{"type":"post","id":"ensuring-similar-computational-resources-to-stateful-workloads-running-45481c","slug":"ensuring-similar-computational-resources-to-stateful-workloads-running-45481c","title":"Ensuring Similar Computational Resources to Stateful Workloads Running on a Diverse Server Fleet","description":"**Thesis:** In a heterogeneous fleet, resource allocation becomes more reliable when the scheduler targets normalized compute performance rather than identical core counts.","retrieval_nugget":"**Thesis:** In a heterogeneous fleet, resource allocation becomes more reliable when the scheduler targets normalized compute performance rather than identical core counts.","published_at":"2026-10-14","updated_at":"2026-10-14","record_date":"2026-10-14","date_kind":"published_at","topics":[],"source_urls":["https://www.uber.com/us/en/blog/diverse-server-fleet"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:ensuring-similar-computational-resources-to-stateful-workloads-running-45481c","status":"published","visuals":[],"editorial_provenance":{"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:0b5744445bb937a021ab37df593f6c28a148a7356a5d05d2cabdb9bb4bc4a7c3","reviewed_at":"2026-10-14T08:02:53.104Z","source_evidence_count":1,"verified_claim_count":2,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":2,"implication_count":2,"watch_condition_count":1,"related_record_count":0},"analysis":{"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"In a heterogeneous fleet, resource allocation becomes more reliable when the scheduler targets normalized compute performance rather than identical core counts.","observed_facts":[{"text":"Uber says Odin runs workloads across roughly five million cores, spanning old and new x86 and ARM hosts, with single-core performance varying by nearly a factor of two.","source_urls":["https://www.uber.com/us/en/blog/diverse-server-fleet"]},{"text":"For Kafka, Uber reports that CPU-utilization spread narrowed from eight percentage points to three and allocated cores fell by about 8% during rollout.","source_urls":["https://www.uber.com/us/en/blog/diverse-server-fleet"]}],"mechanism":"Uber assigns host performance factors, converts CPU usage into normalized compute units, computes cluster targets in those units, then translates the targets back into physical cores for the selected host.","why_now":"The company’s mixed on-premises and public-cloud fleet, along with stateful placement constraints, makes raw core counts a poor proxy for comparable capacity; stateless traffic cannot simply be redistributed across equivalent instances.","implications":["For operators with mixed hardware and stateful workloads, a performance-based target can reduce over-allocation on fast hosts while protecting workloads moved to slower hosts.","The case suggests fleet abstraction can preserve hardware choice while normalizing the resource contract above it."],"evidence_boundary":"The figures are Uber’s reported results for its own Odin rollout and Kafka case, not an independent evaluation or a guarantee for other fleet sizes, workload mixes, or cost structures.","watch_conditions":["Whether Uber’s production-derived performance factors remain stable across technologies and workload mixes, and whether the reported allocation and reliability gains persist as rollout expands."],"related_records":[],"new_branch_reason":"No prior New Runtime record is supplied for this specific production case; it merits a distinct record because it reports measured normalization of stateful compute allocation across heterogeneous hosts."},"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/ensuring-similar-computational-resources-to-stateful-workloads-running-45481c/","markdown":"https://newruntime.com/posts/ensuring-similar-computational-resources-to-stateful-workloads-running-45481c.md","json":"https://newruntime.com/posts/ensuring-similar-computational-resources-to-stateful-workloads-running-45481c.json"},"next_reads":[{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}