Files
scylladb/cdc/log.hh
Benny Halevy 3feb759943 everywhere: use utils::chunked_vector for list of mutations
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
2025-07-13 19:13:11 +03:00

127 lines
4.1 KiB
C++

/*
* Copyright (C) 2019-present ScyllaDB
*/
/*
* SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
*/
/*
* This module manages CDC log tables. It contains facilities used to:
* - perform schema changes to CDC log tables correspondingly when base tables are changed,
* - perform writes to CDC log tables correspondingly when writes to base tables are made.
*/
#pragma once
#include <vector>
#include <seastar/core/future.hh>
#include <seastar/core/lowres_clock.hh>
#include <seastar/core/shared_ptr.hh>
#include <seastar/core/sstring.hh>
#include "timestamp.hh"
#include "tracing/trace_state.hh"
#include "utils/UUID.hh"
class schema;
using schema_ptr = seastar::lw_shared_ptr<const schema>;
namespace locator {
class token_metadata;
} // namespace locator
namespace service {
class migration_notifier;
class storage_proxy;
class query_state;
} // namespace service
class mutation;
class partition_key;
namespace replica {
class database;
}
namespace cdc {
struct operation_result_tracker;
class db_context;
class metadata;
bool is_log_name(const std::string_view& table_name);
/// \brief CDC service, responsible for schema listeners
///
/// CDC service will listen for schema changes and iff CDC is enabled/changed
/// create/modify/delete corresponding log tables etc as part of the schema change.
///
class cdc_service final : public async_sharded_service<cdc::cdc_service> {
class impl;
std::unique_ptr<impl> _impl;
public:
future<> stop();
cdc_service(service::storage_proxy&, cdc::metadata&, service::migration_notifier&);
cdc_service(db_context);
~cdc_service();
// If any of the mutations are cdc enabled, optionally selects preimage, and adds the
// appropriate augments to set the log entries.
// Iff post-image is enabled for any of these, a non-empty callback is also
// returned to be invoked post the mutation query.
future<std::tuple<utils::chunked_vector<mutation>, lw_shared_ptr<operation_result_tracker>>> augment_mutation_call(
lowres_clock::time_point timeout,
utils::chunked_vector<mutation>&& mutations,
tracing::trace_state_ptr tr_state,
db::consistency_level write_cl
);
bool needs_cdc_augmentation(const utils::chunked_vector<mutation>&) const;
};
struct db_context final {
service::storage_proxy& _proxy;
service::migration_notifier& _migration_notifier;
cdc::metadata& _cdc_metadata;
db_context(service::storage_proxy& proxy, cdc::metadata& cdc_meta, service::migration_notifier& notifier) noexcept
: _proxy(proxy), _migration_notifier(notifier), _cdc_metadata(cdc_meta) {}
};
// cdc log table operation
enum class operation : int8_t {
// note: these values will eventually be read by a third party, probably not privvy to this
// enum decl, so don't change the constant values (or the datatype).
pre_image = 0, update = 1, insert = 2, row_delete = 3, partition_delete = 4,
range_delete_start_inclusive = 5, range_delete_start_exclusive = 6, range_delete_end_inclusive = 7, range_delete_end_exclusive = 8,
post_image = 9,
};
bool is_log_for_some_table(const replica::database& db, const sstring& ks_name, const std::string_view& table_name);
schema_ptr get_base_table(const replica::database&, const schema&);
schema_ptr get_base_table(const replica::database&, std::string_view, std::string_view);
seastar::sstring base_name(std::string_view log_name);
seastar::sstring log_name(std::string_view table_name);
seastar::sstring log_data_column_name(std::string_view column_name);
seastar::sstring log_meta_column_name(std::string_view column_name);
bytes log_data_column_name_bytes(const bytes& column_name);
bytes log_meta_column_name_bytes(const bytes& column_name);
seastar::sstring log_data_column_deleted_name(std::string_view column_name);
bytes log_data_column_deleted_name_bytes(const bytes& column_name);
seastar::sstring log_data_column_deleted_elements_name(std::string_view column_name);
bytes log_data_column_deleted_elements_name_bytes(const bytes& column_name);
bool is_cdc_metacolumn_name(const sstring& name);
utils::UUID generate_timeuuid(api::timestamp_type t);
} // namespace cdc