Common methods to locate the cause of poor performance

4

Refer to Revelations of Troublesolving cases on the right.

Other related questions:
Method used to locate LUNs with poor read and write performance
Method used to locate LUNs with poor read and write performance: 1. The LUN write policy is write through. Locate the cause why the LUN write policy is write through. 2. If the host interface is iSCSI, check whether the network rate is 1 Gbit/s, whether the network is stable, and whether ping packets are lost. If the Fibre Channel or SAS network is used, log in to the storage's OSM page to check whether an alarm indicating that the front end encounters continuous error codes is reported. 3. Check whether slow disks exist in RAID groups. Specifically, run iostat -x 1 to check whether some disks differ from other disks (the util value of one or two disks is greater than that of other disks and reaches 100. If the util value of all disks in the RAID group reaches about 100, the configurations are incorrect and back-end disks are slow disks). If slow disks exist, replace them. 4. If a file system exists on the host, the file system produces enormous fragments when the disk space utilization rate exceeds 90%, causing the deterioration of read/write performance. You are advised to use disk space correctly.

Method used to locate common performance problems on OceanStor V3 storage systems
Before optimizing the performance and locating the problem, you must have the current customer performance data at hand. Then, you can use the I/O path to locate the module where the performance problem occurs. Once this is complete you can locate the problem and optimize performance. For details, see Performance Problem Diagnosis .

Solution if the performance of block devices in the AIX system is poor
Solution if the performance of block devices in the AIX system is poor: Use the dd command to test the performance of block devices in the AIX system. The test result is 30 MB/s, which is poor. dd command: dd if=/dev/updisk0 of=/dev/null bs=1024K Block devices in the AIX system can be used only for the transmission of data with a specified size. In this case, I/Os must pass through the kernel buffer cache. In contrast, raw devices read data from or write data to disks directly bypassing the operating system. In this way, different from block devices, I/O requests will not be split and processed and therefore, performance will not be impacted. In the AIX operating system, you are advised to use raw devices. A block device is /dev/updisk0 and a raw device is /dev/rupdisk0.

Method used to develop performance statistics by using the common line interface
You can perform the following operations to develop performance statistics by using the CLI: 1. Fault location and rectification You can use the CLI to manually collect performance data. 2. Solution You can collect performance data through ports and LUNs. The following commands are entered and performed in sequence in CLI mode and their displayed results are saved in logs. a. Collecting data by port OceanStor: admin> chgstatswitch -o -p OceanStor: admin> statperf -p Enter the above commands at an interval of 3s for 10 times. OceanStor: admin> chgstatswitch -c -p Based on port statistics, the maximum latency is not more than 1.5s, the average latency is not more than 300 ms, and I/O processing is in normal state. b. Collecting data by LUN OceanStor: admin> chgstatswitch -o -l OceanStor: admin> statperf -l Enter the above commands at an interval of 3 seconds for 10 times. OceanStor: admin> chgstatswitch -c -1

If you have more questions, you can seek help from following ways:
To iKnow To Live Chat
Scroll to top