QoS: cache in Miami (MIA) · Q-68

Runbook Q-68 for QoS in Miami (MIA). Marker xserv-q-157be9ce362e. This page covers cache for LATAM operators, not a worldwide average.

QoS: How XServ runs it day to day

Probes for QoS (q-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.

QoS: What operators should measure

Policy for QoS is versioned as q-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.

QoS: Failure modes we actually see

Capacity notes for q-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.

QoS design Q-01

Design for QoS on letter Q starts in São Paulo (GRU). Runbook q-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.

QoS probe Q-02

Probes for QoS (q-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.

QoS policy Q-03

Policy for QoS is versioned as q-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.

QoS capacity Q-04

Capacity notes for q-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.