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

[BugFix] limit the state size of FlatJson to avoid excessive memory consumption #57139

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
+30 −0
Draft

[BugFix] limit the state size of FlatJson to avoid excessive memory consumption #57139

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
11 changes: 11 additions & 0 deletions be/src/util/json_flattener.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -473,7 +473,18 @@ void JsonPathDeriver::_derived(const Column* col, size_t mark_row) {
}
}

// TODO: incrementally find the top-k, rather than visit all nodes first
// recursively visit all JSON items to remember common paths
void JsonPathDeriver::_visit_json_paths(const vpack::Slice& value, JsonFlatPath* root, size_t mark_row) {
const size_t COMMON_PATH_STATE_FACTOR = 10;
size_t state_limit = config::json_flat_column_max > 0 ? COMMON_PATH_STATE_FACTOR * config::json_flat_column_max
: std::numeric_limits<size_t>::max();

// Optimize memory usage by limiting the number of paths to prevent excessive memory consumption
if (_derived_maps.size() >= state_limit) {
return;
}

vpack::ObjectIterator it(value, false);

for (; it.valid(); it.next()) {
Expand Down
19 changes: 19 additions & 0 deletions be/test/util/json_flattener_test.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -261,6 +261,25 @@ TEST_F(JsonFlattenerTest, testDeepJson3) {
EXPECT_EQ("NULL", result[2]->debug_item(1));
}

TEST_F(JsonFlattenerTest, testLargeJson) {
std::vector<std::string> json;
for (int k = 0; k < 10; k++) {
json.emplace_back(R"({"k1": 1)");
for (int i = 2; i <= 2000; i++) {
json[k] += fmt::format(", \"k{0}\": {1}", i, i);
}
json[k] += "}";
}

std::vector<std::string> paths = {"k1", "k2", "k1000"};
std::vector<LogicalType> types = {TYPE_BIGINT, TYPE_BIGINT, TYPE_BIGINT};
auto result = test_json(json, paths, types, false);
EXPECT_EQ(3, result.size());
EXPECT_EQ("1", result[0]->debug_item(0));
EXPECT_EQ("2", result[1]->debug_item(0));
EXPECT_EQ("1000", result[2]->debug_item(0));
}

TEST_F(JsonFlattenerTest, testMiddleJson) {
std::vector<std::string> json = {R"( {"k1": {"c1": {"d1": 123 }}, "k2": {"j1": "def", "j2": {"g1": [1,2,3]}}} )",
R"( {"k1": {"c1": {"d1": "abc"}}, "k2": {"j1": "abc", "j2": {"g1": 123}}} )"};
Expand Down
Loading