Skip to content

Improve tracking of module errors or panics for prometheus #3663

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

Closed
wants to merge 1 commit into from
Closed

Improve tracking of module errors or panics for prometheus #3663

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
10 changes: 8 additions & 2 deletions crates/core/src/host/wasm_common/module_host_actor.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -576,9 +576,11 @@ impl InstanceCommon {
WORKER_METRICS
.wasm_instance_errors
.with_label_values(
&self.info.database_identity,
&caller_identity,
&self.info.module_hash,
&caller_connection_id,
&false,
procedure_name,
)
.inc();
Expand Down Expand Up @@ -691,6 +693,7 @@ impl InstanceCommon {
&caller_identity,
&Some(caller_connection_id),
reducer_name,
trapped,
)
}
Err(ExecutionError::User(err)) => {
Expand Down Expand Up @@ -772,13 +775,16 @@ impl InstanceCommon {
caller_identity: &Identity,
caller_connection_id: &Option<ConnectionId>,
reducer_name: &str,
trapped: bool,
) -> EventStatus {
WORKER_METRICS
.wasm_instance_errors
.with_label_values(
&self.info.database_identity,
caller_identity,
&self.info.module_hash,
&caller_connection_id.unwrap_or(ConnectionId::ZERO),
&trapped,
reducer_name,
)
.inc();
Expand Down Expand Up @@ -903,13 +909,13 @@ impl InstanceCommon {
let outcome = match (result.call_result, sender) {
(Err(ExecutionError::Recoverable(err) | ExecutionError::Trap(err)), _) => {
inst.log_traceback("view", &view_name, &err);
self.handle_outer_error(&result.stats.energy, &caller, &None, &view_name)
self.handle_outer_error(&result.stats.energy, &caller, &None, &view_name, trapped)
.into()
}
// TODO: maybe do something else with user errors?
(Err(ExecutionError::User(err)), _) => {
inst.log_traceback("view", &view_name, &anyhow::anyhow!(err));
self.handle_outer_error(&result.stats.energy, &caller, &None, &view_name)
self.handle_outer_error(&result.stats.energy, &caller, &None, &view_name, trapped)
.into()
}
// Materialize anonymous view
Expand Down
5 changes: 3 additions & 2 deletions crates/core/src/worker_metrics/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -242,8 +242,9 @@ metrics_group!(
pub reducer_wait_time: HistogramVec,

#[name = spacetime_worker_wasm_instance_errors_total]
#[help = "The number of fatal WASM instance errors, such as reducer panics."]
#[labels(caller_identity: Identity, module_hash: Hash, caller_connection_id: ConnectionId, reducer_symbol: str)]
#[help = "The number of WASM instance errors, such as reducer panics."]
#[labels(database_identity: Identity, caller_identity: Identity, module_hash: Hash, caller_connection_id: ConnectionId, trapped:
bool, reducer_symbol: str)]
pub wasm_instance_errors: IntCounterVec,

#[name = spacetime_worker_wasm_memory_bytes]
Expand Down
Loading