I am trying to perform a stress test where I need to hit my application server with 4000 requests in exactly one second. I need to increase this value gradually. But the problem is I can't achieve this scenario. I have taken ethereal traces of the requests hitting the application server. The maximum number of requests I get was around 2500 requests per second.
The response of the server or the application is not my concern right now. All I am trying to achieve is "4000+ requests are hitting the server in exactly one second". The request is simple and it's a GET requests. I have tried using "Synchronizing Timer" or defining "Ramp up Time=0" in the thread group level. But still no success. Is it possible to generate 4000+ requests using Jmeter in exactly 1 second? Or there is a limitation for that in JMeter. Please let me know if I need to change any server configuration to achieve this. I am doing all tests from command line. Using Wireshark I can count how many requests are hitting the server in exactly one second and the count is fluctuating. The highest number I get was around 2500 requests in one second. My source server configuration is given below: Architecture : x86_64 CPU op-mode(s): 32-bit, 64-bit Byte Order: Little Endian CPU(s): 12 On-line CPU(s) list: 0-11 Thread(s) per core: 2 Core(s) per socket: 6 Socket(s): 1 NUMA node(s): 1 Vendor ID: GenuineIntel CPU family: 6 Model: 45 Stepping: 7 CPU MHz: 1999.900 BogoMIPS: 3999.80 Virtualization: VT-x L1d cache: 32K L1i cache: 32K L2 cache: 256K L3 cache: 15360K NUMA node0 CPU(s): 0-11 Ram: 16GB -- View this message in context: http://jmeter.512774.n5.nabble.com/How-to-achieve-4000-requests-per-second-using-JMeter-tp5724731.html Sent from the JMeter - Dev mailing list archive at Nabble.com.
