Files
scylladb/test/boost/schema_loader_test.cc
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

336 lines
15 KiB
C++

/*
* Copyright (C) 2021-present ScyllaDB
*/
/*
* SPDX-License-Identifier: LicenseRef-ScyllaDB-Source-Available-1.0
*/
#include "test/lib/log.hh"
#include "test/lib/scylla_test_case.hh"
#include "test/lib/random_schema.hh"
#include "test/lib/random_utils.hh"
#include "test/lib/sstable_test_env.hh"
#include "test/lib/mutation_reader_assertions.hh"
#include "db/config.hh"
#include "index/secondary_index_manager.hh"
#include "sstables/sstable_writer.hh"
#include "readers/from_mutations.hh"
#include "tools/schema_loader.hh"
#include "view_info.hh"
SEASTAR_THREAD_TEST_CASE(test_empty) {
db::config dbcfg;
BOOST_REQUIRE_THROW(tools::load_schemas(dbcfg, "").get(), std::exception);
BOOST_REQUIRE_THROW(tools::load_schemas(dbcfg, ";").get(), std::exception);
}
SEASTAR_THREAD_TEST_CASE(test_keyspace_only) {
db::config dbcfg;
BOOST_REQUIRE_EQUAL(tools::load_schemas(dbcfg, "CREATE KEYSPACE ks WITH replication = {'class': 'NetworkTopologyStrategy', 'replication_factor': 1};").get().size(), 0);
}
SEASTAR_THREAD_TEST_CASE(test_single_table) {
db::config dbcfg;
BOOST_REQUIRE_EQUAL(tools::load_schemas(dbcfg, "CREATE TABLE ks.cf (pk int PRIMARY KEY, v int)").get().size(), 1);
BOOST_REQUIRE_EQUAL(tools::load_schemas(dbcfg, "CREATE TABLE ks.cf (pk int PRIMARY KEY, v map<int, int>)").get().size(), 1);
BOOST_REQUIRE_EQUAL(tools::load_schemas(dbcfg, "CREATE KEYSPACE ks WITH replication = {'class': 'NetworkTopologyStrategy', 'replication_factor': 1}; CREATE TABLE ks.cf (pk int PRIMARY KEY, v int);").get().size(), 1);
}
SEASTAR_THREAD_TEST_CASE(test_keyspace_replication_strategy) {
db::config dbcfg;
BOOST_REQUIRE_EQUAL(tools::load_schemas(dbcfg, "CREATE KEYSPACE ks WITH replication = {'class': 'NetworkTopologyStrategy', 'replication_factor': 1}; CREATE TABLE ks.cf (pk int PRIMARY KEY, v int);").get().size(), 1);
BOOST_REQUIRE_EQUAL(tools::load_schemas(dbcfg, "CREATE KEYSPACE ks WITH replication = {'class': 'NetworkTopologyStrategy', 'replication_factor': 3}; CREATE TABLE ks.cf (pk int PRIMARY KEY, v int);").get().size(), 1);
BOOST_REQUIRE_EQUAL(tools::load_schemas(dbcfg, "CREATE KEYSPACE ks WITH replication = {'class': 'NetworkTopologyStrategy', 'mydc1': 1, 'mydc2': 4}; CREATE TABLE ks.cf (pk int PRIMARY KEY, v int);").get().size(), 1);
}
SEASTAR_THREAD_TEST_CASE(test_multiple_tables) {
db::config dbcfg;
BOOST_REQUIRE_EQUAL(tools::load_schemas(dbcfg, "CREATE TABLE ks.cf1 (pk int PRIMARY KEY, v int); CREATE TABLE ks.cf2 (pk int PRIMARY KEY, v int)").get().size(), 2);
BOOST_REQUIRE_EQUAL(tools::load_schemas(dbcfg, "CREATE TABLE ks.cf1 (pk int PRIMARY KEY, v int); CREATE TABLE ks.cf2 (pk int PRIMARY KEY, v int);").get().size(), 2);
BOOST_REQUIRE_EQUAL(tools::load_schemas(
dbcfg,
"CREATE KEYSPACE ks WITH replication = {'class': 'NetworkTopologyStrategy', 'replication_factor': 1}; "
"CREATE TABLE ks.cf1 (pk int PRIMARY KEY, v int); "
"CREATE TABLE ks.cf2 (pk int PRIMARY KEY, v int); "
"CREATE TABLE ks.cf3 (pk int PRIMARY KEY, v int); "
).get().size(), 3);
BOOST_REQUIRE_EQUAL(tools::load_schemas(
dbcfg,
"CREATE KEYSPACE ks1 WITH replication = {'class': 'NetworkTopologyStrategy', 'replication_factor': 1}; "
"CREATE TABLE ks1.cf (pk int PRIMARY KEY, v int); "
"CREATE KEYSPACE ks2 WITH replication = {'class': 'NetworkTopologyStrategy', 'replication_factor': 1}; "
"CREATE TABLE ks2.cf (pk int PRIMARY KEY, v int); "
).get().size(), 2);
}
SEASTAR_THREAD_TEST_CASE(test_udts) {
db::config dbcfg;
BOOST_REQUIRE_EQUAL(tools::load_schemas(
dbcfg,
"CREATE KEYSPACE ks WITH replication = {'class': 'NetworkTopologyStrategy', 'replication_factor': 1}; "
"CREATE TYPE ks.type1 (f1 int, f2 text); "
"CREATE TABLE ks.cf (pk int PRIMARY KEY, v frozen<type1>); "
).get().size(), 1);
BOOST_REQUIRE_EQUAL(tools::load_schemas(
dbcfg,
"CREATE KEYSPACE ks WITH replication = {'class': 'NetworkTopologyStrategy', 'replication_factor': 1}; "
"CREATE TYPE ks.type1 (f1 int, f2 text); "
"CREATE TABLE ks.cf (pk int PRIMARY KEY, v type1); "
).get().size(), 1);
BOOST_REQUIRE_EQUAL(tools::load_schemas(
dbcfg,
"CREATE KEYSPACE ks1 WITH replication = {'class': 'NetworkTopologyStrategy', 'replication_factor': 1}; "
"CREATE TYPE ks1.type1 (f1 int, f2 text); "
"CREATE TABLE ks1.cf (pk int PRIMARY KEY, v frozen<type1>); "
"CREATE KEYSPACE ks2 WITH replication = {'class': 'NetworkTopologyStrategy', 'replication_factor': 1}; "
"CREATE TYPE ks2.type1 (f1 int, f2 text); "
"CREATE TABLE ks2.cf (pk int PRIMARY KEY, v frozen<type1>); "
).get().size(), 2);
BOOST_REQUIRE_EQUAL(tools::load_schemas(
dbcfg,
"CREATE TYPE ks.type1 (f1 int, f2 text); "
"CREATE TABLE ks.cf (pk int PRIMARY KEY, v frozen<type1>); "
).get().size(), 1);
BOOST_REQUIRE_EQUAL(tools::load_schemas(
dbcfg,
"CREATE TYPE ks1.type1 (f1 int, f2 text); "
"CREATE TABLE ks1.cf (pk int PRIMARY KEY, v frozen<type1>); "
"CREATE TYPE ks2.type1 (f1 int, f2 text); "
"CREATE TABLE ks2.cf (pk int PRIMARY KEY, v frozen<type1>); "
).get().size(), 2);
}
SEASTAR_THREAD_TEST_CASE(test_dropped_columns) {
db::config dbcfg;
BOOST_REQUIRE_EQUAL(tools::load_schemas(
dbcfg,
"CREATE TABLE ks.cf (pk int PRIMARY KEY, v1 int); "
"INSERT INTO system_schema.dropped_columns (keyspace_name, table_name, column_name, dropped_time, type) VALUES ('ks', 'cf', 'v2', 1631011979170675, 'int'); "
).get().size(), 1);
BOOST_REQUIRE_THROW(tools::load_schemas(
dbcfg,
"CREATE TABLE ks.cf (pk int PRIMARY KEY, v1 int); "
"INSERT INTO ks.cf (pk, v1) VALUES (0, 0); "
).get(), std::exception);
BOOST_REQUIRE_THROW(tools::load_schemas(
dbcfg,
"INSERT INTO system_schema.dropped_columns (keyspace_name, table_name, column_name, dropped_time, type) VALUES ('ks', 'cf', 'v2', 1631011979170675, 'int'); "
"CREATE TABLE ks.cf (pk int PRIMARY KEY, v1 int); "
).get(), std::exception);
BOOST_REQUIRE_THROW(tools::load_schemas(
dbcfg,
"CREATE TABLE ks.cf (pk int PRIMARY KEY, v1 int); "
"INSERT INTO system_schema.dropped_columns (keyspace_name, table_name, column_name, dropped_time, type) VALUES ('unknown_ks', 'unknown_cf', 'v2', 1631011979170675, 'int'); "
).get(), std::exception);
BOOST_REQUIRE_THROW(tools::load_schemas(
dbcfg,
"CREATE TABLE ks.cf (pk int PRIMARY KEY, v1 int); "
"INSERT INTO system_schema.dropped_columns (keyspace_name, table_name, column_name, dropped_time, type) VALUES ('unknown_ks', 'cf', 'v2', 1631011979170675, 'int'); "
).get(), std::exception);
BOOST_REQUIRE_THROW(tools::load_schemas(
dbcfg,
"CREATE TABLE ks.cf (pk int PRIMARY KEY, v1 int); "
"INSERT INTO system_schema.dropped_columns (keyspace_name, table_name, column_name, dropped_time, type) VALUES ('ks', 'unknown_cf', 'v2', 1631011979170675, 'int'); "
).get(), std::exception);
}
/// Check that:
/// * schemas[0] is a base schema (it is not a view)
/// * schemas[1]..schemas.back() are views
/// * schemas[0] is the base of each view
/// * the type of schemas[i] matches views_type[i - 1]
enum class view_type {
index,
view
};
void check_views(std::vector<schema_ptr> schemas, std::vector<view_type> views_type, std::source_location sl = std::source_location::current()) {
testlog.info("Checking views built at {}:{}", sl.file_name(), sl.line());
BOOST_REQUIRE_EQUAL(schemas.size(), views_type.size() + 1);
const auto base_schema = schemas.front();
testlog.info("Base table is {}.{}", base_schema->ks_name(), base_schema->cf_name());
BOOST_REQUIRE(!base_schema->is_view());
auto schema_it = schemas.begin() + 1;
auto view_type_it = views_type.begin();
while (schema_it != schemas.end() && view_type_it != views_type.end()) {
auto schema = *schema_it;
auto type = *view_type_it;
testlog.info("Checking view {}.{} is_index={}", schema->ks_name(), schema->cf_name(), type == view_type::index);
BOOST_REQUIRE(schema->is_view());
BOOST_REQUIRE_EQUAL(base_schema->id(), schema->view_info()->base_id());
if (type == view_type::index) {
BOOST_REQUIRE(base_schema->has_index(secondary_index::index_name_from_table_name(schema->cf_name())));
}
++schema_it;
++view_type_it;
}
BOOST_REQUIRE(schema_it == schemas.end());
BOOST_REQUIRE(view_type_it == views_type.end());
}
SEASTAR_THREAD_TEST_CASE(test_materialized_view) {
db::config dbcfg;
check_views(
tools::load_schemas(
dbcfg,
"CREATE TABLE ks.cf (pk int PRIMARY KEY, v int); "
"CREATE MATERIALIZED VIEW ks.cf_by_v AS"
" SELECT * FROM ks.cf"
" WHERE v IS NOT NULL"
" PRIMARY KEY (v, pk);").get(),
{view_type::view});
check_views(
tools::load_schemas(
dbcfg,
"CREATE TABLE ks.cf (pk int PRIMARY KEY, v1 int, v2 int); "
"CREATE MATERIALIZED VIEW ks.cf_by_v1 AS"
" SELECT * FROM ks.cf"
" WHERE v1 IS NOT NULL"
" PRIMARY KEY (v1, pk);"
"CREATE MATERIALIZED VIEW ks.cf_by_v2 AS"
" SELECT * FROM ks.cf"
" WHERE v2 IS NOT NULL"
" PRIMARY KEY (v2, pk);").get(),
{view_type::view, view_type::view});
check_views(
tools::load_schemas(
dbcfg,
"CREATE TABLE ks.cf (pk int PRIMARY KEY, v int); "
"CREATE MATERIALIZED VIEW IF NOT EXISTS ks.cf_by_v AS"
" SELECT * FROM ks.cf"
" WHERE v IS NOT NULL"
" PRIMARY KEY (v, pk);"
"CREATE MATERIALIZED VIEW IF NOT EXISTS ks.cf_by_v AS"
" SELECT * FROM ks.cf"
" WHERE v IS NOT NULL"
" PRIMARY KEY (v, pk);").get(),
{view_type::view});
};
SEASTAR_THREAD_TEST_CASE(test_index) {
db::config dbcfg;
check_views(
tools::load_schemas(
dbcfg,
"CREATE TABLE ks.cf (pk int PRIMARY KEY, v int); "
"CREATE INDEX cf_by_v ON ks.cf (v);").get(),
{view_type::index});
check_views(
tools::load_schemas(
dbcfg,
"CREATE TABLE ks.cf (pk int PRIMARY KEY, v int); "
"CREATE INDEX ON ks.cf (v);").get(),
{view_type::index});
check_views(
tools::load_schemas(
dbcfg,
"CREATE TABLE ks.cf (pk int PRIMARY KEY, v1 int, v2 int); "
"CREATE INDEX cf_by_v1 ON ks.cf (v1);"
"CREATE INDEX cf_by_v2 ON ks.cf (v2);").get(),
{view_type::index, view_type::index});
check_views(
tools::load_schemas(
dbcfg,
"CREATE TABLE ks.cf (pk int PRIMARY KEY, v1 int, v2 int); "
"CREATE INDEX ON ks.cf (v1);"
"CREATE INDEX ON ks.cf (v2);").get(),
{view_type::index, view_type::index});
check_views(
tools::load_schemas(
dbcfg,
"CREATE TABLE ks.cf (pk int PRIMARY KEY, v int); "
"CREATE INDEX IF NOT EXISTS cf_by_v ON ks.cf (v);"
"CREATE INDEX IF NOT EXISTS cf_by_v ON ks.cf (v);").get(),
{view_type::index});
check_views(
tools::load_schemas(
dbcfg,
"CREATE TABLE ks.cf (pk int PRIMARY KEY, v int); "
"CREATE INDEX IF NOT EXISTS ON ks.cf (v);"
"CREATE INDEX IF NOT EXISTS ON ks.cf (v);").get(),
{view_type::index});
}
SEASTAR_THREAD_TEST_CASE(test_mv_index) {
db::config dbcfg;
check_views(
tools::load_schemas(
dbcfg,
"CREATE TABLE ks.cf (pk int PRIMARY KEY, v1 int, v2 int); "
"CREATE MATERIALIZED VIEW ks.cf_by_v1 AS"
" SELECT * FROM ks.cf"
" WHERE v1 IS NOT NULL"
" PRIMARY KEY (v1, pk);"
"CREATE INDEX ON ks.cf (v2);"
"CREATE MATERIALIZED VIEW ks.cf_by_v2 AS"
" SELECT * FROM ks.cf"
" WHERE v2 IS NOT NULL"
" PRIMARY KEY (v2, pk);"
"CREATE INDEX ON ks.cf (v1);").get(),
{view_type::view, view_type::index, view_type::view, view_type::index});
}
void check_sstable_schema(sstables::test_env& env, std::filesystem::path sst_path, const utils::chunked_vector<mutation>& mutations) {
db::config dbcfg;
auto schema = tools::load_schema_from_sstable(dbcfg, sst_path).get();
const auto ed = sstables::parse_path(sst_path, "ks", "tbl");
const auto dir_path = sst_path.parent_path();
auto sst = env.make_sstable(schema, dir_path.c_str(), ed.generation, ed.version, ed.format);
sst->load(schema->get_sharder()).get();
auto rd = assert_that(sst->make_reader(schema, env.make_reader_permit(), query::full_partition_range, schema->full_slice()));
for (const auto& m : mutations) {
rd.produces(m);
}
rd.produces_end_of_stream();
}
SEASTAR_TEST_CASE(test_load_schema_from_sstable) {
return sstables::test_env::do_with_async([&] (sstables::test_env& env) {
auto random_spec = tests::make_random_schema_specification(
get_name(),
std::uniform_int_distribution<size_t>(1, 4), // partition-key
std::uniform_int_distribution<size_t>(0, 4), // clustering-key
std::uniform_int_distribution<size_t>(0, 8), // static
std::uniform_int_distribution<size_t>(0, 8)); // regular
auto random_schema = tests::random_schema{tests::random::get_int<uint32_t>(), *random_spec};
auto schema = random_schema.schema();
const auto mutations = tests::generate_random_mutations(random_schema, 10).get();
for (const auto& version : sstables::writable_sstable_versions) {
auto sst = env.make_sstable(schema, version);
{
auto mr = make_mutation_reader_from_mutations(schema, env.make_reader_permit(), mutations);
auto close_mr = deferred_close(mr);
const auto cfg = env.manager().configure_writer();
auto wr = sst->get_writer(*schema, mutations.size(), cfg, encoding_stats{});
mr.consume_in_thread(std::move(wr));
}
// Do the check in a separate method to ensure we don't accidentally
// re-use the original schema.
check_sstable_schema(env, std::filesystem::path(fmt::to_string(sst->get_filename())), mutations);
}
});
}