---
title: "Monitor a vector database"
description: "Check the CPU and memory usage, request counts and response times of a Qdrant vector database from the Monitoring tab in TIR."
content_type: "how-to"
product: "vector-database"
platform: "TIR"
url: "/tir/vector-database/how-to/monitor-a-vector-database/"
topic: ["monitor"]
---

# Monitor a vector database

Open the **Monitoring** tab to see how busy the Qdrant cluster of a database is: its CPU and memory use, and
the requests it serves.

## Before you begin

You need a database in the **Running** state and a role with Read permission on
Vector Database.

## Read the graphs

1. In **Manage Vector Database**, select the database's row, then open **Monitoring**.
2. Under **Metric Type**, choose **Hardware** or **Service**.
3. In **Interval**, choose **Last 5 minutes**, **Last hour**, **Last 24 hours**, **Last 7 days** or
   **Last month**.
4. To load the latest values, select the refresh button.

**Hardware** shows **CPU Utilization** and **CPU Memory Utilization** for the nodes. **Service**
shows:

- **REST request count** and **gRPC request count**, the requests the database received, including
  the ones that failed.
- **Average REST response duration** and **Average gRPC response duration**, how long responses take.
- **Total pending operations**, the operations waiting in the cluster.

The **Overview** tab also shows **Total number of collections**, **Total number of vectors** and
**Total cluster peers**, the number of nodes in the cluster, while the database is **Running**.

## What to do next

After you [scale up](/tir/vector-database/how-to/scale-up-a-vector-database/), check **Total pending
operations**.