Linux - OpenTelemetry Collector

The Sumo Logic app for Linux allows you to monitor the performance and resource utilization of hosts and processes that your mission-critical applications are dependent upon. In addition to that, it allows you to view information about events, logins, and the security status of your Linux system using Linux system logs.

The app consists of predefined searches and dashboards that provide visibility into your environment for real-time or historical analysis. Our dashboards provide insight into CPU, memory, network, file descriptors, page faults, and TCP connectors. This app uses OpenTelemetry, an open-source collector for the collection of both metrics and log data.

We use the Sumo Logic Distribution for OpenTelemetry Collector to collect Linux metrics and system logs. The OpenTelemetry collector runs on the Linux machine and uses the Host Metric Receiver to obtain Host and process metrics, and the Sumo Logic OpenTelemetry Exporter to send the metrics to Sumo Logic. Linux logs are sent to Sumo Logic through a filelog receiver.

info

This app includes built-in monitors. For details on creating custom monitors, refer to Create monitors for Linux app.

Fields Created in Sumo Logic for Linux

Following are the fields that will be created as part of Linux app install if not already present. 

• sumo.datasource. Has a fixed value of linux.
• deployment.environment. This is a collector level field and is user configured (at the time of collector installation). Through this, the linux host cluster is identified by the environment where it resides. For example: dev, prod, or qa.
• host.group. This is a collector level field and is user configured (at the time of collector installation). Through this, the linux host cluster is identified.
• host.name. This is tagged through the resourcedetection processor. It holds the value of the host name where the OTel collector is installed.

Prereqisites

This app is based on the following log files from the Ubuntu Linux machine.

• auth.log
• syslog
• daemon.log
• dpkg.log
• kern.log
• CentOS, Amazon Linux, and Red Hat
• audit/audit.log
• secure
• messages
• yum.log

note

If you've already configured collection of these log files (for example, during Linux or Linux - PCI app setup), then no additional log file collection is required. If any log files are missing, you can configure the missing file collection in the next step.

For Linux systems with ACL Support, the otelcol install process should have created the ACL grants necessary for the otelcol system user to access default log locations. You can verify the active ACL grants using the getfacl command. Install the ACL in your Linux environment, if not installed.

The required ACL may not be supported for some rare cases, for example, Linux OS Distro, which is officially not supported by Sumo Logic. In this case, you can run the following command to explicitly grant the permissions.

sudo setfacl -R -m d:u:otelcol-sumo:r-x,d:g:otelcol-sumo:r-x,u:otelcol-sumo:r-x,g:otelcol-sumo:r-x <PATH_TO_LOG_FILE>

Run the above command for all the log files in the directory that need to be ingested, which are not residing in the default location.

If Linux ACL Support is not available, traditional Unix-styled user and group permission must be modified. It should be sufficient to add the otelcol system user to the specific group that has access to the log files.

Collection configuration and app installation

note

You can skip this section if you have already set up the logs collection through Linux PCI or Linux - Cloud Security Monitoring and Analytics app installation. Additional collection is not required as the logs used by this app are already ingested into Sumo Logic.

Follow these steps to set up and deploy the source template to collect data in Sumo Logic from a remotely managed OpenTelemetry collector.

Step 1: Set up remotely managed OpenTelemetry collector

note

If you want to configure your source locally, you can do so by downloading the YAML file. For details, see Configure OpenTelemetry collectors locally.

In this step, we'll install remotely managed OpenTelemetry collector and add a uniquely identifiable tag to these collectors.

1. Classic UI. In the main Sumo Logic menu, Select App Catalog.
   New UI. In the Sumo Logic main menu select App Catalog.
2. In the 🔎 Search Apps field, run a search for your desired OpenTelemetry app, then select it. For example, Apache - OpenTelemetry.
3. Click the Manage dropdown and then select Add Collection.
4. On the Set Up Collector page, select Add a New Collector and then click Next.

note

If you want to use an existing OpenTelemetry Collector, you can skip this step by selecting the Use an existing Collector option.

5. Select the platform where you want to install the Sumo Logic OpenTelemetry Collector. For example, Linux.
   This will generate a command that you can execute in the machine environment you need to monitor. Once executed, it will install the Sumo Logic OpenTelemetry Collector.
   The installation commands now include a --remotely-managed flag. When this flag is used, a remotely managed collector is installed automatically instead of a locally managed one. If you prefer to use a locally managed collector, simply remove the flag from the installation command.

Step 2: Configure the source template

In this step, you will configure the YAML required for Linux Collection. Below are the inputs required for configuration:

• Name. Name of the source template.
• Description. Description for the source template.

Logs collection

• Fields/Metadata. You can provide any customer fields to be tagged with the data collected. By default, sumo tags _sourceCategory with the value otel/linux.
• Logs. The following fields are pre-populated with default paths, for common log files that are used in different Linux distributions. Not all paths might be relevant for your operating system. Modify the list of files as required or leave the default values.

Metrics collection

• Metrics. Select the metric scrappers you want to enable. By default, metric collection for CPU, memory, disk, load, file system, network, and paging are enabled and process metric collection is disabled.

Enable process metric collection (optional)

By default, the collector will not send process metrics to Sumo Logic. This is because the number of processes running on a host can be very large, which would result in a significant increase in Data Points per Minute (DPM).

Click the Enable process metric collection checkbox to collect process-level metrics.

• Name of process. Add the list of process names.
• Include/Exclude the above pattern. Signifies if you want to exclude or include the metrics for the processes listed previously.
• Match type for process name. Select if the process name given should be considered for a strict match with the host machine processes or if it should be considered as regex when matching.
  

note

If you need to edit the process list in the future, you can do this manually in the OTEL config yaml by adding or removing in the names list under process scrapper.

process:
  include:
    names: [ <process name1>, <process name2> ... ]
    match_type: <strict|regexp>

• Scan Interval. The frequency at which the source is scanned.
• Processing Rules. You can add processing rules for logs/metrics collected. To learn more, refer to Processing Rules.

Step 3: Push the source template to the desired remotely managed collectors

info

A new source template will always be created with the latest version of the source template.

Follow the below steps to create a data collection configuration to gather the required logs and link them to all the collectors with the help of collector tags.

1. Complete the source template form with the name and file path for your logs (for example, error logs or access logs), then click Next.
2. Under Link Collectors, you will have the option to link the collectors using the collector name or by adding tags to find the group of collectors (for example, application = Apache).
   
3. Preview and confirm the collectors that will be linked (fetched automatically) to the newly created source template.
   
   
4. Click Next to complete the source template creation. In the background, the system will apply the configuration to all the linked collectors and will start collecting the respective telemetry data from the remote host (in the example, it would start collecting Apache error logs).
5. Click the Log Search or Metrics Search icons to search for and analyze your data collected for this source template.

Sample log messages

Dec 13 04:44:00 <1> [zypper++] Summary.cc(readPool):133 I_TsU(27372)Mesa-libGL1-8.0.4-20.4.1.i586(@System)

Sample metrics

{
	"queryId":"A",
	"_source":"linux-otel-metric",
	"process.executable.name":"apache2",
	"_sourceName":"Http Input",
	"process.command":"/usr/sbin/apache2",
	"host":"ip-172-31-90-39.ec2.internal",
	"os.type":"linux",
	"sumo.datasource":"linux",
	"process.executable.path":"/usr/sbin/apache2",
	"process.command_line":"/usr/sbin/apache2_-k_start",
	"process.owner":"www-data",
	"_sourceCategory":"Labs/linux-otel/metric",
	"_contentType":"Carbon2",
	"metric":"process.memory.physical_usage",
	"_collectorId":"000000000C984E1A",
	"_sourceId":"0000000042E512AE",
	"unit":"By",
	"_collector":"Labs - linux-otel",
	"process.pid":"26967",
	"max":42295296,
	"min":536576,
	"avg":9061120,
	"sum":144977920,
	"latest":8069120,
	"count":16
}

Sample queries

Log query

This is a sample log query from the Total Event Distribution panel.

%"sumo.datasource"=linux   
| parse regex "\d+\s+\d+:\d+:\d+\s(?<dest_hostname>\S+)\s(?<process_name>\w*)(?:\[\d+\]|):\s+"
|where dest_hostname matches "{{dest_hostname}}" AND process_name matches "{{process_name}}"
|count as Events by dest_hostname

Metrics query

This is a metrics query from the CPU Utilization Over Time panel.

sumo.datasource=linux host.name=* metric=system.cpu.utilization state=(user OR system OR wait OR steal OR softirq OR interrupt OR nice) | sum by host.name | outlier

Viewing Linux dashboards

All dashboards have a set of filters that you can apply to the entire dashboard. Use these filters to drill down and examine the data to a granular level.

• You can change the time range for a dashboard or panel by selecting a predefined interval from a drop-down list, choosing a recently used time range, or specifying custom dates and times. Learn more.
• You can use template variables to drill down and examine the data on a granular level. For more information, see Filtering Dashboards with Template Variables.

Linux - Overview

The Linux - Overview dashboard provides an overview of Linux activity, including the distribution of system events across hosts, group assignment changes, successful and failed logins, sudo attempts, and the count of reporting hosts. This dashboard also gives you an at-a-glance view of the key metrics like CPU, memory, disk, network, and TCP connections of all your hosts. You can drill down from this dashboard to the Host Metrics - CPU/Disk/Memory/Network/TCP dashboard by using the honeycombs or line charts in all the panels.

Host Metrics - CPU

The Host Metrics - CPU dashboard provides a detailed analysis based on CPU metrics. You can drill down from this dashboard to the Process Metrics - Details dashboard by using the honeycombs or line charts in all the panels.

Use this dashboard to:

• Identify hosts and processes with high CPU utilization.
• Examine CPU usage by type and identify anomalies over time.

Host Metrics - Disk

The Host Metrics - Disk dashboard provides detailed information about on disk utilization and disk IO operations.You can drill down from this dashboard to the Process Metrics - Details dashboard by using the honeycombs or line charts in all the panels.

Use this dashboard to:

• Identify hosts with high disk utilization and disk IO operations.
• Monitor abnormal spikes in read/write rates.
• Compare disk throughput across storage devices of a host.

Host Metrics - Memory

The Host Metrics - Memory dashboard provides detailed information on host memory usage, memory distribution, and swap space utilization. You can drill down from this dashboard to the Process Metrics - Details dashboard by using the honeycombs or line charts in all the panels.

Use this dashboard to:

• Identify hosts with high memory utilization.
• Examine memory distribution (free, buffered-cache, used, total) for a given host.
• Monitor abnormal spikes in memory and swap utilization.

Host Metrics - Network

The Host Metrics - Network dashboard provides detailed information on host network errors, throughput, and packets sent and received.

Use this dashboard to:

• Determine top hosts with network errors and dropped packets.
• Monitor abnormal spikes in incoming/outgoing packets and bytes sent and received.
• Use dashboard filters to compare throughput across the interface of a host.

Host Metrics - TCP

The Host Metrics - TCP dashboard provides detailed information around inbound, outbound, open, and established TCP connections. Use this dashboard to identify abnormal spikes in inbound, outbound, open, or established connections.

Process Metrics - Overview

The Process Metrics - Overview dashboard gives you an at-a-glance view of all the processes by open file descriptors, CPU usage, memory usage, disk read/write operations and thread count.

User this dashboard to:

• Process wise distribution of CPU and memory usage.
• Process wise read/write operations.

Process Metrics - Details

The Process Metrics - Details dashboard gives you a detailed view of key process related metrics such as CPU and memory utilization, disk read/write throughput, and major/minor page faults.

Use this dashboard to:

• Determine the number of open file descriptors in all hosts. If the number of open file descriptors reaches the maximum file descriptor limits, it can cause IOException errors.
• Identify anomalies in CPU usage, memory usage, major/minor page faults and reads/writes over time.
• Troubleshoot memory leaks using the resident set memory trend chart.

Linux - Event Sources

The Linux - Event Sources dashboard provides information about system events, including their distribution across hosts, event counts per host by hour, and even counts by host and service.

Linux - Login Status

The Linux - Login Status dashboard provides information about logins to Linux hosts; including logins by hour; failed logins per host; the top 30 successful and failed logins; and the top 30 successful and failed remote logins.

Linux - Security Status

The Linux - Security Status dashboard provides information about security on Linux hosts, including su, sudo attempts, new and existing user assignments, package operations, and system start events.

Create monitors for Linux app

From your App Catalog:

1. From the Sumo Logic navigation, select App Catalog.
2. In the Search Apps field, search for and then select your app.
3. Make sure the app is installed.
4. Navigate to What's Included tab and scroll down to the Monitors section.
5. Click Create next to the pre-configured monitors. In the create monitors window, adjust the trigger conditions and notifications settings based on your requirements.
6. Scroll down to Monitor Details.
7. Under Location click on New Folder.
   note

   By default, monitor will be saved in the root folder. So to make the maintenance easier, create a new folder in the location of your choice.

8. Enter Folder Name. Folder Description is optional.
   tip

   Using app version in the folder name will be helpful to determine the versioning for future updates.

9. Click Create. Once the folder is created, click on Save.

Linux alerts

Alert Name	Alert Description and conditions	Alert Condition	Recover Condition
Linux - High CPU Utilization Alert	This alert gets triggered when CPU utilization exceeds threshold.	Count > 80	Count < = 80
Linux - High FileSystem Utilization Alert	This alert gets triggered when filesystem utilization exceeds threshold.	Count > 80	Count < = 80
Linux - High Memory Utilization Alert	This alert gets triggered when memory utilization exceeds threshold.	Count > 80	Count < = 80