Using Graphs

CPU Usage in Windows

The key CPU usage metric in Windows is % Usr Time , which monitors the amount of time the CPU spends processing a thread that is not idle. If usage is consistently at 80% to 90%, you may need to upgrade the CPU or add more processors.

You should monitor a separate instance of this counter for each processor on systems with multiple CPUs. The value returned by the counter represents the sum of processor time on a specific processor.

Optionally, you can monitor the following metrics:

• Processor: % Privileged Time

  The percentage of time that the CPU spends executing Windows kernel commands. If this metric is consistently high you should consider using a faster or more efficient disk subsystem.

• Processor: %User Time

  The percentage of time that the CPU spends executing user processes.

• Processor: % Interrupt Time

  The time that the CPU spends managing hardware requests. This metric enables you to determine the level of device activity.

• System: Processor Queue Length

  The number of threads that are waiting for processor time.

To generate a CPU performance graph, do the following:

1. On the Global Scan dashboard or My Infrastructure panel, click the name of the system whose information you want to graph.
2. In the Tree panel, click the Graphing tab.
3. Click one of the following options:
   
   • Usage (% busy)
   • Run Queue Length
   • Run Queue Occupancy
4. Select the start and end dates and times for which the graph will chart data. For more information, see Understanding Dates and Times
5. Click Generate Graph.

To generate a Multi-CPU Usage graph, do the following:

1. On the Global Scan dashboard or My Infrastructure panel, click the name of the system whose information you want to graph.
2. In the Tree panel, click the Graphing tab.
3. Click Multi-CPU Usage.
4. Select the start and end dates and times for which the graph will chart data. For more information, see Understanding Dates and Times
5. Click one of the following options:
   
   • User %: the percentage of CPU user processes that are in use. For Windows systems, this option is % User Time
   • System %: the percentage of CPU kernel processes that are in use. For Windows systems, this option is % System Time
   • % Privileged Time: on Windows systems, the percentage of time that the CPU spends executing kernel commands
   • Wait I/O %: the percentage of time that a process which can be run must wait for a device to perform an I/O operation

   • SMTX: the number of read or write locks that a thread was not able to acquire on the first attempt, as reported by the mpstat command

     While it is trying to acquire locks, the thread is active but is not performing any tasks.

   • XCAL - the number of interprocess cross-calls

     In a multi-processor environment, one processor sends cross-calls to another processor to get that processor to do work. Cross-calls can also be used to ensure consistency in virtual memory. Heavy file system activity, such as NFS, can result in a high number of cross-calls.
     

   • Interrupts: the number of CPU interrupts (on Windows systems, this option is % Interrupt Time)
     Interrupts are a mechanism that a device uses to signal to the kernel that it needs attention, and that immediate processing is required on its behalf.
   • Interrupts/sec: on Windows systems, rate at which CPU handles interrupts from applications or hardware each second
     If the value for Interrupts/sec is high, there could be problems with the hardware on the system.
   • Total %: on Windows systems, this option is % Total and is the total amount of % User Time, % Privileged Time, and % Interrupt Time
     
     
6. Select the CPUs to graph from the Choose CPUs to graph list.
7. Click Generate Graph.

The number of transfers between the system buffers and various disks.

The number of times the system buffer was accessed.

Cache read efficiency should be close to 100%. Cache write efficiency should be approximately 66%. However, low percentages do not always indicate performance problems.

Physical swap space

The actual space on a disk available for swapping.

Virtual swap space

The amount of physical swap space and the amount of memory that is available for swapping.

If the amount of swap space drops to zero, then the system cannot create new processes or store information in the /tmp file system.

Linux swaps data to a dedicated swap partition.

To generate a memory usage graph, do the following:

1. On the Global Scan dashboard or My Infrastructure panel, click the name of the system whose information you want to graph.
2. In the tree panel, click the Graphing tab.
3. Click one of the following options:
   
   • Used
   • Cache Hit Rate
   • Paging Statistics
   • Free Swap
4. Select the start and end dates and times for which the graph will chart data. For more information, see Understanding Dates and Times.
5. Click Generate Graph.

To generate a process graph, do the following:

1. On the Global Scan dashboard or My Infrastructure panel, click the name of the system whose information you want to graph.
2. In the tree panel, click the Graphing tab.
3. Click one of the following options:
   
   • Number of Processes
   • Process Running, Blocked, Waiting
   • Process Creation Rate
4. Select the start and end dates and times for which the graph will chart data. For more information, see Understanding Dates and Times
5. Click Generate Graph .

To generate a TCP retransmits graph, do the following:

1. On the Global Scan dashboard or My Infrastructure panel, click the name of the system whose information you want to graph.
2. In the tree panel, click the Graphing tab.
3. Click TCP Retransmits .
4. Select the start and end dates and times for which the graph will chart data. For more information, see Understanding Dates and Times
5. Click Generate Graph .

To generate a user activity graph, do the following:

1. On the Global Scan dashboard or My Infrastructure panel, click the name of the system whose information you want to graph.
2. In the tree panel, click the Graphing tab.
3. Click either Login History or Sessions .
4. Select the start and end dates and times for which the graph will chart data. For more information, see Understanding Dates and Times
5. Click Generate Graph .

To generate a workload graph, do the following:

1. On the Global Scan dashboard or My Infrastructure panel, click the name of the system whose information you want to graph.
2. In the tree panel, click the Graphing tab.
3. Click one of the following options:
   
   • Workload - User
   • Workload - Group
   • Workload - Process Name
4. Select the start and end dates and times for which the graph will chart data. For more information, see Understanding Dates and Times
5. Click one of the following metrics:
   
   • See CPU %.
   • See Memory Size. or Virtual Bytes (on UNIX and Windows, respectively)

   • See RSS. or Working Set (on UNIX and Windows, respectively)

     You can only graph one metric at a time.

6. Select one or more of the available users, groups, or processes from the list.
   If you are generating a workload graph by processes, (i.e., Workload - Process Name graph), enter a regular expression in the Process Selection Regex field to automatically add matching process names for graphing, and avoid dealing with ungainly lists of system processes.

   The list of available process will vary by server and by operating system.
7. Click Add .
8. Click Generate Graph

To generate a Workload Top 10 graph, do the following:

1. On the Global Scan dashboard or My Infrastructure panel, click the name of the system whose information you want to graph.
2. In the tree panel, click the Graphing tab.
3. Click one of the following options: 
   
   • Workload Top 10 - User
   • Workload Top 10 - Group
   • Workload Top 10 - Process Name
4. Select the start and end dates and times for which the graph will chart data. For more information, see Understanding Dates and Times
5. Click one of the following options:
   
   • CPU %
   • Memory Size
   • RSS
     Graphs generated for SNMP agents only chart the memory size metric.
6. Click Generate Graph .

To generate an LPAR Workload graph, do the following:

1. On the Global Scan dashboard or My Infrastructure panel, click the name of the pSeries server which is hosting the LPARs whose information you want to graph.
2. In the tree panel, click the Graphing tab.
3. Click one of the following options:
   
   • Workload - CPU
   • Workload - Memory
   • Workload - Disk
   • Workload - Network
4. Select the start and end dates and times for which the graph will chart data. For more information, see Understanding Dates and Times
5. Click Generate Graph .

To generate an LPAR CPU Utilization graph, do the following:

1. On the Global Scan dashboard or My Infrastructure panel, click the name of the pSeries server which is hosting the LPAR whose information you want to graph.

In the tree panel, click the

tab.
1. Under the LPAR Workload heading, click Workload - CPU Utilization .
2. Select the start and end dates and times for which the graph will chart data. For more information, see Understanding Dates and Times
3. Select the name of the LPAR whose information you want to graph.

If the message There are no LPARs for this date range is displayed, do one of the following:

• Click the Update List button.
• Change the date range.
• Click Generate Graph .

In bytes

The number of bytes received over the network interface each second.

Out bytes

The number of bytes sent by the network interface each second.

Excessive noise.

Cabling problems.

Problems with backbone connections.

The Errors graph captures the following statistics:

In Errors

A data packet was received but could not be decoded because either the header or trailer of the packet was not available.

Out Errors

A data packet could not be sent due to problems transmitting the packet or formatting the packet for transmission.

Collisions

The simultaneous presence of signals from two nodes on the network. A collision can occur when two nodes start transmitting over a network at the same time. Packets that are involved in a collision are broken into fragments and must be retransmitted.

To generate network graphs, do the following:

1. On the Global Scan dashboard or My Infrastructure panel, click the name of the system whose information you want to graph.
2. In the tree panel, click the Graphing tab.
3. Click one of the following options:
   
   • I/O
   • Errors
   • NetFlow (available if up.time has been integrated with Scrutinizer)
4. For I/O and Errors graphs, select the start and end dates and times for which the graph will chart data. For NetFlow, select one of the set time frames. For more information, see Understanding Dates and Times
5. For I/O and Errors graphs, select one or more network interfaces from the Available Interfaces list, and then click Add.
6. Click Generate Graph.

Network I/O Metrics

The following metrics can be used when generating a Network I/O graph for a network device Element:

Graphing Network I/O Rates for a Network Device

• excessive noise
• cabling problems
• problems with backbone connections

To generate a Disk Performance Statistics graph, do the following:

1. On the Global Scan dashboard or My Infrastructure panel, click the name of the system whose information you want to graph.
2. In the tree panel, click the Graphing tab.
3. Click Disk Performance Statistics .
4. Select the start and end dates and times for which the graph will chart data. For more information, see Understanding Dates and Times
5. Select one of the following options:
   

   • Percent Busy
     The percentage of the disk capacity that is being used.

     For NFS systems, 100% busy does not indicate that the server itself is saturated, but that the client always has outstanding requests to that server.
   • Average Queue
     The average number of processes that are waiting to access the disk.
     The length of the queue is affected by how busy the system is and the amount of time that each transaction requires to perform a disk operation. A complete transaction must occur before the next transaction can start. Longer disk operations per transaction increases the average length of the queue.
   • Read/Writes
     The number of read/write requests, per second, from or to a disk.
   • Throughput (blks/s)
     The amount of disk traffic, in blocks of 512 bytes, that is flowing to and from a disk each second.
   • Average Wait Time
     The average time, in milliseconds, that a transaction is waiting in a queue. The wait time is directly proportional to the length of the queue.
   • Average Serve Time
     The average time, in milliseconds, required to perform a task.
   • All of the above for one disk
     up.time graphs all of the metrics listed above for a single disk.
6. Select the disks for which you want to collect information from the list.
   If you select multiple disks and selected All of the above for one disk in step 5, then up.time only graphs information for the first disk that you selected.
7. Click Generate Graph.

To generate a Top 10 Disks graph, do the following:

1. On the Global Scan dashboard or My Infrastructure panel, click the name of the system whose information you want to graph.
2. In the tree panel, click the Graphing tab.
3. Click Top 10 Disks .
4. Select the start and end dates and times for which the graph will chart data. For more information, see Understanding Dates and Times
5. Select one of the following options:
   

   • Percent Busy
     The percentage of the disk capacity that is being used.

     For NFS systems, 100% busy does not indicate that the server itself is saturated, but that the client has outstanding requests to that server.
   • Average Queue
     The average number of processes that are waiting to access the disk.
     The length of the queue is affected by the amount of time that each transaction requires to perform a disk operation. For both sequential and random disk transactions, a complete transaction must occur before the next transaction can begin. Longer disk operations per transactions increase the average length of the queue.
   • Read/Writes
     The number of read/write requests per second from or to a disk.
   • Throughput (blks/s)
     The amount of traffic, in 512 byte blocks, that is flowing to and from a disk.
   • Average Wait Time
     The average time, in milliseconds, that a transaction is waiting in a queue. The wait time is directly proportional to the length of the queue.
   • Average Serve Time
     The average time, in milliseconds, required to perform a task.
6. Click Generate Graph .

To generate a File System Capacity graph, do the following:

1. On the Global Scan dashboard or My Infrastructure panel, click the name of the system whose information you want to graph.
2. In the tree panel, click the Graphing tab.
3. Click File System Capacity .
4. Select the start and end dates and times for which the graph will chart data. For more information, see Understanding Dates and Times
5. Select one or more file systems from the list.
   If you are generating a graph for a Windows system, you will only be able to generate a graph for the C:\ drive.
6. Click Generate Graph .

To generate a VXVM Stats graph, do the following:

1. On the Global Scan dashboard or My Infrastructure panel, click the name of the system whose information you want to graph.
2. In the tree panel, click the Graphing tab.
3. Click VXVM Stats .
4. Select the start and end dates and times for which the graph will chart data. For more information, see Understanding Dates and Times
5. In the Available Disk Groups and Volumes area, select one or more volumes on which to report.
   The disk groups or volumes that appear in this area will vary from system to system. You must select at least one disk group or volume.
6. Select one of the following options:
   
   • I/O Operations
     The number of times, per second, that data is written to and read from the volume.
   • Block Throughput
     The amount of disk traffic, in blocks of 512 bytes, that is flowing to and from the volume.
   • Average Service Times
     The average amount of time, in milliseconds, that is required for a request to be carried out.
7. If necessary, uncheck either of the Read or Write checkboxes.
   Depending on the option you chose in step 6, the Read and Write options chart the following information in the graph:
1. If you selected I/O Operations in step 6, the number of read and write operations to and from the volume.
2. If you selected Block Throughput in step 6, the number of blocks that were read and written to and from the volume.

3. If you selected Average Service Times in step 6, the amount of time requires to read and write data to and from the volume.

   Select only one option if you are comparing more than one volume.
8. Click Generate Graph .

To generate a Novell NRM graph, do the following:

1. On the Global Scan dashboard or My Infrastructure panel, click the name of the Novell NRM system whose information you want to graph.
2. In the tree panel, click the Graphing tab, then click one of the metrics on the list.
3. Select the start and end dates and times for which the graph will chart data.  For more information, see Understanding Dates and Times
4. Click Generate Graph .

To generate an Instance Motion graph, do the following:

1. On the Global Scan dashboard or My Infrastructure panel, click the name of the ESX instance whose motion you want to graph.
2. In the tree panel, click the Graphing tab.
3. Click Instance Motion .
4. Select the start and end dates and times for which the graph will chart data.  For more information, see Understanding Dates and Times
5. Click Generate Graph .

To display detailed process information, do the following:

1. On the Global Scan dashboard or My Infrastructure panel, click the name of the system whose information you want to graph.
2. In the tree panel, click the Graphing tab.
3. Click Detailed Process Information .
4. Select the start and end dates and times for which the graph will chart data.  For more information, see Understanding Dates and Times
5. Click Display Process Information .
   A window containing a chart that lists the process information for the time period that you specified appears.
   
6. From the dropdown list, select the date and time for which you want to view process information.