mirror of
https://github.com/scylladb/scylladb.git
synced 2026-05-09 01:11:57 +00:00
3feb759943
Currently, we use std::vector<*mutation> to keep
a list of mutations for processing.
This can lead to large allocation, e.g. when the vector
size is a function of the number of tables.
Use a chunked vector instead to prevent oversized allocations.
`perf-simple-query --smp 1` results obtained for fixed 400MHz frequency
and PGO disabled:
Before (read path):
```
enable-cache=1
Running test with config: {partitions=10000, concurrency=100, mode=read, query_single_key=no, counters=no}
Disabling auto compaction
Creating 10000 partitions...
89055.97 tps ( 66.1 allocs/op, 0.0 logallocs/op, 14.2 tasks/op, 39417 insns/op, 18003 cycles/op, 0 errors)
103372.72 tps ( 66.1 allocs/op, 0.0 logallocs/op, 14.2 tasks/op, 39380 insns/op, 17300 cycles/op, 0 errors)
98942.27 tps ( 66.1 allocs/op, 0.0 logallocs/op, 14.2 tasks/op, 39413 insns/op, 17336 cycles/op, 0 errors)
103752.93 tps ( 66.1 allocs/op, 0.0 logallocs/op, 14.2 tasks/op, 39407 insns/op, 17252 cycles/op, 0 errors)
102516.77 tps ( 66.1 allocs/op, 0.0 logallocs/op, 14.2 tasks/op, 39403 insns/op, 17288 cycles/op, 0 errors)
throughput:
mean= 99528.13 standard-deviation=6155.71
median= 102516.77 median-absolute-deviation=3844.59
maximum=103752.93 minimum=89055.97
instructions_per_op:
mean= 39403.99 standard-deviation=14.25
median= 39406.75 median-absolute-deviation=9.30
maximum=39416.63 minimum=39380.39
cpu_cycles_per_op:
mean= 17435.81 standard-deviation=318.24
median= 17300.40 median-absolute-deviation=147.59
maximum=18002.53 minimum=17251.75
```
After (read path)
```
enable-cache=1
Running test with config: {partitions=10000, concurrency=100, mode=read, query_single_key=no, counters=no}
Disabling auto compaction
Creating 10000 partitions...
59755.04 tps ( 66.2 allocs/op, 0.0 logallocs/op, 14.2 tasks/op, 39466 insns/op, 22834 cycles/op, 0 errors)
71854.16 tps ( 66.1 allocs/op, 0.0 logallocs/op, 14.2 tasks/op, 39417 insns/op, 17883 cycles/op, 0 errors)
82149.45 tps ( 66.1 allocs/op, 0.0 logallocs/op, 14.2 tasks/op, 39411 insns/op, 17409 cycles/op, 0 errors)
49640.04 tps ( 66.1 allocs/op, 0.0 logallocs/op, 14.3 tasks/op, 39474 insns/op, 19975 cycles/op, 0 errors)
54963.22 tps ( 66.1 allocs/op, 0.0 logallocs/op, 14.3 tasks/op, 39474 insns/op, 18235 cycles/op, 0 errors)
throughput:
mean= 63672.38 standard-deviation=13195.12
median= 59755.04 median-absolute-deviation=8709.16
maximum=82149.45 minimum=49640.04
instructions_per_op:
mean= 39448.38 standard-deviation=31.60
median= 39466.17 median-absolute-deviation=25.75
maximum=39474.12 minimum=39411.42
cpu_cycles_per_op:
mean= 19267.01 standard-deviation=2217.03
median= 18234.80 median-absolute-deviation=1384.25
maximum=22834.26 minimum=17408.67
```
`perf-simple-query --smp 1 --write` results obtained for fixed 400MHz frequency
and PGO disabled:
Before (write path):
```
enable-cache=1
Running test with config: {partitions=10000, concurrency=100, mode=write, query_single_key=no, counters=no}
Disabling auto compaction
63736.96 tps ( 59.4 allocs/op, 16.4 logallocs/op, 14.3 tasks/op, 49667 insns/op, 19924 cycles/op, 0 errors)
64109.41 tps ( 59.3 allocs/op, 16.0 logallocs/op, 14.3 tasks/op, 49992 insns/op, 20084 cycles/op, 0 errors)
56950.47 tps ( 59.3 allocs/op, 16.0 logallocs/op, 14.3 tasks/op, 50005 insns/op, 20501 cycles/op, 0 errors)
44858.42 tps ( 59.3 allocs/op, 16.0 logallocs/op, 14.3 tasks/op, 50014 insns/op, 21947 cycles/op, 0 errors)
28592.87 tps ( 59.3 allocs/op, 16.0 logallocs/op, 14.3 tasks/op, 50027 insns/op, 27659 cycles/op, 0 errors)
throughput:
mean= 51649.63 standard-deviation=15059.74
median= 56950.47 median-absolute-deviation=12087.33
maximum=64109.41 minimum=28592.87
instructions_per_op:
mean= 49941.18 standard-deviation=153.76
median= 50005.24 median-absolute-deviation=73.01
maximum=50027.07 minimum=49667.05
cpu_cycles_per_op:
mean= 22023.01 standard-deviation=3249.92
median= 20500.74 median-absolute-deviation=1938.76
maximum=27658.75 minimum=19924.32
```
After (write path)
```
enable-cache=1
Running test with config: {partitions=10000, concurrency=100, mode=write, query_single_key=no, counters=no}
Disabling auto compaction
53395.93 tps ( 59.4 allocs/op, 16.5 logallocs/op, 14.3 tasks/op, 50326 insns/op, 21252 cycles/op, 0 errors)
46527.83 tps ( 59.3 allocs/op, 16.0 logallocs/op, 14.3 tasks/op, 50704 insns/op, 21555 cycles/op, 0 errors)
55846.30 tps ( 59.3 allocs/op, 16.0 logallocs/op, 14.3 tasks/op, 50731 insns/op, 21060 cycles/op, 0 errors)
55669.30 tps ( 59.3 allocs/op, 16.0 logallocs/op, 14.3 tasks/op, 50735 insns/op, 21521 cycles/op, 0 errors)
52130.17 tps ( 59.3 allocs/op, 16.0 logallocs/op, 14.3 tasks/op, 50757 insns/op, 21334 cycles/op, 0 errors)
throughput:
mean= 52713.91 standard-deviation=3795.38
median= 53395.93 median-absolute-deviation=2955.40
maximum=55846.30 minimum=46527.83
instructions_per_op:
mean= 50650.57 standard-deviation=182.46
median= 50731.38 median-absolute-deviation=84.09
maximum=50756.62 minimum=50325.87
cpu_cycles_per_op:
mean= 21344.42 standard-deviation=202.86
median= 21334.00 median-absolute-deviation=176.37
maximum=21554.61 minimum=21060.24
```
Fixes #24815
Improvement for rare corner cases. No backport required
Signed-off-by: Benny Halevy <bhalevy@scylladb.com>
Closes scylladb/scylladb#24919
42 lines
4.6 KiB
C++
42 lines
4.6 KiB
C++
/*
|
|
* Copyright 2012-present ScyllaDB
|
|
*/
|
|
|
|
/*
|
|
* SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
|
|
*/
|
|
|
|
#include "inet_address_vectors.hh"
|
|
#include "message/messaging_service.hh"
|
|
|
|
#include "gms/inet_address_serializer.hh"
|
|
#include "utils/chunked_vector.hh"
|
|
|
|
#include "idl/frozen_mutation.idl.hh"
|
|
#include "idl/tracing.idl.hh"
|
|
#include "idl/view.idl.hh"
|
|
#include "idl/consistency_level.idl.hh"
|
|
#include "idl/read_command.idl.hh"
|
|
#include "idl/query.idl.hh"
|
|
#include "idl/result.idl.hh"
|
|
#include "idl/per_partition_rate_limit_info.idl.hh"
|
|
#include "idl/keys.idl.hh"
|
|
#include "idl/uuid.idl.hh"
|
|
#include "idl/storage_service.idl.hh"
|
|
#include "idl/full_position.idl.hh"
|
|
|
|
verb [[with_client_info, with_timeout, one_way]] mutation (frozen_mutation fm [[ref]], inet_address_vector_replica_set forward [[ref]], gms::inet_address reply_to, unsigned shard, uint64_t response_id, std::optional<tracing::trace_info> trace_info [[ref]] [[version 1.3.0]], db::per_partition_rate_limit::info rate_limit_info [[version 5.1.0]], service::fencing_token fence [[version 5.4.0]], host_id_vector_replica_set forward_id [[ref, version 6.3.0]], locator::host_id reply_to_id [[version 6.3.0]]);
|
|
verb [[with_client_info, one_way]] mutation_done (unsigned shard, uint64_t response_id, db::view::update_backlog backlog [[version 3.1.0]]);
|
|
verb [[with_client_info, one_way]] mutation_failed (unsigned shard, uint64_t response_id, size_t num_failed, db::view::update_backlog backlog [[version 3.1.0]], replica::exception_variant exception [[version 5.1.0]]);
|
|
verb [[with_client_info, with_timeout]] counter_mutation (utils::chunked_vector<frozen_mutation> fms, db::consistency_level cl, std::optional<tracing::trace_info> trace_info [[ref]], service::fencing_token fence [[version 5.4.0]]) -> replica::exception_variant [[version 5.4.0]];
|
|
verb [[with_client_info, with_timeout, one_way]] hint_mutation (frozen_mutation fm [[ref]], inet_address_vector_replica_set forward [[ref]], gms::inet_address reply_to, unsigned shard, uint64_t response_id, std::optional<tracing::trace_info> trace_info [[ref]] [[version 1.3.0]] /* this verb was mistakenly introduced with optional trace_info */, service::fencing_token fence [[version 5.4.0]], host_id_vector_replica_set forward_id [[ref, version 6.3.0]], locator::host_id reply_to_id [[version 6.3.0]]);
|
|
verb [[with_client_info, with_timeout]] read_data (query::read_command cmd [[ref]], ::compat::wrapping_partition_range pr, query::digest_algorithm digest [[version 3.0.0]], db::per_partition_rate_limit::info rate_limit_info [[version 5.1.0]], service::fencing_token fence [[version 5.4.0]]) -> query::result [[lw_shared_ptr]], cache_temperature [[version 2.0.0]], replica::exception_variant [[version 5.1.0]];
|
|
verb [[with_client_info, with_timeout]] read_mutation_data (query::read_command cmd [[ref]], ::compat::wrapping_partition_range pr, service::fencing_token fence [[version 5.4.0]]) -> reconcilable_result [[lw_shared_ptr]], cache_temperature [[version 2.0.0]], replica::exception_variant [[version 5.1.0]];
|
|
verb [[with_client_info, with_timeout]] read_digest (query::read_command cmd [[ref]], ::compat::wrapping_partition_range pr, query::digest_algorithm digest [[version 3.0.0]], db::per_partition_rate_limit::info rate_limit_info [[version 5.1.0]], service::fencing_token fence [[version 5.4.0]]) -> query::result_digest, api::timestamp_type [[version 1.2.0]], cache_temperature [[version 2.0.0]], replica::exception_variant [[version 5.1.0]], std::optional<full_position> [[version 5.2.0]];
|
|
verb [[with_timeout]] truncate (sstring, sstring);
|
|
verb [[]] truncate_with_tablets (sstring ks_name, sstring cf_name, service::frozen_topology_guard frozen_guard);
|
|
verb [[with_client_info, with_timeout]] paxos_prepare (query::read_command cmd [[ref]], partition_key key [[ref]], utils::UUID ballot, bool only_digest, query::digest_algorithm da, std::optional<tracing::trace_info> trace_info [[ref]]) -> service::paxos::prepare_response [[unique_ptr]];
|
|
verb [[with_client_info, with_timeout]] paxos_accept (service::paxos::proposal proposal [[ref]], std::optional<tracing::trace_info> trace_info [[ref]]) -> bool;
|
|
verb [[with_client_info, with_timeout, one_way]] paxos_learn (service::paxos::proposal decision [[ref]], inet_address_vector_replica_set forward [[ref]], gms::inet_address reply_to, unsigned shard, uint64_t response_id, std::optional<tracing::trace_info> trace_info [[ref]], host_id_vector_replica_set forward_id [[ref, version 6.3.0]], locator::host_id reply_to_id [[version 6.3.0]]);
|
|
verb [[with_client_info, with_timeout, one_way]] paxos_prune (table_schema_version schema_id, partition_key key [[ref]], utils::UUID ballot, std::optional<tracing::trace_info> trace_info [[ref]]);
|