Files
scylladb/test/lib/data_model.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

168 lines
5.6 KiB
C++

/*
* Copyright (C) 2019-present ScyllaDB
*/
/*
* SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
*/
#pragma once
#include "mutation/mutation.hh"
#include "cql3/cql3_type.hh"
#include "schema/schema.hh"
namespace tests::data_model {
static constexpr api::timestamp_type previously_removed_column_timestamp = 100;
static constexpr api::timestamp_type data_timestamp = 200;
static constexpr api::timestamp_type column_removal_timestamp = 300;
class mutation_description {
public:
struct expiry_info {
gc_clock::duration ttl;
gc_clock::time_point expiry_point;
};
struct row_marker {
api::timestamp_type timestamp;
std::optional<expiry_info> expiring;
row_marker(api::timestamp_type timestamp = data_timestamp);
row_marker(api::timestamp_type timestamp, gc_clock::duration ttl, gc_clock::time_point expiry_point);
};
using key = std::vector<bytes>;
struct atomic_value {
bytes value;
api::timestamp_type timestamp;
std::optional<expiry_info> expiring;
atomic_value(bytes value, api::timestamp_type timestamp = data_timestamp);
atomic_value(bytes value, api::timestamp_type timestamp, gc_clock::duration ttl, gc_clock::time_point expiry_point);
};
struct collection_element {
bytes key;
atomic_value value;
};
struct collection {
tombstone tomb;
std::vector<collection_element> elements;
collection() = default;
collection(std::initializer_list<collection_element> elements);
collection(std::vector<collection_element> elements);
};
using value = std::variant<atomic_value, collection>;
struct cell {
sstring column_name;
value data_value;
};
using row = std::vector<cell>;
struct clustered_row {
row_marker marker;
row_tombstone tomb;
row cells;
};
struct range_tombstone {
interval<key> range;
tombstone tomb;
};
private:
key _partition_key;
tombstone _partition_tombstone;
row _static_row;
std::map<key, clustered_row> _clustered_rows;
std::vector<range_tombstone> _range_tombstones;
private:
static void remove_column(row& r, const sstring& name);
public:
explicit mutation_description(key partition_key);
void set_partition_tombstone(tombstone partition_tombstone);
void add_static_cell(const sstring& column, value v);
void add_clustered_cell(const key& ck, const sstring& column, value v);
void add_clustered_row_marker(const key& ck, row_marker marker = row_marker(data_timestamp));
void add_clustered_row_tombstone(const key& ck, row_tombstone tomb);
void remove_static_column(const sstring& name);
void remove_regular_column(const sstring& name);
// Both overloads accept out-of-order ranges and will make sure the
// range-tombstone is created with start <= end.
void add_range_tombstone(const key& start, const key& end,
tombstone tomb = tombstone(previously_removed_column_timestamp, gc_clock::time_point()));
void add_range_tombstone(interval<key> range,
tombstone tomb = tombstone(previously_removed_column_timestamp, gc_clock::time_point()));
mutation build(schema_ptr s) const;
};
class table_description {
public:
using column = std::tuple<sstring, data_type>;
struct removed_column {
sstring name;
data_type type;
api::timestamp_type removal_timestamp;
};
private:
std::vector<column> _partition_key;
std::vector<column> _clustering_key;
std::vector<column> _static_columns;
std::vector<column> _regular_columns;
std::vector<removed_column> _removed_columns;
utils::chunked_vector<mutation_description> _mutations;
std::vector<sstring> _change_log;
private:
static std::vector<column>::iterator find_column(std::vector<column>& columns, const sstring& name);
static void add_column(std::vector<column>& columns, const sstring& name, data_type type);
void add_old_column(const sstring& name, data_type type);
void remove_column(std::vector<column>& columns, const sstring& name);
static void alter_column_type(std::vector<column>& columns, const sstring& name, data_type new_type);
schema_ptr build_schema() const;
utils::chunked_vector<mutation> build_mutations(schema_ptr s) const;
public:
explicit table_description(std::vector<column> partition_key, std::vector<column> clustering_key);
void add_static_column(const sstring& name, data_type type);
void add_regular_column(const sstring& name, data_type type);
void add_old_static_column(const sstring& name, data_type type);
void add_old_regular_column(const sstring& name, data_type type);
void remove_static_column(const sstring& name);
void remove_regular_column(const sstring& name);
void alter_partition_column_type(const sstring& name, data_type new_type);
void alter_clustering_column_type(const sstring& name, data_type new_type);
void alter_static_column_type(const sstring& name, data_type new_type);
void alter_regular_column_type(const sstring& name, data_type new_type);
void rename_partition_column(const sstring& from, const sstring& to);
void rename_clustering_column(const sstring& from, const sstring& to);
utils::chunked_vector<mutation_description>& unordered_mutations() { return _mutations; }
const utils::chunked_vector<mutation_description>& unordered_mutations() const { return _mutations; }
struct table {
sstring schema_changes_log;
schema_ptr schema;
utils::chunked_vector<mutation> mutations;
};
table build() const;
};
}