Skip to content

perf: whole-file resolution for batch DELETE (A1 starter) #372

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
MPCoreDeveloper merged 1 commit into from
Sep 3, 2026
Merged

perf: whole-file resolution for batch DELETE (A1 starter) #372

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
99 changes: 88 additions & 11 deletions src/SharpCoreDB/DataStructures/Table.CRUD.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3062,6 +3062,10 @@ internal void DeleteMultipleKeys(List<(string Column, string Literal)> condition
// B1: decode only the columns the delete core touches (PK + loaded hash-index columns).
int[] deleteKeyColumns = BuildDeleteKeyColumns();

// A1: when the (plaintext, legacy variable-length) data file is small enough, read it
// ONCE and resolve every target from memory instead of one pread pair per deleted row.
byte[]? wholeFile = TryLoadWholeFileForDeleteResolution();

var recordsToDelete = new List<(long storagePosition, Dictionary<string, object> row)>();

foreach (var (col, literal) in conditions)
Expand All @@ -3076,16 +3080,25 @@ internal void DeleteMultipleKeys(List<(string Column, string Literal)> condition
var fastSearch = this.Index.Search(value);
if (fastSearch.Found)
{
var fastData = engine.Read(Name, fastSearch.Value);
if (fastData != null)
Dictionary<string, object>? fastRow = null;
if (wholeFile != null)
{
var fastRow = DeserializeDeleteKeyRow(fastData, deleteKeyColumns) ?? DeserializeRowFromSpan(fastData);
if (fastRow != null)
fastRow = DeserializeDeleteKeyRowFromFile(wholeFile, fastSearch.Value, deleteKeyColumns);
}
else
{
var fastData = engine.Read(Name, fastSearch.Value);
if (fastData != null)
{
recordsToDelete.Add((fastSearch.Value, fastRow));
fastRow = DeserializeDeleteKeyRow(fastData, deleteKeyColumns) ?? DeserializeRowFromSpan(fastData);
}
}

if (fastRow != null)
{
recordsToDelete.Add((fastSearch.Value, fastRow));
}

continue;
}
}
Expand Down Expand Up @@ -3127,12 +3140,21 @@ _btreeManager is null &&

foreach (var pos in hashIndex.LookupPositionsUnsafe(key))
{
var data = engine.Read(Name, pos);
if (data != null)
Dictionary<string, object>? row = null;
if (wholeFile != null)
{
var row = DeserializeDeleteKeyRow(data, deleteKeyColumns) ?? DeserializeRowFromSpan(data);
if (row != null) recordsToDelete.Add((pos, row));
row = DeserializeDeleteKeyRowFromFile(wholeFile, pos, deleteKeyColumns);
}
else
{
var data = engine.Read(Name, pos);
if (data != null)
{
row = DeserializeDeleteKeyRow(data, deleteKeyColumns) ?? DeserializeRowFromSpan(data);
}
}

if (row != null) recordsToDelete.Add((pos, row));
}

continue;
Expand Down Expand Up @@ -3237,12 +3259,29 @@ private int[] BuildDeleteKeyColumns()
/// </summary>
private Dictionary<string, object>? DeserializeDeleteKeyRow(byte[] data, int[] wanted)
{
if (_fixedWidthRecords || data == null || data.Length == 0 || wanted.Length == 0)
if (data == null)
{
return null;
}

return DeserializeDeleteKeyRow(data.AsSpan(), wanted);
}

/// <summary>
/// B1: decodes only the columns listed in <paramref name="wanted"/> (ascending) from a legacy
/// variable-length serialized row, skipping the unneeded columns' payload parsing entirely.
/// Returns a minimal dictionary (pk + hash-index columns only) so <see cref="DeleteRecordsCore"/>
/// performs the identical PK/hash lookups without materializing the full row. Returns null for
/// fixed-width layouts (those go through the fixed-width codec) or corrupt rows — callers fall
/// back to full-row deserialization in that case.
/// </summary>
private Dictionary<string, object>? DeserializeDeleteKeyRow(ReadOnlySpan<byte> span, int[] wanted)
{
if (_fixedWidthRecords || span.IsEmpty || wanted.Length == 0)
{
return null;
}

ReadOnlySpan<byte> span = data.AsSpan();
int offset = 0;
Dictionary<string, object>? row = null;
int wi = 0;
Expand Down Expand Up @@ -3274,6 +3313,44 @@ private int[] BuildDeleteKeyColumns()
return row;
}

// A1: whole-file delete resolution reads the (small) data file once instead of one pread pair
// per deleted row. Guarded to plaintext legacy variable-length files below this size.
private const long WholeFileDeleteResolutionLimitBytes = 32 * 1024 * 1024;

private byte[]? TryLoadWholeFileForDeleteResolution()
{
if (_fixedWidthRecords ||
this.storage is null ||
this.storage.AreRecordsEncrypted(DataFile))
{
return null;
}

var fi = new System.IO.FileInfo(DataFile);
if (!fi.Exists || fi.Length <= 0 || fi.Length > WholeFileDeleteResolutionLimitBytes)
{
return null;
}

return this.storage.ReadBytesRange(DataFile, 0, (int)fi.Length);
}

private Dictionary<string, object>? DeserializeDeleteKeyRowFromFile(byte[] wholeFile, long position, int[] wanted)
{
if (position < 0 || position + 4 > wholeFile.Length)
{
return null;
}

int recordLength = System.Buffers.Binary.BinaryPrimitives.ReadInt32LittleEndian(wholeFile.AsSpan((int)position, 4));
if (recordLength <= 0 || position + 4 + recordLength > wholeFile.Length)
{
return null;
}

return DeserializeDeleteKeyRow(wholeFile.AsSpan((int)position + 4, recordLength), wanted);
}

/// <summary>
/// Shared B8/B9 probe: resolves each key's record position through the PK B-tree, requires the
/// positions to be physically adjacent at the fixed-width stride, reads the whole contiguous
Expand Down
Loading