ding-young commented on code in PR #16268:
URL: https://github.com/apache/datafusion/pull/16268#discussion_r2153442938
##########
datafusion/core/tests/memory_limit/mod.rs:
##########
@@ -630,6 +635,77 @@ async fn test_disk_spill_limit_not_reached() -> Result<()>
{
Ok(())
}
+/// External query should succeed using zstd as spill compression codec and
+/// and all temporary spill files are properly cleaned up after execution.
+/// Note: This test does not inspect file contents (e.g. magic number),
+/// as spill files are automatically deleted on drop.
+#[tokio::test]
+async fn test_spill_file_compressed_with_zstd() -> Result<()> {
+ let disk_spill_limit = 1024 * 1024; // 1MB
+ let spill_compression = SpillCompression::Zstd;
+ let ctx = setup_context(disk_spill_limit, 128 * 1024,
spill_compression).await?; // 1MB disk limit, 128KB memory limit, zstd
+
+ let df = ctx
+ .sql("select * from generate_series(1, 100000) as t1(v1) order by v1")
+ .await
+ .unwrap();
+ let plan = df.create_physical_plan().await.unwrap();
+
+ let task_ctx = ctx.task_ctx();
+ let _ = collect_batches(Arc::clone(&plan), task_ctx)
+ .await
+ .expect("Query execution failed");
+
+ let spill_count = plan.metrics().unwrap().spill_count().unwrap();
+ let spilled_bytes = plan.metrics().unwrap().spilled_bytes().unwrap();
+
+ println!("spill count {spill_count}");
+ assert!(spill_count > 0);
+ assert!((spilled_bytes as u64) < disk_spill_limit);
+
+ // Verify that all temporary files have been properly cleaned up by
checking
+ // that the total disk usage tracked by the disk manager is zero
+ let current_disk_usage = ctx.runtime_env().disk_manager.used_disk_space();
+ assert_eq!(current_disk_usage, 0);
+
+ Ok(())
+}
+
+/// External query should succeed using lz4_frame as spill compression codec
and
+/// and all temporary spill files are properly cleaned up after execution.
+/// Note: This test does not inspect file contents (e.g. magic number),
+/// as spill files are automatically deleted on drop.
+#[tokio::test]
+async fn test_spill_file_compressed_with_lz4_frame() -> Result<()> {
Review Comment:
I added test here, but unfortunately it is not straightforward to check
whether the file is actually compressed with desired codec in e2e test. Maybe
we can compare `spilled_bytes` after follow up fix.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscr...@datafusion.apache.org
For additional commands, e-mail: github-h...@datafusion.apache.org
