< Previous by Date | Date Index | Next by Date > |
< Previous in Thread | Thread Index | Next in Thread > |
Best regards, Byron Campen
polycarb:test alan$ ./testStack --num-runs=100000 Performing 100000 runs.100000 registrations peformed in 34386 ms, a rate of 2908.16 transactions per second.]Note: this test runs both sides (client and server) polycarb:test alan$polycarb:test alan$ system_profiler | awk '/^Hardware/,/^[^ H]/ {print} /^Memory/,/^[^ M]/ {print} /^Firewall/,/^[^ (Firewall)]/'Hardware: | magic_editHardware Overview: Model Name: MacBook Model Identifier: MacBook2,1 Processor Name: Intel Core 2 Duo Processor Speed: 2 GHz Number Of Processors: 1 Total Number Of Cores: 2 L2 Cache: 4 MB Memory: 2 GB Bus Speed: 667 MHz Memory: BANK 0/DIMM0: Size: 1 GB Type: DDR2 SDRAM Speed: 667 MHz BANK 1/DIMM1: Size: 1 GB Type: DDR2 SDRAM Speed: 667 MHz Firewall: Firewall Settings: Mode: Allow all incoming connections Let's see what happens if I change the firewall settings a little.... polycarb:test alan$ ./testStack Performing 10000 runs.10000 registrations peformed in 3489 ms, a rate of 2866.15 transactions per second.]Note: this test runs both sides (client and server)polycarb:test alan$ ./testStack --num-runs=100000Performing 100000 runs. 100000 registrations peformed in 32582 ms, a rate of 3069.18 transactions per second.]Note: this test runs both sides (client and server) polycarb:test alan$ Roughly the same... Firewall set to 'only allow certain applications'.I was prompted to permit 'testStack' to access the network when starting ...... Firewall: Firewall Settings:Mode: Limit incoming connections to specific services and applicationsSo, no, I don't seem to have a performance problem ... Odd. A On Jul 10, 2008, at 06:06 , Byron Campen wrote:Try doing 100000 runs and see if that ratio holds. Best regards, Byron CampenHard to say -- I'm on 10.5.4 and here is my output from testStack on mainpolycarb:test alan$ ./testStack Performing 10000 runs.10000 registrations peformed in 4319 ms, a rate of 2315.35 transactions per second.]Note: this test runs both sides (client and server) polycarb:test alan$ Tell me what to run and with what args so I can reproduce yours... This is an older MacBook (not Pro) 2GHz. A On Jul 9, 2008, at 15:44 , Byron Campen wrote:I upgraded my laptop to Leopard recently, and it appears that the performance of the resip stack has gone straight down the toilet. I have verified on one other Leopard install. On inspection, it looks like the Leopard firewall is at fault (accounting for >90% of the cycles used by testStack). Has anyone else dealt with this?Best regards, Byron Campen_______________________________________________ resiprocate-devel mailing list resiprocate-devel@xxxxxxxxxxxxxxx https://list.resiprocate.org/mailman/listinfo/resiprocate-devel
Attachment:
smime.p7s
Description: S/MIME cryptographic signature