[draft] chore(plans): DPDK scope assessment — defer for now#63
Draft
skullcrushercmd wants to merge 1 commit intomainfrom
Draft
[draft] chore(plans): DPDK scope assessment — defer for now#63skullcrushercmd wants to merge 1 commit intomainfrom
skullcrushercmd wants to merge 1 commit intomainfrom
Conversation
Phase 1 scope discovery for perf/portscan-dpdk concluded that adding DPDK to the scanner is a 2-3 week effort on a third-party C repo (Lorikazzzz/VulnScanner-zmap-alternative-) and scope-equivalent to the "STOP and surface" category in the original brief. Deferring in favor of waiting on anygpt-31's AF_XDP + multi-NIC results. If 8x ENI AF_XDP clears the 10-14M pps target, DPDK is shelved indefinitely; if it does not, this branch is the starting point for a revisit. No code changes — memo only. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
skullcrushercmd
added a commit
that referenced
this pull request
Apr 28, 2026
Phase 1 design document for adding a DPDK io_engine to the bundled C scanner (AnyVM-Tech/anyscan-engine-c). Mirrors PR #65's AF_XDP plan structure across §1-§10. Why now: PR #65's AF_XDP work landed but the c6in.metal bench revealed ENA on kernel <=6.12.74 forces drv+copy (not drv+zerocopy), capping the 8-NIC ceiling at ~22 M pps — short of the 30-50 M pps projection. DPDK via vfio-pci bypasses the ENA kernel driver entirely, projecting 50-100 M pps realistic on c6in.metal. This supersedes PR #63's deferral recommendation (which was conditioned on AF_XDP clearing the throughput target — it did not). Plan scope: - engine repo: ~1,100 LOC (send-dpdk.c, recv-dpdk.c, dpdk-eal.c, dpdk-defs.h, vtable slot in engine.c, USE_DPDK Makefile block) - AnyScan-side wire-up: ~765 LOC (mirrors PR #71's ANYSCAN_USE_AF_XDP pattern across install-external-deps.sh / package-worker-bundle.sh / deploy.sh / runtime.worker.env.template / adapter.py + new tools/setup-dpdk.sh for hugepages and vfio-pci bind/unbind) - NIC-binding decision: dedicated-DPDK-NIC pattern. eth0 stays on kernel for agentd heartbeat; ENIs eth1..eth7 (c6in.metal) go to vfio-pci. Single-NIC instances are DPDK-ineligible by design. - Effort: 12-15 days implementation + canary, ~3-4 weeks total. Phase 2 implementation is gated on user/orchestrator approval after this plan PR merges. No engine C code, no runtime config, no submodule bumps in this PR. Co-authored-by: skullcmd <skullcmd@anyvm.tech> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Phase 1 scope-discovery deliverable for the DPDK kernel-bypass investigation tracked under anygpt-32. No implementation. No follow-up PR planned at this time. Memo only, opened as draft so the assessment is discoverable in repo history.
Decision
Defer. The user picked option 1 (wait on anygpt-31's AF_XDP × 8-ENI bench). If their numbers clear the 10–14 M pps target on c6in.metal, DPDK is shelved indefinitely. If they do not, this branch is the starting point for a revisit.
Why this is not getting implemented now
https://github.com/Lorikazzzz/VulnScanner-zmap-alternative-— an external 3,643-LOC C repo, masscan+zmap hybrid, not under AnyVM-Tech control (resolved bypackage-worker-bundle.sh:519-525).USE_PFRING_ZC=1but is commercial/license-keyed and has no documented ENA support, so it doesn't help c6in.metal.send-dpdk.c,recv-dpdk.c, EAL bring-up, ARP/MAC resolution out-of-band, Makefile + CLI flags) plus a fork. Realistic effort: 2–3 weeks. Scope-equivalent to the original brief's "STOP and surface" category even though the language is C, not Rust.What's in this PR
plans/2026-04-27-portscan-dpdk-scope-memo-v1.md— full Phase 1 scope memo: A/B/C classification, effort breakdown, AnyGPT-side surface that would be needed (build target,tools/setup-dpdk.sh, env knobs), coordination with anygpt-31, three forward-path options.Test plan
Disposition
🤖 Generated with Claude Code