Skip to content

Section 5: redirects, binding durability, ARP responder lifecycle - #35

Closed
remcovanmook wants to merge 3 commits into
host/multihoming-expositionfrom
router/section5-normative
Closed

remcovanmook wants to merge 3 commits into
host/multihoming-expositionfrom
router/section5-normative

Conversation

@remcovanmook

Copy link
Copy Markdown
Owner

The three Section 5 issues, one commit each.

#6 - scope out ICMPv4 redirects

The old sentence offered redirects as the route to host-to-host IPv4 on the segment. They cannot carry the (destination, interface, sentinel) form that next-hop resolution takes here, so on a multi-homed host a redirect is ambiguous, and they are widely filtered or ignored in practice. The text now states plainly that the mechanism does not rely on them, and points multi-router steering at RFC 4191 Default Router Preference - which is per interface and already required for router selection, so nothing new is introduced.

#3 - router-to-host binding durability (new 5.2, normative)

A first-hop router MUST be able, for the lifetime of a host's IPv4 address assignment, to deliver IPv4 traffic to that host's /32 without depending on opportunistically learned neighbor cache state.

The failure mode is spelled out because it is not obvious and it is unrecoverable: if the /32 route derives from a neighbor cache entry learned only as a side effect of traffic, garbage collection of that entry withdraws the route, and the inbound traffic that would provoke re-resolution is then dropped upstream for want of a route. Nothing restores it. The host cannot detect or repair the condition, because it has no way to learn it has become unreachable from outside - an idle host stays unreachable indefinitely.

Mechanisms stay out of the document per the issue. The closing paragraph names the shape of acceptable answers (lease-derived binding, lease-provoked ND, orchestrated distribution, PD anchoring) and defers the catalogue to the companion draft.

#4 - ARP responder is migration machinery (5.4)

The responder read as a permanent property of the router. It is now explicitly operator-controlled and transitional: SHOULD be enabled while unmodified hosts remain, SHOULD be disabled once none do, and a fully migrated segment exchanges no ARP at all, responder included.

The second paragraph records the design position behind the strict host-side MUST NOT rather than leaving it implicit: a sanctioned ARP fallback would make the responder unretirable from any segment, since a conformant host might fall back at any time. That permanently forecloses the zero-ARP end state, in exchange for masking a misconfiguration better surfaced.

Cross-references

Inserting 5.2 renumbers the two subsections after it, so the four hardcoded Section 4 / Section 5.2 / Section 5.3 mentions are converted to anchors. They now resolve automatically and cannot go stale on the next insertion. Verified in the built text.

Closes #6, closes #3, closes #4

🤖 Generated with Claude Code

remcovm and others added 3 commits September 23, 2026 16:36
The redirect sentence offered redirects as the path for
host-to-host IPv4 on the segment. Redirects cannot carry the
(destination, interface, sentinel) form that next-hop resolution
takes here, so on a multi-homed host the result is ambiguous,
and they are widely filtered or ignored in practice.

State plainly that the mechanism does not rely on redirects, and
point multi-router steering at RFC 4191 Default Router
Preference, which is per interface and is already required for
router selection.

Closes #6

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Add one normative requirement: for the lifetime of a host's IPv4
assignment, the first-hop router MUST be able to deliver to that
host's /32 without depending on opportunistically learned
neighbor cache state.

This prohibits a specific unrecoverable failure. Where the /32
route is derived from a neighbor cache entry learned only as a
side effect of traffic, garbage collection of that entry
withdraws the route; the inbound traffic that would provoke
re-resolution is then discarded upstream for want of a route,
so nothing restores it. The host cannot detect or repair this,
because it has no way to learn it has become unreachable from
outside.

Mechanisms stay out of this document. The paragraph names the
shape of the acceptable answers (lease-derived bindings,
lease-provoked ND, orchestrated distribution, PD anchoring) and
defers the catalogue to a separate document.

Existing cross-references to Sections 4, 5.2 and 5.3 converted
to anchors so the inserted subsection cannot stale them.

Closes #3

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
The responder read as a permanent property of the router. State
that it is operator-controlled and transitional: SHOULD be
enabled while unmodified hosts remain on the segment, SHOULD be
disabled once none do, and a fully migrated segment exchanges no
ARP at all, responder included.

Record the design position behind the strict host-side MUST NOT
while it is being decided rather than after: a sanctioned ARP
fallback would make the responder unretirable from any segment,
because a conformant host might fall back at any time. That
would permanently foreclose the zero-ARP end state in return for
masking a misconfiguration better surfaced.

Closes #4

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
@remcovanmook

remcovanmook commented Sep 23, 2026 •

Copy link
Copy Markdown
Owner Author

Superseded by #42.

@remcovanmook
remcovanmook deleted the router/section5-normative branch September 23, 2026 15:07
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants