Skip to content

branch-3.0: [fix](checker) Fix inverted check and test for checker #54403 #54469

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

Merged
dataroaring merged 1 commit into from
Aug 8, 2025
Merged

branch-3.0: [fix](checker) Fix inverted check and test for checker #54403 #54469

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
43 changes: 35 additions & 8 deletions cloud/src/recycler/checker.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -576,7 +576,7 @@ int InstanceChecker::do_check() {

TabletIndexPB tablet_index;
if (get_tablet_idx(txn_kv_.get(), instance_id_, rs_meta.tablet_id(), tablet_index) == -1) {
LOG(WARNING) << "failedt to get tablet index, tablet_id= " << rs_meta.tablet_id();
LOG(WARNING) << "failed to get tablet index, tablet_id= " << rs_meta.tablet_id();
return;
}

Expand Down Expand Up @@ -605,8 +605,8 @@ int InstanceChecker::do_check() {
InvertedIndexStorageFormatPB::V1) {
for (const auto& index_id : index_ids) {
LOG(INFO) << "check inverted index, tablet_id=" << rs_meta.tablet_id()
<< " rowset_id=" << rs_meta.rowset_id_v2()
<< " segment_index=" << i << " index_id=" << index_id.first
<< " rowset_id=" << rs_meta.rowset_id_v2() << " segment_id=" << i
<< " index_id=" << index_id.first
<< " index_suffix_name=" << index_id.second;
index_path_v.emplace_back(
inverted_index_path_v1(rs_meta.tablet_id(), rs_meta.rowset_id_v2(),
Expand All @@ -619,14 +619,17 @@ int InstanceChecker::do_check() {

if (!index_path_v.empty()) {
if (std::ranges::all_of(index_path_v, [&](const auto& idx_file_path) {
return tablet_files_cache.files.contains(idx_file_path);
if (!tablet_files_cache.files.contains(idx_file_path)) {
LOG(INFO) << "loss index file: " << idx_file_path;
return false;
}
return true;
})) {
continue;
}
}
index_file_loss = true;
data_loss = true;
LOG(WARNING) << "object not exist, key=" << hex(tablet_idx_key);
}
}
};
Expand Down Expand Up @@ -735,6 +738,10 @@ int InstanceChecker::do_inverted_check() {
butil::SplitString(obj_key, '/', &str);
// data/{tablet_id}/{rowset_id}_{seg_num}.dat
if (str.size() < 3) {
// clang-format off
LOG(WARNING) << "split obj_key error, str.size() should be less than 3,"
<< " value = " << str.size();
// clang-format on
return -1;
}

Expand All @@ -744,6 +751,11 @@ int InstanceChecker::do_inverted_check() {
return -1;
}

if (!str[2].ends_with(".dat")) {
// skip check not segment file
return 0;
}

std::string rowset_id;
if (auto pos = str.back().find('_'); pos != std::string::npos) {
rowset_id = str.back().substr(0, pos);
Expand Down Expand Up @@ -813,6 +825,10 @@ int InstanceChecker::do_inverted_check() {
// format v1: data/{tablet_id}/{rowset_id}_{seg_num}_{idx_id}{idx_suffix}.idx
// format v2: data/{tablet_id}/{rowset_id}_{seg_num}.idx
if (str.size() < 3) {
// clang-format off
LOG(WARNING) << "split obj_key error, str.size() should be less than 3,"
<< " value = " << str.size();
// clang-format on
return -1;
}

Expand Down Expand Up @@ -1281,8 +1297,11 @@ int InstanceChecker::check_inverted_index_file_storage_format_v1(

for (const auto& i : rs_meta.tablet_schema().index()) {
if (i.has_index_type() && i.index_type() == IndexType::INVERTED) {
LOG(INFO) << fmt::format(
"record index info, index_id: {}, index_suffix_name: {}", i.index_id(),
i.index_suffix_name());
rowset_index_cache_v1.index_ids.insert(
fmt::format("{}{}", i.index_name(), i.index_suffix_name()));
fmt::format("{}{}", i.index_id(), i.index_suffix_name()));
}
}

Expand All @@ -1296,13 +1315,21 @@ int InstanceChecker::check_inverted_index_file_storage_format_v1(

if (!rowset_index_cache_v1.segment_ids.contains(segment_id)) {
// Garbage data leak
LOG(WARNING) << "rowset should be recycled, key=" << file_path;
// clang-format off
LOG(WARNING) << "rowset_index_cache_v1.segment_ids don't contains segment_id, rowset should be recycled,"
<< " key = " << file_path
<< " segment_id = " << segment_id;
// clang-format on
return 1;
}

if (!rowset_index_cache_v1.index_ids.contains(index_id_with_suffix_name)) {
// Garbage data leak
LOG(WARNING) << "rowset with inde meta should be recycled, key=" << file_path;
// clang-format off
LOG(WARNING) << "rowset_index_cache_v1.index_ids don't contains index_id_with_suffix_name,"
<< " rowset with inde meta should be recycled, key=" << file_path
<< " index_id_with_suffix_name=" << index_id_with_suffix_name;
// clang-format on
return 1;
}

Expand Down
Loading
Loading