --level0_stop_writes_trigger=$(((1 << 31) - 1)) --statistics=true --rate_limiter_bytes_per_sec=1048576 --rate_limiter_refill_period_us=1000 --threads=32 |& grep -E '(flush|compact)\.write\.bytes'` - Before (on branch upstream/master): `rocksdb.compact.write.bytes COUNT : 4014162` `rocksdb.flush.write.bytes COUNT : 26715832` rocksdb.flush.write.bytes/rocksdb.compact.write.bytes ~= 6.66 - After (on branch rate_limiter_user_pri): `rocksdb.compact.write.bytes COUNT : 3807822` `rocksdb.flush.write.bytes COUNT : 26098659` rocksdb.flush.write.bytes/rocksdb.compact.write.bytes ~= 6.85 Reviewed By: ajkr Differential Revision: D30577783 Pulled By: hx235 fbshipit-source-id: 0881f2705ffd13ecd331256bde7e8ec874a353f4
123 lines
3.7 KiB
C++
123 lines
3.7 KiB
C++
// 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) 2011 The LevelDB Authors. All rights reserved.
|
|
// Use of this source code is governed by a BSD-style license that can be
|
|
// found in the LICENSE file. See the AUTHORS file for names of contributors.
|
|
|
|
#pragma once
|
|
|
|
#include <algorithm>
|
|
#include <atomic>
|
|
#include <chrono>
|
|
#include <deque>
|
|
|
|
#include "port/port.h"
|
|
#include "rocksdb/env.h"
|
|
#include "rocksdb/rate_limiter.h"
|
|
#include "rocksdb/system_clock.h"
|
|
#include "util/mutexlock.h"
|
|
#include "util/random.h"
|
|
|
|
namespace ROCKSDB_NAMESPACE {
|
|
|
|
class GenericRateLimiter : public RateLimiter {
|
|
public:
|
|
GenericRateLimiter(int64_t refill_bytes, int64_t refill_period_us,
|
|
int32_t fairness, RateLimiter::Mode mode,
|
|
const std::shared_ptr<SystemClock>& clock,
|
|
bool auto_tuned);
|
|
|
|
virtual ~GenericRateLimiter();
|
|
|
|
// This API allows user to dynamically change rate limiter's bytes per second.
|
|
virtual void SetBytesPerSecond(int64_t bytes_per_second) override;
|
|
|
|
// Request for token to write bytes. If this request can not be satisfied,
|
|
// the call is blocked. Caller is responsible to make sure
|
|
// bytes <= GetSingleBurstBytes()
|
|
using RateLimiter::Request;
|
|
virtual void Request(const int64_t bytes, const Env::IOPriority pri,
|
|
Statistics* stats) override;
|
|
|
|
virtual int64_t GetSingleBurstBytes() const override {
|
|
return refill_bytes_per_period_.load(std::memory_order_relaxed);
|
|
}
|
|
|
|
virtual int64_t GetTotalBytesThrough(
|
|
const Env::IOPriority pri = Env::IO_TOTAL) const override {
|
|
MutexLock g(&request_mutex_);
|
|
if (pri == Env::IO_TOTAL) {
|
|
int64_t total_bytes_through_sum = 0;
|
|
for (int i = Env::IO_LOW; i < Env::IO_TOTAL; ++i) {
|
|
total_bytes_through_sum += total_bytes_through_[i];
|
|
}
|
|
return total_bytes_through_sum;
|
|
}
|
|
return total_bytes_through_[pri];
|
|
}
|
|
|
|
virtual int64_t GetTotalRequests(
|
|
const Env::IOPriority pri = Env::IO_TOTAL) const override {
|
|
MutexLock g(&request_mutex_);
|
|
if (pri == Env::IO_TOTAL) {
|
|
int64_t total_requests_sum = 0;
|
|
for (int i = Env::IO_LOW; i < Env::IO_TOTAL; ++i) {
|
|
total_requests_sum += total_requests_[i];
|
|
}
|
|
return total_requests_sum;
|
|
}
|
|
return total_requests_[pri];
|
|
}
|
|
|
|
virtual int64_t GetBytesPerSecond() const override {
|
|
return rate_bytes_per_sec_;
|
|
}
|
|
|
|
private:
|
|
void RefillBytesAndGrantRequests();
|
|
std::vector<Env::IOPriority> GeneratePriorityIterationOrder();
|
|
int64_t CalculateRefillBytesPerPeriod(int64_t rate_bytes_per_sec);
|
|
Status Tune();
|
|
|
|
uint64_t NowMicrosMonotonic() { return clock_->NowNanos() / std::milli::den; }
|
|
|
|
// This mutex guard all internal states
|
|
mutable port::Mutex request_mutex_;
|
|
|
|
const int64_t kMinRefillBytesPerPeriod = 100;
|
|
|
|
const int64_t refill_period_us_;
|
|
|
|
int64_t rate_bytes_per_sec_;
|
|
// This variable can be changed dynamically.
|
|
std::atomic<int64_t> refill_bytes_per_period_;
|
|
std::shared_ptr<SystemClock> clock_;
|
|
|
|
bool stop_;
|
|
port::CondVar exit_cv_;
|
|
int32_t requests_to_wait_;
|
|
|
|
int64_t total_requests_[Env::IO_TOTAL];
|
|
int64_t total_bytes_through_[Env::IO_TOTAL];
|
|
int64_t available_bytes_;
|
|
int64_t next_refill_us_;
|
|
|
|
int32_t fairness_;
|
|
Random rnd_;
|
|
|
|
struct Req;
|
|
std::deque<Req*> queue_[Env::IO_TOTAL];
|
|
bool wait_until_refill_pending_;
|
|
|
|
bool auto_tuned_;
|
|
int64_t num_drains_;
|
|
int64_t prev_num_drains_;
|
|
const int64_t max_bytes_per_sec_;
|
|
std::chrono::microseconds tuned_time_;
|
|
};
|
|
|
|
} // namespace ROCKSDB_NAMESPACE
|