# Real-time monitoring built for messaging, not adapted to it. - Canonical URL: https://www.broadnet.me/platforms/performance-system - Language: en - Last updated: 2026-09-24 - Publisher: BroadNet (https://www.broadnet.me) - Markdown version of the page above, generated from the rendered page. Performance System · Real-time NOC Unified, real-time visibility across SMS, voice, platforms and infrastructure. Raw counters, CDRs and platform telemetry become live KPIs, threshold alerts and SLA reports — purpose-built for the NOC, not borrowed from a generic APM. [Talk to operations](https://www.broadnet.me/contact) [Request technical spec](https://www.broadnet.me/contact) MNO-grade security GSMA Associate Member Carrier-grade availability ![The BroadNet snow leopard watching a wall of live performance graphs with one anomaly highlighted](https://www.broadnet.me/marketing/art/pf-performance.webp) BroadNet · performance Network performance 99.99% uptime 300M+ events / day 1,000+ operator connections Platform uptime 99.99% Carrier-grade availability for the monitors that watch every other system Refresh window <60s Live KPIs computed from counters, CDRs and platform telemetry in near real-time KPIs out of box 30+ Service, platform and infrastructure metrics tuned for messaging operations NOC operations 24/7 Operated by the same team that runs BroadNet's own messaging network NOC monitoring console ## The wallboard your on-call team lives in. Live KPIs, an alert feed that respects severity, and per-tenant health in one pane — purpose-built for messaging operations. Below is an illustrative snapshot built from sample data. broadnet · noc overview Example B BroadNet Overview Alerts Tenants SLA Logs ### Operations overview last 60 min Events / sec 48,210 Alert latency 3.4s Active tenants 37 Error rate 0.12% Throughput events / sec · last 60 min now Tenant health delivery rate by tenant Northwind Retail 96.1% Atlas Bank OTP 99.4% Gulf Aggregator 98.9% Sahara Telecom 97.2% Meridian Alerts 99.1% Alerts most recent first | 09:12:04 | route ZA-MTN | DLR dipped to 88.4% | Warning | |---|---|---|---| | 09:11:52 | api-gw-3 | p95 latency 512 ms | Major | | 09:10:31 | SS7 firewall | 3 blocked SRI-SM | Info | | 09:08:15 | smsc-node-2 | queue depth 12,480 | Warning | | 09:05:03 | tenant Northwind | SLA credit threshold | Critical | Illustrative example — sample data, not an audited SLA or a live feed. Capabilities ## Everything a NOC team needs to run a messaging platform at scale. Six capabilities, one platform. Real-time KPIs, alerts that fire on the right thresholds, SLA tracking your customers can verify, and integration paths that respect the tooling you already operate. ### Real-time KPIs Service, platform and infrastructure metrics in a single pane. SMS success, DLR ratio, queue depth, API response times, host utilisation — all kept fresh to the sub-minute. Service SMS · DLR Platform API · errors Infra CPU · RAM ### Threshold-based alerts Static thresholds per KPI with warning, major and critical severities. Per-customer and per-route rules. A custom DSL covers conditions the defaults don't. Severities 3 tiers Scope Per route DSL Yes ### SLA monitoring Compliance tracking for the SLAs you signed and the ones you owe. Management reports, partner reports, and customer-facing dashboards with public status if needed. Internal Tracked External Reported Status pages Optional ### NOC tool integration Webhook delivery to ticketing platforms. SNMP v2 and v3 supported. Slots cleanly alongside ManageEngine and other NMS rather than asking you to replace them. SNMP v2 · v3 Webhooks Native NMS Coexists ### Multi-tenant sharing Role-based access scoped per dashboard. Selected views can be shared with operators, partners or enterprise customers. Public status pages available per service. Access RBAC Sharing Per dash Tenants Isolated ### Workflow integration Built around how NOC teams actually work. Alerts arrive with context — related metrics, recent changes, similar incidents. Escalation paths and audit trail included. Context Auto Escalation Tiered Audit Logged Capability matrix ## Every metric, its source, and who gets to see it. Performance System ships with more than thirty KPIs across eight capability groups. Each one is computed from a defined source, evaluated against thresholds or an SLA band, and scoped to the audience that needs it — internal NOC, commercial, partner or customer. | Capability | What it measures | Primary sources | Alerting | Shared with | |---|---|---|---|---| | Service KPIs | SMS success %, DLR ratio, submit-to-deliver latency | SMSC, A2P platform, CDRs | Threshold + SLA | NOC · partners | | Platform KPIs | API response time, error rate, throughput (msg/sec) | Gateway, API layer, app logs | Threshold | NOC | | Infrastructure | CPU, RAM, disk and network per host | Host agents, SNMP v2/v3 | Threshold | NOC | | Queue health | Queue depth, retry backlog, spool age | SMSC counters | Threshold | NOC | | Security counters | Blocked messages, SS7 anomalies, sender-ID violations | SMS Firewall, SS7 Firewall | Threshold + event | NOC · risk | | Route quality | Per-route DLR, conversion, cost anomalies | CDRs, route configuration | Threshold | Commercial | | SLA compliance | Uptime, delivery-SLA band, credit exposure | Aggregated KPI store | SLA report | Customers · partners | | Business KPIs | Volume trend, revenue-affecting drops, top movers | CDRs, billing feed | Report | Management | 30+ KPIs · 8 capability groups · per-tenant scoping How it works ## From raw counter to on-call alert in under a minute. The pipeline is deliberately simple to reason about. Sources emit counters, CDRs and telemetry. Collectors pull them on their native protocol. The metrics engine normalises and computes KPIs on a sub-minute window. The surface layer renders live dashboards and evaluates thresholds, then fans results out to the tools your NOC already lives in. 01 · Sources Data sources - SMSCs & gateways - SMS / SS7 firewalls - Hosts & probes - CDRs & billing 02 · Collectors Collectors - SNMP v2/v3 polls - Webhook ingest - DB & counter reads - Log tail 03 · Engine Metrics engine - Normalise & de-dup - Compute KPIs - Roll-ups & baselines - <60s window 04 · Surface Dashboards & alerts - Live NOC panes - Threshold engine - SLA tracking - Status pages 05 · Delivery Downstream - Ticketing webhooks - Email & SMS - Wallboards - Partner reports counters → collectors → metrics engine → dashboards → alerts Monitoring & alerting ## Three categories of alert, one operational truth. Static thresholds for the easy calls. SLA tracking for the contractual ones. Notification and display so the wallboard, the ticket and the inbox all agree. 01 ### Threshold-based Static thresholds defined per critical KPI. Multi-level severity classifies alerts the moment they fire so on-call sees what matters first. warning · major · critical 02 ### SLA compliance Continuous tracking of internal and external SLAs. Monthly partner and management reports. Credit-calculation evidence kept on file. internal + external 03 ### Notification & display Delivered to NOC tooling, ticketing systems, email and SMS. On-screen indicators light up live dashboards so the wallboard tells the same story as the inbox. wallboard · ticketing · email Worked example ## A DLR dip on one route, start to finish. Thresholds are defined per KPI and per route with three severities. Here is exactly what happens when delivery quality slips on a single destination — the same lifecycle every alert follows. | Severity | Band | Response | Escalation | |---|---|---|---| | Healthy | DLR ≥ 90% | No alert | — | | Warning | DLR < 90% | Amber tile · webhook | On-call notified | | Major | DLR < 85% | Ticket auto-raised | Team lead paged | | Critical | DLR < 80% | Page + escalation | Duty manager paged | Bands are illustrative. Every threshold, severity and escalation path is configured per customer, per route and per KPI. 1. 1 t+0s Ingest The metrics engine computes DLR ratio for route ZA-MTN from the last 60 minutes of CDRs. Value: 88.4%. 2. 2 t+3s Evaluate 88.4% crosses the warning threshold (< 90%). The route is still above the major band (85%), so severity is set to warning. 3. 3 t+4s Notify A webhook fires to the ticketing platform, an SMS reaches the on-call engineer, and the wallboard tile for ZA-MTN turns amber. 4. 4 t+4s Context The alert carries the 60-minute DLR trend, any recent route or config changes, and links to similar past incidents. 5. 5 t+9m Resolve Throughput normalises, DLR recovers to 98.1%, the alert auto-closes, and the full lifecycle is written to the signed audit trail. Who it's for ## Built for the teams that own uptime. ### MNO & carrier NOC teams Run the messaging layer beside your existing NMS. Service, platform and security KPIs in one pane, with alerts that respect on-call rotations. ### A2P aggregators Watch per-route DLR, conversion and cost anomalies in real time, and expose partner-facing SLAs without building a reporting stack from scratch. ### Enterprise messaging ops Monitor the delivery quality behind OTP, alerts and campaigns, with customer-facing status pages that make your SLA verifiable. ### Managed-service customers Let BroadNet's NOC operate the monitoring layer for you, escalating only what needs a human — the same team that runs our own network. Integration points ## Reads from everything that matters. Writes to the tools you already use. Performance System complements your existing infrastructure monitoring. Operators typically run their NMS for hosts and add Performance System for the messaging layer — service KPIs, business KPIs, partner-facing SLAs. SNMP v2/v3 · webhooks · custom APIs ### SMSCs & gateways BroadNet SMSC Gateway, third-party SMSC performance counters, A2P platform telemetry. ### Firewalls SMS Firewall, SS7 Firewall, sender-ID registries — KPI feeds and security counters. ### Infrastructure Host metrics for CPU, RAM, disk and network. Operator and partner connectivity probes. ### NOC & ticketing ManageEngine and existing NMS. Generic SNMP v2/v3. Webhooks to any HTTP endpoint. Trust & governance ## Operated to the standard the network expects. The same governance that protects BroadNet's own messaging platform applies to the monitoring layer that watches it. Audit trails, role-based access, residency on request. Carrier-grade SLA Designed for 24/7 operations at MNO scale GSMA Associate Member Aligned with industry-wide messaging guidelines Audit trail Every operational action logged with retention controls Role-based access Per-tenant data isolation and per-user visibility FAQ ## Questions NOC leads ask first. **What data sources can Performance System monitor?** SMSCs and gateways, SMS and SS7 firewalls, host infrastructure, CDRs and billing feeds, and any endpoint reachable over SNMP v2/v3 or a webhook. It reads the BroadNet SMSC Gateway natively and connects to third-party platforms through their performance counters and APIs. **How fresh are the KPIs?** Live KPIs are computed from counters, CDRs and platform telemetry on a sub-minute window — typically refreshed inside 60 seconds. Longer-horizon roll-ups and baselines are retained for trend analysis and SLA reporting. **How do threshold alerts work?** Every critical KPI carries static thresholds with warning, major and critical severities, scoped per customer and per route. A custom DSL covers conditions the defaults don't. Alerts fire the moment a value crosses a band and carry context — the recent trend, related changes and similar past incidents. **Does it replace our existing NMS?** No — it complements it. Operators typically keep their NMS for hosts and add Performance System for the messaging layer: service KPIs, business KPIs and partner-facing SLAs. It coexists with ManageEngine and other tools rather than asking you to rip them out. **Can we share dashboards with customers or partners?** Yes. Access is role-based and scoped per dashboard, so selected views can be shared with operators, partners or enterprise customers. Public status pages are available per service where you want customers to verify uptime themselves. **How is access controlled and audited?** Role-based access with per-tenant data isolation governs who sees what. Every operational action is written to a signed audit trail with retention controls, and data residency is available on request — the same governance that protects BroadNet's own messaging platform. **What SLAs can it track?** Both the SLAs you owe customers and the ones your suppliers owe you: uptime, delivery-SLA bands and credit exposure. Monthly management and partner reports are generated automatically, with credit-calculation evidence kept on file. Related products ## Works alongside the rest of the BroadNet stack. [All platforms](https://www.broadnet.me/platforms) [Pricing Module Automated rate-card management that pairs naturally with performance monitoring.](https://www.broadnet.me/platforms/pricing-module) [Local SMSC Firewall Security counters surfaced as first-class KPIs inside the same dashboards.](https://www.broadnet.me/operators/sms-firewall) [SMSC Gateway Throughput, DLR and queue depth streamed live to NOC operators.](https://www.broadnet.me/operators/smsc-gateway) [SS7 Firewall Signaling-layer protection observed alongside application telemetry.](https://www.broadnet.me/operators/ss7-firewall) Carrier-grade platform ## Infrastructure engineered since 2003. The same platform that carries 300M+ messages a day, available as building blocks for your stack. 300M+ Msgs·day 99.99% SLA 23+ Years [Talk to sales](https://www.broadnet.me/contact) Operations infrastructure ## Make your NOC dashboards messaging-native. Real-time KPIs, threshold alerts, SLA reports and integration with your existing monitoring — purpose-built for messaging operations. Run it alongside what you have today. [Talk to operations](https://www.broadnet.me/contact) [Request technical spec](https://www.broadnet.me/contact) $ snmpwalk -v3 1.3.6.1.4.1.broadnet.sms