Skip to content

Make io compression zstd level configurable #1111

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

Merged
richox merged 3 commits into from
Aug 7, 2025
Merged

Make io compression zstd level configurable #1111

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
decdd8c
Make io compression zstd level configurable
turboFei Aug 6, 2025
7115804
fmt
turboFei Aug 6, 2025
f7bd762
comments
turboFei Aug 6, 2025
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
1 change: 1 addition & 0 deletions native-engine/blaze-jni-bridge/src/conf.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,7 @@ define_conf!(BooleanConf, PARTIAL_AGG_SKIPPING_SKIP_SPILL);
define_conf!(BooleanConf, PARQUET_ENABLE_PAGE_FILTERING);
define_conf!(BooleanConf, PARQUET_ENABLE_BLOOM_FILTER);
define_conf!(StringConf, SPARK_IO_COMPRESSION_CODEC);
define_conf!(IntConf, SPARK_IO_COMPRESSION_ZSTD_LEVEL);
define_conf!(IntConf, TOKIO_WORKER_THREADS_PER_CPU);
define_conf!(IntConf, SPARK_TASK_CPUS);
define_conf!(StringConf, SPILL_COMPRESSION_CODEC);
Expand Down
12 changes: 9 additions & 3 deletions native-engine/datafusion-ext-plans/src/common/ipc_compression.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,11 @@
use std::io::{BufReader, Read, Take, Write};

use arrow::{array::ArrayRef, datatypes::SchemaRef};
use blaze_jni_bridge::{conf, conf::StringConf, is_jni_bridge_inited};
use blaze_jni_bridge::{
conf,
conf::{IntConf, StringConf},
is_jni_bridge_inited,
};
use byteorder::{LittleEndian, ReadBytesExt, WriteBytesExt};
use datafusion::common::Result;
use datafusion_ext_commons::{
Expand All @@ -28,7 +32,6 @@ use datafusion_ext_commons::{
use once_cell::sync::OnceCell;

pub const DEFAULT_SHUFFLE_COMPRESSION_TARGET_BUF_SIZE: usize = 4194304;
const ZSTD_LEVEL: i32 = 1;

pub struct IpcCompressionWriter<W: Write> {
output: W,
Expand Down Expand Up @@ -181,7 +184,10 @@ impl<W: Write> IoCompressionWriter<W> {
pub fn try_new(codec: &str, inner: W) -> Result<Self> {
match codec {
"lz4" => Ok(Self::LZ4(lz4_flex::frame::FrameEncoder::new(inner))),
"zstd" => Ok(Self::ZSTD(zstd::Encoder::new(inner, ZSTD_LEVEL)?)),
"zstd" => Ok(Self::ZSTD(zstd::Encoder::new(
inner,
conf::SPARK_IO_COMPRESSION_ZSTD_LEVEL.value().unwrap_or(1),
)?)),
_ => df_execution_err!("unsupported codec: {}", codec),
}
}
Expand Down
3 changes: 3 additions & 0 deletions spark-extension/src/main/java/org/apache/spark/sql/blaze/BlazeConf.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,6 +75,9 @@ public enum BlazeConf {
// spark io compression codec
SPARK_IO_COMPRESSION_CODEC("spark.io.compression.codec", "lz4"),

// spark io compression zstd level
SPARK_IO_COMPRESSION_ZSTD_LEVEL("spark.io.compression.zstd.level", 1),

// tokio worker threads per cpu (spark.task.cpus), 0 for auto detection
TOKIO_WORKER_THREADS_PER_CPU("spark.blaze.tokio.worker.threads.per.cpu", 0),

Expand Down