teleo-codex/inbox/archive/2021-09-00-vlahakis-aimd-scheduling-distributed-computing.md

type	title	author	url	date	domain	format	status	tags	processed_by	processed_date	claims_extracted	extraction_model	extraction_notes
source	AIMD Scheduling and Resource Allocation in Distributed Computing Systems	Vlahakis, Athanasopoulos et al.	https://arxiv.org/abs/2109.02589	2021-09-06	internet-finance	paper	processed	pipeline-architecture operations-research AIMD distributed-computing resource-allocation congestion-control	rio	2026-03-11	aimd-congestion-control-generalizes-to-distributed-resource-allocation-because-matching-producer-rate-to-consumer-capacity-is-structurally-identical-across-networks-and-compute-pipelines.md aimd-scaling-policy-eliminates-load-prediction-requirements-by-reacting-to-observed-queue-state-through-additive-increase-when-stable-and-multiplicative-decrease-when-congested.md	anthropic/claude-sonnet-4.5	Extracted two mechanism design claims about AIMD generalization from network congestion control to distributed computing resource allocation. The paper provides formal proofs of stability and convergence properties. Key insight is that producer-consumer rate matching is the same coordination problem across domains. Relevance to Teleo pipeline architecture noted in source but claims focus on the general mechanism properties rather than specific application.

AIMD Scheduling and Resource Allocation in Distributed Computing Systems

Applies TCP's AIMD (Additive Increase Multiplicative Decrease) congestion control to distributed computing resource allocation — scheduling incoming requests across computing nodes.

Key Content

• Models distributed system as multi-queue scheme with computing nodes
• Proposes AIMD-like admission control: stable irrespective of total node count and AIMD parameters
• Key insight: congestion control in networks and worker scaling in compute pipelines are the same problem — matching producer rate to consumer capacity
• Decentralized resource allocation using nonlinear state feedback achieves global convergence to bounded set in finite time
• Connects to QoS via Little's Law: local queuing time calculable from simple formula
• AIMD is proven optimal for fair allocation of shared resources among competing agents without centralized control

Relevance to Teleo Pipeline

AIMD provides an elegant scaling policy: when queue is shrinking (system healthy), add workers linearly (e.g., +1 per cycle). When queue is growing (system overloaded), cut workers multiplicatively (e.g., halve them). This is self-correcting, proven stable, and doesn't require predicting load — it reacts to observed queue state.

The TCP analogy is precise: our pipeline "bandwidth" is eval throughput. When extract produces faster than eval can consume, we need backpressure (slow extraction) or scale-up (more eval workers). AIMD handles this naturally.

Key Facts

• AIMD achieves stable resource allocation irrespective of total node count and AIMD parameters (Vlahakis et al. 2021)
• Decentralized resource allocation using nonlinear state feedback achieves global convergence to bounded set in finite time
• Little's Law enables local queuing time calculation from AIMD parameters