Navigation

Disk I/O % Utilization

Description

Disk I/O % Utilization alerts indicate that the percentage of disk IOPS utilized reaches a specified threshold. This threshold is specified when the alert is created.

Note

The utilization measurements for the following alerts include requests from all processes, not just MongoDB processes.

Disk I/O % utilization on Data Partition occurs if the percentage of time during which requests are being issued to any partition that contains the MongoDB collection data meets or exceeds the threshold.

Disk I/O % utilization on Index Partition occurs if the percentage of time during which requests are being issued to any partition that contains the MongoDB index data meets or exceeds the threshold.

Disk I/O % utilization on Journal Partition occurs if the percentage of time during which requests are being issued to the partition that contains the MongoDB journal meets or exceeds the threshold.

Possible Observations

These are a few possible methods to observe high Disk I/O % Utilization:

  • The disk IOPS use from the Disk IOPS graph in the cluster metrics is higher than the provisioned IOPS from the Atlas cluster configuration page.
  • There is a high IOWait curve in the Normalized System CPU metric. IOWait measures the percentage of time the CPU is idle and waiting for an I/O operation to complete. The Normalized System CPU chart is located under the Hardware Metrics section of the Metrics tab.

Common Triggers

These are a few common events which may lead to high Disk I/O % Utilization and trigger these alerts:

  • Unoptimized queries can cause extra disk IOPS usage.
  • There may be a one-time event which causes a spike in disk IOPS and exceeds the IOPS threshold, such as an index build.

Possible Solutions

These are a few possible actions to consider to help resolve Disk I/O % Utilization alerts:

Disk IOPS Burst Credits for Atlas Clusters on AWS

Atlas clusters deployed to AWS with following criteria may use burst credits when exceeding configured IOPS thresholds during periods of high disk I/O:

  • Clusters where the Provision IOPS setting is disabled.

  • Clusters configured with less than 1 TB of storage capacity.

    Note

    By default, all clusters smaller than the M140 cluster tier are configured with less than 1 TB of storage capacity.

AWS uses burst credits to temporarily increase IOPS beyond the configured threshold during periods of high disk I/O activity. These clusters refresh spent credits during periods of low disk I/0 activity. When burst credits are exhausted, AWS limits IOPS for these clusters to the configured threshold. This may result in decreased disk I/O performance on these clusters and a high IOWait curve in the Normalized System CPU metric.

See the AWS EBS Volume Type documentation for more information about burst credits and the rates at which they deplete and refresh.

If you regularly exceed your configured IOPS threshold, you can avoid depleting your burst credits by increasing your configured IOPS with any of the following actions:

  • Increase Cluster IOPS to increase the cluster’s IOPS threshold.

  • Enable the Provision IOPS configuration option option. Clusters configured with this option use Provisioned IOPS SSD (io1) storage volumes, which do not use burst credits and offer greater IOPS thresholds.

  • Increase Storage Capacity. The IOPS threshold increases as you increase storage capacity. Clusters configured to use at least 1 TB of storage have baseline IOPS performance that is equal to or greater than the maximum burst performance. These volumes do not deplete burst credit balances.

  • Upgrade Cluster Tier. Larger cluster tiers include higher IOPS thresholds.

    Note

    Cluster tiers M140 and larger are deployed with at least 1 TB of storage capacity by default. Clusters with 1 TB or more of storage capacity do not deplete burst credit balances.