Re: [SR-Users] TLS performance testing

2012-05-16 Thread Jijo
Hi Daniel, Please let me know if you are aware about any fix on this issue. Thanks Jijo On Tue, May 15, 2012 at 6:55 PM, Jijo realj...@gmail.com wrote: Hi, I'm seeing similar issue in 3.1.0.. How did we fix it? The back trace from my test is, #2 0x0819c66c in qm_free (qm=0x7861c000,

Re: [SR-Users] TLS performance testing

2012-05-15 Thread Jijo
Hi, I'm seeing similar issue in 3.1.0.. How did we fix it? The back trace from my test is, #2 0x0819c66c in qm_free (qm=0x7861c000, p=0x798fa2b0, file=0xb6f0b140 tls: tls_init.c, func=0xb6f0bce0 ser_free, line=296) at mem/q_malloc.c:462 *#3 0xb6eec404 in ser_free (ptr=0x798fa2b0) at

Re: [SR-Users] TLS performance testing

2011-12-21 Thread Daniel-Constantin Mierla
Hello, can you send also the last log messages (especially the ones before the crash, printed by the same pid that wrote the core, there should be a 'BUG...' message)? Looks like a double free in the libssl, what is your libssl version? Cheers, Daniel On 12/21/11 2:58 AM, Kristian

Re: [SR-Users] TLS performance testing

2011-12-21 Thread Kristian Kielhofner
On Wed, Dec 21, 2011 at 4:36 AM, Daniel-Constantin Mierla mico...@gmail.com wrote: Hello, can you send also the last log messages (especially the ones before the crash, printed by the same pid that wrote the core, there should be a 'BUG...' message)? Looks like a double free in the libssl,

Re: [SR-Users] TLS performance testing

2011-12-21 Thread Daniel-Constantin Mierla
Hello, On 12/21/11 8:26 PM, Kristian Kielhofner wrote: On Wed, Dec 21, 2011 at 4:36 AM, Daniel-Constantin Mierla mico...@gmail.com wrote: Hello, can you send also the last log messages (especially the ones before the crash, printed by the same pid that wrote the core, there should be a

Re: [SR-Users] TLS performance testing

2011-12-21 Thread Kristian Kielhofner
On Wed, Dec 21, 2011 at 2:56 PM, Daniel-Constantin Mierla mico...@gmail.com wrote: it has to be at least the message printed by:        LOG(L_CRIT, BUG: qm_free: freeing already freed pointer,                 first free: %s: %s(%ld) - aborting\n,                f-file, f-func, f-line); Can

[SR-Users] TLS performance testing

2011-12-20 Thread Kristian Kielhofner
Hello everyone, I'm doing some TLS performance testing on Kamailio 3.2.1. Here's my setup: kamailio -V version: kamailio 3.2.1 (x86_64/linux) 31c991 flags: STATS: Off, USE_IPV6, USE_TCP, USE_TLS, TLS_HOOKS, USE_RAW_SOCKS, USE_STUN, DISABLE_NAGLE, USE_MCAST, DNS_IP_HACK, SHM_MEM, SHM_MMAP,

Re: [SR-Users] TLS performance testing

2011-12-20 Thread Daniel-Constantin Mierla
Hello, On 12/20/11 10:27 PM, Kristian Kielhofner wrote: Hello everyone, I'm doing some TLS performance testing on Kamailio 3.2.1. Here's my setup: kamailio -V version: kamailio 3.2.1 (x86_64/linux) 31c991 flags: STATS: Off, USE_IPV6, USE_TCP, USE_TLS, TLS_HOOKS, USE_RAW_SOCKS, USE_STUN,

Re: [SR-Users] TLS performance testing

2011-12-20 Thread Kristian Kielhofner
On Tue, Dec 20, 2011 at 5:20 PM, Daniel-Constantin Mierla mico...@gmail.com wrote: Hello, with tls the limit is usually the cpu or memory, due to encryption/decryption, but you say they look ok. What log level are you using in config? Is the test tool keeping the tls connections open or

Re: [SR-Users] TLS performance testing

2011-12-20 Thread Daniel-Constantin Mierla
On 12/20/11 11:55 PM, Kristian Kielhofner wrote: On Tue, Dec 20, 2011 at 5:20 PM, Daniel-Constantin Mierla mico...@gmail.com wrote: Hello, with tls the limit is usually the cpu or memory, due to encryption/decryption, but you say they look ok. What log level are you using in config? Is