Merge pull request #1594 from quickwit-oss/flat_map_with_buffer

Removing alloc on all .next() in MultiValueColumn
This commit is contained in:
PSeitz
2022-10-05 18:34:15 +08:00
committed by GitHub
3 changed files with 74 additions and 5 deletions

View File

@@ -0,0 +1,69 @@
pub struct FlatMapWithBuffer<T, F, Iter> {
buffer: Vec<T>,
fill_buffer: F,
underlying_it: Iter,
}
impl<T, F, Iter, I> Iterator for FlatMapWithBuffer<T, F, Iter>
where
Iter: Iterator<Item = I>,
F: Fn(I, &mut Vec<T>),
{
type Item = T;
fn next(&mut self) -> Option<Self::Item> {
while self.buffer.is_empty() {
let next_el = self.underlying_it.next()?;
(self.fill_buffer)(next_el, &mut self.buffer);
// We will pop elements, so we reverse the buffer first.
self.buffer.reverse();
}
self.buffer.pop()
}
}
pub trait FlatMapWithBufferIter: Iterator {
/// Function similar to `flat_map`, but allows reusing a shared `Vec`.
fn flat_map_with_buffer<F, T>(self, fill_buffer: F) -> FlatMapWithBuffer<T, F, Self>
where
F: Fn(Self::Item, &mut Vec<T>),
Self: Sized,
{
FlatMapWithBuffer {
buffer: Vec::with_capacity(10),
fill_buffer,
underlying_it: self,
}
}
}
impl<T: ?Sized> FlatMapWithBufferIter for T where T: Iterator {}
#[cfg(test)]
mod tests {
use crate::indexer::flat_map_with_buffer::FlatMapWithBufferIter;
#[test]
fn test_flat_map_with_buffer_empty() {
let mut empty_iter = std::iter::empty::<usize>()
.flat_map_with_buffer(|_val: usize, _buffer: &mut Vec<usize>| {});
assert!(empty_iter.next().is_none());
}
#[test]
fn test_flat_map_with_buffer_simple() {
let vals: Vec<usize> = (1..5)
.flat_map_with_buffer(|val: usize, buffer: &mut Vec<usize>| buffer.extend(0..val))
.collect();
assert_eq!(&[0, 0, 1, 0, 1, 2, 0, 1, 2, 3], &vals[..]);
}
#[test]
fn test_flat_map_filling_no_elements_does_not_stop_iterator() {
let vals: Vec<usize> = [2, 0, 0, 3]
.into_iter()
.flat_map_with_buffer(|val: usize, buffer: &mut Vec<usize>| buffer.extend(0..val))
.collect();
assert_eq!(&[0, 1, 0, 1, 2], &vals[..]);
}
}

View File

@@ -3,6 +3,7 @@ pub mod delete_queue;
pub mod demuxer;
pub mod doc_id_mapping;
mod doc_opstamp_mapping;
mod flat_map_with_buffer;
pub mod index_writer;
mod index_writer_status;
mod json_term_writer;

View File

@@ -2,10 +2,11 @@ use std::cmp;
use fastfield_codecs::Column;
use super::flat_map_with_buffer::FlatMapWithBufferIter;
use crate::fastfield::MultiValuedFastFieldReader;
use crate::indexer::doc_id_mapping::SegmentDocIdMapping;
use crate::schema::Field;
use crate::SegmentReader;
use crate::{DocAddress, SegmentReader};
pub(crate) struct RemappedDocIdMultiValueColumn<'a> {
doc_id_mapping: &'a SegmentDocIdMapping,
@@ -74,11 +75,9 @@ impl<'a> Column for RemappedDocIdMultiValueColumn<'a> {
Box::new(
self.doc_id_mapping
.iter_old_doc_addrs()
.flat_map(|old_doc_addr| {
.flat_map_with_buffer(|old_doc_addr: DocAddress, buffer| {
let ff_reader = &self.fast_field_readers[old_doc_addr.segment_ord as usize];
let mut vals = Vec::new();
ff_reader.get_vals(old_doc_addr.doc_id, &mut vals);
vals.into_iter()
ff_reader.get_vals(old_doc_addr.doc_id, buffer);
}),
)
}