Skip to content

Core: Add total size fields for position and equality delete files in PartitionsTable #14820

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

Closed
xxubai wants to merge 10 commits into from
Closed

Core: Add total size fields for position and equality delete files in PartitionsTable #14820

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
8ccb4ca
Core: Add total size fields for position and equality delete files in…
xxubai Dec 11, 2025
c7bfb41
address
xxubai Dec 12, 2025
a1d2758
change totalDeleteFileSizeInBytes method to static
xxubai Dec 12, 2025
999b8e3
spotless
xxubai Dec 12, 2025
f6c9a55
Add total size fields for position and equality delete files
xxubai Dec 16, 2025
4545eca
add for spark3.5, spark3.4
xxubai Dec 16, 2025
45783c3
Add tests for partitions table schema and data validation
xxubai Feb 10, 2026
ec90f6c
Add total size fields for position and equality delete files in parti…
xxubai Feb 10, 2026
e9e40ff
fix
xxubai Feb 10, 2026
8c46f88
Add tests for partitions table delete stats with delete vectors
xxubai Mar 17, 2026
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
22 changes: 22 additions & 0 deletions core/src/main/java/org/apache/iceberg/PartitionsTable.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,6 +71,11 @@ public class PartitionsTable extends BaseMetadataTable {
"position_delete_file_count",
Types.IntegerType.get(),
"Count of position delete files"),
Types.NestedField.required(
12,
"total_position_delete_file_size_in_bytes",
Types.LongType.get(),
"Total size in bytes of position delete files"),
Types.NestedField.required(
7,
"equality_delete_record_count",
Expand All @@ -81,6 +86,11 @@ public class PartitionsTable extends BaseMetadataTable {
"equality_delete_file_count",
Types.IntegerType.get(),
"Count of equality delete files"),
Types.NestedField.required(
13,
"total_equality_delete_file_size_in_bytes",
Types.LongType.get(),
"Total size in bytes of equality delete files"),
Types.NestedField.optional(
9,
"last_updated_at",
Expand Down Expand Up @@ -108,8 +118,10 @@ public Schema schema() {
"total_data_file_size_in_bytes",
"position_delete_record_count",
"position_delete_file_count",
"total_position_delete_file_size_in_bytes",
"equality_delete_record_count",
"equality_delete_file_count",
"total_equality_delete_file_size_in_bytes",
"last_updated_at",
"last_updated_snapshot_id");
}
Expand Down Expand Up @@ -137,8 +149,10 @@ private DataTask task(StaticTableScan scan) {
root.dataFileSizeInBytes,
root.posDeleteRecordCount,
root.posDeleteFileCount,
root.posDeleteFileSizeInBytes,
root.eqDeleteRecordCount,
root.eqDeleteFileCount,
root.eqDeleteFileSizeInBytes,
root.lastUpdatedAt,
root.lastUpdatedSnapshotId));
} else {
Expand All @@ -160,8 +174,10 @@ private static StaticDataTask.Row convertPartition(Partition partition) {
partition.dataFileSizeInBytes,
partition.posDeleteRecordCount,
partition.posDeleteFileCount,
partition.posDeleteFileSizeInBytes,
partition.eqDeleteRecordCount,
partition.eqDeleteFileCount,
partition.eqDeleteFileSizeInBytes,
partition.lastUpdatedAt,
partition.lastUpdatedSnapshotId);
}
Expand Down Expand Up @@ -277,8 +293,10 @@ static class Partition {
private long dataFileSizeInBytes;
private long posDeleteRecordCount;
private int posDeleteFileCount;
private long posDeleteFileSizeInBytes;
private long eqDeleteRecordCount;
private int eqDeleteFileCount;
private long eqDeleteFileSizeInBytes;
private Long lastUpdatedAt;
private Long lastUpdatedSnapshotId;

Expand All @@ -290,8 +308,10 @@ static class Partition {
this.dataFileSizeInBytes = 0L;
this.posDeleteRecordCount = 0L;
this.posDeleteFileCount = 0;
this.posDeleteFileSizeInBytes = 0L;
this.eqDeleteRecordCount = 0L;
this.eqDeleteFileCount = 0;
this.eqDeleteFileSizeInBytes = 0L;
}

void update(ContentFile<?> file, Snapshot snapshot) {
Expand All @@ -314,10 +334,12 @@ void update(ContentFile<?> file, Snapshot snapshot) {
case POSITION_DELETES:
this.posDeleteRecordCount += file.recordCount();
this.posDeleteFileCount += 1;
this.posDeleteFileSizeInBytes += file.fileSizeInBytes();
break;
case EQUALITY_DELETES:
this.eqDeleteRecordCount += file.recordCount();
this.eqDeleteFileCount += 1;
this.eqDeleteFileSizeInBytes += file.fileSizeInBytes();
break;
default:
throw new UnsupportedOperationException(
Expand Down
12 changes: 6 additions & 6 deletions docs/docs/flink-queries.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -492,12 +492,12 @@ To show a table's current partitions:
SELECT * FROM prod.db.table$partitions;
```

| partition | spec_id | record_count | file_count | total_data_file_size_in_bytes | position_delete_record_count | position_delete_file_count | equality_delete_record_count | equality_delete_file_count | last_updated_at(μs) | last_updated_snapshot_id |
| -------------- |---------|---------------|------------|--------------------------|------------------------------|----------------------------|------------------------------|----------------------------|---------------------|--------------------------|
| {20211001, 11} | 0 | 1 | 1 | 100 | 2 | 1 | 0 | 0 | 1633086034192000 | 9205185327307503337 |
| {20211002, 11} | 0 | 4 | 3 | 500 | 1 | 1 | 0 | 0 | 1633172537358000 | 867027598972211003 |
| {20211001, 10} | 0 | 7 | 4 | 700 | 0 | 0 | 0 | 0 | 1633082598716000 | 3280122546965981531 |
| {20211002, 10} | 0 | 3 | 2 | 400 | 0 | 0 | 1 | 1 | 1633169159489000 | 6941468797545315876 |
| partition | spec_id | record_count | file_count | total_data_file_size_in_bytes | position_delete_record_count | position_delete_file_count | total_position_delete_file_size_in_bytes | equality_delete_record_count | equality_delete_file_count | total_equality_delete_file_size_in_bytes | last_updated_at(μs) | last_updated_snapshot_id |
Copy link
Copy Markdown
Member

@ebyhr ebyhr Jan 23, 2026 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does Flink expose PartitionsTable as-is? I'm asking this question because this PR doesn't contain any changes in Flink module.

Can we update Flink tests if this PR affects the module?

Copy link
Copy Markdown
Contributor Author

@xxubai xxubai Feb 10, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@ebyhr The update is ready. Please take a look.

| -------------- |---------|---------------|------------|--------------------------|------------------------------|----------------------------|------------------------------------------|------------------------------|----------------------------|------------------------------------------|---------------------|--------------------------|
| {20211001, 11} | 0 | 1 | 1 | 100 | 2 | 1 | 50 | 0 | 0 | 0 | 1633086034192000 | 9205185327307503337 |
| {20211002, 11} | 0 | 4 | 3 | 500 | 1 | 1 | 100 | 0 | 0 | 0 | 1633172537358000 | 867027598972211003 |
| {20211001, 10} | 0 | 7 | 4 | 700 | 0 | 0 | 0 | 0 | 0 | 0 | 1633082598716000 | 3280122546965981531 |
| {20211002, 10} | 0 | 3 | 2 | 400 | 0 | 0 | 0 | 1 | 1 | 400 | 1633169159489000 | 6941468797545315876 |

Note:
For unpartitioned tables, the partitions table will not contain the partition and spec_id fields.
Expand Down
12 changes: 6 additions & 6 deletions docs/docs/spark-queries.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -427,12 +427,12 @@ To show a table's current partitions:
SELECT * FROM prod.db.table.partitions;
```

| partition | spec_id | record_count | file_count | total_data_file_size_in_bytes | position_delete_record_count | position_delete_file_count | equality_delete_record_count | equality_delete_file_count | last_updated_at(μs) | last_updated_snapshot_id |
| -------------- |---------|---------------|------------|--------------------------|------------------------------|----------------------------|------------------------------|----------------------------|---------------------|--------------------------|
| {20211001, 11} | 0 | 1 | 1 | 100 | 2 | 1 | 0 | 0 | 1633086034192000 | 9205185327307503337 |
| {20211002, 11} | 0 | 4 | 3 | 500 | 1 | 1 | 0 | 0 | 1633172537358000 | 867027598972211003 |
| {20211001, 10} | 0 | 7 | 4 | 700 | 0 | 0 | 0 | 0 | 1633082598716000 | 3280122546965981531 |
| {20211002, 10} | 0 | 3 | 2 | 400 | 0 | 0 | 1 | 1 | 1633169159489000 | 6941468797545315876 |
| partition | spec_id | record_count | file_count | total_data_file_size_in_bytes | position_delete_record_count | position_delete_file_count | total_position_delete_file_size_in_bytes | equality_delete_record_count | equality_delete_file_count | total_equality_delete_file_size_in_bytes | last_updated_at(μs) | last_updated_snapshot_id |
| -------------- |---------|---------------|------------|--------------------------|------------------------------|----------------------------|------------------------------------------|------------------------------|----------------------------|------------------------------------------|---------------------|--------------------------|
| {20211001, 11} | 0 | 1 | 1 | 100 | 2 | 1 | 50 | 0 | 0 | 0 | 1633086034192000 | 9205185327307503337 |
| {20211002, 11} | 0 | 4 | 3 | 500 | 1 | 1 | 100 | 0 | 0 | 0 | 1633172537358000 | 867027598972211003 |
| {20211001, 10} | 0 | 7 | 4 | 700 | 0 | 0 | 0 | 0 | 0 | 0 | 1633082598716000 | 3280122546965981531 |
| {20211002, 10} | 0 | 3 | 2 | 400 | 0 | 0 | 0 | 1 | 1 | 400 | 1633169159489000 | 6941468797545315876 |

Note:

Expand Down
Loading
Loading