Opportunistic Packet Forwarding for Proactive Transport in Datacenters
Bibliographic record
Abstract
Proactive transport protocols in datacenters are designed to avoid congestion by regulating flow sending rates via credit allocation. However, when a new flow starts, it takes one RTT before credits can be assigned to the new flow. To avoid stalling flows, modern proactive protocols such as NDP and Homa allow a new flow to blast a burst of unscheduled packets at line rate during the pre-credit phase. However, sending too many unscheduled packets could cause temporary traffic spikes that lead to queue build-ups, packet losses, and retransmissions, which are particularly detrimental to short flows. In this paper, we present the design and evaluation of Opportunistic Packet Forwarding (OPF), a data-plane building block for proactive transports designed to minimize pre-credit packet losses with negligible overhead on network switches. The key idea in OPF is to allow pre-credit packets to opportunistically take detours to avoid congested links on the shortest paths, effectively trading off packet losses for slightly increased delay. We have implemented OPF using P4 switches and integrated our implementation with both Homa and NDP. Our results on a range of traffic loads show significant improvement in the 99-th percentile of flow completion time for short flows, namely up to 54% reduction in NDP and 50% in Homa.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".