mirror of https://github.com/facebook/rocksdb.git
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
This commit is contained in:
Hui Xiao
Facebook GitHub Bot
parent
7b55554605
commit
240c4126fd
|
|
@ -434,7 +434,13 @@ class Env {
|
|||
static std::string PriorityToString(Priority priority);
|
||||
|
||||
// Priority for requesting bytes in rate limiter scheduler
|
||||
enum IOPriority { IO_LOW = 0, IO_HIGH = 1, IO_TOTAL = 2 };
|
||||
enum IOPriority {
|
||||
IO_LOW = 0,
|
||||
IO_MID = 1,
|
||||
IO_HIGH = 2,
|
||||
IO_USER = 3,
|
||||
IO_TOTAL = 4
|
||||
};
|
||||
|
||||
// Arrange to run "(*function)(arg)" once in a background thread, in
|
||||
// the thread pool specified by pri. By default, jobs go to the 'LOW'
|
||||
|
|
|
|||
|
|
@ -68,23 +68,28 @@ GenericRateLimiter::GenericRateLimiter(
|
|||
prev_num_drains_(0),
|
||||
max_bytes_per_sec_(rate_bytes_per_sec),
|
||||
tuned_time_(NowMicrosMonotonic()) {
|
||||
total_requests_[0] = 0;
|
||||
total_requests_[1] = 0;
|
||||
total_bytes_through_[0] = 0;
|
||||
total_bytes_through_[1] = 0;
|
||||
for (int i = Env::IO_LOW; i < Env::IO_TOTAL; ++i) {
|
||||
total_requests_[i] = 0;
|
||||
total_bytes_through_[i] = 0;
|
||||
}
|
||||
}
|
||||
|
||||
GenericRateLimiter::~GenericRateLimiter() {
|
||||
MutexLock g(&request_mutex_);
|
||||
stop_ = true;
|
||||
requests_to_wait_ = static_cast<int32_t>(queue_[Env::IO_LOW].size() +
|
||||
queue_[Env::IO_HIGH].size());
|
||||
for (auto& r : queue_[Env::IO_HIGH]) {
|
||||
r->cv.Signal();
|
||||
std::deque<Req*>::size_type queues_size_sum = 0;
|
||||
for (int i = Env::IO_LOW; i < Env::IO_TOTAL; ++i) {
|
||||
queues_size_sum += queue_[i].size();
|
||||
}
|
||||
for (auto& r : queue_[Env::IO_LOW]) {
|
||||
r->cv.Signal();
|
||||
requests_to_wait_ = static_cast<int32_t>(queues_size_sum);
|
||||
|
||||
for (int i = Env::IO_TOTAL - 1; i >= Env::IO_LOW; --i) {
|
||||
std::deque<Req*> queue = queue_[i];
|
||||
for (auto& r : queue) {
|
||||
r->cv.Signal();
|
||||
}
|
||||
}
|
||||
|
||||
while (requests_to_wait_ > 0) {
|
||||
exit_cv_.Wait();
|
||||
}
|
||||
|
|
@ -171,10 +176,12 @@ void GenericRateLimiter::Request(int64_t bytes, const Env::IOPriority pri,
|
|||
// If there is any remaining requests, make sure there exists at least
|
||||
// one candidate is awake for future duties by signaling a front request
|
||||
// of a queue.
|
||||
if (!queue_[Env::IO_HIGH].empty()) {
|
||||
queue_[Env::IO_HIGH].front()->cv.Signal();
|
||||
} else if (!queue_[Env::IO_LOW].empty()) {
|
||||
queue_[Env::IO_LOW].front()->cv.Signal();
|
||||
for (int i = Env::IO_TOTAL - 1; i >= Env::IO_LOW; --i) {
|
||||
std::deque<Req*> queue = queue_[i];
|
||||
if (!queue.empty()) {
|
||||
queue.front()->cv.Signal();
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -205,6 +212,45 @@ void GenericRateLimiter::Request(int64_t bytes, const Env::IOPriority pri,
|
|||
}
|
||||
}
|
||||
|
||||
std::vector<Env::IOPriority>
|
||||
GenericRateLimiter::GeneratePriorityIterationOrder() {
|
||||
std::vector<Env::IOPriority> pri_iteration_order(Env::IO_TOTAL /* 4 */);
|
||||
// We make Env::IO_USER a superior priority by always iterating its queue
|
||||
// first
|
||||
pri_iteration_order[0] = Env::IO_USER;
|
||||
|
||||
bool high_pri_iterated_after_mid_low_pri = rnd_.OneIn(fairness_);
|
||||
TEST_SYNC_POINT_CALLBACK(
|
||||
"GenericRateLimiter::GeneratePriorityIterationOrder::"
|
||||
"PostRandomOneInFairnessForHighPri",
|
||||
&high_pri_iterated_after_mid_low_pri);
|
||||
bool mid_pri_itereated_after_low_pri = rnd_.OneIn(fairness_);
|
||||
TEST_SYNC_POINT_CALLBACK(
|
||||
"GenericRateLimiter::GeneratePriorityIterationOrder::"
|
||||
"PostRandomOneInFairnessForMidPri",
|
||||
&mid_pri_itereated_after_low_pri);
|
||||
|
||||
if (high_pri_iterated_after_mid_low_pri) {
|
||||
pri_iteration_order[3] = Env::IO_HIGH;
|
||||
pri_iteration_order[2] =
|
||||
mid_pri_itereated_after_low_pri ? Env::IO_MID : Env::IO_LOW;
|
||||
pri_iteration_order[1] =
|
||||
(pri_iteration_order[2] == Env::IO_MID) ? Env::IO_LOW : Env::IO_MID;
|
||||
} else {
|
||||
pri_iteration_order[1] = Env::IO_HIGH;
|
||||
pri_iteration_order[3] =
|
||||
mid_pri_itereated_after_low_pri ? Env::IO_MID : Env::IO_LOW;
|
||||
pri_iteration_order[2] =
|
||||
(pri_iteration_order[3] == Env::IO_MID) ? Env::IO_LOW : Env::IO_MID;
|
||||
}
|
||||
|
||||
TEST_SYNC_POINT_CALLBACK(
|
||||
"GenericRateLimiter::GeneratePriorityIterationOrder::"
|
||||
"PreReturnPriIterationOrder",
|
||||
&pri_iteration_order);
|
||||
return pri_iteration_order;
|
||||
}
|
||||
|
||||
void GenericRateLimiter::RefillBytesAndGrantRequests() {
|
||||
TEST_SYNC_POINT("GenericRateLimiter::RefillBytesAndGrantRequests");
|
||||
next_refill_us_ = NowMicrosMonotonic() + refill_period_us_;
|
||||
|
|
@ -215,10 +261,13 @@ void GenericRateLimiter::RefillBytesAndGrantRequests() {
|
|||
available_bytes_ += refill_bytes_per_period;
|
||||
}
|
||||
|
||||
int use_low_pri_first = rnd_.OneIn(fairness_) ? 0 : 1;
|
||||
for (int q = 0; q < 2; ++q) {
|
||||
auto use_pri = (use_low_pri_first == q) ? Env::IO_LOW : Env::IO_HIGH;
|
||||
auto* queue = &queue_[use_pri];
|
||||
std::vector<Env::IOPriority> pri_iteration_order =
|
||||
GeneratePriorityIterationOrder();
|
||||
|
||||
for (int i = Env::IO_LOW; i < Env::IO_TOTAL; ++i) {
|
||||
assert(!pri_iteration_order.empty());
|
||||
Env::IOPriority current_pri = pri_iteration_order[i];
|
||||
auto* queue = &queue_[current_pri];
|
||||
while (!queue->empty()) {
|
||||
auto* next_req = queue->front();
|
||||
if (available_bytes_ < next_req->request_bytes) {
|
||||
|
|
@ -232,7 +281,7 @@ void GenericRateLimiter::RefillBytesAndGrantRequests() {
|
|||
}
|
||||
available_bytes_ -= next_req->request_bytes;
|
||||
next_req->request_bytes = 0;
|
||||
total_bytes_through_[use_pri] += next_req->bytes;
|
||||
total_bytes_through_[current_pri] += next_req->bytes;
|
||||
queue->pop_front();
|
||||
|
||||
next_req->granted = true;
|
||||
|
|
|
|||
|
|
@ -50,8 +50,11 @@ class GenericRateLimiter : public RateLimiter {
|
|||
const Env::IOPriority pri = Env::IO_TOTAL) const override {
|
||||
MutexLock g(&request_mutex_);
|
||||
if (pri == Env::IO_TOTAL) {
|
||||
return total_bytes_through_[Env::IO_LOW] +
|
||||
total_bytes_through_[Env::IO_HIGH];
|
||||
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];
|
||||
}
|
||||
|
|
@ -60,7 +63,11 @@ class GenericRateLimiter : public RateLimiter {
|
|||
const Env::IOPriority pri = Env::IO_TOTAL) const override {
|
||||
MutexLock g(&request_mutex_);
|
||||
if (pri == Env::IO_TOTAL) {
|
||||
return total_requests_[Env::IO_LOW] + total_requests_[Env::IO_HIGH];
|
||||
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];
|
||||
}
|
||||
|
|
@ -71,6 +78,7 @@ class GenericRateLimiter : public RateLimiter {
|
|||
|
||||
private:
|
||||
void RefillBytesAndGrantRequests();
|
||||
std::vector<Env::IOPriority> GeneratePriorityIterationOrder();
|
||||
int64_t CalculateRefillBytesPerPeriod(int64_t rate_bytes_per_sec);
|
||||
Status Tune();
|
||||
|
||||
|
|
|
|||
|
|
@ -11,6 +11,7 @@
|
|||
|
||||
#include <chrono>
|
||||
#include <cinttypes>
|
||||
#include <cstdint>
|
||||
#include <limits>
|
||||
|
||||
#include "db/db_test_util.h"
|
||||
|
|
@ -35,6 +36,59 @@ TEST_F(RateLimiterTest, StartStop) {
|
|||
std::unique_ptr<RateLimiter> limiter(NewGenericRateLimiter(100, 100, 10));
|
||||
}
|
||||
|
||||
TEST_F(RateLimiterTest, GetTotalBytesThrough) {
|
||||
std::unique_ptr<RateLimiter> limiter(NewGenericRateLimiter(
|
||||
20 /* rate_bytes_per_sec */, 1000 * 1000 /* refill_period_us */,
|
||||
10 /* fairness */));
|
||||
for (int i = Env::IO_LOW; i <= Env::IO_TOTAL; ++i) {
|
||||
ASSERT_EQ(limiter->GetTotalBytesThrough(static_cast<Env::IOPriority>(i)),
|
||||
0);
|
||||
}
|
||||
|
||||
std::int64_t request_byte = 10;
|
||||
std::int64_t request_byte_sum = 0;
|
||||
for (int i = Env::IO_LOW; i < Env::IO_TOTAL; ++i) {
|
||||
limiter->Request(request_byte, static_cast<Env::IOPriority>(i),
|
||||
nullptr /* stats */, RateLimiter::OpType::kWrite);
|
||||
request_byte_sum += request_byte;
|
||||
}
|
||||
|
||||
for (int i = Env::IO_LOW; i < Env::IO_TOTAL; ++i) {
|
||||
EXPECT_EQ(limiter->GetTotalBytesThrough(static_cast<Env::IOPriority>(i)),
|
||||
request_byte)
|
||||
<< "Failed to track total_bytes_through_ correctly when IOPriority = "
|
||||
<< static_cast<Env::IOPriority>(i);
|
||||
}
|
||||
EXPECT_EQ(limiter->GetTotalBytesThrough(Env::IO_TOTAL), request_byte_sum)
|
||||
<< "Failed to track total_bytes_through_ correctly when IOPriority = "
|
||||
"Env::IO_TOTAL";
|
||||
}
|
||||
|
||||
TEST_F(RateLimiterTest, GetTotalRequests) {
|
||||
std::unique_ptr<RateLimiter> limiter(NewGenericRateLimiter(
|
||||
20 /* rate_bytes_per_sec */, 1000 * 1000 /* refill_period_us */,
|
||||
10 /* fairness */));
|
||||
for (int i = Env::IO_LOW; i <= Env::IO_TOTAL; ++i) {
|
||||
ASSERT_EQ(limiter->GetTotalRequests(static_cast<Env::IOPriority>(i)), 0);
|
||||
}
|
||||
|
||||
std::int64_t total_requests_sum = 0;
|
||||
for (int i = Env::IO_LOW; i < Env::IO_TOTAL; ++i) {
|
||||
limiter->Request(10, static_cast<Env::IOPriority>(i), nullptr /* stats */,
|
||||
RateLimiter::OpType::kWrite);
|
||||
total_requests_sum += 1;
|
||||
}
|
||||
|
||||
for (int i = Env::IO_LOW; i < Env::IO_TOTAL; ++i) {
|
||||
EXPECT_EQ(limiter->GetTotalRequests(static_cast<Env::IOPriority>(i)), 1)
|
||||
<< "Failed to track total_requests_ correctly when IOPriority = "
|
||||
<< static_cast<Env::IOPriority>(i);
|
||||
}
|
||||
EXPECT_EQ(limiter->GetTotalRequests(Env::IO_TOTAL), total_requests_sum)
|
||||
<< "Failed to track total_requests_ correctly when IOPriority = "
|
||||
"Env::IO_TOTAL";
|
||||
}
|
||||
|
||||
TEST_F(RateLimiterTest, Modes) {
|
||||
for (auto mode : {RateLimiter::Mode::kWritesOnly,
|
||||
RateLimiter::Mode::kReadsOnly, RateLimiter::Mode::kAllIo}) {
|
||||
|
|
@ -60,6 +114,75 @@ TEST_F(RateLimiterTest, Modes) {
|
|||
}
|
||||
}
|
||||
|
||||
TEST_F(RateLimiterTest, GeneratePriorityIterationOrder) {
|
||||
std::unique_ptr<RateLimiter> limiter(NewGenericRateLimiter(
|
||||
20 /* rate_bytes_per_sec */, 1000 * 1000 /* refill_period_us */,
|
||||
10 /* fairness */));
|
||||
|
||||
bool possible_random_one_in_fairness_results_for_high_mid_pri[4][2] = {
|
||||
{false, false}, {false, true}, {true, false}, {true, true}};
|
||||
std::vector<Env::IOPriority> possible_priority_iteration_orders[4] = {
|
||||
{Env::IO_USER, Env::IO_HIGH, Env::IO_MID, Env::IO_LOW},
|
||||
{Env::IO_USER, Env::IO_HIGH, Env::IO_LOW, Env::IO_MID},
|
||||
{Env::IO_USER, Env::IO_MID, Env::IO_LOW, Env::IO_HIGH},
|
||||
{Env::IO_USER, Env::IO_LOW, Env::IO_MID, Env::IO_HIGH}};
|
||||
|
||||
for (int i = 0; i < 4; ++i) {
|
||||
SyncPoint::GetInstance()->SetCallBack(
|
||||
"GenericRateLimiter::GeneratePriorityIterationOrder::"
|
||||
"PostRandomOneInFairnessForHighPri",
|
||||
[&](void* arg) {
|
||||
bool* high_pri_iterated_after_mid_low_pri = (bool*)arg;
|
||||
*high_pri_iterated_after_mid_low_pri =
|
||||
possible_random_one_in_fairness_results_for_high_mid_pri[i][0];
|
||||
});
|
||||
|
||||
SyncPoint::GetInstance()->SetCallBack(
|
||||
"GenericRateLimiter::GeneratePriorityIterationOrder::"
|
||||
"PostRandomOneInFairnessForMidPri",
|
||||
[&](void* arg) {
|
||||
bool* mid_pri_itereated_after_low_pri = (bool*)arg;
|
||||
*mid_pri_itereated_after_low_pri =
|
||||
possible_random_one_in_fairness_results_for_high_mid_pri[i][1];
|
||||
});
|
||||
|
||||
SyncPoint::GetInstance()->SetCallBack(
|
||||
"GenericRateLimiter::GeneratePriorityIterationOrder::"
|
||||
"PreReturnPriIterationOrder",
|
||||
[&](void* arg) {
|
||||
std::vector<Env::IOPriority>* pri_iteration_order =
|
||||
(std::vector<Env::IOPriority>*)arg;
|
||||
EXPECT_EQ(*pri_iteration_order, possible_priority_iteration_orders[i])
|
||||
<< "Failed to generate priority iteration order correctly when "
|
||||
"high_pri_iterated_after_mid_low_pri = "
|
||||
<< possible_random_one_in_fairness_results_for_high_mid_pri[i][0]
|
||||
<< ", mid_pri_itereated_after_low_pri = "
|
||||
<< possible_random_one_in_fairness_results_for_high_mid_pri[i][1]
|
||||
<< std::endl;
|
||||
});
|
||||
|
||||
SyncPoint::GetInstance()->EnableProcessing();
|
||||
|
||||
limiter->Request(20 /* request max bytes to drain so that refill and order
|
||||
generation will be triggered every time
|
||||
GenericRateLimiter::Request() is called */
|
||||
,
|
||||
Env::IO_USER, nullptr /* stats */,
|
||||
RateLimiter::OpType::kWrite);
|
||||
}
|
||||
|
||||
SyncPoint::GetInstance()->DisableProcessing();
|
||||
SyncPoint::GetInstance()->ClearCallBack(
|
||||
"GenericRateLimiter::GeneratePriorityIterationOrder::"
|
||||
"PreReturnPriIterationOrder");
|
||||
SyncPoint::GetInstance()->ClearCallBack(
|
||||
"GenericRateLimiter::GeneratePriorityIterationOrder::"
|
||||
"PostRandomOneInFairnessForMidPri");
|
||||
SyncPoint::GetInstance()->ClearCallBack(
|
||||
"GenericRateLimiter::GeneratePriorityIterationOrder::"
|
||||
"PostRandomOneInFairnessForHighPri");
|
||||
}
|
||||
|
||||
TEST_F(RateLimiterTest, Rate) {
|
||||
auto* env = Env::Default();
|
||||
struct Arg {
|
||||
|
|
@ -83,11 +206,24 @@ TEST_F(RateLimiterTest, Rate) {
|
|||
Random r((uint32_t)(thread_clock->NowNanos() %
|
||||
std::numeric_limits<uint32_t>::max()));
|
||||
while (thread_clock->NowMicros() < until) {
|
||||
for (int i = 0; i < static_cast<int>(r.Skewed(arg->burst * 2) + 1); ++i) {
|
||||
arg->limiter->Request(r.Uniform(arg->request_size - 1) + 1,
|
||||
Env::IO_USER, nullptr /* stats */,
|
||||
RateLimiter::OpType::kWrite);
|
||||
}
|
||||
|
||||
for (int i = 0; i < static_cast<int>(r.Skewed(arg->burst) + 1); ++i) {
|
||||
arg->limiter->Request(r.Uniform(arg->request_size - 1) + 1,
|
||||
Env::IO_HIGH, nullptr /* stats */,
|
||||
RateLimiter::OpType::kWrite);
|
||||
}
|
||||
|
||||
for (int i = 0; i < static_cast<int>(r.Skewed(arg->burst / 2 + 1) + 1);
|
||||
++i) {
|
||||
arg->limiter->Request(r.Uniform(arg->request_size - 1) + 1, Env::IO_MID,
|
||||
nullptr /* stats */, RateLimiter::OpType::kWrite);
|
||||
}
|
||||
|
||||
arg->limiter->Request(r.Uniform(arg->request_size - 1) + 1, Env::IO_LOW,
|
||||
nullptr /* stats */, RateLimiter::OpType::kWrite);
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in New Issue