diff --git a/datafusion/physical-plan/src/aggregates/group_values/multi_group_by/dictionary.rs b/datafusion/physical-plan/src/aggregates/group_values/multi_group_by/dictionary.rs index 4dd488380a9d8..8ec8c808b5400 100644 --- a/datafusion/physical-plan/src/aggregates/group_values/multi_group_by/dictionary.rs +++ b/datafusion/physical-plan/src/aggregates/group_values/multi_group_by/dictionary.rs @@ -57,6 +57,9 @@ pub struct DictionaryGroupValuesColumn val_to_inner: Vec, /// Reusable hash buffer for the dictionary values array. val_hashes: Vec, + /// The last `dict.values()` Arc hashed in `append_val`. When the incoming + /// values array is `ptr_eq` to this, `val_hashes` can be reused directly. + cached_values: Option, _phantom: PhantomData, } @@ -73,6 +76,7 @@ impl DictionaryGroupValuesColumn { random_state: AGGREGATION_HASH_SEED, val_to_inner: Vec::default(), val_hashes: Vec::default(), + cached_values: None, _phantom: PhantomData, } } @@ -159,6 +163,7 @@ impl DictionaryGroupValuesColumn { } fn hash_values(&mut self, values: &ArrayRef) { + self.cached_values = None; self.val_hashes.clear(); self.val_hashes.resize(values.len(), 0); create_hashes( @@ -296,9 +301,25 @@ impl GroupColumn } Some(val_idx) => { let dict_values = dict.values(); - let single = dict_values.slice(val_idx, 1); - self.hash_values(&single); - self.find_or_insert_value(dict_values, val_idx, self.val_hashes[0])? + // check if the dictionary values array we are hashing was already seen. + // if its arc was already stored we dont need to rehash the entire array again + // if its new hash the entire array and store an arc ptr for future use + let cache_hit = self + .cached_values + .as_ref() + .is_some_and(|c| Arc::ptr_eq(c, dict_values)); + if !cache_hit { + self.val_hashes.clear(); + self.val_hashes.resize(dict_values.len(), 0); + create_hashes( + std::slice::from_ref(dict_values), + &self.random_state, + &mut self.val_hashes, + ) + .unwrap(); + self.cached_values = Some(Arc::clone(dict_values)); + } + self.find_or_insert_value(dict_values, val_idx, self.val_hashes[val_idx])? } }; self.group_to_inner.push(inner_slot);