Merge pull request #1484 from Altinity/fix_parquet_metadata_cache_max_size

Use serialized metadata size to calculate the cache entry cell

Author: zvonand

src/Processors/Formats/Impl/ParquetFileMetaDataCache.cpp

@@ -2,11 +2,21 @@
 
 #if USE_PARQUET
 
+#include <parquet/metadata.h>
+
 namespace DB
 {
 
+size_t ParquetFileMetaDataWeightFunction::operator()(const parquet::FileMetaData & metadata) const
+{
+    /// TODO fix-me: using the size on disk is not ideal, but it is the simplest and best we can do for now.
+    /// this implementation is only used by the v1 reader, which is going to be deprecated and a new implementation for the v3
+    /// reader will be added in the future.
+    return metadata.size();
+}
+
 ParquetFileMetaDataCache::ParquetFileMetaDataCache()
-    : CacheBase<String, parquet::FileMetaData>(CurrentMetrics::end(), CurrentMetrics::end(), 0)
+    : CacheBase<String, parquet::FileMetaData, std::hash<String>, ParquetFileMetaDataWeightFunction>(CurrentMetrics::end(), CurrentMetrics::end(), 0)
 {}
 
 ParquetFileMetaDataCache * ParquetFileMetaDataCache::instance()

src/Processors/Formats/Impl/ParquetFileMetaDataCache.h

@@ -16,7 +16,12 @@ class FileMetaData;
 namespace DB
 {
 
-class ParquetFileMetaDataCache : public CacheBase<String, parquet::FileMetaData>
+struct ParquetFileMetaDataWeightFunction
+{
+    size_t operator()(const parquet::FileMetaData & metadata) const;
+};
+
+class ParquetFileMetaDataCache : public CacheBase<String, parquet::FileMetaData, std::hash<String>, ParquetFileMetaDataWeightFunction>
 {
 public:
     static ParquetFileMetaDataCache * instance();