Implement ListMultipartUploads (#171)

Implement ListMultipartUploads, also refactor ListObjects and ListObjectsV2.

It took me some times as I wanted to propose the following things:
  - Using an iterator instead of the loop+goto pattern. I find it easier to read and it should enable some optimizations. For example, when consuming keys of a common prefix, we do many [redundant checks](https://git.deuxfleurs.fr/Deuxfleurs/garage/src/branch/main/src/api/s3_list.rs#L125-L156) while the only thing to do is to [check if the following key is still part of the common prefix](https://git.deuxfleurs.fr/Deuxfleurs/garage/src/branch/feature/s3-multipart-compat/src/api/s3_list.rs#L476).
  - Try to name things (see ExtractionResult and RangeBegin enums) and to separate concerns (see ListQuery and Accumulator)
  - An IO closure to make unit tests possibles.
  - Unit tests, to track regressions and document how to interact with the code
  - Integration tests with `s3api`. In the future, I would like to move them in Rust with the aws rust SDK.

Merging of the logic of ListMultipartUploads and ListObjects was not a goal but a consequence of the previous modifications.

Some points that we might want to discuss:
  - ListObjectsV1, when using pagination and delimiters, has a weird behavior (it lists multiple times the same prefix) with `aws s3api` due to the fact that it can not use our optimization to skip the whole prefix. It is independant from my refactor and can be tested with the commented `s3api` tests in `test-smoke.sh`. It probably has the same weird behavior on the official AWS S3 implementation.
  - Considering ListMultipartUploads, I had to "abuse" upload id marker to support prefix skipping. I send an `upload-id-marker` with the hardcoded value `include` to emulate your "including" token.
  - Some ways to test ListMultipartUploads with existing software (my tests are limited to s3api for now).

Co-authored-by: Quentin Dufour <quentin@deuxfleurs.fr>
Reviewed-on: https://git.deuxfleurs.fr/Deuxfleurs/garage/pulls/171
Co-authored-by: Quentin <quentin@dufour.io>
Co-committed-by: Quentin <quentin@dufour.io>
This commit is contained in:
Quentin
2022-01-12 19:04:55 +01:00
committed by Alex
parent 9cb2e9e57c
commit b4592a00fe
17 changed files with 1285 additions and 283 deletions
+43 -12
View File
@@ -1,3 +1,4 @@
use std::cmp::{max, min};
use std::net::SocketAddr;
use std::sync::Arc;
@@ -217,16 +218,18 @@ async fn handler_inner(garage: Arc<Garage>, req: Request<Body>) -> Result<Respon
handle_list(
garage,
&ListObjectsQuery {
common: ListQueryCommon {
bucket_name: bucket,
bucket_id,
delimiter: delimiter.map(|d| d.to_string()),
page_size: max_keys.map(|p| min(1000, max(1, p))).unwrap_or(1000),
prefix: prefix.unwrap_or_default(),
urlencode_resp: encoding_type.map(|e| e == "url").unwrap_or(false),
},
is_v2: false,
bucket_name: bucket,
bucket_id,
delimiter: delimiter.map(|d| d.to_string()),
max_keys: max_keys.unwrap_or(1000),
prefix: prefix.unwrap_or_default(),
marker,
continuation_token: None,
start_after: None,
urlencode_resp: encoding_type.map(|e| e == "url").unwrap_or(false),
},
)
.await
@@ -246,16 +249,18 @@ async fn handler_inner(garage: Arc<Garage>, req: Request<Body>) -> Result<Respon
handle_list(
garage,
&ListObjectsQuery {
common: ListQueryCommon {
bucket_name: bucket,
bucket_id,
delimiter: delimiter.map(|d| d.to_string()),
page_size: max_keys.map(|p| min(1000, max(1, p))).unwrap_or(1000),
urlencode_resp: encoding_type.map(|e| e == "url").unwrap_or(false),
prefix: prefix.unwrap_or_default(),
},
is_v2: true,
bucket_name: bucket,
bucket_id,
delimiter: delimiter.map(|d| d.to_string()),
max_keys: max_keys.unwrap_or(1000),
prefix: prefix.unwrap_or_default(),
marker: None,
continuation_token,
start_after,
urlencode_resp: encoding_type.map(|e| e == "url").unwrap_or(false),
},
)
.await
@@ -266,6 +271,32 @@ async fn handler_inner(garage: Arc<Garage>, req: Request<Body>) -> Result<Respon
)))
}
}
Endpoint::ListMultipartUploads {
bucket,
delimiter,
encoding_type,
key_marker,
max_uploads,
prefix,
upload_id_marker,
} => {
handle_list_multipart_upload(
garage,
&ListMultipartUploadsQuery {
common: ListQueryCommon {
bucket_name: bucket,
bucket_id,
delimiter: delimiter.map(|d| d.to_string()),
page_size: max_uploads.map(|p| min(1000, max(1, p))).unwrap_or(1000),
prefix: prefix.unwrap_or_default(),
urlencode_resp: encoding_type.map(|e| e == "url").unwrap_or(false),
},
key_marker,
upload_id_marker,
},
)
.await
}
Endpoint::DeleteObjects { .. } => {
handle_delete_objects(garage, bucket_id, req, content_sha256).await
}
+2 -1
View File
@@ -7,6 +7,7 @@ use garage_model::bucket_alias_table::*;
use garage_model::bucket_table::Bucket;
use garage_model::garage::Garage;
use garage_model::key_table::Key;
use garage_model::object_table::ObjectFilter;
use garage_model::permission::BucketKeyPerm;
use garage_table::util::*;
use garage_util::crdt::*;
@@ -226,7 +227,7 @@ pub async fn handle_delete_bucket(
// Check bucket is empty
let objects = garage
.object_table
.get_range(&bucket_id, None, Some(DeletedFilter::NotDeleted), 10)
.get_range(&bucket_id, None, Some(ObjectFilter::IsData), 10)
.await?;
if !objects.is_empty() {
return Err(Error::BucketNotEmpty);
+953 -257
View File
File diff suppressed because it is too large Load Diff
+1 -1
View File
@@ -610,7 +610,7 @@ pub(crate) fn get_headers(req: &Request<Body>) -> Result<ObjectVersionHeaders, E
})
}
fn decode_upload_id(id: &str) -> Result<Uuid, Error> {
pub fn decode_upload_id(id: &str) -> Result<Uuid, Error> {
let id_bin = hex::decode(id).map_err(|_| Error::NoSuchUpload)?;
if id_bin.len() != 32 {
return Err(Error::NoSuchUpload);
+1 -1
View File
@@ -350,7 +350,7 @@ pub enum Endpoint {
delimiter: Option<char>,
encoding_type: Option<String>,
key_marker: Option<String>,
max_uploads: Option<u64>,
max_uploads: Option<usize>,
prefix: Option<String>,
upload_id_marker: Option<String>,
},
+106
View File
@@ -141,6 +141,60 @@ pub struct CompleteMultipartUploadResult {
pub etag: Value,
}
#[derive(Debug, Serialize, PartialEq)]
pub struct Initiator {
#[serde(rename = "DisplayName")]
pub display_name: Value,
#[serde(rename = "ID")]
pub id: Value,
}
#[derive(Debug, Serialize, PartialEq)]
pub struct ListMultipartItem {
#[serde(rename = "Initiated")]
pub initiated: Value,
#[serde(rename = "Initiator")]
pub initiator: Initiator,
#[serde(rename = "Key")]
pub key: Value,
#[serde(rename = "UploadId")]
pub upload_id: Value,
#[serde(rename = "Owner")]
pub owner: Owner,
#[serde(rename = "StorageClass")]
pub storage_class: Value,
}
#[derive(Debug, Serialize, PartialEq)]
pub struct ListMultipartUploadsResult {
#[serde(serialize_with = "xmlns_tag")]
pub xmlns: (),
#[serde(rename = "Bucket")]
pub bucket: Value,
#[serde(rename = "KeyMarker")]
pub key_marker: Option<Value>,
#[serde(rename = "UploadIdMarker")]
pub upload_id_marker: Option<Value>,
#[serde(rename = "NextKeyMarker")]
pub next_key_marker: Option<Value>,
#[serde(rename = "NextUploadIdMarker")]
pub next_upload_id_marker: Option<Value>,
#[serde(rename = "Prefix")]
pub prefix: Value,
#[serde(rename = "Delimiter")]
pub delimiter: Option<Value>,
#[serde(rename = "MaxUploads")]
pub max_uploads: IntValue,
#[serde(rename = "IsTruncated")]
pub is_truncated: Value,
#[serde(rename = "Upload")]
pub upload: Vec<ListMultipartItem>,
#[serde(rename = "CommonPrefixes")]
pub common_prefixes: Vec<CommonPrefix>,
#[serde(rename = "EncodingType")]
pub encoding_type: Option<Value>,
}
#[derive(Debug, Serialize, PartialEq)]
pub struct ListBucketItem {
#[serde(rename = "Key")]
@@ -432,6 +486,58 @@ mod tests {
Ok(())
}
#[test]
fn list_multipart_uploads_result() -> Result<(), ApiError> {
let result = ListMultipartUploadsResult {
xmlns: (),
bucket: Value("example-bucket".to_string()),
key_marker: None,
next_key_marker: None,
upload_id_marker: None,
encoding_type: None,
next_upload_id_marker: None,
upload: vec![],
delimiter: Some(Value("/".to_string())),
prefix: Value("photos/2006/".to_string()),
max_uploads: IntValue(1000),
is_truncated: Value("false".to_string()),
common_prefixes: vec![
CommonPrefix {
prefix: Value("photos/2006/February/".to_string()),
},
CommonPrefix {
prefix: Value("photos/2006/January/".to_string()),
},
CommonPrefix {
prefix: Value("photos/2006/March/".to_string()),
},
],
};
assert_eq!(
to_xml_with_header(&result)?,
"<?xml version=\"1.0\" encoding=\"UTF-8\"?>\
<ListMultipartUploadsResult xmlns=\"http://s3.amazonaws.com/doc/2006-03-01/\">\
<Bucket>example-bucket</Bucket>\
<Prefix>photos/2006/</Prefix>\
<Delimiter>/</Delimiter>\
<MaxUploads>1000</MaxUploads>\
<IsTruncated>false</IsTruncated>\
<CommonPrefixes>\
<Prefix>photos/2006/February/</Prefix>\
</CommonPrefixes>\
<CommonPrefixes>\
<Prefix>photos/2006/January/</Prefix>\
</CommonPrefixes>\
<CommonPrefixes>\
<Prefix>photos/2006/March/</Prefix>\
</CommonPrefixes>\
</ListMultipartUploadsResult>"
);
Ok(())
}
#[test]
fn list_objects_v1_1() -> Result<(), ApiError> {
let result = ListBucketResult {