rocksdb/util/rate_limiter.h

140 lines
4.4 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).
//
// 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/status.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() and bytes >= 0. Negative bytes
// passed in will be rounded up to 0.
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) {
Implement superior user & mid IO priority level in GenericRateLimiter (#8595) 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
2021-08-31 19:59:14 +02:00
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) {
Implement superior user & mid IO priority level in GenericRateLimiter (#8595) 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
2021-08-31 19:59:14 +02:00
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 Status GetTotalPendingRequests(
int64_t* total_pending_requests,
const Env::IOPriority pri = Env::IO_TOTAL) const override {
assert(total_pending_requests != nullptr);
MutexLock g(&request_mutex_);
if (pri == Env::IO_TOTAL) {
int64_t total_pending_requests_sum = 0;
for (int i = Env::IO_LOW; i < Env::IO_TOTAL; ++i) {
total_pending_requests_sum += static_cast<int64_t>(queue_[i].size());
}
*total_pending_requests = total_pending_requests_sum;
} else {
*total_pending_requests = static_cast<int64_t>(queue_[pri].size());
}
return Status::OK();
}
virtual int64_t GetBytesPerSecond() const override {
return rate_bytes_per_sec_;
}
private:
void RefillBytesAndGrantRequests();
Implement superior user & mid IO priority level in GenericRateLimiter (#8595) 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
2021-08-31 19:59:14 +02:00
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 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];
Simplify GenericRateLimiter algorithm (#8602) Summary: `GenericRateLimiter` slow path handles requests that cannot be satisfied immediately. Such requests enter a queue, and their thread stays in `Request()` until they are granted or the rate limiter is stopped. These threads are responsible for unblocking themselves. The work to do so is split into two main duties. (1) Waiting for the next refill time. (2) Refilling the bytes and granting requests. Prior to this PR, the slow path logic involved a leader election algorithm to pick one thread to perform (1) followed by (2). It elected the thread whose request was at the front of the highest priority non-empty queue since that request was most likely to be granted. This algorithm was efficient in terms of reducing intermediate wakeups, which is a thread waking up only to resume waiting after finding its request is not granted. However, the conceptual complexity of this algorithm was too high. It took me a long time to draw a timeline to understand how it works for just one edge case yet there were so many. This PR drops the leader election to reduce conceptual complexity. Now, the two duties can be performed by whichever thread acquires the lock first. The risk of this change is increasing the number of intermediate wakeups, however, we took steps to mitigate that. - `wait_until_refill_pending_` flag ensures only one thread performs (1). This\ prevents the thundering herd problem at the next refill time. The remaining\ threads wait on their condition variable with an unbounded duration -- thus we\ must remember to notify them to ensure forward progress. - (1) is typically done by a thread at the front of a queue. This is trivial\ when the queues are initially empty as the first choice that arrives must be\ the only entry in its queue. When queues are initially non-empty, we achieve\ this by having (2) notify a thread at the front of a queue (preferring higher\ priority) to perform the next duty. - We do not require any additional wakeup for (2). Typically it will just be\ done by the thread that finished (1). Combined, the second and third bullet points above suggest the refill/granting will typically be done by a request at the front of its queue. This is important because one wakeup is saved when a granted request happens to be in an already running thread. Note there are a few cases that still lead to intermediate wakeup, however. The first two are existing issues that also apply to the old algorithm, however, the third (including both subpoints) is new. - No request may be granted (only possible when rate limit dynamically\ decreases). - Requests from a different queue may be granted. - (2) may be run by a non-front request thread causing it to not be granted even\ if some requests in that same queue are granted. It can happen for a couple\ (unlikely) reasons. - A new request may sneak in and grab the lock at the refill time, before the\ thread finishing (1) can wake up and grab it. - A new request may sneak in and grab the lock and execute (1) before (2)'s\ chosen candidate can wake up and grab the lock. Then that non-front request\ thread performing (1) can carry over to perform (2). Pull Request resolved: https://github.com/facebook/rocksdb/pull/8602 Test Plan: - Use existing tests. The edge cases listed in the comment are all performance\ related; I could not really think of any related to correctness. The logic\ looks the same whether a thread wakes up/finishes its work early/on-time/late,\ or whether the thread is chosen vs. "steals" the work. - Verified write throughput and CPU overhead are basically the same with and\ without this change, even in a rate limiter heavy workload: Test command: ``` $ rm -rf /dev/shm/dbbench/ && TEST_TMPDIR=/dev/shm /usr/bin/time ./db_bench -benchmarks=fillrandom -num_multi_db=64 -num_low_pri_threads=64 -num_high_pri_threads=64 -write_buffer_size=262144 -target_file_size_base=262144 -max_bytes_for_level_base=1048576 -rate_limiter_bytes_per_sec=16777216 -key_size=24 -value_size=1000 -num=10000 -compression_type=none -rate_limiter_refill_period_us=1000 ``` Results before this PR: ``` fillrandom : 108.463 micros/op 9219 ops/sec; 9.0 MB/s 7.40user 8.84system 1:26.20elapsed 18%CPU (0avgtext+0avgdata 256140maxresident)k ``` Results after this PR: ``` fillrandom : 108.108 micros/op 9250 ops/sec; 9.0 MB/s 7.45user 8.23system 1:26.68elapsed 18%CPU (0avgtext+0avgdata 255688maxresident)k ``` Reviewed By: hx235 Differential Revision: D30048013 Pulled By: ajkr fbshipit-source-id: 6741bba9d9dfbccab359806d725105817fef818b
2021-08-10 01:46:14 +02:00
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