Skip to content

[fix](filecache) add OFFSET column for table file_cache_info #59645

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

Open
freemandealer wants to merge 1 commit into
base: master
Choose a base branch
from
+20 −9
Open

[fix](filecache) add OFFSET column for table file_cache_info #59645

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
23 changes: 14 additions & 9 deletions be/src/exec/schema_scanner/schema_file_cache_info_scanner.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,7 @@ namespace doris {
std::vector<SchemaScanner::ColumnDesc> SchemaFileCacheInfoScanner::_s_tbls_columns = {
// name, type, size, is_null
{"HASH", TYPE_STRING, sizeof(StringRef), true},
{"OFFSET", TYPE_BIGINT, sizeof(int64_t), true},
{"TABLET_ID", TYPE_BIGINT, sizeof(int64_t), true},
{"SIZE", TYPE_BIGINT, sizeof(int64_t), true},
{"TYPE", TYPE_STRING, sizeof(StringRef), true},
Expand Down Expand Up @@ -68,7 +69,7 @@ Status SchemaFileCacheInfoScanner::_fill_block_impl(vectorized::Block* block) {
}

// Collect all cache entries from all file cache instances
std::vector<std::tuple<std::string, int64_t, int64_t, int, std::string>> cache_entries;
std::vector<std::tuple<std::string, int64_t, int64_t, int64_t, int, std::string>> cache_entries;

// Get all cache instances using the public getter
const auto& caches = file_cache_factory->get_caches();
Expand Down Expand Up @@ -116,7 +117,8 @@ Status SchemaFileCacheInfoScanner::_fill_block_impl(vectorized::Block* block) {
std::string hash_str = key.hash.to_string();

// Add to cache entries
cache_entries.emplace_back(hash_str, key.tablet_id, value.size, value.type, cache_path);
cache_entries.emplace_back(hash_str, static_cast<int64_t>(key.offset), key.tablet_id,
static_cast<int64_t>(value.size), value.type, cache_path);

iterator->next();
}
Expand All @@ -137,21 +139,21 @@ Status SchemaFileCacheInfoScanner::_fill_block_impl(vectorized::Block* block) {

for (size_t row_idx = 0; row_idx < row_num; ++row_idx) {
const auto& entry = cache_entries[row_idx];
const auto& [hash, tablet_id, size, type, cache_path] = entry;
const auto& [hash, offset, tablet_id, size, type, cache_path] = entry;

if (col_desc.type == TYPE_STRING) {
switch (col_idx) {
case 0: // HASH
column_values[row_idx] = hash;
break;
case 3: // TYPE
case 4: // TYPE
Copy link
Contributor

@gavinchou gavinchou Jan 8, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

is there any compatibility issues?

column_values[row_idx] = doris::io::cache_type_to_string(
static_cast<doris::io::FileCacheType>(type));
break;
case 4: // REMOTE_PATH
case 5: // REMOTE_PATH
column_values[row_idx] = ""; // TODO: Implement remote path retrieval
break;
case 5: // CACHE_PATH
case 6: // CACHE_PATH
column_values[row_idx] = cache_path;
break;
default:
Expand All @@ -163,13 +165,16 @@ Status SchemaFileCacheInfoScanner::_fill_block_impl(vectorized::Block* block) {
datas[row_idx] = &str_refs[row_idx];
} else if (col_desc.type == TYPE_BIGINT) {
switch (col_idx) {
case 1: // TABLET_ID
case 1: // OFFSET
int64_vals[row_idx] = offset;
break;
case 2: // TABLET_ID
int64_vals[row_idx] = tablet_id;
break;
case 2: // SIZE
case 3: // SIZE
int64_vals[row_idx] = size;
break;
case 6: // BE_ID
case 7: // BE_ID
int64_vals[row_idx] = ExecEnv::GetInstance()->cluster_info()->backend_id;
break;
default:
Expand Down
1 change: 1 addition & 0 deletions fe/fe-core/src/main/java/org/apache/doris/catalog/SchemaTable.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -713,6 +713,7 @@ public class SchemaTable extends Table {
.put("file_cache_info",
new SchemaTable(SystemIdGenerator.getNextId(), "file_cache_info", TableType.SCHEMA,
builder().column("HASH", ScalarType.createStringType())
.column("OFFSET", ScalarType.createType(PrimitiveType.BIGINT))
.column("TABLET_ID", ScalarType.createType(PrimitiveType.BIGINT))
.column("SIZE", ScalarType.createType(PrimitiveType.BIGINT))
.column("TYPE", ScalarType.createStringType())
Expand Down
5 changes: 5 additions & 0 deletions regression-test/suites/cloud_p0/cache/test_file_cache_info.groovy
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,6 +83,11 @@ suite("test_file_cache_info") {
def tablet_id = get_tablet_id("customer")
println "Tablet ID: ${tablet_id}"

def desc_cache_info = sql "desc information_schema.file_cache_info"
assertTrue(desc_cache_info.size() > 0, "desc information_schema.file_cache_info should not be empty")
assertEquals(desc_cache_info[0][0].toString().toUpperCase(), "HASH")
assertEquals(desc_cache_info[1][0].toString().toUpperCase(), "OFFSET")

def cache_info = sql "select * from information_schema.file_cache_info"

assertTrue(cache_info.size() > 0, "file_cache_info should not be empty for tablet_id ${tablet_id}")
Expand Down
Loading