Skip to content

Change default S3 repository chunk_size #112708

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
wants to merge 2 commits into from
Closed

Change default S3 repository chunk_size #112708

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
28a8b94
change default s3 chunk_size
mhl-b Sep 10, 2024
e08aabb
test
mhl-b Sep 10, 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
18 changes: 17 additions & 1 deletion modules/repository-s3/src/main/java/org/elasticsearch/repositories/s3/S3Repository.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -117,6 +117,22 @@ class S3Repository extends MeteredBlobStoreRepository {
*/
static final ByteSizeValue MAX_FILE_SIZE_USING_MULTIPART = new ByteSizeValue(5, ByteSizeUnit.TB);

/**
* Maximum number of parts that can be uploaded using the Multipart Upload API.
* (see http://docs.aws.amazon.com/AmazonS3/latest/dev/qfacts.html)
*/
static final long MAX_PARTS_NUMBER_USING_MULTIPART = 10_000;

/**
* Big files should be broken down into chunks taking into account S3 maximum object size and number of parts.
* Chunk size would be in range {@code part_size * max_number_of_parts = [50Gb, 5Tb]}, where {@code part_size = [5Mb, 5Gb]}
* and {@code max_number_of_parts = 10_000}
*/
static final ByteSizeValue DEFAULT_CHUNK_SIZE = new ByteSizeValue(
DEFAULT_BUFFER_SIZE.getBytes() * MAX_PARTS_NUMBER_USING_MULTIPART,
ByteSizeUnit.BYTES
);

/**
* Minimum threshold below which the chunk is uploaded using a single request. Beyond this threshold,
* the S3 repository will use the AWS Multipart Upload API to split the chunk into several parts, each of buffer_size length, and
Expand All @@ -135,7 +151,7 @@ class S3Repository extends MeteredBlobStoreRepository {
*/
static final Setting<ByteSizeValue> CHUNK_SIZE_SETTING = Setting.byteSizeSetting(
"chunk_size",
MAX_FILE_SIZE_USING_MULTIPART,
DEFAULT_CHUNK_SIZE,
new ByteSizeValue(5, ByteSizeUnit.MB),
MAX_FILE_SIZE_USING_MULTIPART
);
Expand Down
11 changes: 11 additions & 0 deletions ...ository-s3/src/test/java/org/elasticsearch/repositories/s3/S3BlobStoreContainerTests.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@

import org.elasticsearch.common.blobstore.BlobPath;
import org.elasticsearch.common.blobstore.BlobStoreException;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.common.unit.ByteSizeUnit;
import org.elasticsearch.core.Tuple;
import org.elasticsearch.test.ESTestCase;
Expand Down Expand Up @@ -84,6 +85,16 @@ public void testExecuteSingleUploadBlobSizeLargerThanBufferSize() {
assertEquals("Upload request size [2097152] can't be larger than buffer size", e.getMessage());
}

public void testDefaultChunkPartsLimit() {
var settings = Settings.EMPTY;
var blobSize = S3Repository.CHUNK_SIZE_SETTING.getDefault(settings).getBytes();
var partSize = S3Repository.BUFFER_SIZE_SETTING.getDefault(settings).getBytes();
var parts = S3BlobContainer.numberOfMultiparts(blobSize, partSize);
var gotParts = parts.v1();
var maxParts = S3Repository.MAX_PARTS_NUMBER_USING_MULTIPART;
assertTrue("numbers of parts should be less-or-equal " + maxParts + ", got " + gotParts, gotParts <= maxParts);
}

public void testExecuteSingleUpload() throws IOException {
final String bucketName = randomAlphaOfLengthBetween(1, 10);
final String blobName = randomAlphaOfLengthBetween(1, 10);
Expand Down