1. Average Transaction Response Time
Average transation response time excellent: <2 S
Good: 2-5 S
Pass: 6-10 s
Fail:> 10 s
2. Click rate per second
Hits per second
When the system pressure is increased (or the number of concurrent users is increased), the throughput is roughly the same as the TPS curve, and the system is basically stable. If the pressure increases, when the throughput curve increases to a certain extent, the changes are slow or even flat, which may result in a bandwidth bottleneck. similarly, if the CTR/TPS curve changes slowly or flat, the server begins to appear.
3. Request Response Time
Time to last byte
4. Number of transactions processed by the system per second
Transaction per second
5. Throughput
Throughout
6. CPU utilization
Processor/% processor time: 70%
Bad: 85%
Poor: over 90%
7.DatabaseCPU time consumed by the Operation
Processor/% USER time if the value is large, you can consider whether to reduce this value through friendly algorithms and other methods. If the server is a database server, the reason for the large processor \ % USER time value is probably that database sorting or function operations consume too much CPU time, in this case, you can consider optimizing the database system.
8. Average CPU usage in core Mode
Processor/% privileged time if the value of this parameter and the value of the "physical disk" parameter remain high, it indicates that I/O is faulty. Consider replacing a faster hard drive system
9. Number of threads in the processing queue
Processor/processor queue length if this value remains unchanged (> = 2) and % processor time exceeds 90%, a processor bottleneck may exist. If we find that the processor utilization rate exceeds 2, but the processor utilization rate remains low, we should solve the problem of processor congestion. Here, the processor is generally not a bottleneck.
10. File System Cache
Memory/cache bytes 50% available physical memory
11. remaining available memory
Memory/avaiable Mbytes must have at least 10% of the physical memory value
This article is from 51testing software testing network. I would like to thank the Member fms00005 for their wonderful answers every Monday (08-12-29. Http://bbs.51testing.com/forum-157-1.html
12. Number of pages downloaded per second
Memory/pages/sec: no page Switching
Bad: CPU 10 page exchanges per second
Poor: more page exchanges
13. Page read Speed
Memory/Page read/sec If the page read speed is very low and the value of % disk Time and AVG. Disk queue length is very high, there may be disk bottle diameter. However, if the length of the queue increases while the page read rate does not decrease, the memory is insufficient.
14. physical disk Utilization
Physical Disk/% disk Time: <30%
Bad: <40%
Poor: <50% +
15. Average length of the physical disk I/O queue
Physical Disk/avg. Disk queue length the value should not exceed 1.5 ~ 2 times. To improve performance, you can add disks.
16. network throughput
Network Interface/bytes total/sec determine whether the network connection speed is a bottleneck. You can use the counter value and the current network bandwidth. The result should be less than 50%.
17. Data Cache hit rate should be greater than 0.90, preferably
18. The hit rate of the cache area in the shared area should be greater than 0.99.
19. The hit rate of the Dictionary Buffer in monitoring SGA should be greater than 0.85
20. Check that the competition for rollback segments is less than 1%
21. Monitor SGA for re-engineeringLogsCache hit rate
Less than 1%
22. Monitor the memory-to-Hard Disk sorting ratio to make it smaller than 10%
From: http://www.51testing.com/html/80/n-126580.html