Skip to content
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

Update VFS S3 to ListObjectsV2 #4216

Merged
merged 3 commits into from
Aug 3, 2023
Merged

Update VFS S3 to ListObjectsV2 #4216

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
106733e
Test with ListObjectsV2
shaunrd0 Jul 27, 2023
f440b32
Remove empty string delim used to test
shaunrd0 Jul 27, 2023
6be3a89
Update remaining call to ListObjectsV1
shaunrd0 Jul 27, 2023
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
40 changes: 20 additions & 20 deletions tiledb/sm/filesystem/s3.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -709,18 +709,20 @@ Status S3::is_empty_bucket(const URI& bucket, bool* is_empty) const {

bool exists;
RETURN_NOT_OK(is_bucket(bucket, &exists));
if (!exists)
if (!exists) {
return LOG_STATUS(Status_S3Error(
"Cannot check if bucket is empty; Bucket does not exist"));
}

Aws::Http::URI aws_uri = bucket.c_str();
Aws::S3::Model::ListObjectsRequest list_objects_request;
Aws::S3::Model::ListObjectsV2Request list_objects_request;
list_objects_request.SetBucket(aws_uri.GetAuthority());
list_objects_request.SetPrefix("");
list_objects_request.SetDelimiter("/");
if (request_payer_ != Aws::S3::Model::RequestPayer::NOT_SET)
if (request_payer_ != Aws::S3::Model::RequestPayer::NOT_SET) {
list_objects_request.SetRequestPayer(request_payer_);
auto list_objects_outcome = client_->ListObjects(list_objects_request);
}
auto list_objects_outcome = client_->ListObjectsV2(list_objects_request);

if (!list_objects_outcome.IsSuccess()) {
return LOG_STATUS(Status_S3Error(
Expand Down Expand Up @@ -823,22 +825,24 @@ tuple<Status, optional<std::vector<directory_entry>>> S3::ls_with_sizes(
Aws::Http::URI aws_uri = prefix_str.c_str();
auto aws_prefix = remove_front_slash(aws_uri.GetPath().c_str());
std::string aws_auth = aws_uri.GetAuthority().c_str();
Aws::S3::Model::ListObjectsRequest list_objects_request;
Aws::S3::Model::ListObjectsV2Request list_objects_request;
list_objects_request.SetBucket(aws_uri.GetAuthority());
list_objects_request.SetPrefix(aws_prefix.c_str());
list_objects_request.SetDelimiter(delimiter.c_str());
if (request_payer_ != Aws::S3::Model::RequestPayer::NOT_SET)
if (request_payer_ != Aws::S3::Model::RequestPayer::NOT_SET) {
list_objects_request.SetRequestPayer(request_payer_);
}

std::vector<directory_entry> entries;

bool is_done = false;
while (!is_done) {
// Not requesting more items than needed
if (max_paths != -1)
if (max_paths != -1) {
list_objects_request.SetMaxKeys(
max_paths - static_cast<int>(entries.size()));
auto list_objects_outcome = client_->ListObjects(list_objects_request);
}
auto list_objects_outcome = client_->ListObjectsV2(list_objects_request);

if (!list_objects_outcome.IsSuccess()) {
auto st = LOG_STATUS(Status_S3Error(
Expand Down Expand Up @@ -870,19 +874,15 @@ tuple<Status, optional<std::vector<directory_entry>>> S3::ls_with_sizes(
!list_objects_outcome.GetResult().GetIsTruncated() ||
(max_paths != -1 && entries.size() >= static_cast<size_t>(max_paths));
if (!is_done) {
// The documentation states that "GetNextMarker" will be non-empty only
// when the delimiter in the request is non-empty. When the delimiter is
// non-empty, we must used the last returned key as the next marker.
assert(
!delimiter.empty() ||
!list_objects_outcome.GetResult().GetContents().empty());
Aws::String next_marker =
!delimiter.empty() ?
list_objects_outcome.GetResult().GetNextMarker() :
list_objects_outcome.GetResult().GetContents().back().GetKey();
assert(!next_marker.empty());

list_objects_request.SetMarker(std::move(next_marker));
list_objects_outcome.GetResult().GetNextContinuationToken();
if (next_marker.empty()) {
auto st =
LOG_STATUS(Status_S3Error("Failed to retrieve next continuation "
"token for ListObjectsV2 request."));
return {st, nullopt};
}
list_objects_request.SetContinuationToken(std::move(next_marker));
}
}

Expand Down
2 changes: 1 addition & 1 deletion tiledb/sm/filesystem/s3.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,7 +71,7 @@
#include <aws/s3/model/GetObjectRequest.h>
#include <aws/s3/model/HeadBucketRequest.h>
#include <aws/s3/model/HeadObjectRequest.h>
#include <aws/s3/model/ListObjectsRequest.h>
#include <aws/s3/model/ListObjectsV2Request.h>
#include <aws/s3/model/PutObjectRequest.h>
#include <aws/s3/model/UploadPartRequest.h>
#include <sys/types.h>
Expand Down