Performance warnings and recommendations
FSx for Lustre displays a warning for CloudWatch metrics when one of these metrics approaches or crosses a predetermined threshold for multiple consecutive data points. These warnings provide you with actionable recommendations that you can use to optimize your file system's performance.
Warnings are accessible in several areas of the Monitoring & performance dashboard on the Amazon FSx for Lustre console. All active or recent Amazon FSx performance warnings and CloudWatch alarms configured for the file system that are in an alarm state appear in the Monitoring & performance panel in the Summary section. The warning also appears in the section of the dashboard where the metric graph is displayed.
You can create CloudWatch alarms for any of the Amazon FSx metrics. For more information, see Creating CloudWatch alarms to monitor metrics.
Use performance warnings to improve file system performance
Amazon FSx provides actionable recommendations that you can use to optimize your file system's performance. You can take the recommended action if you expect the issue to continue, or if it's causing an impact to your file system's performance. Depending on which metric has triggered a warning, you can resolve it by increasing the file system's throughput capacity, storage capacity, or metadata IOPS, as described in the following table.
| Dashboard section | If there's a warning for this metric | Do this |
|---|---|---|
| Storage | Storage capacity utilization |
Increase your file system's storage capacity. If your storage capacity utilization is only higher for a subset of your file system's Object Storage Targets (OSTs), then you can also rebalance your workload so that your storage capacity utilization is more evenly balanced across your file system. |
Storage capacity utilization with cached writes |
Reduce the size of your client write cache by configuring the max_dirty_mb parameter on your clients. |
|
| Object storage performance | Network throughput |
Increase your file system's throughput capacity. If your throughput utilization is higher for a subset of your file system's Object Storage Servers (OSSs), then you can also rebalance your workload so that your throughput utilization is more evenly balanced across your file system. |
Disk throughput |
Increase your file system's throughput capacity. If your disk throughput utilization is higher for a subset of your file system's Object Storage Servers (OSSs), then you can also rebalance your workload so that your disk throughput utilization is more evenly balanced across your file system. |
|
Disk IOPS |
Increase your file system's storage capacity. If your disk IOPS utilization is higher for a subset of your file system's Object Storage Targets (OSTs), then you can also rebalance your workload so that your disk IOPS utilization is more evenly balanced across your file system. |
|
| Metadata performance | CPU utilization |
Increase your file system's storage capacity. If you need to scale metadata performance independent of the storage capacity, you can migrate to a new file system that supports provisioning metadata performance independent of the storage capacity using the MetadataConfiguration parameter. |
Metadata IOPS |
For more information about file system performance, see Amazon FSx for Lustre performance.
