currently using the REL5-provided package on two nodes on local Cisco-switched LAN:
openais.x86_64 0.80.6-28.el5_6.1 installed with following configuration: # Please read the openais.conf.5 manual page aisexec { user: asterisk group: asterisk } totem { version: 2 secauth: off threads: 0 interface { ringnumber: 0 bindnetaddr: 172.24.100.0 mcastaddr: 239.255.4.1 mcastport: 5405 } } logging { debug: off syslog_facility: local1 syslog_priority: info timestamp: off to_file: no to_syslog: yes } amf { mode: disabled } to enable Asterisk distributed device state. we see cases where aisexec crashes, both with Asterisk running and stopped - strace output below: 0.000073 poll([{fd=1, events=POLLIN}, {fd=3, events=POLLIN}, {fd=4, events=POLLIN|POLLNVAL}], 3, 10) = 0 (Timeout) <0.009994> 0.010031 poll([{fd=1, events=POLLIN}, {fd=3, events=POLLIN}, {fd=4, events=POLLIN|POLLNVAL}], 3, 237) = 1 ([{fd=1, revents=POLLIN}]) <0.000007> 0.000037 recvmsg(1, {msg_name(16)={sa_family=AF_INET, sin_port=htons(5149), sin_addr=inet_addr("172.24.100.10")}, msg_iov(1)=[{"\2\0\"\377\254\30d\n\254\30d\n\2\0\254\30d\n\10\0\2\0\254\30d\n\10\0\4\0\0\0"..., 10000}], msg_controllen=0, msg_flags=0}, MSG_DONTWAIT|MSG_NOSIGNAL) = 82 <0.000010> 0.000072 poll([{fd=1, events=POLLIN}, {fd=3, events=POLLIN}, {fd=4, events=POLLIN|POLLNVAL}], 3, 237) = 1 ([{fd=3, revents=POLLIN}]) <0.180257> 0.180339 recvmsg(3, {msg_name(16)={sa_family=AF_INET, sin_port=htons(5149), sin_addr=inet_addr("172.24.100.10")}, msg_iov(1)=[{"\0\0\"\377\254\30d\fN\1\0\0004/\0\0N\1\0\0\0\0\0\0\254\30d\n\2\0\254\30"..., 10000}], msg_controllen=0, msg_flags=0}, MSG_DONTWAIT|MSG_NOSIGNAL) = 70 <0.000022> 0.000104 sendmsg(2, {msg_name(16)={sa_family=AF_INET, sin_port=htons(5405), sin_addr=inet_addr("172.24.100.10")}, msg_iov(1)=[{"\0\0\"\377\254\30d\fN\1\0\0005/\0\0N\1\0\0\0\0\0\0\254\30d\n\2\0\254\30"..., 70}], msg_controllen=0, msg_flags=0}, MSG_NOSIGNAL) = 70 <0.000014> 0.000072 poll([{fd=1, events=POLLIN}, {fd=3, events=POLLIN}, {fd=4, events=POLLIN|POLLNVAL}], 3, 209) = 1 ([{fd=4, revents=POLLIN}]) <0.037614> 0.037682 accept(4, {sa_family=AF_FILE, path=@""}, [4294967298]) = 5 <0.000023> 0.000096 fcntl(5, F_SETFL, O_RDONLY|O_NONBLOCK) = 0 <0.000012> 0.000040 setsockopt(5, SOL_SOCKET, SO_PASSCRED, [1], 4) = 0 <0.000006> 0.000070 poll([{fd=1, events=POLLIN}, {fd=3, events=POLLIN}, {fd=4, events=POLLIN|POLLNVAL}, {fd=5, events=POLLIN|POLLNVAL}], 4, 172) = 1 ([{fd=5, revents=POLLIN}]) <0.000158> 0.000207 setsockopt(5, SOL_SOCKET, SO_PASSCRED, [1], 4) = 0 <0.000006> 0.000029 recvmsg(5, {msg_name(0)=NULL, msg_iov(1)=[{"\1\0\0\0\252*\0\0\224\343TE\0\0\0\0\270\355\362+\0\0\0\0", 24}], msg_controllen=32, {cmsg_len=28, cmsg_level=SOL_SOCKET, cmsg_type=SCM_CREDENTIALS{pid=819, uid=301, gid=301}}, msg_flags=0}, MSG_NOSIGNAL) = 24 <0.000014> 0.000084 setsockopt(5, SOL_SOCKET, SO_PASSCRED, [0], 4) = 0 <0.000006> 0.000028 sendto(5, "\1\0\0\0\0\0\0\0", 8, MSG_WAITALL, NULL, 0) = 8 <0.000007> 0.000031 shmget(0x4554e394, 3000008, 0600) = 5144599 <0.000118> 0.000198 shmat(5144599, 0, 0) = ? <0.002286> 0.002332 semget(0x2bf2edb8, 3, 0600) = 1081360 <0.000108> 0.000155 mmap(NULL, 200000, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS|MAP_32BIT, -1, 0) = 0x41781000 <0.000212> 0.000262 mprotect(0x41781000, 4096, PROT_NONE) = 0 <0.000020> 0.000051 clone(child_stack=0x417b0f90, flags=CLONE_VM|CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD|CLONE_SYSVSEM|CLONE_SETTLS|CLONE_PARENT_SETTID|CLONE_CHILD_CLEARTID, parent_tidptr=0x417b1710, tls=0x417b1680, child_tidptr=0x417b1710) = 859 <0.000046> 0.000109 poll([{fd=1, events=POLLIN}, {fd=3, events=POLLIN}, {fd=4, events=POLLIN|POLLNVAL}, {fd=5, events=POLLIN|POLLNVAL}], 4, 168) = 1 ([{fd=4, revents=POLLIN}]) <0.000924> 0.000980 accept(4, {sa_family=AF_FILE, path=@""}, [4294967298]) = 6 <0.000011> 0.000063 fcntl(6, F_SETFL, O_RDONLY|O_NONBLOCK) = 0 <0.000006> 0.000049 setsockopt(6, SOL_SOCKET, SO_PASSCRED, [1], 4) = 0 <0.000006> 0.000033 poll([{fd=1, events=POLLIN}, {fd=3, events=POLLIN}, {fd=4, events=POLLIN|POLLNVAL}, {fd=5, events=POLLIN|POLLNVAL}, {fd=6, events=POLLIN|POLLNVAL}], 5, 167) = 1 ([{fd=6, revents=POLLIN}]) <0.000007> 0.000044 setsockopt(6, SOL_SOCKET, SO_PASSCRED, [1], 4) = 0 <0.000006> 0.000042 recvmsg(6, {msg_name(0)=NULL, msg_iov(1)=[{"\4\0\0\0\252*\0\0Rv-b\0\0\0\0A\246\10B\0\0\0\0", 24}], msg_controllen=32, {cmsg_len=28, cmsg_level=SOL_SOCKET, cmsg_type=SCM_CREDENTIALS{pid=819, uid=301, gid=301}}, msg_flags=0}, MSG_NOSIGNAL) = 24 <0.000010> 0.000072 setsockopt(6, SOL_SOCKET, SO_PASSCRED, [0], 4) = 0 <0.000006> 0.000041 sendto(6, "\1\0\0\0\0\0\0\0", 8, MSG_WAITALL, NULL, 0) = 8 <0.000007> 0.000037 shmget(0x622d7652, 3000008, 0600) = 5177368 <0.000006> 0.000036 shmat(5177368, 0, 0) = ? <0.002768> 0.002814 semget(0x4208a641, 3, 0600) = 1114129 <0.000008> 0.000054 mmap(NULL, 200000, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS|MAP_32BIT, -1, 0) = 0x4144c000 <0.000155> 0.000194 mprotect(0x4144c000, 4096, PROT_NONE) = 0 <0.000017> 0.000048 clone(child_stack=0x4147bf90, flags=CLONE_VM|CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD|CLONE_SYSVSEM|CLONE_SETTLS|CLONE_PARENT_SETTID|CLONE_CHILD_CLEARTID, parent_tidptr=0x4147c710, tls=0x4147c680, child_tidptr=0x4147c710) = 860 <0.000120> 0.000170 poll([{fd=1, events=POLLIN}, {fd=3, events=POLLIN}, {fd=4, events=POLLIN|POLLNVAL}, {fd=5, events=POLLIN|POLLNVAL}, {fd=6, events=POLLIN|POLLNVAL}], 5, 163) = 1 ([{fd=1, revents=POLLIN}]) <0.000013> 0.000069 recvmsg(1, {msg_name(16)={sa_family=AF_INET, sin_port=htons(5149), sin_addr=inet_addr("172.24.100.12")}, msg_iov(1)=[{"\5\0\"\377\254\30d\f\254\30d\n\2\0\254\30d\n\10\0\2\0\254\30d\n\10\0\4\0P\17"..., 10000}], msg_controllen=0, msg_flags=0}, MSG_DONTWAIT|MSG_NOSIGNAL) = 38 <0.000013> 0.000080 poll([{fd=1, events=POLLIN}, {fd=3, events=POLLIN}, {fd=4, events=POLLIN|POLLNVAL}, {fd=5, events=POLLIN|POLLNVAL}, {fd=6, events=POLLIN|POLLNVAL}], 5, 163) = 1 ([{fd=3, revents=POLLIN}]) <0.000007> 0.000064 recvmsg(3, {msg_name(16)={sa_family=AF_INET, sin_port=htons(5149), sin_addr=inet_addr("172.24.100.10")}, msg_iov(1)=[{"\0\0\"\377\254\30d\fN\1\0\0006/\0\0N\1\0\0\0\0\0\0\254\30d\n\2\0\254\30"..., 10000}], msg_controllen=0, msg_flags=0}, MSG_DONTWAIT|MSG_NOSIGNAL) = 70 <0.000007> 0.000066 sendmsg(2, {msg_name(16)={sa_family=AF_INET, sin_port=htons(5405), sin_addr=inet_addr("239.255.4.1")}, msg_iov(4)=[{"\1\2\"\377\254\30d\f\254\30d\f\2\0\254\30d\f\10\0\2\0\254\30d\f\10\0\4\0\0\0"..., 98}, {"\0\0\0\0\0\0\1\0", 8}, {"-\1", 2}, {"\1\0\1\0a(\1\0\0\0\0\0\0\1\0\4\0\0\0\0\0\0\0\0\0\0\0\0\0\f\0\0"..., 301}], msg_controllen=0, msg_flags=0}, MSG_NOSIGNAL) = 409 <0.000023> 0.000130 sendmsg(2, {msg_name(16)={sa_family=AF_INET, sin_port=htons(5405), sin_addr=inet_addr("172.24.100.10")}, msg_iov(1)=[{"\0\0\"\377\254\30d\fO\1\0\0007/\0\0O\1\0\0\0\0\0\0\254\30d\n\2\0\254\30"..., 70}], msg_controllen=0, msg_flags=0}, MSG_NOSIGNAL) = 70 <0.000012> 0.000118 semop(1114129, 0x7fffe515f810, 1) = 0 <0.000007> 0.000047 poll([{fd=1, events=POLLIN}, {fd=3, events=POLLIN}, {fd=4, events=POLLIN|POLLNVAL}, {fd=5, events=POLLIN|POLLNVAL}, {fd=6, events=POLLIN|POLLNVAL}], 5, 163) = 2 ([{fd=1, revents=POLLIN}, {fd=3, revents=POLLIN}]) <0.000007> 0.021694 +++ killed by SIGABRT +++ wondering if this resembles any known issues ?? Thanks, -- Chris Kirke Director - Systems Architecture Multi Service Corporation www.multiservice.com +1.913.663.9483 (direct) +1.816.718.0468 (mobile) +1.913.217.9318 (fax) --------------------------------------------------------------------------------------- This email is intended solely for the use of the addressee and may contain information that is confidential, proprietary, or both. If you receive this email in error please immediately notify the sender and delete the email. ---------------------------------------------------------------------------------------
_______________________________________________ Openais mailing list Openais@lists.linux-foundation.org https://lists.linux-foundation.org/mailman/listinfo/openais