Skip to content

Performance optimizations (primarily for multihost) #6641

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
blp merged 8 commits into from
Jul 15, 2026
Merged

Performance optimizations (primarily for multihost) #6641

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
54906da
[dbsp] Simplify dyn_shard_accumulate().
blp Jun 9, 2026
a8ee7a6
[dbsp] Implement streaming exchange to a subset of workers.
blp Jun 9, 2026
53e856a
[dbsp] Turn `ExchangeReceiver` into a "synchronous" operator.
blp Jun 10, 2026
06b4db8
[dbsp] Skip exchange overhead for input operators during transaction …
blp Jun 10, 2026
0e8e08d
[dbsp] Segregate inter-host exchange channels by message size and type.
blp Jun 12, 2026
e3cfded
[dbsp] Simplify `ChildCircuit::add_exchange_with_preference`.
blp Jun 17, 2026
b1474fd
[dbsp] Break sharded accumulator waiting for merging into separate op…
blp Jun 17, 2026
c87d78e
[dbsp] Improve comment.
blp Jul 15, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 6 additions & 25 deletions crates/dbsp/src/circuit/circuit_builder.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3939,31 +3939,12 @@ where
SndOp: SinkOperator<I>,
RcvOp: SourceOperator<O>,
{
let sender_id = self.add_node(|id| {
self.log_circuit_event(&CircuitEvent::operator(
GlobalNodeId::child_of(self, id),
sender.name(),
sender.location(),
));

let node = SinkNode::new(sender, input_stream.clone(), self.clone(), id);
self.connect_stream(input_stream, id, input_preference);
(node, id)
});

let output_stream = self.add_node(|id| {
self.log_circuit_event(&CircuitEvent::operator(
GlobalNodeId::child_of(self, id),
receiver.name(),
receiver.location(),
));

let node = SourceNode::new(receiver, self.clone(), id);
let output_stream = node.output_stream();
(node, output_stream)
});

self.add_dependency(sender_id, output_stream.local_node_id());
let sender_id = self.add_sink_with_preference(sender, input_stream, input_preference);
let output_stream = self.add_source(receiver);
self.add_dependency(
sender_id.local_node_id().unwrap(),
output_stream.local_node_id(),
);
output_stream
}

Expand Down
8 changes: 5 additions & 3 deletions crates/dbsp/src/circuit/runtime.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ use crate::SchedulerError;
use crate::circuit::checkpointer::Checkpointer;
use crate::circuit::dbsp_handle::StepSize;
use crate::error::Error as DbspError;
use crate::operator::communication::Exchange;
use crate::operator::communication::{Exchange, ExchangeActivity};
use crate::storage::backend::StorageBackend;
use crate::storage::file::format::Compression;
use crate::storage::file::writer::Parameters;
Expand Down Expand Up @@ -1383,7 +1383,8 @@ where
match Runtime::runtime() {
Some(runtime) if Runtime::num_workers() > 1 => {
let exchange_id = runtime.sequence_next().try_into().unwrap();
let exchange = Exchange::with_runtime(&runtime, exchange_id);
let exchange =
Exchange::with_runtime(&runtime, exchange_id, ExchangeActivity::AllSteps);
let identifier = Arc::new(format!("broadcast {name} (exchange {exchange_id})"));

Self::MultiThreaded {
Expand Down Expand Up @@ -1426,8 +1427,9 @@ where
.await;

exchange
.receive_all(|data| serde_json::from_slice(&data).unwrap())
.receive_all(|data| serde_json::from_slice(&data).unwrap(), None)
.await
.0
})
.await
.ok_or(SchedulerError::Killed)
Expand Down
7 changes: 5 additions & 2 deletions crates/dbsp/src/operator/communication.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,9 @@ mod gather;
mod shard;

pub(crate) use exchange::{
Exchange, ExchangeClients, ExchangeDelivery, ExchangeDirectory, ExchangeId, pop_flushed,
Exchange, ExchangeClients, ExchangeDelivery, ExchangeDirectory, ExchangeId, MessageType,
pop_flushed,
};
pub use exchange::{
ExchangeActivity, ExchangeReceiver, ExchangeSender, Mailbox, new_exchange_operators,
};
pub use exchange::{ExchangeReceiver, ExchangeSender, Mailbox, new_exchange_operators};
Loading
Loading