improve internal item counter mechanisms and implement bucket quotas (#326)

- [x] Refactoring of internal counting API
- [x] Repair procedure for counters (it's an offline procedure!!!)
- [x] New counter for objects in buckets
- [x] Add quotas to buckets struct
- [x] Add CLI to manage bucket quotas
- [x] Add admin API to manage bucket quotas
- [x] Apply quotas by adding checks on put operations
- [x] Proof-read

Co-authored-by: Alex Auvolat <alex@adnab.me>
Reviewed-on: https://git.deuxfleurs.fr/Deuxfleurs/garage/pulls/326
Co-authored-by: Alex <alex@adnab.me>
Co-committed-by: Alex <alex@adnab.me>
This commit is contained in:
Alex
2022-06-15 20:20:28 +02:00
parent d544a0e0e0
commit 77e3fd6db2
32 changed files with 962 additions and 347 deletions
+1 -6
View File
@@ -156,12 +156,7 @@ impl ApiHandler for AdminApiServer {
}
Endpoint::CreateBucket => handle_create_bucket(&self.garage, req).await,
Endpoint::DeleteBucket { id } => handle_delete_bucket(&self.garage, id).await,
Endpoint::PutBucketWebsite { id } => {
handle_put_bucket_website(&self.garage, id, req).await
}
Endpoint::DeleteBucketWebsite { id } => {
handle_delete_bucket_website(&self.garage, id).await
}
Endpoint::UpdateBucket { id } => handle_update_bucket(&self.garage, id, req).await,
// Bucket-key permissions
Endpoint::BucketAllowKey => {
handle_bucket_change_key_perm(&self.garage, req, true).await
+67 -29
View File
@@ -14,6 +14,7 @@ use garage_model::bucket_alias_table::*;
use garage_model::bucket_table::*;
use garage_model::garage::Garage;
use garage_model::permission::*;
use garage_model::s3::object_table::*;
use crate::admin::error::*;
use crate::admin::key::ApiBucketKeyPerm;
@@ -77,6 +78,13 @@ struct BucketLocalAlias {
alias: String,
}
#[derive(Serialize, Deserialize)]
#[serde(rename_all = "camelCase")]
struct ApiBucketQuotas {
max_size: Option<u64>,
max_objects: Option<u64>,
}
pub async fn handle_get_bucket_info(
garage: &Arc<Garage>,
id: Option<String>,
@@ -108,6 +116,14 @@ async fn bucket_info_results(
.get_existing_bucket(bucket_id)
.await?;
let counters = garage
.object_counter_table
.table
.get(&bucket_id, &EmptyKey)
.await?
.map(|x| x.filtered_values(&garage.system.ring.borrow()))
.unwrap_or_default();
let mut relevant_keys = HashMap::new();
for (k, _) in bucket
.state
@@ -148,6 +164,7 @@ async fn bucket_info_results(
let state = bucket.state.as_option().unwrap();
let quotas = state.quotas.get();
let res =
GetBucketInfoResult {
id: hex::encode(&bucket.id),
@@ -191,6 +208,16 @@ async fn bucket_info_results(
}
})
.collect::<Vec<_>>(),
objects: counters.get(OBJECTS).cloned().unwrap_or_default(),
bytes: counters.get(BYTES).cloned().unwrap_or_default(),
unfinshed_uploads: counters
.get(UNFINISHED_UPLOADS)
.cloned()
.unwrap_or_default(),
quotas: ApiBucketQuotas {
max_size: quotas.max_size,
max_objects: quotas.max_objects,
},
};
Ok(json_ok_response(&res)?)
@@ -205,6 +232,10 @@ struct GetBucketInfoResult {
#[serde(default)]
website_config: Option<GetBucketInfoWebsiteResult>,
keys: Vec<GetBucketInfoKey>,
objects: i64,
bytes: i64,
unfinshed_uploads: i64,
quotas: ApiBucketQuotas,
}
#[derive(Serialize)]
@@ -363,14 +394,12 @@ pub async fn handle_delete_bucket(
.body(Body::empty())?)
}
// ---- BUCKET WEBSITE CONFIGURATION ----
pub async fn handle_put_bucket_website(
pub async fn handle_update_bucket(
garage: &Arc<Garage>,
id: String,
req: Request<Body>,
) -> Result<Response<Body>, Error> {
let req = parse_json_body::<PutBucketWebsiteRequest>(req).await?;
let req = parse_json_body::<UpdateBucketRequest>(req).await?;
let bucket_id = parse_bucket_id(&id)?;
let mut bucket = garage
@@ -379,10 +408,31 @@ pub async fn handle_put_bucket_website(
.await?;
let state = bucket.state.as_option_mut().unwrap();
state.website_config.update(Some(WebsiteConfig {
index_document: req.index_document,
error_document: req.error_document,
}));
if let Some(wa) = req.website_access {
if wa.enabled {
state.website_config.update(Some(WebsiteConfig {
index_document: wa.index_document.ok_or_bad_request(
"Please specify indexDocument when enabling website access.",
)?,
error_document: wa.error_document,
}));
} else {
if wa.index_document.is_some() || wa.error_document.is_some() {
return Err(Error::bad_request(
"Cannot specify indexDocument or errorDocument when disabling website access.",
));
}
state.website_config.update(None);
}
}
if let Some(q) = req.quotas {
state.quotas.update(BucketQuotas {
max_size: q.max_size,
max_objects: q.max_objects,
});
}
garage.bucket_table.insert(&bucket).await?;
@@ -391,29 +441,17 @@ pub async fn handle_put_bucket_website(
#[derive(Deserialize)]
#[serde(rename_all = "camelCase")]
struct PutBucketWebsiteRequest {
index_document: String,
#[serde(default)]
error_document: Option<String>,
struct UpdateBucketRequest {
website_access: Option<UpdateBucketWebsiteAccess>,
quotas: Option<ApiBucketQuotas>,
}
pub async fn handle_delete_bucket_website(
garage: &Arc<Garage>,
id: String,
) -> Result<Response<Body>, Error> {
let bucket_id = parse_bucket_id(&id)?;
let mut bucket = garage
.bucket_helper()
.get_existing_bucket(bucket_id)
.await?;
let state = bucket.state.as_option_mut().unwrap();
state.website_config.update(None);
garage.bucket_table.insert(&bucket).await?;
bucket_info_results(garage, bucket_id).await
#[derive(Deserialize)]
#[serde(rename_all = "camelCase")]
struct UpdateBucketWebsiteAccess {
enabled: bool,
index_document: Option<String>,
error_document: Option<String>,
}
// ---- BUCKET/KEY PERMISSIONS ----
+2 -6
View File
@@ -48,10 +48,7 @@ pub enum Endpoint {
DeleteBucket {
id: String,
},
PutBucketWebsite {
id: String,
},
DeleteBucketWebsite {
UpdateBucket {
id: String,
},
// Bucket-Key Permissions
@@ -113,8 +110,7 @@ impl Endpoint {
GET "/v0/bucket" => ListBuckets,
POST "/v0/bucket" => CreateBucket,
DELETE "/v0/bucket" if id => DeleteBucket (query::id),
PUT "/v0/bucket/website" if id => PutBucketWebsite (query::id),
DELETE "/v0/bucket/website" if id => DeleteBucketWebsite (query::id),
PUT "/v0/bucket" if id => UpdateBucket (query::id),
// Bucket-key permissions
POST "/v0/bucket/allow" => BucketAllowKey,
POST "/v0/bucket/deny" => BucketDenyKey,
+1 -1
View File
@@ -10,7 +10,7 @@ use garage_rpc::ring::Ring;
use garage_table::util::*;
use garage_model::garage::Garage;
use garage_model::k2v::counter_table::{BYTES, CONFLICTS, ENTRIES, VALUES};
use garage_model::k2v::item_table::{BYTES, CONFLICTS, ENTRIES, VALUES};
use crate::k2v::error::*;
use crate::k2v::range::read_range;
+2 -2
View File
@@ -212,7 +212,7 @@ impl ApiHandler for S3ApiServer {
.await
}
Endpoint::PutObject { key } => {
handle_put(garage, req, bucket_id, &key, content_sha256).await
handle_put(garage, req, &bucket, &key, content_sha256).await
}
Endpoint::AbortMultipartUpload { key, upload_id } => {
handle_abort_multipart_upload(garage, bucket_id, &key, &upload_id).await
@@ -226,7 +226,7 @@ impl ApiHandler for S3ApiServer {
garage,
req,
&bucket_name,
bucket_id,
&bucket,
&key,
&upload_id,
content_sha256,
+10 -5
View File
@@ -22,7 +22,7 @@ use crate::signature::payload::{parse_date, verify_v4};
pub async fn handle_post_object(
garage: Arc<Garage>,
req: Request<Body>,
bucket: String,
bucket_name: String,
) -> Result<Response<Body>, Error> {
let boundary = req
.headers()
@@ -126,13 +126,18 @@ pub async fn handle_post_object(
let bucket_id = garage
.bucket_helper()
.resolve_bucket(&bucket, &api_key)
.resolve_bucket(&bucket_name, &api_key)
.await?;
if !api_key.allow_write(&bucket_id) {
return Err(Error::forbidden("Operation is not allowed for this key."));
}
let bucket = garage
.bucket_helper()
.get_existing_bucket(bucket_id)
.await?;
let decoded_policy = base64::decode(&policy).ok_or_bad_request("Invalid policy")?;
let decoded_policy: Policy =
serde_json::from_slice(&decoded_policy).ok_or_bad_request("Invalid policy")?;
@@ -227,7 +232,7 @@ pub async fn handle_post_object(
garage,
headers,
StreamLimiter::new(stream, conditions.content_length),
bucket_id,
&bucket,
&key,
None,
None,
@@ -244,7 +249,7 @@ pub async fn handle_post_object(
{
target
.query_pairs_mut()
.append_pair("bucket", &bucket)
.append_pair("bucket", &bucket_name)
.append_pair("key", &key)
.append_pair("etag", &etag);
let target = target.to_string();
@@ -289,7 +294,7 @@ pub async fn handle_post_object(
let xml = s3_xml::PostObject {
xmlns: (),
location: s3_xml::Value(location),
bucket: s3_xml::Value(bucket),
bucket: s3_xml::Value(bucket_name),
key: s3_xml::Value(key),
etag: s3_xml::Value(etag),
};
+103 -26
View File
@@ -1,4 +1,4 @@
use std::collections::{BTreeMap, BTreeSet, VecDeque};
use std::collections::{BTreeMap, BTreeSet, HashMap, VecDeque};
use std::sync::Arc;
use futures::prelude::*;
@@ -14,7 +14,9 @@ use garage_util::error::Error as GarageError;
use garage_util::time::*;
use garage_block::manager::INLINE_THRESHOLD;
use garage_model::bucket_table::Bucket;
use garage_model::garage::Garage;
use garage_model::index_counter::CountedItem;
use garage_model::s3::block_ref_table::*;
use garage_model::s3::object_table::*;
use garage_model::s3::version_table::*;
@@ -26,7 +28,7 @@ use crate::signature::verify_signed_content;
pub async fn handle_put(
garage: Arc<Garage>,
req: Request<Body>,
bucket_id: Uuid,
bucket: &Bucket,
key: &str,
content_sha256: Option<Hash>,
) -> Result<Response<Body>, Error> {
@@ -46,7 +48,7 @@ pub async fn handle_put(
garage,
headers,
body,
bucket_id,
bucket,
key,
content_md5,
content_sha256,
@@ -59,7 +61,7 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
garage: Arc<Garage>,
headers: ObjectVersionHeaders,
body: S,
bucket_id: Uuid,
bucket: &Bucket,
key: &str,
content_md5: Option<String>,
content_sha256: Option<FixedBytes32>,
@@ -80,6 +82,7 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
let data_md5sum_hex = hex::encode(data_md5sum);
let data_sha256sum = sha256sum(&first_block[..]);
let size = first_block.len() as u64;
ensure_checksum_matches(
data_md5sum.as_slice(),
@@ -88,20 +91,22 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
content_sha256,
)?;
check_quotas(&garage, bucket, key, size).await?;
let object_version = ObjectVersion {
uuid: version_uuid,
timestamp: version_timestamp,
state: ObjectVersionState::Complete(ObjectVersionData::Inline(
ObjectVersionMeta {
headers,
size: first_block.len() as u64,
size,
etag: data_md5sum_hex.clone(),
},
first_block,
)),
};
let object = Object::new(bucket_id, key.into(), vec![object_version]);
let object = Object::new(bucket.id, key.into(), vec![object_version]);
garage.object_table.insert(&object).await?;
return Ok((version_uuid, data_md5sum_hex));
@@ -114,36 +119,42 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
timestamp: version_timestamp,
state: ObjectVersionState::Uploading(headers.clone()),
};
let object = Object::new(bucket_id, key.into(), vec![object_version.clone()]);
let object = Object::new(bucket.id, key.into(), vec![object_version.clone()]);
garage.object_table.insert(&object).await?;
// Initialize corresponding entry in version table
// Write this entry now, even with empty block list,
// to prevent block_ref entries from being deleted (they can be deleted
// if the reference a version that isn't found in the version table)
let version = Version::new(version_uuid, bucket_id, key.into(), false);
let version = Version::new(version_uuid, bucket.id, key.into(), false);
garage.version_table.insert(&version).await?;
// Transfer data and verify checksum
let first_block_hash = blake2sum(&first_block[..]);
let tx_result = read_and_put_blocks(
&garage,
&version,
1,
first_block,
first_block_hash,
&mut chunker,
)
.await
.and_then(|(total_size, data_md5sum, data_sha256sum)| {
let tx_result = (|| async {
let (total_size, data_md5sum, data_sha256sum) = read_and_put_blocks(
&garage,
&version,
1,
first_block,
first_block_hash,
&mut chunker,
)
.await?;
ensure_checksum_matches(
data_md5sum.as_slice(),
data_sha256sum,
content_md5.as_deref(),
content_sha256,
)
.map(|()| (total_size, data_md5sum))
});
)?;
check_quotas(&garage, bucket, key, total_size).await?;
Ok((total_size, data_md5sum))
})()
.await;
// If something went wrong, clean up
let (total_size, md5sum_arr) = match tx_result {
@@ -151,7 +162,7 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
Err(e) => {
// Mark object as aborted, this will free the blocks further down
object_version.state = ObjectVersionState::Aborted;
let object = Object::new(bucket_id, key.into(), vec![object_version.clone()]);
let object = Object::new(bucket.id, key.into(), vec![object_version.clone()]);
garage.object_table.insert(&object).await?;
return Err(e);
}
@@ -167,7 +178,7 @@ pub(crate) async fn save_stream<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
},
first_block_hash,
));
let object = Object::new(bucket_id, key.into(), vec![object_version]);
let object = Object::new(bucket.id, key.into(), vec![object_version]);
garage.object_table.insert(&object).await?;
Ok((version_uuid, md5sum_hex))
@@ -200,6 +211,64 @@ fn ensure_checksum_matches(
Ok(())
}
/// Check that inserting this object with this size doesn't exceed bucket quotas
async fn check_quotas(
garage: &Arc<Garage>,
bucket: &Bucket,
key: &str,
size: u64,
) -> Result<(), Error> {
let quotas = bucket.state.as_option().unwrap().quotas.get();
if quotas.max_objects.is_none() && quotas.max_size.is_none() {
return Ok(());
};
let key = key.to_string();
let (prev_object, counters) = futures::try_join!(
garage.object_table.get(&bucket.id, &key),
garage.object_counter_table.table.get(&bucket.id, &EmptyKey),
)?;
let counters = counters
.map(|x| x.filtered_values(&garage.system.ring.borrow()))
.unwrap_or_default();
let (prev_cnt_obj, prev_cnt_size) = match prev_object {
Some(o) => {
let prev_cnt = o.counts().into_iter().collect::<HashMap<_, _>>();
(
prev_cnt.get(OBJECTS).cloned().unwrap_or_default(),
prev_cnt.get(BYTES).cloned().unwrap_or_default(),
)
}
None => (0, 0),
};
let cnt_obj_diff = 1 - prev_cnt_obj;
let cnt_size_diff = size as i64 - prev_cnt_size;
if let Some(mo) = quotas.max_objects {
let current_objects = counters.get(OBJECTS).cloned().unwrap_or_default();
if cnt_obj_diff > 0 && current_objects + cnt_obj_diff > mo as i64 {
return Err(Error::forbidden(format!(
"Object quota is reached, maximum objects for this bucket: {}",
mo
)));
}
}
if let Some(ms) = quotas.max_size {
let current_size = counters.get(BYTES).cloned().unwrap_or_default();
if cnt_size_diff > 0 && current_size + cnt_size_diff > ms as i64 {
return Err(Error::forbidden(format!(
"Bucket size quota is reached, maximum total size of objects for this bucket: {}. The bucket is already {} bytes, and this object would add {} bytes.",
ms, current_size, size
)));
}
}
Ok(())
}
async fn read_and_put_blocks<S: Stream<Item = Result<Bytes, Error>> + Unpin>(
garage: &Garage,
version: &Version,
@@ -473,7 +542,7 @@ pub async fn handle_complete_multipart_upload(
garage: Arc<Garage>,
req: Request<Body>,
bucket_name: &str,
bucket_id: Uuid,
bucket: &Bucket,
key: &str,
upload_id: &str,
content_sha256: Option<Hash>,
@@ -497,7 +566,7 @@ pub async fn handle_complete_multipart_upload(
// Get object and version
let key = key.to_string();
let (object, version) = futures::try_join!(
garage.object_table.get(&bucket_id, &key),
garage.object_table.get(&bucket.id, &key),
garage.version_table.get(&version_uuid, &EmptyKey),
)?;
@@ -590,6 +659,14 @@ pub async fn handle_complete_multipart_upload(
// Calculate total size of final object
let total_size = version.blocks.items().iter().map(|x| x.1.size).sum();
if let Err(e) = check_quotas(&garage, bucket, &key, total_size).await {
object_version.state = ObjectVersionState::Aborted;
let final_object = Object::new(bucket.id, key.clone(), vec![object_version]);
garage.object_table.insert(&final_object).await?;
return Err(e);
}
// Write final object version
object_version.state = ObjectVersionState::Complete(ObjectVersionData::FirstBlock(
ObjectVersionMeta {
@@ -600,7 +677,7 @@ pub async fn handle_complete_multipart_upload(
version.blocks.items()[0].1.hash,
));
let final_object = Object::new(bucket_id, key.clone(), vec![object_version]);
let final_object = Object::new(bucket.id, key.clone(), vec![object_version]);
garage.object_table.insert(&final_object).await?;
// Send response saying ok we're done