Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Increase DeltaBitPackEncoder miniblock size to 64 for 64-bit integers (#2282) #2319

Merged
merged 1 commit into from
Aug 5, 2022
Merged

Increase DeltaBitPackEncoder miniblock size to 64 for 64-bit integers (#2282) #2319

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 11 additions & 5 deletions parquet/src/encodings/encoding/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -241,7 +241,6 @@ impl<T: DataType> Encoder<T> for RleValueEncoder<T> {

const MAX_PAGE_HEADER_WRITER_SIZE: usize = 32;
const MAX_BIT_WRITER_SIZE: usize = 10 * 1024 * 1024;
const DEFAULT_BLOCK_SIZE: usize = 128;
const DEFAULT_NUM_MINI_BLOCKS: usize = 4;

/// Delta bit packed encoder.
Expand Down Expand Up @@ -284,12 +283,19 @@ pub struct DeltaBitPackEncoder<T: DataType> {
impl<T: DataType> DeltaBitPackEncoder<T> {
/// Creates new delta bit packed encoder.
pub fn new() -> Self {
let block_size = DEFAULT_BLOCK_SIZE;
let num_mini_blocks = DEFAULT_NUM_MINI_BLOCKS;
let mini_block_size = block_size / num_mini_blocks;
assert_eq!(mini_block_size % 8, 0);
Self::assert_supported_type();

// Size miniblocks so that they can be efficiently decoded
let mini_block_size = match T::T::PHYSICAL_TYPE {
Type::INT32 => 32,
Type::INT64 => 64,
_ => unreachable!(),
};

let num_mini_blocks = DEFAULT_NUM_MINI_BLOCKS;
let block_size = mini_block_size * num_mini_blocks;
assert_eq!(block_size % 128, 0);

DeltaBitPackEncoder {
page_header_writer: BitWriter::new(MAX_PAGE_HEADER_WRITER_SIZE),
bit_writer: BitWriter::new(MAX_BIT_WRITER_SIZE),
Expand Down