1. Intent
Flyte
Workflow: rnaseq_workflow
Task: star_align
Execution: rnaseq_workflow-2025-12-30-4521
Project / Domain: bio-prod

Declared resources:
CPUs: 64
Memory: 488 GB
2. Execution (Flyte Task Execution / Kubernetes)
Execution Reality
Flyte task execution: star_align
Plugin: K8sTask
Pod: star-align-4521
Node / instance: r5.16xlarge
Container image: ../biocontainers/star
Duration: 47 min
Flyte scheduled the task using statically declared resource requests. Runtime behavior inside the container was not observable from Flyte task logs or execution metadata.
3. Reality
Observed inside Flyte task execution star_align
Flyte workflow rnaseq_workflow → execution → task star_align
CPU
8%
Memory
18%
Disk I/O
114%
Diagnosis: Task execution is I/O-bound. Increasing CPU or memory in the Flyte task resource spec will not improve runtime.
4. The Fix
Recommended Flyte task resource update for star_align:
Task resources:
CPUs: 8
Memory: 64 GB
Storage: Local NVMe / high-throughput volume
Node / instance: r6id.2xlarge
Plugin: K8sTask (io-optimized node selector)
Scope: Task-level resource spec (workflow semantics unchanged)
This updates the Flyte task's resource specification. Same workflow, same task — ~85% lower compute cost and 3.7× faster runtime.