Re: LTTng - some problem - not able to see kernel traces
Mathieu Desnoyers <[email protected]>
| Newsgroups | gmane.linux.kernel.tracing |
|---|---|
| Message-ID | <20070405181448.GA2714@Krystal> |
You should probably check the compiler warnings, and verify the rejects with the original LTTng code for 2.6.18. * Naval Saini ([email protected]) wrote: > Hi Yes, > I have verified, timestamps are not 0. > > But still the same problem, i dont get any events in files in > directory /tmp/tracer > Files empty are cpy_0 and files in subdirectory /tmp/tracer/control/ > > TIA > Naval > > On 4/4/07, Mathieu Desnoyers <[email protected]> wrote: > >Hi, > > > >see below, > > > >* Naval Saini ([email protected]) wrote: > >> Hi: > >> > >> I am porting LTTng (version info given below) on linux-2.6.18.2 for arm > >arch. > >> > >> LTTng 0.6.41 > >> LTT Control 0.3.35 > >> > >> No LTTng userspace tracer > >> No Genevent > >> > >> I have checked that above config should work from, > >> > >http://ltt.polymtl.ca/svn/ltt/branches/poly/doc/developer/lttng-lttv-compatibility.html > >> > >> I have applied the kernel patches, compiled and installed ltt-control > >> on my rootfs. Selected probes options in kernel config as built-in. > >> > >> This is the output i am getting. I am only interested in getting kernel > >traces. > >> > >> Maybe someone can tell me if i forgot to include something or merely > >> incorrectly trying to use LTTng from command line. > >> > >> Thanks and Regards, > >> Naval Saini > >> > >> > >> > >> # mount /mnt/debugfs > >> # > >> # lttctl -n trace -d -l /mnt/debugfs/ltt -t /tmp/trace > >> > >> > >> Linux Trace Toolkit Trace Control 0.35-12032007 > >> > >> Controlling trace : trace > >> > >> ltt_control : trace trace > >> Linux Trace Toolkit Trace Daemon 0.35-12032007 > >> > >> Reading from debugfs directory : /mnt/debugfs/ltt/trace > >> Writing to trace directory : /tmp/trace > >> > >> Creating supplementary trace files > >> Appending facility file kernel_arch_c2.xml > >> Appending facility file kernel_arch_mips.xml > >> Appending facility file kernel_arch_ppc.xml > >> Appending facility file compact.xml > >> Appending facility file locking.xml > >> Appending facility file fs_data.xml > >> Appending facility file statedump.xml > >> Appending facility file kernel_arch_arm.xml > >> Appending facility file network.xml > >> Appending facility file socket.xml > >> Appending facility file timer.xml > >> Appending facility file ipc.xml > >> Appending facility file kernel_arch_powerpc.xml > >> Appending facility file user_generic.xml > >> Appending facility file kernel_arch_x86_64.xml > >> Appending facility file kernel.xml > >> Appending facility file memory.xml > >> Appending facility file network_ip_interface.xml > >> Appending facility file kernel_arch_i386.xml > >> Appending facility file fs.xml > >> Appending facility file xen.xml > >> Appending facility file core.xml > >> Appending facility file process.xml > >> Appending facility file stack.xml > >> ltt_control : trace trace > >> > >> # > >> # > >> # lttctl -n trace -R > >> > >> > >> Linux Trace Toolkit Trace Control 0.35-12032007 > >> > >> Controlling trace : trace > >> > >> ltt_control : trace trace > >> ltt_control : trace trace > >> finish for cpu 0 , 405dcdb0 > >> finish for cpu 0 , 405dcc98 > >> finish for cpu 0 , 405dcb80 > >> finish for cpu 0 , 405dcaf4 > >> finish for cpu 0 , 405dc9dc > >> finish for cpu 0 , 405dc950 > >> LTT : facilities_ : 19 events lost in facilities_ channel (cpu 0). > > > >It looks like the events are not even written in the trace. It is most > >likely caused by a bad include/asm-arm/ltt.h header where the > >timestamping function would return a 0 time. Can you verify this ? > > > > > >> LTT : unread channel facilities_ offset is 196608 and cons_off : 0 (cpu > >0) > >> LTT : facilities_ : subbuffer 0 has non zero commit count. > >> LTT : facilities_ : commit count : 106, subbuf size 65536 > >> LTT : unread channel facilities_ offset is 196608 and cons_off : 65536 > >(cpu 0) > >> LTT : facilities_ : commit count : 0, subbuf size 65536 > >> LTT : unread channel facilities_ offset is 196608 and cons_off : 131072 > >(cpu 0) > >> LTT : facilities_ : subbuffer 0 has non zero commit count. > >> LTT : facilities_ : commit count : 106, subbuf size 65536 > >> LTT : interrupts_ : 6 events lost in interrupts_ channel (cpu 0). > >> LTT : unread channel interrupts_ offset is 196608 and cons_off : 0 (cpu > >0) > >> LTT : interrupts_ : subbuffer 0 has non zero commit count. > >> LTT : interrupts_ : commit count : 106, subbuf size 65536 > >> LTT : unread channel interrupts_ offset is 196608 and cons_off : 65536 > >(cpu 0) > >> LTT : interrupts_ : commit count : 0, subbuf size 65536 > >> LTT : unread channel interrupts_ offset is 196608 and cons_off : 131072 > >(cpu 0) > >> LTT : interrupts_ : subbuffer 0 has non zero commit count. > >> LTT : interrupts_ : commit count : 106, subbuf size 65536 > >> LTT : processes_ : 17 events lost in processes_ channel (cpu 0). > >> LTT : unread channel processes_ offset is 786432 and cons_off : 0 (cpu 0) > >> LTT : processes_ : subbuffer 0 has non zero commit count. > >> LTT : processes_ : commit count : 106, subbuf size 262144 > >> LTT : unread channel processes_ offset is 786432 and cons_off : 262144 > >(cpu 0) > >> LTT : processes_ : commit count : 0, subbuf size 262144 > >> LTT : unread channel processes_ offset is 786432 and cons_off : 524288 > >(cpu 0) > >> LTT : processes_ : subbuffer 0 has non zero commit count. > >> LTT : processes_ : commit count : 106, subbuf size 262144 > >> LTT : modules_ : 6 events lost in modules_ channel (cpu 0). > >> LTT : unread channel modules_ offset is 196608 and cons_off : 0 (cpu 0) > >> LTT : modules_ : subbuffer 0 has non zero commit count. > >> LTT : modules_ : commit count : 106, subbuf size 65536 > >> LTT : unread channel modules_ offset is 196608 and cons_off : 65536 (cpu > >0) > >> LTT : modules_ : commit count : 0, subbuf size 65536 > >> LTT : unread channel modules_ offset is 196608 and cons_off : 131072 > >(cpu 0) > >> LTT : modules_ : subbuffer 0 has non zero commit count. > >> LTT : modules_ : commit count : 106, subbuf size 65536 > >> LTT : cpu_ : 13070 events lost in cpu_ channel (cpu 0). > >> LTT : unread channel cpu_ offset is 3145728 and cons_off : 0 (cpu 0) > >> LTT : cpu_ : subbuffer 0 has non zero commit count. > >> LTT : cpu_ : commit count : 106, subbuf size 1048576 > >> LTT : unread channel cpu_ offset is 3145728 and cons_off : 1048576 (cpu > >0) > >> LTT : cpu_ : commit count : 0, subbuf size 1048576 > >> LTT : unread channel cpu_ offset is 3145728 and cons_off : 2097152 (cpu > >0) > >> LTT : cpu_ : subbuffer 0 has non zero commit count. > >> LTT : cpu_ : commit count : 106, subbuf size 1048576 > >> LTT : network_ : 6 events lost in network_ channel (cpu 0). > >> LTT : unread channel network_ offset is 196608 and cons_off : 0 (cpu 0) > >> LTT : network_ : subbuffer 0 has non zero commit count. > >> LTT : network_ : commit count : 106, subbuf size 65536 > >> LTT : unread channel network_ offset is 196608 and cons_off : 65536 (cpu > >0) > >> LTT : network_ : commit count : 0, subbuf size 65536 > >> LTT : unread channel network_ offset is 196608 and cons_off : 131072 > >(cpu 0) > >> LTT : network_ : subbuffer 0 has non zero commit count. > >> LTT : network_ : commit count : 106, subbuf size 65536 > >> _______________________________________________ > >> Ltt-dev mailing list > >> [email protected] > >> http://listserv.shafik.org/mailman/listinfo/ltt-dev > >> > > > >-- > >Mathieu Desnoyers > >Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal > >OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68 > > > -- Mathieu Desnoyers Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68