mkleen commented on code in PR #20047:
URL: https://github.com/apache/datafusion/pull/20047#discussion_r2763701123
##########
datafusion/execution/src/cache/cache_unit.rs:
##########
@@ -41,32 +41,137 @@ pub use crate::cache::DefaultFilesMetadataCache;
/// [`FileStatisticsCache`]: crate::cache::cache_manager::FileStatisticsCache
#[derive(Default)]
pub struct DefaultFileStatisticsCache {
- cache: DashMap<Path, CachedFileMetadata>,
+ state: Mutex<DefaultFileStatisticsCacheState>,
+}
+
+impl DefaultFileStatisticsCache {
+ pub fn new(memory_limit: usize) -> Self {
+ Self {
+ state:
Mutex::new(DefaultFileStatisticsCacheState::new(memory_limit)),
+ }
+ }
+
+ /// Returns the size of the cached memory, in bytes.
+ pub fn memory_used(&self) -> usize {
+ let state = self.state.lock().unwrap();
+ state.memory_used
+ }
+}
+
+pub struct DefaultFileStatisticsCacheState {
+ lru_queue: LruQueue<Path, CachedFileMetadata>,
+ memory_limit: usize,
+ memory_used: usize,
+}
+
+pub const DEFAULT_FILE_STATISTICS_MEMORY_LIMIT: usize = 1024 * 1024; // 1MiB
+
+impl Default for DefaultFileStatisticsCacheState {
+ fn default() -> Self {
+ Self {
+ lru_queue: LruQueue::new(),
+ memory_limit: DEFAULT_FILE_STATISTICS_MEMORY_LIMIT,
+ memory_used: 0,
+ }
+ }
}
+impl DefaultFileStatisticsCacheState {
+ fn new(memory_limit: usize) -> Self {
+ Self {
+ lru_queue: LruQueue::new(),
+ memory_limit,
+ memory_used: 0,
+ }
+ }
+ fn get(&mut self, key: &Path) -> Option<CachedFileMetadata> {
+ self.lru_queue.get(key).cloned()
+ }
+
+ fn put(
+ &mut self,
+ key: &Path,
+ value: CachedFileMetadata,
+ ) -> Option<CachedFileMetadata> {
+ let entry_size = value.heap_size();
+
+ if entry_size > self.memory_limit {
+ return None;
+ }
+
+ let old_value = self.lru_queue.put(key.clone(), value);
+ self.memory_used += entry_size;
+
+ if let Some(old_entry) = &old_value {
+ self.memory_used -= old_entry.heap_size();
+ }
+
+ self.evict_entries();
+
+ old_value
+ }
+
+ fn remove(&mut self, k: &Path) -> Option<CachedFileMetadata> {
+ self.lru_queue.remove(k)
+ }
Review Comment:
I also added tests for this now.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
