enhancement(core): add support for spawning supervisors on a dedicated runtime

[tobz]

Summary

This PR adds support to the runtime system to configure/spawn supervisors on a dedicated asynchronous runtime.

As part of the goal to supervisor-ify the various tasks that compromise the control plane and data plane functionality of ADP, a major consideration is that we spawn various tasks on dedicated runtimes: we have a dedicated control plane runtime, internal observability runtime, the main multi-threaded runtime where the topology runs, and then the dedicated multi-threaded runtime we use for compute-heavy tasks. Supervisor was designed with nesting in mind, but everything assumed that we'd spawn tasks on the exact same runtime across the entire supervision tree... which doesn't align with our needs in practice.

This PR adds support for customizing a Supervisor to specify what runtime it should execute on: the ambient runtime (wherever its run from at that moment), or a dedicated runtime. When using a dedicated runtime, we can configure whether or not a single-threaded or multi-threaded runtime is created behind the scenes. A dedicated background OS thread is spawned in either case to drive the supervisor to completion, with the difference being that for single-threaded runtimes, all work happens on that thread, while multi-threaded runtimes have a pool of dedicated worker threads where all meaningful task execution occurs.

Change Type

• Bug fix
• New feature
• Non-functional (chore, refactoring, docs)
• Performance

How did you test this PR?

Existing unit tests.

References

AGTMETRICS-393

[tobz]

• enhancement(api): add dynamic API router based on runtime state #1179
• enhancement(runtime): add resource/pubsub registry for generalized state management in processes #1178
• chore(agent-data-plane): initialize TLS early on before spawning supervisor #1177
• chore(agent-data-plane): update health registry worker to allow being restarted #1176
• chore(agent-data-plane): move internal observability/control plane to supervisor scheme #1148
• enhancement(core): make initialization async in Supervisable #1146
• enhancement(core): add support for spawning supervisors on a dedicated runtime #1145 👈 (View in Graphite)
• main

This stack of pull requests is managed by Graphite. Learn more about stacking.

[pr-commenter]

Binary Size Analysis (Agent Data Plane)

Target: 9fe09ef (baseline) vs 694d69e (comparison) diff
Analysis Type: Stripped binaries (debug symbols excluded)
Baseline Size: 26.96 MiB
Comparison Size: 26.98 MiB
Size Change: +25.34 KiB (+0.09%)
Pass/Fail Threshold: +5%
Result: PASSED ✅

Changes by Module

Module	File Size	Symbols
tokio	+19.15 KiB	2709
core	+6.78 KiB	11100
[Unmapped]	-2.59 KiB	1
alloc	+1.88 KiB	1216
[sections]	+1.09 KiB	7
saluki_env::workload::helpers	-698 B	60
std	+386 B	285
saluki_app::api::APIBuilder	+370 B	4
saluki_common::task::instrument	-361 B	86
agent_data_plane::cli::dogstatsd	-301 B	34
agent_data_plane::cli::debug	+301 B	92
agent_data_plane::internal::remote_agent	-244 B	62
miniz_oxide	-227 B	1
futures_util	-208 B	86
tonic	-161 B	356
saluki_components::common::datadog	+160 B	326
tokio_util	-158 B	38
hyper	+130 B	594
saluki_components::forwarders::otlp	+120 B	60
agent_data_plane::main	-120 B	2

Detailed Symbol Changes

    FILE SIZE        VM SIZE    
 --------------  -------------- 
  [NEW] +1.79Mi  [NEW] +1.79Mi    std::thread::local::LocalKey<T>::with::h938f6ddf7aedbbb8
  [NEW]  +113Ki  [NEW]  +113Ki    agent_data_plane::cli::run::create_topology::_{{closure}}::hfb0b645d0bb8c8cf
  [NEW] +84.5Ki  [NEW] +84.4Ki    agent_data_plane::internal::control_plane::spawn_control_plane::_{{closure}}::h6a61f8e463394a17
  [NEW] +68.2Ki  [NEW] +68.1Ki    h2::hpack::decoder::Decoder::try_decode_string::hd1c9a39c48e78a6e
  [NEW] +63.7Ki  [NEW] +63.6Ki    saluki_components::common::datadog::io::run_endpoint_io_loop::_{{closure}}::hd35493454b2aefa0
  [NEW] +62.3Ki  [NEW] +62.2Ki    agent_data_plane::main::_{{closure}}::hd35953e90113f5c5
  [NEW] +57.8Ki  [NEW] +57.7Ki    agent_data_plane::cli::run::handle_run_command::_{{closure}}::hb1b79147c6e6e2ef
  [NEW] +48.8Ki  [NEW] +48.7Ki    saluki_app::bootstrap::AppBootstrapper::bootstrap::_{{closure}}::hc8e634acdf97ad33
  [NEW] +47.7Ki  [NEW] +47.6Ki    moka::sync::base_cache::Inner<K,V,S>::do_run_pending_tasks::h0ef6755dbc77ea2a
  [NEW] +46.1Ki  [NEW] +46.0Ki    h2::proto::connection::Connection<T,P,B>::poll::h1671860da0918c66
  +0.2% +26.0Ki  +0.2% +23.3Ki    [29572 Others]
  [DEL] -46.1Ki  [DEL] -46.0Ki    h2::proto::connection::Connection<T,P,B>::poll::h2aedcbe1089b311c
  [DEL] -47.7Ki  [DEL] -47.6Ki    moka::sync::base_cache::Inner<K,V,S>::do_run_pending_tasks::ha97a2f55834f17a3
  [DEL] -48.8Ki  [DEL] -48.7Ki    saluki_app::bootstrap::AppBootstrapper::bootstrap::_{{closure}}::hbb5d0d8e944d3a21
  [DEL] -57.8Ki  [DEL] -57.7Ki    agent_data_plane::cli::run::handle_run_command::_{{closure}}::hd8d13580d16cc8a3
  [DEL] -62.3Ki  [DEL] -62.2Ki    agent_data_plane::main::_{{closure}}::h1c7c640002ce8ad1
  [DEL] -63.8Ki  [DEL] -63.6Ki    saluki_components::common::datadog::io::run_endpoint_io_loop::_{{closure}}::hc194831d658db8cc
  [DEL] -68.2Ki  [DEL] -68.1Ki    h2::hpack::decoder::Decoder::try_decode_string::hbfc0bb5a77e7669f
  [DEL] -84.5Ki  [DEL] -84.4Ki    agent_data_plane::internal::control_plane::spawn_control_plane::_{{closure}}::heace61ab0f2bde0c
  [DEL]  -113Ki  [DEL]  -113Ki    agent_data_plane::cli::run::create_topology::_{{closure}}::h6a8b41fa76a89e2c
  [DEL] -1.79Mi  [DEL] -1.79Mi    std::thread::local::LocalKey<T>::with::h0d8770940d38805b
  +0.1% +25.3Ki  +0.1% +22.6Ki    TOTAL

[pr-commenter]

Regression Detector (Agent Data Plane)

Regression Detector Results

Run ID: 50fbb559-f4d7-4cc6-9f12-9a57fdfcd067

Baseline: 9fe09ef
Comparison: 694d69e
Diff

❌ Experiments with retried target crashes

This is a critical error. One or more replicates failed with a non-zero exit code. These replicates may have been retried. See Replicate Execution Details for more information.

• otlp_ingest_logs_5mb_throughput
• quality_gates_rss_dsd_medium
• otlp_ingest_metrics_5mb_memory
• otlp_ingest_traces_5mb_memory
• dsd_uds_100mb_3k_contexts_cpu

Optimization Goals: ✅ Improvement(s) detected

perf	experiment	goal	Δ mean %	Δ mean % CI	trials	links
✅	otlp_ingest_metrics_5mb_memory	memory utilization	-5.63	[-5.87, -5.40]	1	(metrics) (profiles) (logs)

Experiments ignored for regressions

Regressions in experiments with settings containing erratic: true are ignored.

perf	experiment	goal	Δ mean %	Δ mean % CI	trials	links
➖	otlp_ingest_logs_5mb_memory	memory utilization	+2.09	[+1.51, +2.67]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_logs_5mb_throughput	ingress throughput	+0.00	[-0.13, +0.13]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_logs_5mb_cpu	% cpu utilization	-1.20	[-6.29, +3.88]	1	(metrics) (profiles) (logs)

Fine details of change detection per experiment

perf	experiment	goal	Δ mean %	Δ mean % CI	trials	links
➖	dsd_uds_512kb_3k_contexts_cpu	% cpu utilization	+9.82	[-49.12, +68.76]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_traces_5mb_cpu	% cpu utilization	+2.84	[+0.21, +5.48]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_logs_5mb_memory	memory utilization	+2.09	[+1.51, +2.67]	1	(metrics) (profiles) (logs)
➖	dsd_uds_100mb_3k_contexts_memory	memory utilization	+1.29	[+1.09, +1.49]	1	(metrics) (profiles) (logs)
➖	dsd_uds_500mb_3k_contexts_memory	memory utilization	+0.98	[+0.80, +1.16]	1	(metrics) (profiles) (logs)
➖	dsd_uds_500mb_3k_contexts_throughput	ingress throughput	+0.94	[+0.81, +1.07]	1	(metrics) (profiles) (logs)
➖	quality_gates_rss_idle	memory utilization	+0.82	[+0.76, +0.88]	1	(metrics) (profiles) (logs)
➖	quality_gates_rss_dsd_medium	memory utilization	+0.56	[+0.37, +0.76]	1	(metrics) (profiles) (logs)
➖	dsd_uds_512kb_3k_contexts_memory	memory utilization	+0.48	[+0.30, +0.66]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_traces_5mb_memory	memory utilization	+0.43	[+0.19, +0.68]	1	(metrics) (profiles) (logs)
➖	quality_gates_rss_dsd_heavy	memory utilization	+0.29	[+0.17, +0.41]	1	(metrics) (profiles) (logs)
➖	quality_gates_rss_dsd_ultraheavy	memory utilization	+0.29	[+0.16, +0.42]	1	(metrics) (profiles) (logs)
➖	quality_gates_rss_dsd_low	memory utilization	+0.19	[+0.02, +0.37]	1	(metrics) (profiles) (logs)
➖	dsd_uds_10mb_3k_contexts_memory	memory utilization	+0.14	[-0.06, +0.34]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_metrics_5mb_throughput	ingress throughput	+0.02	[-0.11, +0.14]	1	(metrics) (profiles) (logs)
➖	dsd_uds_100mb_3k_contexts_throughput	ingress throughput	+0.01	[-0.03, +0.05]	1	(metrics) (profiles) (logs)
➖	dsd_uds_1mb_3k_contexts_throughput	ingress throughput	+0.00	[-0.05, +0.06]	1	(metrics) (profiles) (logs)
➖	dsd_uds_512kb_3k_contexts_throughput	ingress throughput	+0.00	[-0.05, +0.06]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_logs_5mb_throughput	ingress throughput	+0.00	[-0.13, +0.13]	1	(metrics) (profiles) (logs)
➖	dsd_uds_10mb_3k_contexts_throughput	ingress throughput	-0.00	[-0.16, +0.15]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_traces_5mb_throughput	ingress throughput	-0.01	[-0.09, +0.07]	1	(metrics) (profiles) (logs)
➖	dsd_uds_1mb_3k_contexts_memory	memory utilization	-0.33	[-0.52, -0.15]	1	(metrics) (profiles) (logs)
➖	dsd_uds_100mb_3k_contexts_cpu	% cpu utilization	-0.60	[-6.45, +5.25]	1	(metrics) (profiles) (logs)
➖	dsd_uds_10mb_3k_contexts_cpu	% cpu utilization	-0.78	[-29.49, +27.94]	1	(metrics) (profiles) (logs)
➖	dsd_uds_500mb_3k_contexts_cpu	% cpu utilization	-1.17	[-2.45, +0.11]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_logs_5mb_cpu	% cpu utilization	-1.20	[-6.29, +3.88]	1	(metrics) (profiles) (logs)
➖	otlp_ingest_metrics_5mb_cpu	% cpu utilization	-1.72	[-7.64, +4.19]	1	(metrics) (profiles) (logs)
✅	otlp_ingest_metrics_5mb_memory	memory utilization	-5.63	[-5.87, -5.40]	1	(metrics) (profiles) (logs)
➖	dsd_uds_1mb_3k_contexts_cpu	% cpu utilization	-8.64	[-58.91, +41.63]	1	(metrics) (profiles) (logs)

Bounds Checks: ✅ Passed

perf	experiment	bounds_check_name	replicates_passed	links
✅	quality_gates_rss_dsd_heavy	memory_usage	10/10	(metrics) (profiles) (logs)
✅	quality_gates_rss_dsd_low	memory_usage	10/10	(metrics) (profiles) (logs)
✅	quality_gates_rss_dsd_medium	memory_usage	10/10	(metrics) (profiles) (logs)
✅	quality_gates_rss_dsd_ultraheavy	memory_usage	10/10	(metrics) (profiles) (logs)
✅	quality_gates_rss_idle	memory_usage	10/10	(metrics) (profiles) (logs)

Explanation

Confidence level: 90.00%
Effect size tolerance: |Δ mean %| ≥ 5.00%

Performance changes are noted in the perf column of each table:

• ✅ = significantly better comparison variant performance
• ❌ = significantly worse comparison variant performance
• ➖ = no significant change in performance

A regression test is an A/B test of target performance in a repeatable rig, where "performance" is measured as "comparison variant minus baseline variant" for an optimization goal (e.g., ingress throughput). Due to intrinsic variability in measuring that goal, we can only estimate its mean value for each experiment; we report uncertainty in that value as a 90.00% confidence interval denoted "Δ mean % CI".

For each experiment, we decide whether a change in performance is a "regression" -- a change worth investigating further -- if all of the following criteria are true:

1. Its estimated |Δ mean %| ≥ 5.00%, indicating the change is big enough to merit a closer look.

2. Its 90.00% confidence interval "Δ mean % CI" does not contain zero, indicating that if our statistical model is accurate, there is at least a 90.00% chance there is a difference in performance between baseline and comparison variants.

3. Its configuration does not mark it "erratic".

Replicate Execution Details

We run multiple replicates for each experiment/variant. However, we allow replicates to be automatically retried if there are any failures, up to 8 times, at which point the replicate is marked dead and we are unable to run analysis for the entire experiment. We call each of these attempts at running replicates a replicate execution. This section lists all replicate executions that failed due to the target crashing or being oom killed.

Note: In the below tables we bucket failures by experiment, variant, and failure type. For each of these buckets we list out the replicate indexes that failed with an annotation signifying how many times said replicate failed with the given failure mode. In the below example the baseline variant of the experiment named experiment_with_failures had two replicates that failed by oom kills. Replicate 0, which failed 8 executions, and replicate 1 which failed 6 executions, all with the same failure mode.

Experiment	Variant	Replicates	Failure	Logs	Debug Dashboard
experiment_with_failures	baseline	0 (x8) 1 (x6)	Oom killed		Debug Dashboard

The debug dashboard links will take you to a debugging dashboard specifically designed to investigate replicate execution failures.

❌ Retried Normal Replicate Execution Failures (non-profiling)

Experiment	Variant	Replicates	Failure	Debug Dashboard
dsd_uds_100mb_3k_contexts_cpu	comparison	6	Failed to shutdown when requested	Debug Dashboard
otlp_ingest_logs_5mb_throughput	baseline	8	Failed to shutdown when requested	Debug Dashboard
otlp_ingest_metrics_5mb_memory	comparison	4	Failed to shutdown when requested	Debug Dashboard
otlp_ingest_traces_5mb_memory	comparison	3	Failed to shutdown when requested	Debug Dashboard
quality_gates_rss_dsd_medium	comparison	0	Failed to shutdown when requested	Debug Dashboard

[Copilot]

Pull request overview

This PR enhances the supervisor runtime system to support spawning supervisors on dedicated asynchronous runtimes, enabling runtime isolation for different components of the control and data planes.

Changes:

• Added RuntimeMode enum to control whether supervisors run on ambient or dedicated runtimes
• Implemented RuntimeConfiguration for configuring single-threaded or multi-threaded dedicated runtimes
• Extended Supervisor API with methods to configure dedicated runtime execution

Reviewed changes

Copilot reviewed 4 out of 5 changed files in this pull request and generated 1 comment.

File	Description
lib/saluki-core/src/runtime/supervisor.rs	Added runtime mode field and methods to support dedicated runtime configuration and execution
lib/saluki-core/src/runtime/mod.rs	Exported new RuntimeConfiguration and RuntimeMode types
lib/saluki-core/src/runtime/dedicated.rs	Implemented dedicated runtime spawning logic with OS thread management and initialization handling
Cargo.toml	Updated tokio version to 1.49 to support new runtime features

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.