Where is WAN measured first?

From Santiago (SCL) toward Bogotá. A global average is not an SLO for letter W.

How fast is rollback for w-03?

The runbook is a command plus a named owner. There is no wait for a weekly change freeze.

WAN: probes in Santiago (SCL) · W-50

Runbook W-50 for WAN in Santiago (SCL). Marker xserv-w-d0e7cae3b42e. This page covers probes for LATAM operators, not a worldwide average.

WAN: How XServ runs it day to day

Probes for WAN (w-02) leave Santiago every 15s toward Bogotá. XServ pages the named owner if loss or RTT crosses the letter budget. A probe never shares a queue with bulk transfers, so a saturated WAN does not hide a dead PoP.

WAN: What operators should measure

Policy for WAN is versioned as w-03. Operators measure error rate, p95 from Bogotá, and time-to-rollback — not a worldwide average. Changes land in Bogotá first, then Miami, with a hold if either region regresses.

WAN: Failure modes we actually see

Capacity notes for w-04 assume rainy-season power in Miami and festival peaks toward São Paulo. The failure we actually see is a single uplink, not a cartoon partition of the whole continent. Spare ports and a second provider sit on the same runbook.

WAN timeouts W-10

Timeouts on w-10 are tighter than the WAN RTT to Bogotá. WAN in Santiago fails fast and retries once; a third try needs a human because it is no longer a blip.

WAN regions W-11

Region names on w-11 match DNS and tickets: Bogotá / BOG, with Miami as the documented pair. WAN dashboards never say “LATAM” as if it were one RTT.

WAN docs W-12

Public docs for letter W stay aligned with identifier xserv-w-pack. Page w-12 is the WAN slice operators search before the homepage. Edits in Miami show up in São Paulo on the next publish.

WAN design W-01

Design for WAN on letter W starts in São Paulo (GRU). Runbook w-01 keeps a single owner, a written rollback, and a traffic split that can be reversed without a global freeze. Neighbors in Santiago only take overflow after the local pool fails a health window.