SLA: cache in Miami (MIA) · S-80

Runbook S-80 for SLA in Miami (MIA). Marker xserv-s-1edd362610a5. This page covers cache for LATAM operators, not a worldwide average.

SLA: How XServ runs it day to day

Probes for SLA (s-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.

SLA: What operators should measure

Policy for SLA is versioned as s-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.

SLA: Failure modes we actually see

Capacity notes for s-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.

SLA design S-01

Design for SLA on letter S starts in São Paulo (GRU). Runbook s-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.

SLA probe S-02

Probes for SLA (s-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.

SLA policy S-03

Policy for SLA is versioned as s-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.

SLA capacity S-04

Capacity notes for s-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.