mkleen commented on code in PR #20047:
URL: https://github.com/apache/datafusion/pull/20047#discussion_r2807927115
##########
datafusion/execution/src/cache/cache_unit.rs:
##########
@@ -36,37 +36,167 @@ pub use crate::cache::DefaultFilesMetadataCache;
/// 2. If `Some(cached)`, validate with `cached.is_valid_for(¤t_meta)`
/// 3. If invalid or missing, compute new value and call `put(path, new_value)`
///
-/// Uses DashMap for lock-free concurrent access.
+/// # Internal details
+///
+/// The `memory_limit` controls the maximum size of the cache, which uses a
+/// Least Recently Used eviction algorithm. When adding a new entry, if the
total
+/// size of the cached entries exceeds `memory_limit`, the least recently used
entries
+/// are evicted until the total size is lower than `memory_limit`.
+///
///
/// [`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
+ }
+}
+
+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 {
Review Comment:
Yes, i had the same thought. Shall i create a follow-up ticket on that?
--
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]
