Viewing Analysis Results

Prerequisites

A storage I/O diagnosis task has been created and the analysis is complete.

Procedure

1. In the System Diagnosis area on the left, click the name of the target analysis task.

   The node list is displayed.

2. Click the name of the target node to view the analysis results.
   • Click a node name. The Pressure Test Result tab page is displayed by default, as shown in Figure 1. Table 1 describes the parameters.
     Figure 1 Pressure test result
     

     Table 1 Parameters in the pressure test result

     Parameter	Description
     Pressure Test Object	Object that has been tested.
     Request Block Size	Size of the request block.
     Read/Write Mode	Read or write mode.
     I/O Queue Depth	Depth of an I/O queue.
     I/O Engine	I/O engine.
     Concurrency	Concurrency statistics.
     Direct I/O	Indicates whether to read the buffer first.
     I/O Size (MiB)	Size of the I/O.
     Test Duration (s)	Time used by the test.
     Read Throughput	Throughput of reads.
     Write Throughput	Throughput of writes.
     Read IOPS	Read throughput per second.
     Write IOPS	Write throughput per second.
     Read Latency	Latency of read operations.
     Write Latency	Latency of write operations.
     Throughput (KiB/s)	Total throughput.
     IOPS	Total throughput per second.
     Latency (ms)	Total latency.
     Latency
     Type	Latency type.
     Max. (ms)	Maximum latency.
     Min. (ms)	Minimum latency.
     Average (ms)	Average latency.
     Standard Variance (ms)	Standard variance of the latency.
     Latency Distribution
     Latency Range (ms)	Distribution range of the latency.
     Proportion (%)	Proportion of the latency in each range.
     I/O Depth Distribution
     I/O Depth Range	I/O depth distribution range.
     Proportion (%)	Distribution proportion of I/Os in each depth range.
     Pressure Test Process Performance
     %user	Percentage of CPU time occupied when the pressure test process is running in user mode.
     %system	Percentage of CPU time occupied when the pressure test process is running in kernel mode. This metric does not include the time spent on service hardware and software interrupts.
     context switches	Number of times that the pressure test process is switched.
     major page faults	Number of major page faults of the pressure test process. When a virtual memory address is mapped to a physical memory address, the corresponding page is in the swap memory. Such page faults are major page faults, which are generated when the memory is insufficient. Pages need to be loaded from the drive.
     minor page faults	Number of secondary page faults of the pressure test process, that is, number of page faults generated when a virtual memory address is mapped to a physical memory address. No page needs to be loaded from the drive.
     Storage Device Performance
     Device Name	Name of the device for which the pressure test is performed.
     I/O number	Total number of I/O times executed by the pressure test process.
     merge number	Total number of merged I/Os in the pressure test process.
     tick number	Total number of ticks when the drive is busy.
     time spent in queue	Time spent in the queue.
     util (%)	Drive usage statistics.

   • Click the System Load tab to view the system load details, as shown in Figure 2. Table 2 describes the parameters.
     Figure 2 System load
     

     Table 2 System load parameters

     Parameter	Description
     CPU Usage
     CPU core	CPU core ID.
     NUMA NODE	NUMA node ID.
     %user	Percentage of CPU time occupied when the system is running in user mode.
     %nice	Percentage of CPU time occupied by the process that has changed the priority when the system is running in user mode.
     %system	Percentage of the CPU time occupied when the system is running in kernel mode (excluding the hardware interrupt time and software interrupt time).
     %iowait	Percentage of CPU time during which the CPU is idle and waiting for drive I/O operations.
     %irq	Percentage of CPU time spent on service hardware interrupts.
     %soft	Percentage of CPU time spent on service software interrupts.
     %idle	Percentage of CPU time during which the CPU is idle and the system has no unfinished drive I/O request.
     CPU Load
     runq-sz	Length of the running queue, that is, the number of tasks to be run.
     plist-sz	Number of tasks in the task list.
     ldavg-1	Average system load in the last minute.
     ldavg-5	Average system load in the last 5 minutes.
     idavg-15	Average system load in the last 15 minutes.
     blocked	Number of blocked tasks waiting for I/O operations.
     Memory Usage
     total (KB)	Total available memory size of the system.
     free (KB)	Available memory size.
     used (KB)	Size of used memory.
     %used	Percentage of the used memory to the total memory.
     avail (KB)	Size of the memory that can be used by applications.
     buffers (KB)	Size of buffered memory.
     cached (KB)	Size of memory in the cache.
     Network I/O Statistics
     IFACE	Network port name.
     rx (pck/s)	Total number of packets received per second.
     tx (pck/s)	Total number of packets sent per second.
     rx (KB/s)	Total number of bytes received per second.
     tx (KB/s)	Total number of bytes sent per second.
     Network Ports	You can select a value from the drop-down list to view the network PPS and throughput.

3. Click the Task Information tab to view the detailed configuration and sampling information about the task on the current node.
   

   If a task fails to be executed, the failure cause will be displayed on the Task Information tab page.

   If some data fails to be collected but the overall task execution is not affected, you can view the exception message in Exception Information.

   Collection End Cause displays the reason why the data collection of the current task ends, for example, "Task collection times up" or "File size reaches the collection limit."