ryerraguntla commented on code in PR #4258:
URL: https://github.com/apache/iggy/pull/4258#discussion_r4088474558
##########
gateways/kafka/src/protocol/handlers/create_topics.rs:
##########
@@ -17,44 +17,378 @@
//! `CreateTopics` (API key 19).
+use std::collections::HashSet;
+use std::time::Duration;
+
use bytes::Bytes;
-use kafka_protocol::messages::create_topics_request::CreatableTopic;
+use iggy::prelude::IggyError;
+use
kafka_protocol::messages::create_topics_request::{CreatableReplicaAssignment,
CreatableTopic};
use kafka_protocol::messages::create_topics_response::CreatableTopicResult;
-use kafka_protocol::messages::{CreateTopicsRequest, CreateTopicsResponse};
+use kafka_protocol::messages::{CreateTopicsRequest, CreateTopicsResponse,
TopicName};
+use kafka_protocol::protocol::StrBytes;
+use crate::bridge::{BridgeError, IggyBridge, TopicCreationOutcome};
use crate::error::Result;
use crate::protocol::api::{
- API_KEY_CREATE_TOPICS, ApiVersionRange, ERROR_INVALID_PARTITIONS,
- ERROR_INVALID_REPLICATION_FACTOR, ERROR_NONE, ERROR_NOT_CONTROLLER,
GatewayState,
- HandleOutcome,
+ API_KEY_CREATE_TOPICS, ApiVersionRange, ERROR_INVALID_CONFIG,
ERROR_INVALID_PARTITIONS,
+ ERROR_INVALID_REPLICA_ASSIGNMENT, ERROR_INVALID_REPLICATION_FACTOR,
ERROR_INVALID_REQUEST,
+ ERROR_NONE, ERROR_NOT_CONTROLLER, ERROR_REQUEST_TIMED_OUT,
ERROR_TOPIC_ALREADY_EXISTS,
+ GatewayState, HandleOutcome,
};
use crate::protocol::bounds_guard::validate_create_topics_shape;
-use crate::protocol::handlers::{decode_guarded, encode_message,
handle_versioned_request};
+use crate::protocol::handlers::{
+ decode_guarded, encode_message, handle_versioned_request,
is_supported_version,
+ respond_or_close, unsupported_version_response,
+};
pub const RANGE: ApiVersionRange = ApiVersionRange {
api_key: API_KEY_CREATE_TOPICS,
min_version: 2,
max_version: 5,
};
-#[expect(
- clippy::unused_async,
- reason = "the shared handler signature, kept until a handler awaits the
bridge"
-)]
+/// KIP-464 `num_partitions = -1` with no manual assignment: the count this
bridge creates.
+///
+/// Matches real Kafka's own out-of-box `num.partitions=1` broker default. Not
read from any
+/// bridge config - there is no such config surface today.
+const DEFAULT_PARTITION_COUNT: u32 = 1;
+
+/// Cap on distinct topic names one `CreateTopics` request may address through
the bridge.
+///
+/// `bounds_guard`'s `MAX_REQUEST_ELEMENTS` (4,096) is a pre-decode `DoS`
ceiling, not a usability
+/// recommendation: each non-duplicate requested name here costs up to ~4 Iggy
round trips
+/// (`ensure_stream` + `create_topic`, plus a possible race-retry read on
either) against the
+/// single lockstep `IggyClient` every Kafka connection on this gateway shares
+/// (`bridge/iggy_bridge/mod.rs`'s "Concurrency ceiling"). 100 keeps a
worst-case batch's
+/// aggregate bridge cost small relative to that shared resource while
remaining generous for any
+/// real admin batch. Duplicate names never count against this cap - they're
rejected by
+/// [`find_duplicate_names`] before ever reaching the bridge.
+const MAX_BRIDGE_BACKED_TOPICS: usize = 100;
+
+/// Bounds imposed on the request's own `timeout_ms` before it becomes the
aggregate bridge-work
+/// deadline. That value is client-supplied and otherwise unchecked: `0` or
negative would abort
+/// every topic on arrival, and an oversized one would tie up the shared
`IggyClient` past any
+/// reasonable request.
+const MIN_REQUEST_TIMEOUT: Duration = Duration::from_millis(1_000);
+const MAX_REQUEST_TIMEOUT: Duration = Duration::from_secs(30);
+
+/// Clamps the wire's own `timeout_ms` (KIP-4's field for exactly this) into
+/// `[MIN_REQUEST_TIMEOUT, MAX_REQUEST_TIMEOUT]` - unlike
`ListOffsets`/`Metadata`, `CreateTopics`
+/// carries a real client-supplied deadline to honor, not just a fixed
internal ceiling.
+fn clamp_request_timeout(timeout_ms: i32) -> Duration {
+ let requested =
Duration::from_millis(u64::try_from(timeout_ms).unwrap_or(0));
+ requested.clamp(MIN_REQUEST_TIMEOUT, MAX_REQUEST_TIMEOUT)
+}
+
pub async fn handle(state: &GatewayState, api_version: i16, body: Bytes) ->
HandleOutcome {
- handle_versioned_request(
- API_KEY_CREATE_TOPICS,
- api_version,
- body,
- |v, b| {
- decode_guarded::<CreateTopicsRequest>(v, b, |v, b| {
- validate_create_topics_shape(v, b, state.max_frame_size)
+ let Some(bridge) = &state.bridge else {
+ return handle_versioned_request(
+ API_KEY_CREATE_TOPICS,
+ api_version,
+ body,
+ |v, b| {
+ decode_guarded::<CreateTopicsRequest>(v, b, |v, b| {
+ validate_create_topics_shape(v, b, state.max_frame_size)
+ })
+ },
+ encode_response,
+ encode_error_response,
+ "CreateTopics",
+ );
+ };
+
+ if !is_supported_version(API_KEY_CREATE_TOPICS, api_version) {
+ return unsupported_version_response(API_KEY_CREATE_TOPICS,
api_version, |version| {
+ encode_error_response(version, ERROR_INVALID_REQUEST)
+ });
+ }
+
+ let req = match decode_guarded::<CreateTopicsRequest>(api_version, body,
|v, b| {
+ validate_create_topics_shape(v, b, state.max_frame_size)
+ }) {
+ Ok(req) => req,
+ Err(error) => {
+ // debug!, not warn!: attacker-controlled, not operator-actionable.
+ tracing::debug!(%error, "Failed to decode CreateTopics request");
+ return respond_or_close(
+ encode_error_response(api_version, ERROR_INVALID_REQUEST),
+ "CreateTopics",
+ );
+ }
+ };
+
+ let duplicate_names = find_duplicate_names(&req.topics);
+
+ let distinct_bridge_backed: HashSet<&TopicName> = req
+ .topics
+ .iter()
+ .map(|topic| &topic.name)
+ .filter(|name| !duplicate_names.contains(*name))
+ .collect();
+ if distinct_bridge_backed.len() > MAX_BRIDGE_BACKED_TOPICS {
+ tracing::warn!(
+ distinct_topics = distinct_bridge_backed.len(),
+ max = MAX_BRIDGE_BACKED_TOPICS,
+ "CreateTopics request addresses too many distinct topics;
rejecting"
+ );
+ let results = req
+ .topics
+ .iter()
+ .map(|topic| {
+ CreatableTopicResult::default()
+ .with_name(topic.name.clone())
+ .with_error_code(ERROR_INVALID_REQUEST)
})
- },
- encode_response,
- encode_error_response,
- "CreateTopics",
+ .collect();
+ let resp = CreateTopicsResponse::default().with_topics(results);
+ return respond_or_close(encode_message(&resp, api_version, 256),
"CreateTopics");
+ }
+
+ let deadline = clamp_request_timeout(req.timeout_ms);
+ let results = match tokio::time::timeout(
+ deadline,
+ create_all_topics(
+ bridge,
+ api_version,
+ &req.topics,
+ &duplicate_names,
+ req.validate_only,
+ ),
)
+ .await
+ {
+ Ok(results) => results,
+ Err(_elapsed) => {
+ tracing::warn!(
+ distinct_topics = distinct_bridge_backed.len(),
+ deadline_ms = deadline.as_millis(),
+ "CreateTopics request's aggregate bridge work exceeded its
deadline; \
+ answering retriable instead of blocking further"
+ );
+ req.topics
+ .iter()
+ .map(|topic| {
+ CreatableTopicResult::default()
+ .with_name(topic.name.clone())
+ .with_error_code(ERROR_REQUEST_TIMED_OUT)
+ })
+ .collect()
+ }
+ };
+ let resp = CreateTopicsResponse::default().with_topics(results);
+ respond_or_close(encode_message(&resp, api_version, 256), "CreateTopics")
+}
+
+/// Creates (or reports on) every requested topic, skipping the bridge
entirely for a duplicate
+/// name - real Kafka refuses the whole name, not a first-wins/last-wins
split: creating one
+/// occurrence and reporting `TOPIC_ALREADY_EXISTS` for the other would let a
client observe a
+/// create it never got a `NONE` for (`AdminClient` keys its futures by name,
so a second
+/// per-topic result for the same name is silently discarded client-side
regardless of which one
+/// this bridge picked).
+async fn create_all_topics(
+ bridge: &IggyBridge,
+ api_version: i16,
+ topics: &[CreatableTopic],
+ duplicate_names: &HashSet<TopicName>,
+ validate_only: bool,
+) -> Vec<CreatableTopicResult> {
+ let mut results = Vec::with_capacity(topics.len());
+ for topic in topics {
+ let result = if duplicate_names.contains(&topic.name) {
+ CreatableTopicResult::default()
+ .with_name(topic.name.clone())
+ .with_error_code(ERROR_INVALID_REQUEST)
+ } else {
+ create_one_topic(bridge, api_version, topic, validate_only).await
+ };
+ results.push(result);
+ }
+ results
+}
+
+/// Every topic name that appears more than once in `topics` - real Kafka
+/// (`ControllerApis.createTopics`) refuses every occurrence of a duplicate
name with
+/// `INVALID_REQUEST` (42) and creates nothing for it, rather than creating
the first occurrence
+/// and reporting the rest as already existing.
+fn find_duplicate_names(topics: &[CreatableTopic]) -> HashSet<TopicName> {
+ let mut seen = HashSet::with_capacity(topics.len());
+ let mut duplicates = HashSet::new();
+ for topic in topics {
+ if !seen.insert(topic.name.clone()) {
+ duplicates.insert(topic.name.clone());
+ }
+ }
+ duplicates
+}
+
+/// Validates and, when the topic is not rejected outright, provisions one
requested topic.
+///
+/// `configs` is rejected before the shape check - a config-bearing request is
rejected the same
+/// way regardless of how its partitions/replication are shaped.
+///
+/// `validate_only` and the real create path diverge deliberately below that
point, not just in
+/// whether they call the bridge: `validate_only` never mutates anything, so a
plain existence
+/// read ([`IggyBridge::get_kafka_topic`]) is fine - there's no race to
protect against when
+/// nothing gets created either way. The real path instead calls
+/// [`IggyBridge::create_kafka_topic`], which folds the existence check and
the create into one
+/// atomic call - a separate read-then-write here would let two concurrent
`CreateTopics` for the
+/// same new name both observe `Ok(None)` and both receive `NONE`, when Kafka
guarantees exactly
+/// one caller does.
+async fn create_one_topic(
+ bridge: &IggyBridge,
+ version: i16,
+ topic: &CreatableTopic,
+ validate_only: bool,
+) -> CreatableTopicResult {
+ let result = CreatableTopicResult::default().with_name(topic.name.clone());
+
+ if !topic.configs.is_empty() {
+ return result
+ .with_error_code(ERROR_INVALID_CONFIG)
+ .with_error_message(Some(StrBytes::from(
+ "per-topic configs are not supported by this
bridge".to_string(),
+ )));
+ }
+
+ let partition_count = match validate_create_topic_shape(version, topic) {
+ Ok(count) => count,
+ Err(code) => return result.with_error_code(code),
+ };
+
+ let kafka_topic = topic.name.as_str();
+ let success = || {
+ result
+ .clone()
+ .with_error_code(ERROR_NONE)
+
.with_num_partitions(i32::try_from(partition_count).unwrap_or(i32::MAX))
+ .with_replication_factor(1)
+ };
+
+ if validate_only {
+ return match bridge.get_kafka_topic(kafka_topic).await {
+ Ok(Some(_existing)) =>
result.with_error_code(ERROR_TOPIC_ALREADY_EXISTS),
+ Ok(None) => success(),
+ Err(err) => result
+ .with_error_code(err.to_kafka_error_code())
+
.with_error_message(Some(StrBytes::from(error_message_for(&err)))),
+ };
+ }
+
+ match bridge
+ .create_kafka_topic(kafka_topic, partition_count)
+ .await
+ {
+ // The second arm: the write committed on its first attempt, the SDK's
own reconnect path
+ // replayed it, and the server's client-table dedup caught the replay
- not a fault.
+ // `to_kafka_error_code`'s shared mapping deliberately doesn't
special-case this - it's a
+ // write-only fact, checked here, at the one write this bridge makes,
rather than assumed
+ // true for the reads that share that mapping too.
+ Ok(TopicCreationOutcome::Created)
+ | Err(BridgeError::Iggy(IggyError::RequestAlreadyApplied)) =>
success(),
+ Ok(TopicCreationOutcome::AlreadyExists) => {
+ result.with_error_code(ERROR_TOPIC_ALREADY_EXISTS)
+ }
+ Err(err) => result
+ .with_error_code(err.to_kafka_error_code())
+ .with_error_message(Some(StrBytes::from(error_message_for(&err)))),
+ }
+}
+
+/// Error text for `CreatableTopicResult.error_message`, without re-embedding
the topic name:
+/// `result.name` (`CreatableTopicResult::with_name`) already carries it, so
`err.to_string()`'s
+/// own embedded copy for these two variants would double the per-topic
response cost for a name
+/// the client already sent and already has back. Validation runs before any
bridge I/O, so this
+/// is a purely local, zero-round-trip amplification if left in - 100 topics
named with a maximal
+/// legal length build a response roughly twice the size the name alone would
justify.
+fn error_message_for(err: &BridgeError) -> String {
+ match err {
+ BridgeError::InvalidKafkaTopicName { reason, .. } => reason.clone(),
+ BridgeError::InvalidPartitionCount { .. } => {
+ "partition count must be at least 1".to_string()
+ }
+ other => other.to_string(),
+ }
+}
+
+/// Validates one requested topic's KIP-464 shape and resolves its partition
count.
+///
+/// A manual partition `assignments` list and an explicit
`num_partitions`/`replication_factor`
+/// are mutually exclusive inputs, not two independently-checked values that
happen to agree: real
+/// Kafka's own `ReplicationControlManager` rejects a manual assignment unless
both are exactly
+/// `-1`, regardless of whether an explicit `num_partitions` matches
`assignments.len()`. A count
+/// that only *disagrees* with the assignment length is not a distinct, more
lenient case - the
+/// combination itself is what's invalid, so both are `INVALID_REQUEST` (42),
never `NONE`.
+///
+/// An assignment's own partition indices are checked too, not just its
length: real Kafka
+/// requires the key set to be exactly `0..assignments.len()`, each index
appearing once, and
+/// rejects anything else - a duplicate or non-consecutive index (`{5: [...],
7: [...]}`) - with
+/// `INVALID_REPLICA_ASSIGNMENT` (39), the one condition that code exists for.
This bridge doesn't
+/// model per-partition replica placement, so only the index set is checked,
not each entry's
+/// replica list.
+///
+/// With no assignments, `num_partitions = -1` / `replication_factor = -1`
mean "use the broker
+/// default" from v4+ (pre-v4 requires an explicit positive value for both,
since v2/v3 have no
+/// broker-default sentinel absent a manual assignment).
+fn validate_create_topic_shape(
+ version: i16,
+ topic: &CreatableTopic,
+) -> core::result::Result<u32, i16> {
+ if !topic.assignments.is_empty() {
+ if topic.num_partitions != -1 || topic.replication_factor != -1 {
+ return Err(ERROR_INVALID_REQUEST);
+ }
+ if !assignment_indices_are_consecutive_from_zero(&topic.assignments) {
Review Comment:
New assignment_replicas_are_valid() — this gateway has exactly one broker,
so the only legal replica list is [1]; that single check rules out empty,
duplicate, and unregistered in one shot. Fixed the test helper (broker_id 0 →
1) and added 3 negative unit tests matching the reviewer's exact repro
shapes.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
