High Memory Usage per Chassis and Blade-bluecoat-sgos

sgos
bluecoat
error
health-checks
High Memory Usage per Chassis and Blade-bluecoat-sgos
0

#1

High Memory Usage per Chassis and Blade-bluecoat-sgos

Vendor: bluecoat

OS: sgos

Description:
Alert when Memory usage is high

Remediation Steps:
Review the load on this thread to see if the memory utilization is valid.

How does this work?
This script logs into the Bluecoat Proxy using SSH and retrieves the memory utilization from the “show resources” command.

Why is this important?
Monitoring memory usage is critical for evaluate the system’s health and make sure it’s not over utilized. High memory usage could lead to production impact in terms of dropped packets.

Without Indeni how would you find this?
It is possible to poll this data through SNMP.

bluecoat-show-resources

#! META
name: bluecoat-show-resources
description: Fetch cpu usage stats
type: monitoring
monitoring_interval: 1 minute
includes_resource_data: true
requires:
    vendor: "bluecoat"
    os.name: "sgos"

#! COMMENTS
memory-total-kbytes:
    skip-documentation: true

memory-free-kbytes:
    skip-documentation: true

memory-usage:
    why: |
        Monitoring memory usage is critical for evaluate the system's health and make sure it's not over utilized.
        High memory usage could lead to production impact in terms of dropped packets.
    how: |
       This script logs into the Bluecoat Proxy using SSH and retrieves the memory utilization from the "show resources" command.
    without-indeni: |
       It is possible to poll this data through SNMP.
    can-with-snmp: true
    can-with-syslog: false

#! REMOTE::SSH
show resources

#! PARSER::AWK

BEGIN {
    tags["name"] = "RAM"
}

function convertToKB(memBytes){

    #4,105,961,472
    gsub(/,/, "", memBytes)
    totalMemKbytes = memBytes/1000

    return totalMemKbytes
}

#  Total memory available                      :            4,105,961,472 bytes
/^\s+Total memory available/{
    totalMemKbytes = convertToKB($(NF-1))
    writeDoubleMetricWithLiveConfig("memory-total-kbytes", tags, "gauge", "60", totalMemKbytes, "Memory - Total", "kilobytes", "name")
}

#    Total memory free                         :            2,780,155,904 bytes
/^\s+Total memory free/{
    totalMemKbytesFree = convertToKB($(NF-1))
    writeDoubleMetricWithLiveConfig("memory-free-kbytes", tags, "gauge", "300", totalMemKbytesFree, "Memory - Free", "kilobytes", "name")
}

#    Committed memory:(% of total available)   :                       24 %
/^\s+Committed memory:\(%/{
    tags["resource-metric"] = "true"
    memoryUsage = $(NF-1)
    writeDoubleMetricWithLiveConfig("memory-usage", tags, "gauge", "60", memoryUsage, "Memory - Usage", "percentage", "name")
}

high_per_chassis_blade_memory_usage

package com.indeni.server.rules.library

import com.indeni.ruleengine.Scope.{Scope, ScopeValueHelper}
import com.indeni.ruleengine.expressions.Expression
import com.indeni.ruleengine.expressions.conditions.GreaterThanOrEqual
import com.indeni.ruleengine.expressions.core.{StatusTreeExpression, _}
import com.indeni.ruleengine.expressions.data.{SelectTagsExpression, SelectTimeSeriesExpression, TimeSeriesExpression}
import com.indeni.ruleengine.expressions.math.AverageExpression
import com.indeni.ruleengine.expressions.scope.ScopableExpression
import com.indeni.server.common.ParameterValue
import com.indeni.server.common.data.conditions.{Equals, True}
import com.indeni.server.params.ParameterDefinition
import com.indeni.server.params.ParameterDefinition.UIType
import com.indeni.server.rules.RuleCategory.RuleCategory
import com.indeni.server.rules._
import com.indeni.server.rules.config.expressions.DynamicParameterExpression
import com.indeni.server.rules.library.core.PerDeviceRule
import com.indeni.server.sensor.models.managementprocess.alerts.dto.AlertSeverity


/**
  * Created by amir on 04/02/2016.
  */
case class HighPerChassisBladeMemoryUsageRule() extends PerDeviceRule {

  private val highThresholdParameterName: String = "High_Threshold_of_Memory_Usage"

  private val highThresholdParameter = new ParameterDefinition(highThresholdParameterName,
    "",
    "High Threshold of Memory Usage",
    "What is the threshold for the memory usage for which once it is crossed an issue will be triggered.",
    UIType.DOUBLE,
    new ParameterValue((85.0).asInstanceOf[Object])
  )

  override val metadata: RuleMetadata =
    RuleMetadata.builder(
      "high_per_chassis_blade_memory_usage",
      "High Memory Usage per Chassis and Blade",
      "Alert when Memory usage is high",
      AlertSeverity.ERROR,
      Set(RuleCategory.HealthChecks)).configParameter(highThresholdParameter).build()

  override def expressionTree(context: RuleContext): StatusTreeExpression = {

    val usagePercentage = AverageExpression(TimeSeriesExpression[Double]("memory-usage"))
    val usagePercentageThreshold = DynamicParameterExpression.withConstantDefault(highThresholdParameter.getName, highThresholdParameter.getDefaultValue.asDouble.toDouble).noneable
    val isUsagePercentageAboveThreshold = GreaterThanOrEqual(usagePercentage, usagePercentageThreshold)

    val mountSpaceFailDescription = new ScopableExpression[String] {
      override protected def evalWithScope(time: Long, scope: Scope): String =
        "Memory usage (" + usagePercentage.eval(time) + "%) above threshold (" + usagePercentageThreshold.eval(time) + "%) " +
          "for chassis: " + scope.getVisible("Chassis").get + ", blade: " + scope.getVisible("Blade").get

      override def args: Set[Expression[_]] = Set(usagePercentage, usagePercentageThreshold)
    }
    val mountSpaceFailHeadline = new ScopableExpression[String] {
      override protected def evalWithScope(time: Long, scope: Scope): String = "chassis: " + scope.getVisible("Chassis").get + ", blade: " + scope.getVisible("Blade").get

      override def args: Set[Expression[_]] = Set()
    }
    val tsQuery = SelectTimeSeriesExpression[Double](context.tsDao, Set("memory-usage"), denseOnly = false)
    val forTsCondition = StatusTreeExpression(tsQuery, isUsagePercentageAboveThreshold).withSecondaryInfo(
      mountSpaceFailHeadline, mountSpaceFailDescription, title = "Problematic Blades"
    ).asCondition()

    val chassisBladeQuery = SelectTagsExpression(context.tsDao, Set("Chassis", "Blade"), True)
    val highMemoryUsagePerDevicePerChassisBladeLogic = StatusTreeExpression(chassisBladeQuery, forTsCondition)
      .withoutInfo().asCondition()

    val headline = ConstantExpression("High memory usage")
    val description = ConstantExpression("The memory usage in the operating system is higher than the high threshold.")
    val remediation = ConditionalRemediationSteps("Review the load on this thread to see if the memory utilization is valid.",
      ConditionalRemediationSteps.OS_NXOS ->
        """1. Check from the Indeni  the memory utilization history graph for this device an review the pattern. Correlate any change to the pattern with any configuration change.
          |2. The next NX-OS commands output can inform whether the platform memory utilization is normal or un-expected:
          | a. "show system resources"
          | b. "show processes memory"
          |3. For more information, please review: <a target="_blank" href="http://docwiki.cisco.com/wiki/Cisco_Nexus_7000_Series_NX-OS_Troubleshooting_Guide_--_Troubleshooting_Memory">Troubleshooting Guide For High Memory Utilization</a>.""".stripMargin,
      ConditionalRemediationSteps.VENDOR_JUNIPER ->
        """|1. On the device command line interface execute "show chassis routing-engine" command to check overall routing engine memory usage.
           |2. Run "show system processes extensive" command to review the memory allocation status for processes.
           |3. Identify the processes which are consuming too much memory.
           |4. Consider turning off some processes which are not vital to ensure bigger memory space allocation for other sessions and processes.
           |5. Review the following article on Juniper tech support site: <a target="_blank" href="https://www.juniper.net/documentation/en_US/release-independent/nce/topics/task/operational/security-policy-memory-testing.html">Checking Memory Status</a>.""".stripMargin
    )

    val devicesFilter = Equals("model", "CheckPoint61k")
    val devicesQuery = SelectTagsExpression(context.metaDao, Set(DeviceKey), devicesFilter)

    StatusTreeExpression(devicesQuery, highMemoryUsagePerDevicePerChassisBladeLogic).withRootInfo(
      headline, description, remediation
    )
  }
}