Compare commits

..

3 Commits

Author SHA1 Message Date
houseme b3c79cd71a Merge branch 'main' into overtrue/wait-bucket-metadata-reload 2026-08-23 12:30:36 +08:00
唐小鸭 5f72209446 fix(ecstore): keep unknown-size sentinel in create_bitrot_writer (#6380)
SSE and compression wrap the payload so its length is unknown and
advertise HashReader::SIZE_PRESERVE_LAYER (-1). Every layer preserved
that sentinel except create_bitrot_writer, which clamped it to 0 before
calling DiskAPI::create_file. RemoteDisk forwards that size verbatim in
the put_file_stream query, so remote peers were told the body was empty.

Since the authenticated put-file trailer (#5868) the receiver used the
declared size to split body from trailer, turning the clamp into a fatal
"auth trailer has trailing data" failure for every SSE PUT on multi-node
deployments (rc.2). #6320 relaxed the receiver to only trust size > 0;
this change fixes the sender so the sentinel survives end to end and the
wire no longer conflates empty objects with unknown-length streams.

Refs #6331
2026-08-23 12:29:52 +08:00
overtrue c57f22c3a0 fix(app): wait for peer bucket metadata reload 2026-08-22 15:49:37 +08:00
13 changed files with 255 additions and 802 deletions
@@ -15,12 +15,14 @@
use crate::common::RustFSTestClusterEnvironment;
use aws_sdk_s3::Client;
use aws_sdk_s3::error::SdkError;
use aws_sdk_s3::types::{CorsConfiguration, CorsRule};
use bytes::Bytes;
use std::sync::Arc;
use tokio::sync::Barrier;
use tracing::{info, warn};
const BUCKET: &str = "conditional-put-race-bucket";
const BUCKET_METADATA_RELOAD_BUCKET: &str = "bucket-metadata-reload-barrier";
async fn cleanup_object(client: &Client, key: &str) {
if let Err(e) = client.delete_object().bucket(BUCKET).key(key).send().await {
@@ -28,6 +30,16 @@ async fn cleanup_object(client: &Client, key: &str) {
}
}
async fn assert_bucket_cors_missing(client: &Client) {
let result = client.get_bucket_cors().bucket(BUCKET_METADATA_RELOAD_BUCKET).send().await;
match result {
Err(SdkError::ServiceError(error)) => {
assert_eq!(error.err().meta().code(), Some("NoSuchCORSConfiguration"));
}
result => panic!("expected the peer to report a missing CORS configuration: {result:?}"),
}
}
async fn conditional_put(
client: &Client,
key: &str,
@@ -236,3 +248,48 @@ async fn test_conditional_put_basic_cluster() -> Result<(), Box<dyn std::error::
cleanup_object(&client, test_key).await;
Ok(())
}
#[tokio::test]
async fn test_bucket_cors_write_is_visible_on_peer_before_response() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
crate::common::init_logging();
let mut cluster = RustFSTestClusterEnvironment::new(2).await?;
cluster.start().await?;
cluster.create_test_bucket(BUCKET_METADATA_RELOAD_BUCKET).await?;
let writer = cluster.create_s3_client(0)?;
let reader = cluster.create_s3_client(1)?;
assert_bucket_cors_missing(&reader).await;
let rule = CorsRule::builder()
.allowed_methods("GET")
.allowed_origins("https://example.com")
.build()?;
let configuration = CorsConfiguration::builder().cors_rules(rule).build()?;
writer
.put_bucket_cors()
.bucket(BUCKET_METADATA_RELOAD_BUCKET)
.cors_configuration(configuration)
.send()
.await?;
let response = reader.get_bucket_cors().bucket(BUCKET_METADATA_RELOAD_BUCKET).send().await?;
let rules = response.cors_rules();
assert_eq!(
rules.len(),
1,
"peer should observe the committed CORS rule before the write response returns"
);
assert_eq!(rules[0].allowed_methods(), ["GET"]);
assert_eq!(rules[0].allowed_origins(), ["https://example.com"]);
writer
.delete_bucket_cors()
.bucket(BUCKET_METADATA_RELOAD_BUCKET)
.send()
.await?;
assert_bucket_cors_missing(&reader).await;
writer.delete_bucket().bucket(BUCKET_METADATA_RELOAD_BUCKET).send().await?;
Ok(())
}
+9 -10
View File
@@ -196,16 +196,15 @@ pub mod bucket {
ReplicationOperation, ReplicationPoolTrait, ReplicationPriority, ReplicationQueueAdmission, ReplicationScannerBridge,
ReplicationState, ReplicationStats, ReplicationStatusType, ReplicationStorage, ReplicationTargetValidationError,
ReplicationType, ResyncOpts, ResyncStatusType, RuntimeReplicationTargetBacklog, TargetReplicationResyncStatus,
VersionPurgeStatusType, XferStats, assign_site_replication_rule_priorities, commit_force_delete_intent,
complete_force_delete_intent, delete_replication_state_from_config, delete_replication_version_id,
get_global_replication_pool, get_global_replication_stats, get_proxy_targets, init_background_replication,
invalid_replication_config_status_field, is_site_replication_rule, merge_incoming_replication_config,
merge_user_replication_config, persist_force_delete_intent, read_durable_mrf_backlog, replication_state_to_filemeta,
replication_status_to_filemeta, replication_statuses_map, replication_target_arn_deployment_id,
replication_target_arns, resync_start_conflict_id, should_remove_replication_target,
should_schedule_delete_replication, should_use_existing_delete_replication_info,
should_use_existing_delete_replication_source, unsupported_replication_config_field,
validate_replication_config_structure, validate_replication_config_target_arns, version_purge_status_to_filemeta,
VersionPurgeStatusType, XferStats, commit_force_delete_intent, complete_force_delete_intent,
delete_replication_state_from_config, delete_replication_version_id, get_global_replication_pool,
get_global_replication_stats, get_proxy_targets, init_background_replication,
invalid_replication_config_status_field, persist_force_delete_intent, read_durable_mrf_backlog,
replication_state_to_filemeta, replication_status_to_filemeta, replication_statuses_map, replication_target_arns,
resync_start_conflict_id, should_remove_replication_target, should_schedule_delete_replication,
should_use_existing_delete_replication_info, should_use_existing_delete_replication_source,
unsupported_replication_config_field, validate_replication_config_structure, validate_replication_config_target_arns,
version_purge_status_to_filemeta,
};
}
+2 -4
View File
@@ -47,10 +47,8 @@ pub use replication_config_boundary::{
ObjectOpts, REMOTE_TARGET_CAPABILITY_CONTRACT_VERSION, REMOTE_TARGET_UNSUPPORTED_FIELDS, REMOTE_TARGET_WRITABLE_FIELDS,
REPLICATION_CAPABILITY_CONTRACT_VERSION, REPLICATION_READ_ONLY_HISTORICAL_FIELDS, REPLICATION_WRITABLE_FIELDS,
ReplicationConfigStructureError, ReplicationConfigurationExt, ReplicationTargetValidationError,
assign_site_replication_rule_priorities, invalid_replication_config_status_field, is_site_replication_rule,
merge_incoming_replication_config, merge_user_replication_config, replication_target_arn_deployment_id,
replication_target_arns, should_remove_replication_target, unsupported_replication_config_field,
validate_replication_config_structure, validate_replication_config_target_arns,
invalid_replication_config_status_field, replication_target_arns, should_remove_replication_target,
unsupported_replication_config_field, validate_replication_config_structure, validate_replication_config_target_arns,
};
pub(crate) use replication_filemeta_boundary::version_purge_statuses_map;
pub use replication_filemeta_boundary::{
@@ -16,8 +16,6 @@ pub use rustfs_replication::{
ObjectOpts, REMOTE_TARGET_CAPABILITY_CONTRACT_VERSION, REMOTE_TARGET_UNSUPPORTED_FIELDS, REMOTE_TARGET_WRITABLE_FIELDS,
REPLICATION_CAPABILITY_CONTRACT_VERSION, REPLICATION_READ_ONLY_HISTORICAL_FIELDS, REPLICATION_WRITABLE_FIELDS,
ReplicationConfigStructureError, ReplicationConfigurationExt, ReplicationRuleExt, ReplicationTargetValidationError,
assign_site_replication_rule_priorities, invalid_replication_config_status_field, is_site_replication_rule,
merge_incoming_replication_config, merge_user_replication_config, replication_target_arn_deployment_id,
replication_target_arns, should_remove_replication_target, unsupported_replication_config_field,
validate_replication_config_structure, validate_replication_config_target_arns,
invalid_replication_config_status_field, replication_target_arns, should_remove_replication_target,
unsupported_replication_config_field, validate_replication_config_structure, validate_replication_config_target_arns,
};
@@ -85,6 +85,7 @@ const PEER_REST_RECOVERY_MAX_ATTEMPTS: u32 = 60;
const PEER_REST_RECOVERY_MAX_BACKOFF: Duration = Duration::from_secs(30);
const SCANNER_ACTIVITY_MAX_MESSAGE_SIZE: usize = 1024;
const REPLICATION_STATS_MAX_MESSAGE_SIZE: usize = 8 * 1024 * 1024;
const BUCKET_METADATA_RELOAD_TIMEOUT: Duration = Duration::from_secs(5);
/// Error for a peer that reported `success = false` without an `error_info` payload.
///
@@ -1328,27 +1329,38 @@ impl PeerRestClient {
}
pub async fn load_bucket_metadata(&self, bucket: &str, scanner_maintenance_change: bool) -> Result<()> {
self.finalize_result(
async {
let mut client = self.get_client().await?;
let mut request = Request::new(LoadBucketMetadataRequest {
bucket: bucket.to_string(),
scanner_maintenance_change,
});
set_tonic_mutation_body_digest(&mut request)?;
let response = client.load_bucket_metadata(request).await?.into_inner();
if !response.success {
if let Some(msg) = response.error_info {
return Err(Error::other(msg));
}
return Err(peer_failure_without_details("load_bucket_metadata", Some(bucket)));
}
Ok(())
let result = tokio::time::timeout(BUCKET_METADATA_RELOAD_TIMEOUT, async {
let result = self.load_bucket_metadata_once(bucket, scanner_maintenance_change).await;
if let Err(err) = &result
&& Self::is_network_like_error(err)
{
self.prepare_retry().await;
return self.load_bucket_metadata_once(bucket, scanner_maintenance_change).await;
}
.await,
)
result
})
.await
.unwrap_or_else(|_| Err(Error::other(format!("load_bucket_metadata({bucket}) timed out"))));
self.finalize_result(result).await
}
async fn load_bucket_metadata_once(&self, bucket: &str, scanner_maintenance_change: bool) -> Result<()> {
let mut client = self.get_client().await?;
let mut request = Request::new(LoadBucketMetadataRequest {
bucket: bucket.to_string(),
scanner_maintenance_change,
});
set_tonic_mutation_body_digest(&mut request)?;
request.set_timeout(BUCKET_METADATA_RELOAD_TIMEOUT);
let response = client.load_bucket_metadata(request).await?.into_inner();
if !response.success {
if let Some(msg) = response.error_info {
return Err(Error::other(msg));
}
return Err(peer_failure_without_details("load_bucket_metadata", Some(bucket)));
}
Ok(())
}
pub async fn delete_bucket_metadata(&self, bucket: &str) -> Result<()> {
+38 -6
View File
@@ -784,6 +784,24 @@ pub(crate) fn create_deferred_bitrot_reader_with_stripe_handle(
///
/// # Returns
/// A Result containing the BitrotWriterWrapper or an error
/// Size hint handed to `DiskAPI::create_file` for a bitrot-wrapped shard.
///
/// A known length is grown by one checksum per shard so the on-disk file size
/// matches what the bitrot writer emits. A negative length is the
/// unknown-size sentinel (`HashReader::SIZE_PRESERVE_LAYER`, used by SSE and
/// compression) and must be preserved: `RemoteDisk::create_file` forwards it
/// in the `put_file_stream` query, and the receiver only treats `size > 0` as
/// a fixed body length when locating the authenticated trailer. Clamping it
/// to `0` would claim an empty body and misframe the stream. `0` stays `0`
/// because a genuinely empty object still means an empty body.
fn bitrot_create_file_size(length: i64, shard_size: usize, checksum_algo: &HashAlgorithm) -> i64 {
if length <= 0 {
return length;
}
let length = length as usize;
(length.div_ceil(shard_size) * checksum_algo.size() + length) as i64
}
pub async fn create_bitrot_writer(
is_inline_buffer: bool,
disk: Option<&DiskStore>,
@@ -796,12 +814,7 @@ pub async fn create_bitrot_writer(
let writer = if is_inline_buffer {
CustomWriter::new_inline_buffer()
} else if let Some(disk) = disk {
let length = if length > 0 {
let length = length as usize;
(length.div_ceil(shard_size) * checksum_algo.size() + length) as i64
} else {
0
};
let length = bitrot_create_file_size(length, shard_size, &checksum_algo);
let file = disk.create_file("", volume, path, length).await?;
#[cfg(feature = "hotpath")]
@@ -820,6 +833,25 @@ mod tests {
use rustfs_rio::ChunkReader;
use std::collections::VecDeque;
#[test]
fn bitrot_create_file_size_grows_known_length_by_checksums() {
// 10 bytes over 4-byte shards = 3 shards, each followed by a 32-byte hash.
assert_eq!(bitrot_create_file_size(10, 4, &HashAlgorithm::HighwayHash256), 10 + 3 * 32);
assert_eq!(bitrot_create_file_size(10, 4, &HashAlgorithm::None), 10);
}
#[test]
fn bitrot_create_file_size_keeps_empty_and_unknown_distinct() {
assert_eq!(bitrot_create_file_size(0, 4, &HashAlgorithm::HighwayHash256), 0);
// SSE/compression streams advertise SIZE_PRESERVE_LAYER (-1); the remote
// put_file_stream receiver relies on a non-positive size to parse the auth
// trailer from the stream tail, so the sentinel must survive untouched.
assert_eq!(
bitrot_create_file_size(rustfs_rio::HashReader::SIZE_PRESERVE_LAYER, 4, &HashAlgorithm::HighwayHash256),
rustfs_rio::HashReader::SIZE_PRESERVE_LAYER
);
}
struct TestChunkReader {
chunks: VecDeque<Bytes>,
}
-253
View File
@@ -270,160 +270,6 @@ pub fn active_replication_rule_destination_arns(config: &ReplicationConfiguratio
arns
}
/// Deployment id extracted from a site-replication target ARN
/// (`arn:{rustfs|minio}:replication::<deployment-id>:<bucket>`), or `None`
/// for an operator-authored ARN.
pub fn replication_target_arn_deployment_id(arn: &str) -> Option<String> {
let parts: Vec<_> = arn.split(':').collect();
if parts.len() == 6
&& parts[0] == "arn"
&& matches!(parts[1], "rustfs" | "minio")
&& parts[2] == "replication"
&& !parts[4].is_empty()
{
return Some(parts[4].to_string());
}
None
}
/// Rule id prefix the site-replication reconciler stamps on the rules it
/// derives (`site-repl-<peer deployment id>`).
pub const SITE_REPLICATION_RULE_ID_PREFIX: &str = "site-repl-";
/// Whether `rule` carries a site-replication rule id (`site-repl-*`). The
/// reconciler and the peer ingestion path treat the whole namespace as theirs
/// on a site-replication bucket; the S3 edit path must not — rule ids are not
/// reserved, so see [`site_replication_rule_deployment_id`].
pub fn is_site_replication_rule(rule: &ReplicationRule) -> bool {
rule.id
.as_deref()
.is_some_and(|id| id.starts_with(SITE_REPLICATION_RULE_ID_PREFIX))
}
/// Deployment id of the peer a reconciler-derived rule replicates to, or
/// `None` for any other rule. The reconciler builds each rule from one peer:
/// the id is `site-repl-<deployment id>` and the destination ARN names that
/// same deployment id — an operator-authored `site-repl-user` rule, or a
/// `site-repl-<peer>` id pasted onto a foreign ARN, fails the agreement check.
/// Callers that know the current peer set must also confirm the id is one of
/// those peers before treating the rule as reconciler-owned.
pub fn site_replication_rule_deployment_id(rule: &ReplicationRule) -> Option<&str> {
let deployment_id = rule.id.as_deref()?.strip_prefix(SITE_REPLICATION_RULE_ID_PREFIX)?;
(!deployment_id.is_empty()
&& replication_target_arn_deployment_id(&rule.destination.bucket).as_deref() == Some(deployment_id))
.then_some(deployment_id)
}
/// Whether `rule` is one the local reconciler derived for a current remote
/// site-replication peer in `peer_deployment_ids`. With an empty peer set
/// (site replication disabled) nothing qualifies, so a bucket outside site
/// replication keeps the verbatim S3 put/delete semantics.
pub fn is_reconciler_owned_site_replication_rule(rule: &ReplicationRule, peer_deployment_ids: &HashSet<String>) -> bool {
site_replication_rule_deployment_id(rule).is_some_and(|deployment_id| peer_deployment_ids.contains(deployment_id))
}
/// Merge an incoming replication config into the local one.
///
/// `site-repl-*` rules encode the *holder's* outbound direction — their
/// destination ARN names another site — so applying an external rule set
/// verbatim replaces the local reverse rule with one this site can never
/// satisfy (no bucket target backs it) and replication silently stops. Only
/// operator-authored rules travel: the site-replication peer ingestion path
/// and the S3 put/delete-bucket-replication path both keep the local site's
/// `site-repl-*` rules through this merge. `incoming == None` models a
/// delete of the operator-authored rules.
pub fn merge_incoming_replication_config(
incoming: Option<ReplicationConfiguration>,
local: Option<ReplicationConfiguration>,
) -> Option<ReplicationConfiguration> {
merge_replication_config_keeping_site_rules(incoming, local, is_site_replication_rule)
}
/// [`merge_incoming_replication_config`] for the S3 put/delete-bucket-replication
/// path (issue #1948): only rules the local reconciler derived for a current
/// peer in `peer_deployment_ids` survive as site rules; every other stored
/// rule — including an operator-authored `site-repl-*` id — is operator state
/// that the request replaces or deletes. An incoming rule whose id is a
/// current peer's `site-repl-<id>` is dropped whatever its ARN: accepting it
/// would duplicate the reconciler rule's id.
pub fn merge_user_replication_config(
incoming: Option<ReplicationConfiguration>,
local: Option<ReplicationConfiguration>,
peer_deployment_ids: &HashSet<String>,
) -> Option<ReplicationConfiguration> {
let incoming = incoming.map(|mut config| {
config.rules.retain(|rule| {
!rule
.id
.as_deref()
.and_then(|id| id.strip_prefix(SITE_REPLICATION_RULE_ID_PREFIX))
.is_some_and(|deployment_id| peer_deployment_ids.contains(deployment_id))
});
config
});
merge_replication_config_keeping_site_rules(incoming, local, |rule| {
is_reconciler_owned_site_replication_rule(rule, peer_deployment_ids)
})
}
fn merge_replication_config_keeping_site_rules(
incoming: Option<ReplicationConfiguration>,
local: Option<ReplicationConfiguration>,
is_site_rule: impl Fn(&ReplicationRule) -> bool,
) -> Option<ReplicationConfiguration> {
let incoming_role = incoming.as_ref().map(|config| config.role.clone()).unwrap_or_default();
// Operator rules first, then the local site rules — the same order the
// site-replication reconciler produces, so its no-op check matches and
// the bucket metadata is written once per broadcast, not twice.
let mut rules: Vec<ReplicationRule> = incoming
.into_iter()
.flat_map(|config| config.rules)
.filter(|rule| !is_site_rule(rule))
.collect();
rules.extend(local.into_iter().flat_map(|config| config.rules).filter(&is_site_rule));
if rules.is_empty() {
return None;
}
assign_site_replication_rule_priorities(&mut rules, &is_site_rule);
// A site-replication ARN in `role` is the sender's, and the reconciler's
// per-peer target lookup reads it — carrying it over would pin the
// receiver's targets to the sender's identity.
let role = match replication_target_arn_deployment_id(&incoming_role) {
Some(_) => String::new(),
None => incoming_role,
};
Some(ReplicationConfiguration { role, rules })
}
/// Give the site rules in `rules` the lowest priorities no operator rule uses,
/// in rule order, leaving every operator rule's priority untouched. Operator
/// priorities decide which rule wins per target, so they are part of the
/// submitted policy; site rules are derived state and only need to be unique
/// (`validate_replication_config_structure` rejects duplicates). The result
/// is a pure function of the rule list, so the site-replication reconciler,
/// the peer ingestion merge and the S3 edit merge all converge on the same
/// bytes and the reconciler's no-op check holds.
pub fn assign_site_replication_rule_priorities(rules: &mut [ReplicationRule], is_site_rule: impl Fn(&ReplicationRule) -> bool) {
let taken: HashSet<i32> = rules
.iter()
.filter(|rule| !is_site_rule(rule))
.map(|rule| rule.priority.unwrap_or(0))
.collect();
let mut next = 1;
for rule in rules.iter_mut().filter(|rule| is_site_rule(rule)) {
while taken.contains(&next) {
next += 1;
}
rule.priority = Some(next);
next = next.saturating_add(1);
}
}
pub fn replication_target_arns(config: &ReplicationConfiguration) -> HashSet<String> {
let role = config.role.trim();
if !role.is_empty() {
@@ -1698,103 +1544,4 @@ mod tests {
"the child rule must win for target A while the overlapping child target B remains eligible"
);
}
#[test]
fn site_replication_rule_deployment_id_requires_id_and_arn_agreement() {
let reconciler_rule = replication_rule("site-repl-peer-dep", "arn:rustfs:replication::peer-dep:bucket");
assert_eq!(site_replication_rule_deployment_id(&reconciler_rule), Some("peer-dep"));
// A remote-target ARN carries the remote's deployment id (or a random
// uuid), never the operator's rule id.
let operator_named_rule = replication_rule("site-repl-user", "arn:minio:replication:us-east-1:2f1c-remote:bucket");
assert_eq!(site_replication_rule_deployment_id(&operator_named_rule), None);
let foreign_arn = replication_rule("site-repl-peer-dep", "arn:rustfs:replication::other-dep:bucket");
assert_eq!(site_replication_rule_deployment_id(&foreign_arn), None);
let empty_id = replication_rule("site-repl-", "arn:rustfs:replication::peer-dep:bucket");
assert_eq!(site_replication_rule_deployment_id(&empty_id), None);
let peers = HashSet::from(["peer-dep".to_string()]);
assert!(is_reconciler_owned_site_replication_rule(&reconciler_rule, &peers));
assert!(!is_reconciler_owned_site_replication_rule(&reconciler_rule, &HashSet::new()));
let removed_peer = replication_rule("site-repl-gone-dep", "arn:rustfs:replication::gone-dep:bucket");
assert!(!is_reconciler_owned_site_replication_rule(&removed_peer, &peers));
}
// The merge must not rewrite the operator's priorities: with the
// priority-5 rule listed first and renumbered 1 then 2, the priority-1
// delete-marker-disabled rule would win the replication decision.
#[test]
fn merge_keeps_operator_priorities_and_replication_decision() {
let user_arn = "arn:minio:replication:us-east-1:2f1c-remote:bucket";
let peer_arn = "arn:rustfs:replication::peer-dep:bucket";
let incoming = ReplicationConfiguration {
role: String::new(),
rules: vec![
delete_marker_rule("dm-enabled", user_arn, "logs/", 5, true),
delete_marker_rule("dm-disabled", user_arn, "logs/2026/", 1, false),
],
};
let mut site_rule = delete_marker_rule("site-repl-peer-dep", peer_arn, "", 7, true);
site_rule.prefix = None;
let local = structure_config(vec![site_rule]);
let opts = ObjectOpts {
name: "logs/2026/app.log".to_string(),
op_type: ReplicationType::Delete,
delete_marker: true,
version_id: None,
..Default::default()
};
let submitted: Vec<_> = incoming.filter_target_replication_decisions(&opts);
let peers = HashSet::from(["peer-dep".to_string()]);
let merged = merge_user_replication_config(Some(incoming.clone()), Some(local.clone()), &peers).expect("rules");
let priorities: Vec<_> = merged
.rules
.iter()
.map(|rule| (rule.id.as_deref().unwrap(), rule.priority))
.collect();
assert_eq!(
priorities,
vec![
("dm-enabled", Some(5)),
("dm-disabled", Some(1)),
("site-repl-peer-dep", Some(2))
],
"operator priorities are kept verbatim; the site rule takes the lowest free slot"
);
assert!(validate_replication_config_structure(&merged).is_ok());
let mut decisions = merged.filter_target_replication_decisions(&opts);
decisions.retain(|(arn, _)| arn == user_arn);
assert_eq!(decisions, submitted, "the merged config must replicate exactly as the operator submitted");
assert_eq!(decisions, vec![(user_arn.to_string(), true)]);
// The peer ingestion merge follows the same rule.
let merged = merge_incoming_replication_config(Some(incoming), Some(local)).expect("rules");
let priorities: Vec<_> = merged.rules.iter().map(|rule| rule.priority).collect();
assert_eq!(priorities, vec![Some(5), Some(1), Some(2)]);
}
#[test]
fn site_rule_priorities_skip_every_operator_priority() {
let mut rules = vec![
delete_marker_rule("a", "arn:a", "", 2, true),
delete_marker_rule("site-repl-x", "arn:rustfs:replication::x:b", "", 9, true),
delete_marker_rule("b", "arn:a", "", 1, true),
delete_marker_rule("site-repl-y", "arn:rustfs:replication::y:b", "", 9, true),
delete_marker_rule("c", "arn:a", "", 4, true),
];
assign_site_replication_rule_priorities(&mut rules, is_site_replication_rule);
let priorities: Vec<_> = rules.iter().map(|rule| rule.priority).collect();
assert_eq!(priorities, vec![Some(2), Some(3), Some(1), Some(5), Some(4)]);
assert!(validate_replication_config_structure(&structure_config(rules.clone())).is_ok());
// Idempotent, so the reconciler's pass over an already-merged config
// is a byte-stable no-op rather than a rewrite every period.
let settled = rules.clone();
assign_site_replication_rule_priorities(&mut rules, is_site_replication_rule);
assert_eq!(rules, settled);
}
}
+3 -5
View File
@@ -32,11 +32,9 @@ pub use config::{
ObjectOpts, REMOTE_TARGET_CAPABILITY_CONTRACT_VERSION, REMOTE_TARGET_UNSUPPORTED_FIELDS, REMOTE_TARGET_WRITABLE_FIELDS,
REPLICATION_CAPABILITY_CONTRACT_VERSION, REPLICATION_READ_ONLY_HISTORICAL_FIELDS, REPLICATION_WRITABLE_FIELDS,
ReplicationConfigStructureError, ReplicationConfigurationExt, ReplicationTargetValidationError,
active_replication_rule_destination_arns, assign_site_replication_rule_priorities, invalid_replication_config_status_field,
is_reconciler_owned_site_replication_rule, is_site_replication_rule, merge_incoming_replication_config,
merge_user_replication_config, replication_target_arn_deployment_id, replication_target_arns,
should_remove_replication_target, site_replication_rule_deployment_id, unsupported_replication_config_field,
validate_replication_config_structure, validate_replication_config_target_arns,
active_replication_rule_destination_arns, invalid_replication_config_status_field, replication_target_arns,
should_remove_replication_target, unsupported_replication_config_field, validate_replication_config_structure,
validate_replication_config_target_arns,
};
pub use delete::{
DeletedObjectReplicationInfo, delete_marker_purge_mrf_entry, delete_marker_purge_version_id,
+73 -42
View File
@@ -31,10 +31,6 @@ use crate::admin::storage_api::bucket::metadata::{
use crate::admin::storage_api::bucket::metadata_sys;
use crate::admin::storage_api::bucket::quota::BucketQuota;
use crate::admin::storage_api::bucket::replication;
use crate::admin::storage_api::bucket::replication::{
assign_site_replication_rule_priorities, is_site_replication_rule, merge_incoming_replication_config,
replication_target_arn_deployment_id,
};
use crate::admin::storage_api::bucket::target::{ARN, BucketTarget, BucketTargetType, BucketTargets, Credentials};
use crate::admin::storage_api::bucket::target_sys::BucketTargetSys;
use crate::admin::storage_api::bucket::utils::{deserialize, serialize};
@@ -1122,36 +1118,6 @@ async fn load_site_replication_state() -> S3Result<SiteReplicationState> {
}
}
/// Whether this deployment participates in site replication (two or more
/// peers in the persisted state). Read by the S3 interface layer to gate
/// replication-config edits (MinIO `ErrReplicationDenyEditError` semantics,
/// issue #1948); a state-read failure propagates so the gate fails closed.
pub(crate) async fn site_replication_enabled() -> S3Result<bool> {
Ok(load_site_replication_state().await?.enabled())
}
/// Deployment ids of the remote peers the reconciler derives a
/// `site-repl-<id>` rule for on every bucket (the same peer filter as
/// `build_site_replication_config`); empty when site replication is not
/// enabled. Read by the bucket usecase so an S3 replication-config edit keeps
/// exactly the reconciler-owned rules (issue #1948); a state-read failure
/// propagates so the edit fails closed.
pub(crate) async fn site_replication_remote_peer_deployment_ids() -> S3Result<HashSet<String>> {
let state = load_site_replication_state().await?;
if !state.enabled() {
return Ok(HashSet::new());
}
let local_peer = current_local_runtime_peer(&state);
Ok(state
.peers
.values()
.filter(|peer| {
peer.deployment_id != local_peer.deployment_id && !same_identity_endpoint(&peer.endpoint, &local_peer.endpoint)
})
.map(|peer| peer.deployment_id.clone())
.collect())
}
async fn load_site_replication_state_no_lock(store: Arc<ECStore>) -> S3Result<SiteReplicationState> {
match read_config_no_lock(store, SITE_REPLICATION_STATE_PATH).await {
Ok(data) => parse_site_replication_state(&data),
@@ -7796,6 +7762,20 @@ fn bucket_target_deployment_id(target: &BucketTarget) -> Option<String> {
replication_target_arn_deployment_id(&target.arn)
}
fn replication_target_arn_deployment_id(arn: &str) -> Option<String> {
let parts: Vec<_> = arn.split(':').collect();
if parts.len() == 6
&& parts[0] == "arn"
&& matches!(parts[1], "rustfs" | "minio")
&& parts[2] == "replication"
&& !parts[4].is_empty()
{
return Some(parts[4].to_string());
}
None
}
fn prune_removed_site_replication_bucket_targets(
existing: BucketTargets,
removed_deployment_ids: &HashSet<String>,
@@ -7820,6 +7800,10 @@ fn prune_removed_site_replication_bucket_targets(
(BucketTargets { targets }, removed)
}
fn is_site_replication_rule(rule: &ReplicationRule) -> bool {
rule.id.as_deref().is_some_and(|id| id.starts_with("site-repl-"))
}
/// Whether every `site-repl-*` rule on this bucket resolves to a live remote target.
///
/// The rule set alone cannot answer this: a rule can be perfectly formed while the endpoint
@@ -7845,6 +7829,52 @@ async fn site_replication_targets_online(bucket: &str, replication_config_xml: &
true
}
/// Merge a peer's replication config into the local one.
///
/// `site-repl-*` rules encode the *sender's* outbound direction — their destination ARN
/// names the receiver — so applying a peer's rule set verbatim replaces the receiver's
/// reverse rule with one pointing at itself. No bucket target can satisfy that ARN
/// (`reconcile_site_replication_bucket_targets` skips the local peer), so the receiver
/// silently stops replicating back: the one-directional symptom. Only operator-authored
/// rules travel between sites; each site owns its own `site-repl-*` rules.
fn merge_incoming_replication_config(
incoming: Option<ReplicationConfiguration>,
local: Option<ReplicationConfiguration>,
) -> Option<ReplicationConfiguration> {
let incoming_role = incoming.as_ref().map(|config| config.role.clone()).unwrap_or_default();
// Operator rules first, then the local site rules — the same order
// `ensure_site_replication_bucket_replication_config_with_runtime` produces, so its
// no-op check matches and the bucket metadata is written once per broadcast, not twice.
let mut rules: Vec<ReplicationRule> = incoming
.into_iter()
.flat_map(|config| config.rules)
.filter(|rule| !is_site_replication_rule(rule))
.collect();
rules.extend(
local
.into_iter()
.flat_map(|config| config.rules)
.filter(is_site_replication_rule),
);
if rules.is_empty() {
return None;
}
for (index, rule) in rules.iter_mut().enumerate() {
rule.priority = Some(i32::try_from(index + 1).unwrap_or(i32::MAX));
}
// A site-replication ARN in `role` is the sender's, and `site_replication_target_arns_by_peer`
// reads it — carrying it over would pin the receiver's targets to the sender's identity.
let role = match replication_target_arn_deployment_id(&incoming_role) {
Some(_) => String::new(),
None => incoming_role,
};
Some(ReplicationConfiguration { role, rules })
}
/// Merge a peer's ILM expiry document into the local lifecycle config.
///
/// Mirrors MinIO's `mergeWithCurrentLCConfig` with one hardening: incoming
@@ -8183,7 +8213,9 @@ fn prune_removed_site_replication_rules(
return (None, removed);
}
assign_site_replication_rule_priorities(&mut config.rules, is_site_replication_rule);
for (index, rule) in config.rules.iter_mut().enumerate() {
rule.priority = Some(i32::try_from(index + 1).unwrap_or(i32::MAX));
}
(Some(config), removed)
}
@@ -8357,10 +8389,9 @@ async fn ensure_site_replication_bucket_replication_config_with_runtime(
.cloned()
.collect();
rules.extend(desired.rules);
// Operator priorities are the operator's policy; only the derived rules
// take free slots, by the same function as the config merges so a merged
// write and this pass agree byte for byte.
assign_site_replication_rule_priorities(&mut rules, is_site_replication_rule);
for (index, rule) in rules.iter_mut().enumerate() {
rule.priority = Some(i32::try_from(index + 1).unwrap_or(i32::MAX));
}
// Only a site-replication ARN in `role` is ours to drop — an operator-authored role is
// part of the bucket's S3-visible configuration, and repairing a reverse rule must not
@@ -17058,7 +17089,7 @@ mod tests {
}
#[test]
fn test_prune_removed_site_replication_rules_removes_site_rule_and_keeps_operator_priority() {
fn test_prune_removed_site_replication_rules_removes_site_rule_and_reorders_priorities() {
let removed_deployment_ids = HashSet::from(["removed-dep".to_string()]);
let kept_rule = build_site_replication_rule("arn:rustfs:replication::kept-dep:photos", 3, "site-repl-kept-dep");
let removed_rule = build_site_replication_rule("arn:rustfs:replication::removed-dep:photos", 1, "site-repl-removed-dep");
@@ -17075,9 +17106,9 @@ mod tests {
assert!(updated.role.is_empty());
assert_eq!(updated.rules.len(), 2);
assert_eq!(updated.rules[0].id.as_deref(), Some("user-managed-rule"));
assert_eq!(updated.rules[0].priority, Some(9), "the operator's priority is policy and stays");
assert_eq!(updated.rules[0].priority, Some(1));
assert_eq!(updated.rules[1].id.as_deref(), Some("site-repl-kept-dep"));
assert_eq!(updated.rules[1].priority, Some(1), "the derived rule moves to the lowest free slot");
assert_eq!(updated.rules[1].priority, Some(2));
}
#[test]
-2
View File
@@ -443,8 +443,6 @@ pub(crate) mod replication {
pub(crate) use super::ecstore_bucket::replication::{
REMOTE_TARGET_CAPABILITY_CONTRACT_VERSION, REMOTE_TARGET_UNSUPPORTED_FIELDS, REMOTE_TARGET_WRITABLE_FIELDS,
REPLICATION_CAPABILITY_CONTRACT_VERSION, REPLICATION_READ_ONLY_HISTORICAL_FIELDS, REPLICATION_WRITABLE_FIELDS,
assign_site_replication_rule_priorities, is_site_replication_rule, merge_incoming_replication_config,
replication_target_arn_deployment_id,
};
pub(crate) type BucketReplicationResyncStatus = super::ecstore_bucket::replication::BucketReplicationResyncStatus;
pub(crate) type BucketStats = super::ecstore_bucket::replication::BucketStats;
+38 -286
View File
@@ -38,9 +38,9 @@ use super::storage_api::bucket_usecase::bucket::{
metadata_sys,
policy_sys::PolicySys,
replication::{
ReplicationTargetValidationError, invalid_replication_config_status_field, merge_user_replication_config,
replication_target_arns, should_remove_replication_target, unsupported_replication_config_field,
validate_replication_config_structure, validate_replication_config_target_arns,
ReplicationTargetValidationError, invalid_replication_config_status_field, replication_target_arns,
should_remove_replication_target, unsupported_replication_config_field, validate_replication_config_structure,
validate_replication_config_target_arns,
},
target::{BucketTargetType, BucketTargets},
utils::serialize,
@@ -513,13 +513,15 @@ fn sr_bucket_meta_item(bucket: String, item_type: &str) -> SRBucketMeta {
}
}
fn notify_bucket_metadata_reload(
async fn notify_bucket_metadata_reload(
bucket: String,
operation: &'static str,
request_context: Option<request_context::RequestContext>,
scanner_maintenance_change: bool,
) {
record_local_scanner_maintenance_reload(&bucket, scanner_maintenance_change);
// Keep reload detached across request cancellation, but wait before a healthy peer can serve the previous config.
let (completed_tx, completed_rx) = tokio::sync::oneshot::channel();
spawn_background_with_context(request_context, async move {
if let Some(notification_sys) = current_notification_system() {
let result = if scanner_maintenance_change {
@@ -531,7 +533,9 @@ fn notify_bucket_metadata_reload(
warn!(bucket = %bucket, error = %err, "failed to notify peers after {operation}");
}
}
let _ = completed_tx.send(());
});
let _ = completed_rx.await;
}
fn record_local_scanner_maintenance_reload(bucket: &str, scanner_maintenance_change: bool) {
@@ -623,52 +627,11 @@ async fn validate_bucket_replication_update(bucket: &str, config: &ReplicationCo
validate_replication_config_targets(&targets, config)
}
/// Defense in depth for site-replication-managed buckets (issue #1948): an S3
/// PutBucketReplication replaces the operator-authored rules but must not wipe
/// the rules the reconciler derived for the current remote peers
/// (`site_peer_deployment_ids`) — until its next pass (600s period) every
/// peer link on this bucket would be silently dead. The same merge also drops
/// incoming impostors of those rules. An empty peer set (site replication
/// disabled) keeps the verbatim overwrite semantics: rule ids are not
/// reserved, so an operator's own `site-repl-*` rule is ordinary state there.
fn merge_user_replication_config_update(
incoming: ReplicationConfiguration,
existing: Option<ReplicationConfiguration>,
site_peer_deployment_ids: &HashSet<String>,
) -> ReplicationConfiguration {
if site_peer_deployment_ids.is_empty() {
return incoming;
}
// `incoming` passed structure validation, so it holds at least one rule;
// `None` is only reachable when every incoming rule impersonates a
// reconciler rule, and then the stored reconciler rules are what remains.
merge_user_replication_config(Some(incoming.clone()), existing, site_peer_deployment_ids).unwrap_or(incoming)
}
/// Split of an S3 DeleteBucketReplication on the stored config (issue #1948):
/// the operator-authored rules are removed, the rules the reconciler derived
/// for the current remote peers survive (`None` means nothing survives and
/// the config is deleted), and the returned ARNs are the ones whose bucket
/// targets may be garbage-collected — never an ARN a surviving reconciler
/// rule still points at.
fn split_replication_config_for_user_delete(
config: ReplicationConfiguration,
site_peer_deployment_ids: &HashSet<String>,
) -> (Option<ReplicationConfiguration>, HashSet<String>) {
let mut removable_arns = replication_target_arns(&config);
let remaining = merge_user_replication_config(None, Some(config), site_peer_deployment_ids);
if let Some(remaining) = remaining.as_ref() {
for rule in &remaining.rules {
removable_arns.remove(rule.destination.bucket.trim());
}
}
(remaining, removable_arns)
}
async fn replication_targets_without_arns(
async fn replication_targets_without_config_targets(
bucket: &str,
target_arns: &HashSet<String>,
config: &ReplicationConfiguration,
) -> S3Result<Option<(BucketTargets, usize)>> {
let target_arns = replication_target_arns(config);
if target_arns.is_empty() {
return Ok(None);
}
@@ -679,7 +642,7 @@ async fn replication_targets_without_arns(
Err(err) => return Err(ApiError::from(err).into()),
};
let removed = remove_replication_targets_from_config_targets(&mut targets, target_arns);
let removed = remove_replication_targets_from_config_targets(&mut targets, &target_arns);
if removed == 0 {
return Ok(None);
}
@@ -1517,7 +1480,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "delete bucket encryption", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "delete bucket encryption", request_context, false).await;
let item = sr_bucket_meta_item(bucket.clone(), "sse-config");
if let Err(err) = site_replication_bucket_meta_hook(item).await {
@@ -1549,7 +1512,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "delete bucket cors", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "delete bucket cors", request_context, false).await;
let item = sr_bucket_meta_item(bucket.clone(), "cors-config");
if let Err(err) = site_replication_bucket_meta_hook(item).await {
@@ -1581,7 +1544,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "delete bucket lifecycle", request_context, true);
notify_bucket_metadata_reload(bucket.clone(), "delete bucket lifecycle", request_context, true).await;
let item = sr_bucket_meta_item(bucket.clone(), "lc-config");
if let Err(err) = site_replication_bucket_meta_hook(item).await {
@@ -1613,7 +1576,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "delete bucket policy", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "delete bucket policy", request_context, false).await;
let item = sr_bucket_meta_item(bucket.clone(), "policy");
if let Err(err) = site_replication_bucket_meta_hook(item).await {
@@ -1623,15 +1586,9 @@ impl DefaultBucketUsecase {
Ok(S3Response::new(DeleteBucketPolicyOutput {}))
}
/// `site_peers` is the set of remote site-replication peer deployment ids
/// (empty when site replication is disabled). The interface layer reads it
/// from the persisted state and fails closed on a read error, so this
/// usecase stays a pure function of its inputs (layer rule: app never
/// imports interface).
pub async fn execute_delete_bucket_replication(
&self,
req: S3Request<DeleteBucketReplicationInput>,
site_peers: HashSet<String>,
) -> S3Result<S3Response<DeleteBucketReplicationOutput>> {
let expected_incarnation_id = bucket_config_mutation_incarnation(&req, &req.input.bucket)?;
let request_context = req.extensions.get::<request_context::RequestContext>().cloned();
@@ -1651,29 +1608,15 @@ impl DefaultBucketUsecase {
Err(StorageError::ConfigNotFound) => None,
Err(err) => return Err(ApiError::from(err).into()),
};
let (remaining_config, updated_targets) = if let Some(config) = replication_config.as_ref() {
let (remaining, removable_arns) = split_replication_config_for_user_delete(config.clone(), &site_peers);
let targets = replication_targets_without_arns(&bucket, &removable_arns).await?;
(remaining, targets)
let updated_targets = if let Some(config) = replication_config.as_ref() {
replication_targets_without_config_targets(&bucket, config).await?
} else {
(None, None)
None
};
match remaining_config {
// Site-replication rules and the targets backing them survive the
// S3 delete (issue #1948); only the operator-authored rules go.
Some(remaining) => {
let data = serialize_config(&remaining)?;
update_bucket_config_for_incarnation(&bucket, BUCKET_REPLICATION_CONFIG, data, expected_incarnation_id)
.await
.map_err(ApiError::from)?;
}
None => {
delete_bucket_config_for_incarnation(&bucket, BUCKET_REPLICATION_CONFIG, expected_incarnation_id)
.await
.map_err(ApiError::from)?;
}
}
delete_bucket_config_for_incarnation(&bucket, BUCKET_REPLICATION_CONFIG, expected_incarnation_id)
.await
.map_err(ApiError::from)?;
if let Some((targets, removed)) = updated_targets
&& let Err(err) =
write_replication_targets_after_config_delete(&bucket, &targets, removed, expected_incarnation_id).await
@@ -1691,7 +1634,7 @@ impl DefaultBucketUsecase {
}
drop(targets_guard);
notify_bucket_metadata_reload(bucket.clone(), "delete bucket replication", request_context, true);
notify_bucket_metadata_reload(bucket.clone(), "delete bucket replication", request_context, true).await;
let item = sr_bucket_meta_item(bucket.clone(), "replication-config");
if let Err(err) = site_replication_bucket_meta_hook(item).await {
@@ -1716,7 +1659,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "delete bucket tagging", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "delete bucket tagging", request_context, false).await;
let item = sr_bucket_meta_item(bucket.clone(), "tags");
if let Err(err) = site_replication_bucket_meta_hook(item).await {
@@ -1749,7 +1692,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "delete public access block", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "delete public access block", request_context, false).await;
Ok(S3Response::with_status(DeletePublicAccessBlockOutput::default(), StatusCode::NO_CONTENT))
}
@@ -2204,7 +2147,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "put bucket encryption", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "put bucket encryption", request_context, false).await;
let mut item = sr_bucket_meta_item(bucket.clone(), "sse-config");
item.sse_config = Some(
@@ -2283,7 +2226,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "put bucket lifecycle", request_context, true);
notify_bucket_metadata_reload(bucket.clone(), "put bucket lifecycle", request_context, true).await;
let mut item = sr_bucket_meta_item(bucket.clone(), "lc-config");
item.expiry_lc_config =
@@ -2368,7 +2311,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "put bucket notification", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "put bucket notification", request_context, false).await;
let region = resolve_notification_region(self.global_region(), request_region);
let notify = current_notify_interface_for_context(self.context.as_deref());
@@ -2473,7 +2416,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "put bucket policy", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "put bucket policy", request_context, false).await;
let mut item = sr_bucket_meta_item(bucket.clone(), "policy");
item.policy = Some(serde_json::from_str(&policy).map_err(|e| s3_error!(InvalidArgument, "parse policy failed {:?}", e))?);
@@ -2508,7 +2451,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "put bucket cors", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "put bucket cors", request_context, false).await;
let mut item = sr_bucket_meta_item(bucket.clone(), "cors-config");
item.cors =
@@ -2520,11 +2463,9 @@ impl DefaultBucketUsecase {
Ok(S3Response::new(PutBucketCorsOutput::default()))
}
/// See [`Self::execute_delete_bucket_replication`] for `site_peers`.
pub async fn execute_put_bucket_replication(
&self,
req: S3Request<PutBucketReplicationInput>,
site_peers: HashSet<String>,
) -> S3Result<S3Response<PutBucketReplicationOutput>> {
let expected_incarnation_id = bucket_config_mutation_incarnation(&req, &req.input.bucket)?;
let request_context = req.extensions.get::<request_context::RequestContext>().cloned();
@@ -2548,20 +2489,13 @@ impl DefaultBucketUsecase {
let targets_guard = lock_bucket_targets_metadata(&bucket).await;
validate_bucket_replication_update(&bucket, &replication_configuration).await?;
let existing_config = match metadata_sys::get_replication_config(&bucket).await {
Ok((config, _)) => Some(config),
Err(StorageError::ConfigNotFound) => None,
Err(err) => return Err(ApiError::from(err).into()),
};
let replication_configuration =
merge_user_replication_config_update(replication_configuration, existing_config, &site_peers);
let data = serialize_config(&replication_configuration)?;
update_bucket_config_for_incarnation(&bucket, BUCKET_REPLICATION_CONFIG, data, expected_incarnation_id)
.await
.map_err(ApiError::from)?;
drop(targets_guard);
notify_bucket_metadata_reload(bucket.clone(), "put bucket replication", request_context, true);
notify_bucket_metadata_reload(bucket.clone(), "put bucket replication", request_context, true).await;
let mut item = sr_bucket_meta_item(bucket.clone(), "replication-config");
item.replication_config = Some(
@@ -2601,7 +2535,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "put public access block", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "put public access block", request_context, false).await;
Ok(S3Response::new(PutPublicAccessBlockOutput::default()))
}
@@ -2630,7 +2564,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "put bucket tagging", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "put bucket tagging", request_context, false).await;
let mut item = sr_bucket_meta_item(bucket.clone(), "tags");
item.tags = Some(serialize_config(&tagging).and_then(|bytes| String::from_utf8(bytes).map_err(to_internal_error))?);
@@ -2663,7 +2597,7 @@ impl DefaultBucketUsecase {
.await
.map_err(ApiError::from)?;
notify_bucket_metadata_reload(bucket.clone(), "put bucket versioning", request_context, false);
notify_bucket_metadata_reload(bucket.clone(), "put bucket versioning", request_context, false).await;
let mut item = sr_bucket_meta_item(bucket.clone(), "version-config");
item.versioning = Some(
@@ -3114,7 +3048,7 @@ mod tests {
"{method} should identify the bucket metadata operation in reload logs"
);
let expected_reload = format!(
"notify_bucket_metadata_reload(bucket.clone(), \"{operation}\", request_context, {scanner_maintenance_change});"
"notify_bucket_metadata_reload(bucket.clone(), \"{operation}\", request_context, {scanner_maintenance_change}).await;"
);
assert!(
body.contains(&expected_reload),
@@ -3184,185 +3118,6 @@ mod tests {
assert!(arns.contains(destination));
}
fn replication_rule_with_id(arn: &str, id: &str, priority: i32) -> ReplicationRule {
let mut rule = replication_rule_for_target(arn);
rule.id = Some(id.to_string());
rule.priority = Some(priority);
rule
}
fn site_peers(deployment_ids: &[&str]) -> HashSet<String> {
deployment_ids.iter().map(|id| id.to_string()).collect()
}
#[test]
fn put_replication_merge_preserves_site_replication_rules() {
let existing = ReplicationConfiguration {
role: String::new(),
rules: vec![
replication_rule_with_id("arn:rustfs:replication::peer-dep:bucket", "site-repl-peer-dep", 1),
replication_rule_with_id("arn:rustfs:replication:us-east-1:old:bucket", "old-user-rule", 2),
],
};
let incoming = ReplicationConfiguration {
role: String::new(),
rules: vec![
replication_rule_with_id("arn:rustfs:replication:us-east-1:new:bucket", "new-user-rule", 1),
replication_rule_with_id("arn:rustfs:replication::forged-dep:bucket", "site-repl-peer-dep", 2),
replication_rule_with_id("arn:rustfs:replication::other-dep:bucket", "site-repl-other", 3),
],
};
let merged = merge_user_replication_config_update(incoming, Some(existing), &site_peers(&["peer-dep"]));
let rules: Vec<_> = merged
.rules
.iter()
.map(|rule| (rule.id.as_deref().unwrap_or_default(), rule.destination.bucket.as_str()))
.collect();
assert_eq!(
rules,
vec![
("new-user-rule", "arn:rustfs:replication:us-east-1:new:bucket"),
("site-repl-other", "arn:rustfs:replication::other-dep:bucket"),
("site-repl-peer-dep", "arn:rustfs:replication::peer-dep:bucket"),
],
"user rules replaced, the reconciler rule for the current peer kept over the incoming impostor, \
a site-repl-* id that names no current peer is ordinary operator state"
);
}
// Rule ids do not reserve `site-repl-*`: outside site replication an
// owner's `site-repl-user` rule is ordinary state, so PUT stores it
// verbatim and DELETE removes it and garbage-collects its target.
#[test]
fn put_then_delete_replication_without_site_replication_treats_site_repl_id_as_user_rule() {
let user_arn = "arn:minio:replication:us-east-1:2f1c-remote:bucket";
let incoming = ReplicationConfiguration {
role: String::new(),
rules: vec![replication_rule_with_id(user_arn, "site-repl-user", 1)],
};
let stored = merge_user_replication_config_update(incoming.clone(), None, &HashSet::new());
assert_eq!(stored, incoming, "PUT on a non-site-replication bucket is verbatim");
let (remaining, removable) = split_replication_config_for_user_delete(stored, &HashSet::new());
assert!(remaining.is_none(), "DELETE must remove the operator's site-repl-* rule");
assert_eq!(removable, HashSet::from([user_arn.to_string()]));
}
// Under site replication only a rule the reconciler would derive — id
// `site-repl-<peer>` for a current peer, destination ARN naming the same
// peer — is reconciler-owned. Everything else is operator state.
#[test]
fn delete_replication_split_keeps_only_reconciler_derived_rules() {
let peer_arn = "arn:rustfs:replication::peer-dep:bucket";
let user_arn = "arn:minio:replication:us-east-1:2f1c-remote:bucket";
let config = ReplicationConfiguration {
role: String::new(),
rules: vec![
replication_rule_with_id(user_arn, "site-repl-user", 1),
replication_rule_with_id(user_arn, "site-repl-peer-dep", 2),
replication_rule_with_id("arn:rustfs:replication::gone-dep:bucket", "site-repl-gone-dep", 3),
replication_rule_with_id(peer_arn, "site-repl-peer-dep", 4),
],
};
let (remaining, removable) = split_replication_config_for_user_delete(config, &site_peers(&["peer-dep"]));
let remaining = remaining.expect("the reconciler-derived rule must survive");
assert_eq!(remaining.rules.len(), 1);
assert_eq!(remaining.rules[0].destination.bucket, peer_arn);
assert_eq!(
removable,
HashSet::from([user_arn.to_string(), "arn:rustfs:replication::gone-dep:bucket".to_string()]),
"targets of operator rules and of a removed peer are garbage-collected"
);
}
#[test]
fn put_replication_merge_returns_incoming_verbatim_without_site_rules() {
let existing = ReplicationConfiguration {
role: String::new(),
rules: vec![replication_rule_with_id(
"arn:rustfs:replication:us-east-1:old:bucket",
"old-user-rule",
7,
)],
};
let incoming = ReplicationConfiguration {
role: String::new(),
rules: vec![replication_rule_with_id(
"arn:rustfs:replication:us-east-1:new:bucket",
"new-user-rule",
5,
)],
};
let merged = merge_user_replication_config_update(incoming.clone(), Some(existing), &HashSet::new());
assert_eq!(merged.role, incoming.role);
assert_eq!(merged.rules, incoming.rules, "non-SR buckets keep the verbatim overwrite semantics");
}
#[test]
fn delete_replication_split_keeps_site_rules_and_their_targets() {
let sr_arn = "arn:rustfs:replication::peer-dep:bucket";
let user_arn = "arn:rustfs:replication:us-east-1:user:bucket";
let config = ReplicationConfiguration {
role: String::new(),
rules: vec![
replication_rule_with_id(user_arn, "user-rule", 1),
replication_rule_with_id(sr_arn, "site-repl-peer-dep", 2),
],
};
let (remaining, removable) = split_replication_config_for_user_delete(config, &site_peers(&["peer-dep"]));
let remaining = remaining.expect("site-replication rules must survive a user delete");
let ids: Vec<_> = remaining
.rules
.iter()
.map(|rule| rule.id.as_deref().unwrap_or_default())
.collect();
assert_eq!(ids, vec!["site-repl-peer-dep"]);
assert_eq!(removable, HashSet::from([user_arn.to_string()]));
}
#[test]
fn delete_replication_split_protects_targets_shared_with_site_rules() {
let sr_arn = "arn:rustfs:replication::peer-dep:bucket";
let config = ReplicationConfiguration {
role: String::new(),
rules: vec![
replication_rule_with_id(sr_arn, "user-rule-on-sr-target", 1),
replication_rule_with_id(sr_arn, "site-repl-peer-dep", 2),
],
};
let (remaining, removable) = split_replication_config_for_user_delete(config, &site_peers(&["peer-dep"]));
assert!(remaining.is_some());
assert!(
removable.is_empty(),
"a target still referenced by a surviving site-replication rule must not be removed"
);
}
#[test]
fn delete_replication_split_removes_everything_without_site_rules() {
let user_arn = "arn:rustfs:replication:us-east-1:user:bucket";
let config = ReplicationConfiguration {
role: String::new(),
rules: vec![replication_rule_with_id(user_arn, "user-rule", 1)],
};
let (remaining, removable) = split_replication_config_for_user_delete(config, &site_peers(&["peer-dep"]));
assert!(remaining.is_none(), "without site-replication rules the whole config is deleted");
assert_eq!(removable, HashSet::from([user_arn.to_string()]));
}
fn replication_targets_with_arn(arns: &[&str]) -> BucketTargets {
BucketTargets {
targets: arns
@@ -3700,10 +3455,7 @@ mod tests {
let req = build_request(input, Method::DELETE);
let usecase = DefaultBucketUsecase::without_context();
let err = usecase
.execute_delete_bucket_replication(req, HashSet::new())
.await
.unwrap_err();
let err = usecase.execute_delete_bucket_replication(req).await.unwrap_err();
assert_eq!(err.code(), &S3ErrorCode::InternalError);
}
@@ -4789,7 +4541,7 @@ mod tests {
let req = build_request(input, Method::PUT);
let usecase = DefaultBucketUsecase::without_context();
let err = usecase.execute_put_bucket_replication(req, HashSet::new()).await.unwrap_err();
let err = usecase.execute_put_bucket_replication(req).await.unwrap_err();
assert_eq!(err.code(), &S3ErrorCode::InternalError);
}
@@ -4807,7 +4559,7 @@ mod tests {
.unwrap();
let err = DefaultBucketUsecase::without_context()
.execute_put_bucket_replication(build_request(input, Method::PUT), HashSet::new())
.execute_put_bucket_replication(build_request(input, Method::PUT))
.await
.expect_err("unsupported fields must be rejected before store access");
-2
View File
@@ -619,8 +619,6 @@ pub(crate) mod bucket {
use crate::storage::storage_api::ecstore_bucket::replication as replication_contracts;
pub(crate) use replication_contracts::merge_user_replication_config;
type ReplicationObjectBridge = crate::storage::storage_api::ecstore_bucket::replication::ReplicationObjectBridge;
pub(crate) type DeleteReplicationConfigSnapshot =
crate::storage::storage_api::ecstore_bucket::replication::DeleteReplicationConfigSnapshot;
+2 -169
View File
@@ -63,69 +63,6 @@ use crate::app::storage_api::object_usecase::bucket::replication::{
};
use crate::storage::storage_api::ecfs_consumer::StorageObjectOptions as ObjectOptions;
#[cfg(test)]
static SITE_REPLICATION_GATE_TEST_OVERRIDE: std::sync::atomic::AtomicU8 = std::sync::atomic::AtomicU8::new(0);
#[cfg(test)]
const SITE_REPLICATION_GATE_FORCE_DISABLED: u8 = 1;
#[cfg(test)]
const SITE_REPLICATION_GATE_FORCE_ENABLED: u8 = 2;
async fn site_replication_gate_enabled() -> S3Result<bool> {
#[cfg(test)]
match SITE_REPLICATION_GATE_TEST_OVERRIDE.load(std::sync::atomic::Ordering::SeqCst) {
SITE_REPLICATION_GATE_FORCE_DISABLED => return Ok(false),
SITE_REPLICATION_GATE_FORCE_ENABLED => return Ok(true),
_ => {}
}
crate::admin::handlers::site_replication::site_replication_enabled().await
}
/// Remote site-replication peer deployment ids handed to the bucket usecase
/// so an S3 replication-config edit keeps exactly the reconciler-owned rules
/// (issue #1948). Read here, in the interface layer, because the usecase must
/// not import the admin handlers (layer guard); a state-read failure
/// propagates so the edit fails closed.
async fn site_replication_peer_deployment_ids_for_edit() -> S3Result<std::collections::HashSet<String>> {
// While the gate override is in effect the test exercises the deny/allow
// branch, not the peer set; there is no persisted state to read.
#[cfg(test)]
if SITE_REPLICATION_GATE_TEST_OVERRIDE.load(std::sync::atomic::Ordering::SeqCst) != 0 {
return Ok(std::collections::HashSet::new());
}
crate::admin::handlers::site_replication::site_replication_remote_peer_deployment_ids().await
}
/// MinIO `ErrReplicationDenyEditError`.
fn replication_deny_edit_error() -> S3Error {
let mut err = S3Error::with_message(
S3ErrorCode::Custom("XMinioReplicationDenyEdit".into()),
"Sub-User is not allowed to edit Replication configuration",
);
err.set_status_code(StatusCode::BAD_REQUEST);
err
}
/// Site-replication gate for S3 replication-config edits (issue #1948).
///
/// On a site-replication deployment the bucket's replication config carries
/// the operator-managed `site-repl-*` rules that keep every peer in sync, and
/// a successful edit is broadcast to all peers — so a user holding only
/// bucket-scoped `s3:PutReplicationConfiguration` could rewrite or erase
/// replication net-wide. MinIO parity (`ErrReplicationDenyEditError`): only
/// owner credentials (root or root-parented) may edit. Runs after the policy
/// authorization in the access layer and only on the external S3 path — the
/// reconciler and peer bucket-meta ingestion never route through these
/// handlers.
async fn deny_replication_config_edit_for_non_owner<T>(req: &S3Request<T>) -> S3Result<()> {
if crate::storage::access::req_info_ref(req)?.is_owner {
return Ok(());
}
if site_replication_gate_enabled().await? {
return Err(replication_deny_edit_error());
}
Ok(())
}
#[derive(Debug, Clone)]
pub struct FS {
/// This server's late-bound application-context slot (backlog#1052 S2).
@@ -563,10 +500,8 @@ impl S3 for FS {
&self,
req: S3Request<DeleteBucketReplicationInput>,
) -> S3Result<S3Response<DeleteBucketReplicationOutput>> {
deny_replication_config_edit_for_non_owner(&req).await?;
let site_peers = site_replication_peer_deployment_ids_for_edit().await?;
let usecase = s3_api::bucket_usecase_for(self);
usecase.execute_delete_bucket_replication(req, site_peers).await
usecase.execute_delete_bucket_replication(req).await
}
#[instrument(level = "debug", skip(self))]
@@ -1418,10 +1353,8 @@ impl S3 for FS {
&self,
req: S3Request<PutBucketReplicationInput>,
) -> S3Result<S3Response<PutBucketReplicationOutput>> {
deny_replication_config_edit_for_non_owner(&req).await?;
let site_peers = site_replication_peer_deployment_ids_for_edit().await?;
let usecase = s3_api::bucket_usecase_for(self);
usecase.execute_put_bucket_replication(req, site_peers).await
usecase.execute_put_bucket_replication(req).await
}
async fn put_bucket_request_payment(
@@ -1986,103 +1919,3 @@ impl S3 for FS {
Box::pin(usecase.execute_upload_part_copy(req)).await
}
}
#[cfg(test)]
mod tests {
use super::{
FS, SITE_REPLICATION_GATE_FORCE_DISABLED, SITE_REPLICATION_GATE_FORCE_ENABLED, SITE_REPLICATION_GATE_TEST_OVERRIDE,
};
use crate::storage::access::ReqInfo;
use http::Method;
use http::StatusCode;
use s3s::dto::{DeleteBucketReplicationInput, PutBucketReplicationInput, ReplicationConfiguration};
use s3s::{S3, S3Error, S3ErrorCode, S3Request};
use std::sync::atomic::Ordering;
fn replication_config_edit_request<T>(input: T, is_owner: bool) -> S3Request<T> {
let mut req = S3Request {
input,
method: Method::PUT,
uri: http::Uri::from_static("/"),
headers: http::HeaderMap::new(),
extensions: http::Extensions::new(),
credentials: None,
region: None,
service: None,
trailing_headers: None,
};
req.extensions.insert(ReqInfo {
is_owner,
..Default::default()
});
req
}
fn put_bucket_replication_input() -> PutBucketReplicationInput {
PutBucketReplicationInput {
bucket: "test-bucket".to_string(),
checksum_algorithm: None,
content_md5: None,
expected_bucket_owner: None,
replication_configuration: ReplicationConfiguration {
role: String::new(),
rules: Vec::new(),
},
token: None,
}
}
fn delete_bucket_replication_input() -> DeleteBucketReplicationInput {
DeleteBucketReplicationInput {
bucket: "test-bucket".to_string(),
expected_bucket_owner: None,
}
}
fn assert_replication_deny_edit(err: &S3Error) {
match err.code() {
S3ErrorCode::Custom(code) => assert_eq!(code, "XMinioReplicationDenyEdit"),
other => panic!("expected XMinioReplicationDenyEdit, got {other:?}"),
}
assert_eq!(err.status_code(), Some(StatusCode::BAD_REQUEST));
}
/// Single test on purpose: the branches share the process-wide gate
/// override, and parallel tests would race it.
#[tokio::test]
async fn replication_config_edit_gate_denies_only_non_owner_under_site_replication() {
let fs = FS::new();
SITE_REPLICATION_GATE_TEST_OVERRIDE.store(SITE_REPLICATION_GATE_FORCE_ENABLED, Ordering::SeqCst);
// Non-owner PUT/DELETE through the real S3 handlers: denied by the
// gate before the usecase (and thus the store) is ever touched.
let err = fs
.put_bucket_replication(replication_config_edit_request(put_bucket_replication_input(), false))
.await
.expect_err("non-owner PutBucketReplication must be denied while site replication is enabled");
assert_replication_deny_edit(&err);
let err = fs
.delete_bucket_replication(replication_config_edit_request(delete_bucket_replication_input(), false))
.await
.expect_err("non-owner DeleteBucketReplication must be denied while site replication is enabled");
assert_replication_deny_edit(&err);
// Owner passes the gate (the usecase's empty-rules structure error
// proves the request reached the usecase instead of the deny path).
let err = fs
.put_bucket_replication(replication_config_edit_request(put_bucket_replication_input(), true))
.await
.expect_err("owner request should pass the gate and fail later on config validation");
assert_eq!(err.code(), &S3ErrorCode::InvalidRequest);
// Without site replication the policy check alone still governs the edit.
SITE_REPLICATION_GATE_TEST_OVERRIDE.store(SITE_REPLICATION_GATE_FORCE_DISABLED, Ordering::SeqCst);
let err = fs
.put_bucket_replication(replication_config_edit_request(put_bucket_replication_input(), false))
.await
.expect_err("non-owner request should pass the gate and fail later on config validation");
assert_eq!(err.code(), &S3ErrorCode::InvalidRequest);
SITE_REPLICATION_GATE_TEST_OVERRIDE.store(0, Ordering::SeqCst);
}
}