Skip to main content

Full-stack observability

Virtana’s observability platform delivers end‑to‑end visibility across the entire technology stack—from core infrastructure (compute, storage, network) and containerized or hybrid environments to services, applications, and even AI workloads such as GPU training jobs. By consolidating telemetry from every layer into a single unified fabric, the platform enables teams to assess performance and health in a correlated, business‑impact–driven context rather than through isolated silos.

Core visibility layers

Let's take a closer look at how the components in Virtana Platform provides visibility across your tech stack.

Virtana Global View

Global View serves as the centralized observability layer within the Virtana Platform. It ingests, correlates, and visualizes telemetry from on-premises, cloud, and hybrid environments.

Key capabilities include:

  • Unified dashboards combining topology, service health, and impact-aware alerts.

  • Automated discovery and continuous topology mapping across compute, storage, network, and containers.

  • Real-time cross-layer correlation that links infrastructure behavior to service-level impact.

This contextual visibility enables operators to understand relationships and dependencies across the stack, not just individual component performance. To view the unified graphical view of the Global View topology, see Global View Topology.

Virtana Infrastructure Observability

Virtana Infrastructure Observability provides deep visibility into physical and virtual resources that support applications and services. Collected telemetry includes:

  • Compute metrics such as CPU, memory, and hardware utilization

  • Storage performance and capacity indicators

  • Network latency, throughput, and topology

  • Application discovery

To view the graphical view of the IO, see IO Topology.

Virtana Container Observability

Virtana extends observability into containerized environments through its Container Observability module. The platform captures metrics from compute, storage, and network resources, and extends visibility into Kubernetes clusters. This ensures cloud-native workloads are fully visible and correlated with the underlying infrastructure.

Capabilities include:

  • Automated deployment of Kubernetes collection agents

  • Cluster-wide visibility across nodes, pods, namespaces, and services

  • Dependency mapping within and across clusters

  • Support for hybrid Kubernetes deployments spanning on-premises and cloud

To view a structural view of Virtana Container Observability in detail, see Container Observability Topology.

Virtana Service Observability and Virtana Application Observability

Service and application observability layers provide insight above raw infrastructure metrics. Virtana tracks service health, application performance, and events across distributed systems.

Operators can visualize service dependencies, analyze correlated metrics, and assess user-facing impact. This service-centric perspective is essential for modern microservices and distributed architectures. To view more details about Service Observability, see Network Topology.

AI Factory Observability

Virtana AI Factory Observability (AIFO) extends full-stack visibility into AI and machine learning (ML) environments.

The platform collects and correlates telemetry from:

  • GPU clusters and accelerators

  • CPU, memory, and network fabrics

  • Power, thermal, and utilization metrics

  • AI training and inference workloads

By correlating infrastructure behavior with model performance, Virtana helps you identify bottlenecks, optimize resource usage, and control operational costs for AI workloads. To view AIFO in detail, see IO Topology.

Automated discovery and data correlation

Automated discovery is foundational to Virtana’s observability model. The platform continuously scans servers, virtual machines, containers, storage, and network components to maintain a live representation of the environment.

This dynamic topology enables:

  • Accurate dependency mapping across layers

  • Time-synchronized correlation of metrics and events

  • Faster root cause analysis and impact assessment

Operational Outcomes

With full-stack observability, organizations gain:

  • End-to-end visibility from hardware to user-facing services

  • Contextual insight that links technical telemetry to business services

  • Unified operations across hybrid, multi-cloud, and AI-driven environments

These capabilities enable teams to reduce troubleshooting time, improve service reliability, and make informed operational decisions.

Virtana Platform provides a unified, intelligent observability foundation for modern IT environments. By combining automated discovery, cross-domain correlation, and service-centric visibility, the platform helps organizations operate complex infrastructure with clarity, confidence, and business alignment.