Skip to content
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

feat(bench): Add sink bench tool #14064

Merged
merged 16 commits into from
Jan 16, 2024
Merged

feat(bench): Add sink bench tool #14064

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
16 commits
Select commit Hold shift + click to select a range
fed8cf9
save
xxhZs Dec 12, 2023
98f3cc5
save
xxhZs Dec 12, 2023
8b717dc
save
xxhZs Dec 12, 2023
61d1968
fmt
xxhZs Dec 19, 2023
fb9457f
fix zip error
xxhZs Dec 20, 2023
e0a6432
Merge branch 'main' into xxh/bench-sink
xxhZs Dec 20, 2023
e04571f
Merge branch 'main' into xxh/bench-sink
xxhZs Dec 20, 2023
232db26
fix merge
xxhZs Dec 20, 2023
c7cc8d5
Merge branch 'main' into xxh/bench-sink
xxhZs Jan 2, 2024
73f543f
save
xxhZs Jan 2, 2024
3fdd3e9
Merge branch 'main' into xxh/bench-sink
xxhZs Jan 4, 2024
aab3160
add mock coordination
xxhZs Jan 4, 2024
7ae1611
Merge branch 'main' into xxh/bench-sink
xxhZs Jan 4, 2024
2c5a9a5
save
xxhZs Jan 11, 2024
0922ba8
use channal instead of lock
xxhZs Jan 16, 2024
223be70
fix
xxhZs Jan 16, 2024
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
5 changes: 5 additions & 0 deletions Cargo.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

10 changes: 10 additions & 0 deletions ...-node/risingwave-sink-cassandra/src/main/java/com/risingwave/connector/CassandraSink.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,8 @@

public class CassandraSink extends SinkWriterBase {
private static final Logger LOG = LoggerFactory.getLogger(CassandraSink.class);
private static final Integer MAX_BATCH_SIZE = 1024 * 16;

private final CqlSession session;
private final List<SinkRow> updateRowCache = new ArrayList<>(1);
private final HashMap<String, PreparedStatement> stmtMap;
Expand Down Expand Up @@ -122,6 +124,7 @@ private void write_append_only(Iterator<SinkRow> rows) {
.withDescription("Unknown operation: " + op)
.asRuntimeException();
}
tryCommit();
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This optimization of cassandra sink can be put in a separate PR and we can paste improvement gained from the optimization in the PR description.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is a bug, fixed in this pr by the way, the exact description has been added to the pr description

}
}

Expand Down Expand Up @@ -155,6 +158,13 @@ private void write_upsert(Iterator<SinkRow> rows) {
.withDescription("Unknown operation: " + op)
.asRuntimeException();
}
tryCommit();
}
}

private void tryCommit() {
if (batchBuilder.getStatementsCount() >= MAX_BATCH_SIZE) {
sync();
}
}

Expand Down
4 changes: 2 additions & 2 deletions java/connector-node/risingwave-sink-es-7/src/main/java/com/risingwave/connector/EsSink.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -268,7 +268,7 @@ public BulkListener(RequestTracker requestTracker) {
/** This method is called just before bulk is executed. */
@Override
public void beforeBulk(long executionId, BulkRequest request) {
LOG.info("Sending bulk of {} actions to Elasticsearch.", request.numberOfActions());
LOG.debug("Sending bulk of {} actions to Elasticsearch.", request.numberOfActions());
}

/** This method is called after bulk execution. */
Expand All @@ -282,7 +282,7 @@ public void afterBulk(long executionId, BulkRequest request, BulkResponse respon
this.requestTracker.addErrResult(errMessage);
} else {
this.requestTracker.addOkResult(request.numberOfActions());
LOG.info("Sent bulk of {} actions to Elasticsearch.", request.numberOfActions());
LOG.debug("Sent bulk of {} actions to Elasticsearch.", request.numberOfActions());
}
}

Expand Down
9 changes: 9 additions & 0 deletions src/bench/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@ bytes = "1"
bytesize = { version = "1", features = ["serde"] }
clap = { version = "4", features = ["derive"] }
futures = { version = "0.3", default-features = false, features = ["alloc"] }
futures-async-stream = { workspace = true }
hdrhistogram = "7"
itertools = "0.12"
libc = "0.2"
Expand All @@ -26,9 +27,13 @@ parking_lot = "0.12"
prometheus = { version = "0.13", features = ["process"] }
rand = "0.8"
risingwave_common = { workspace = true }
risingwave_connector = { workspace = true }
risingwave_pb = { workspace = true }
risingwave_rt = { workspace = true, optional = true }
risingwave_storage = { workspace = true }
risingwave_stream = { workspace = true }
serde = { version = "1", features = ["derive"] }
serde_yaml = "0.9"
tokio = { version = "0.2", package = "madsim-tokio", features = [
"fs",
"rt",
Expand All @@ -53,6 +58,10 @@ nix = { version = "0.27", features = ["fs", "mman"] }
name = "s3-bench"
path = "s3_bench/main.rs"

[[bin]]
name = "sink-bench"
path = "sink_bench/main.rs"

[features]
bpf = ["bcc", "risingwave_storage/bpf"]
trace = ["opentelemetry", "risingwave_rt", "tracing/release_max_level_trace"]
Expand Down
Loading
Loading