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

Rechunk uncompressed vortex files in benchmarks #926

Merged
merged 2 commits into from
Sep 25, 2024
Merged

Rechunk uncompressed vortex files in benchmarks #926

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
eb53d68
Rechunk uncompressed vortex files in benchmarks
robert3005 Sep 25, 2024
93bda4d
comment
robert3005 Sep 25, 2024
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
24 changes: 14 additions & 10 deletions bench-vortex/src/tpch/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,10 @@ pub const EXPECTED_ROW_COUNTS: [usize; 23] = [
0, 4, 460, 11620, 5, 5, 1, 4, 2, 175, 37967, 1048, 2, 42, 1, 1, 18314, 1, 57, 1, 186, 411, 7,
];

// Sizes match default compressor configuration
const TARGET_BLOCK_BYTESIZE: usize = 16 * (1 << 20);
const TARGET_BLOCK_SIZE: usize = 64 * (1 << 10);

#[derive(Clone, Copy, Debug, Hash, PartialEq, Eq)]
pub enum Format {
Csv,
Expand Down Expand Up @@ -245,8 +249,7 @@ async fn register_vortex_file(

// Create a ChunkedArray from the set of chunks.
let sts = record_batches
.iter()
.cloned()
.into_iter()
.map(Array::try_from)
.map(|a| a.unwrap().into_struct().unwrap())
.collect::<Vec<_>>();
Expand Down Expand Up @@ -274,11 +277,14 @@ async fn register_vortex_file(
let name: Arc<str> = field.name().as_str().into();
let dtype = types_map[&name].clone();
let chunks = arrays_map.remove(&name).unwrap();
let mut chunked_child = ChunkedArray::try_new(chunks, dtype).unwrap();
if !enable_compression {
chunked_child = chunked_child
.rechunk(TARGET_BLOCK_BYTESIZE, TARGET_BLOCK_SIZE)
.unwrap()
}

(
name.clone(),
ChunkedArray::try_new(chunks, dtype).unwrap().into_array(),
)
(name, chunked_child.into_array())
})
.collect::<Vec<_>>();

Expand Down Expand Up @@ -359,8 +365,7 @@ async fn register_vortex(

// Create a ChunkedArray from the set of chunks.
let chunks: Vec<Array> = record_batches
.iter()
.cloned()
.into_iter()
.map(ArrowStructArray::from)
.map(|struct_array| Array::from_arrow(&struct_array, false))
.collect();
Expand Down Expand Up @@ -403,8 +408,7 @@ pub async fn load_table(data_dir: impl AsRef<Path>, name: &str, schema: &Schema)
.unwrap();

let chunks: Vec<Array> = record_batches
.iter()
.cloned()
.into_iter()
.map(ArrowStructArray::from)
.map(|struct_array| Array::from_arrow(&struct_array, false))
.collect();
Expand Down
Loading