Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Remove unused table versions along with schema versions in TSchemaVer… #10058

Merged
merged 3 commits into from
Oct 9, 2024
Merged

Remove unused table versions along with schema versions in TSchemaVer… #10058

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4104588
Remove unused table versions along with schema versions in TSchemaVer…
aavdonkin Oct 3, 2024
1d66f02
Added test
aavdonkin Oct 4, 2024
49e9b47
Moved repeated code to lambda
aavdonkin Oct 8, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
76 changes: 70 additions & 6 deletions ydb/core/tx/columnshard/normalizer/schema_version/version.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,20 +23,44 @@ class TSchemaVersionNormalizer::TNormalizerResult : public INormalizerChanges {
}
};

class TTableKey {
public:
ui64 PathId;
ui64 Step;
ui64 TxId;
ui64 Version;

public:
TTableKey(ui64 pathId, ui64 step, ui64 txId, ui64 version)
: PathId(pathId)
, Step(step)
, TxId(txId)
, Version(version)
{
}
};

std::vector<TKey> VersionsToRemove;
std::vector<TTableKey> TableVersionsToRemove;

public:
TNormalizerResult(std::vector<TKey>&& versions)
TNormalizerResult(std::vector<TKey>&& versions, std::vector<TTableKey>&& tableVersions)
: VersionsToRemove(versions)
, TableVersionsToRemove(tableVersions)
{
}

bool ApplyOnExecute(NTabletFlatExecutor::TTransactionContext& txc, const TNormalizationController& /* normController */) const override {
using namespace NColumnShard;
NIceDb::TNiceDb db(txc.DB);
for (auto& key: VersionsToRemove) {
LOG_S_DEBUG("Removing schema version in TSchemaVersionNormalizer " << key.Version);
db.Table<Schema::SchemaPresetVersionInfo>().Key(key.Id, key.Step, key.TxId).Delete();
}
for (auto& key: TableVersionsToRemove) {
LOG_S_DEBUG("Removing table version in TSchemaVersionNormalizer " << key.Version << " pathId " << key.PathId);
db.Table<Schema::TableVersionInfo>().Key(key.PathId, key.Step, key.TxId).Delete();
}
return true;
}

Expand Down Expand Up @@ -78,6 +102,7 @@ class TSchemaVersionNormalizer::TNormalizerResult : public INormalizerChanges {
}

std::vector<TKey> unusedSchemaIds;
std::vector<TTableKey> unusedTableSchemaIds;
std::optional<ui64> maxVersion;
std::vector<INormalizerChanges::TPtr> changes;

Expand Down Expand Up @@ -107,18 +132,57 @@ class TSchemaVersionNormalizer::TNormalizerResult : public INormalizerChanges {
}
}

{
auto rowset = db.Table<Schema::TableVersionInfo>().Select();
if (!rowset.IsReady()) {
return std::nullopt;
}

while (!rowset.EndOfSet()) {
const ui64 pathId = rowset.GetValue<Schema::TableVersionInfo::PathId>();

NKikimrTxColumnShard::TTableVersionInfo versionInfo;
Y_ABORT_UNLESS(versionInfo.ParseFromString(rowset.GetValue<Schema::TableVersionInfo::InfoProto>()));
if (versionInfo.HasSchema()) {
ui64 version = versionInfo.GetSchema().GetVersion();
if (!usedSchemaVersions.contains(version)) {
unusedTableSchemaIds.emplace_back(pathId, rowset.GetValue<Schema::TableVersionInfo::SinceStep>(), rowset.GetValue<Schema::TableVersionInfo::SinceTxId>(), version);
}
}

if (!rowset.Next()) {
return std::nullopt;
}
}
}

std::vector<TTableKey> tablePortion;
std::vector<TKey> portion;
tablePortion.reserve(10000);
portion.reserve(10000);
auto addPortion = [&]() {
if (portion.size() + tablePortion.size() >= 10000) {
changes.emplace_back(std::make_shared<TNormalizerResult>(std::move(portion), std::move(tablePortion)));
portion = std::vector<TKey>();
tablePortion = std::vector<TTableKey>();
}
};
for (const auto& id: unusedSchemaIds) {
if (!maxVersion.has_value() || (id.Version != *maxVersion)) {
portion.push_back(id);
if (portion.size() >= 10000) {
changes.emplace_back(std::make_shared<TNormalizerResult>(std::move(portion)));
}
addPortion();
}
}

for (const auto& id: unusedTableSchemaIds) {
if (!maxVersion.has_value() || (id.Version != *maxVersion)) {
tablePortion.push_back(id);
addPortion();
}
}
if (portion.size() > 0) {
changes.emplace_back(std::make_shared<TNormalizerResult>(std::move(portion)));

if (portion.size() + tablePortion.size() > 0) {
changes.emplace_back(std::make_shared<TNormalizerResult>(std::move(portion), std::move(tablePortion)));
}
return changes;
}
Expand Down
6 changes: 6 additions & 0 deletions ydb/core/tx/columnshard/ut_rw/ut_normalizer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -176,6 +176,12 @@ class TSchemaVersionsCleaner : public NYDBTest::ILocalDBModifier {
Y_ABORT_UNLESS(info.SerializeToString(&serialized));
db.Table<Schema::SchemaPresetVersionInfo>().Key(11, 1, 1).Update(NIceDb::TUpdate<Schema::SchemaPresetVersionInfo::InfoProto>(serialized));

// Add invalid widow table version, if SchemaVersionCleaner will not erase it, then test will fail
NKikimrTxColumnShard::TTableVersionInfo versionInfo;
versionInfo.MutableSchema()->SetVersion(minVersion - 1);
Y_ABORT_UNLESS(versionInfo.SerializeToString(&serialized));
db.Table<Schema::TableVersionInfo>().Key(1, 1, 1).Update(NIceDb::TUpdate<Schema::TableVersionInfo::InfoProto>(serialized));

db.Table<Schema::SchemaPresetInfo>().Key(10).Update(NIceDb::TUpdate<Schema::SchemaPresetInfo::Name>("default"));

}
Expand Down
Loading