Skip to content

Commit

Permalink
Fix perf regression in ShuffleRows (#5417)
Browse files Browse the repository at this point in the history
RowShufflingTransformer is using ChannelReader incorrectly. It needs to block waiting for items to read and was Thread.Sleeping in order to wait, but not spin the current core. This caused a major perf regression.

The fix is to block synchronously correctly - by calling AsTask() on the ValueTask that is returned from the ChannelReader and block on the Task.

Fix #5416
  • Loading branch information
eerhardt authored and mstfbl committed Nov 11, 2020
1 parent 05acb93 commit 274e384
Showing 1 changed file with 53 additions and 0 deletions.
53 changes: 53 additions & 0 deletions test/Microsoft.ML.Benchmarks/ShuffleRowsBench.cs
Original file line number Diff line number Diff line change
@@ -0,0 +1,53 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

using BenchmarkDotNet.Attributes;
using Microsoft.ML.Benchmarks.Harness;
using Microsoft.ML.Data;

namespace Microsoft.ML.Benchmarks
{
[CIBenchmark]
public class ShuffleRowsBench : BenchmarkBase
{
private TrainRow[] _rows;
private MLContext _context;

[GlobalSetup]
public void Setup()
{
_rows = new TrainRow[10_000];
for (var i = 0; i < _rows.Length; i++)
{
_rows[i] = new TrainRow() { Sample = i.ToString(), Week = i, Label = i / 2 };
}

_context = new MLContext();
}

[Benchmark]
public void ShuffleRows()
{
IDataView data = _context.Data.LoadFromEnumerable(_rows);

IDataView shuffledData = _context.Data.ShuffleRows(data, seed: 0);

foreach (string sample in shuffledData.GetColumn<string>("Sample"))
{
}
}

private class TrainRow
{
[ColumnName("Sample")]
public string Sample;

[ColumnName("Week")]
public float Week;

[ColumnName("Label")]
public float Label;
}
}
}

0 comments on commit 274e384

Please sign in to comment.