fche changed the topic of #systemtap to: http://sourceware.org/systemtap; email systemtap@sourceware.org if answers here not timely, conversations may be logged
orivej has quit [Ping timeout: 256 seconds]
gromero has quit [Ping timeout: 245 seconds]
gromero has joined #systemtap
hpt has joined #systemtap
gromero has quit [Ping timeout: 240 seconds]
orivej has joined #systemtap
orivej has quit [Ping timeout: 240 seconds]
scox has joined #systemtap
sanoj has joined #systemtap
prefork has quit [Read error: Connection reset by peer]
ggherdov` has quit [Read error: Connection reset by peer]
DuncanT has quit [Ping timeout: 256 seconds]
prefork has joined #systemtap
gila has quit [Ping timeout: 260 seconds]
gila has joined #systemtap
ggherdov` has joined #systemtap
ggherdov` has quit [Excess Flood]
DuncanT has joined #systemtap
ggherdov` has joined #systemtap
ggherdov` has quit [Excess Flood]
ggherdov` has joined #systemtap
ggherdov` has quit [Excess Flood]
ggherdov` has joined #systemtap
ggherdov` has quit [Excess Flood]
naveen has joined #systemtap
slowfranklin has joined #systemtap
ggherdov` has joined #systemtap
ggherdov` has quit [Excess Flood]
naveen has quit [Quit: WeeChat 2.0.1]
slowfranklin has quit [Quit: slowfranklin]
slowfranklin has joined #systemtap
slowfranklin has quit [Client Quit]
slowfranklin has joined #systemtap
acaringi__ has joined #systemtap
ggherdov` has joined #systemtap
ggherdov` has quit [Excess Flood]
acaringi has quit [Ping timeout: 256 seconds]
acaringi has joined #systemtap
acaringi__ has quit [Ping timeout: 248 seconds]
ggherdov` has joined #systemtap
ggherdov` has quit [Excess Flood]
naveen has joined #systemtap
naveen_ has joined #systemtap
naveen has quit [Ping timeout: 255 seconds]
naveen_ has quit [Quit: WeeChat 2.0.1]
hpt has quit [Quit: Lost terminal]
naveen has joined #systemtap
ggherdov` has joined #systemtap
ggherdov` has quit [Excess Flood]
mjw has joined #systemtap
RenHoekNL has joined #systemtap
<RenHoekNL> Hi I have a question. Does the kernel keep track of how many cycles a process has used (user and kernel space) that I can print when a process ends? Or do I have to keep track of it myself with timer.profile? If so, isn't that a lot of overhead?
<izabera> RenHoekNL: did you try perf stat?
<RenHoekNL> I'm new to systemtap, what exactly should I be looking for?
<izabera> it's not a systemtap thing
<izabera> your distro probably has a package called perf-tools or similar
<RenHoekNL> Oh yes, I looked at that.. problem is I need to analyse a pipeline that spawns multiple other process and see where the bottlenecks are.. so it's not just the performance of one process.. I thought systemtap would be the way to go since I can hook process creating and termination
<RenHoekNL> I don't think perf would be very useful here.. or am I wrong?
gila has quit [Quit: Textual IRC Client: www.textualapp.com]
ggherdov` has joined #systemtap
ggherdov` has quit [Excess Flood]
RenHoekNL has quit [Ping timeout: 260 seconds]
sanoj has quit [Ping timeout: 245 seconds]
ggherdov` has joined #systemtap
ggherdov` has quit [Excess Flood]
orivej has joined #systemtap
gromero has joined #systemtap
mbenitez has joined #systemtap
mbenitez has joined #systemtap
mbenitez has quit [Changing host]
wcohen has quit [Remote host closed the connection]
ggherdov` has joined #systemtap
ggherdov` has quit [Excess Flood]
wcohen has joined #systemtap
naveen has quit [Ping timeout: 245 seconds]
naveen has joined #systemtap
tromey has joined #systemtap
naveen has quit [Quit: WeeChat 2.0.1]
naveen has joined #systemtap
ggherdov` has joined #systemtap
ggherdov` has quit [Excess Flood]
tromey has quit [Read error: Connection reset by peer]
ggherdov` has joined #systemtap
ggherdov` has quit [Excess Flood]
naveen has quit [Ping timeout: 276 seconds]
naveen has joined #systemtap
slowfranklin has quit [Quit: slowfranklin]
slowfranklin has joined #systemtap
ggherdov` has joined #systemtap
ggherdov` has quit [Excess Flood]
slowfranklin has quit [Quit: slowfranklin]
slowfranklin has joined #systemtap
slowfranklin has quit [Client Quit]
zodbot has quit [Disconnected by services]
zodbot has joined #systemtap
ggherdov` has joined #systemtap
ggherdov` has quit [Excess Flood]
tromey has joined #systemtap
naveen has quit [Quit: WeeChat 2.0.1]
naveen has joined #systemtap
mjw has quit [Quit: Leaving]
irker230 has joined #systemtap
<irker230> systemtap: dsmith systemtap.git:refs/heads/master * release-3.2-121-g2f6fcfc / tapset/linux/ipmib.stp tapset/linux/netfilter.stp tapset/linux/networking.stp tapset/linux/tcp.stp tapset/linux/tcpmib.stp: Fix BZ1546179 by being careful when accessing sk_buff structures. http://tinyurl.com/ya4nexv5
eklitzke has quit [Quit: bye]
eklitzke has joined #systemtap
ggherdov` has joined #systemtap
ggherdov` has quit [Excess Flood]
mjw has joined #systemtap
slowfranklin has joined #systemtap
naveen has quit [Quit: WeeChat 2.0.1]
slowfranklin has quit [Quit: slowfranklin]
slowfranklin has joined #systemtap
ggherdov` has joined #systemtap
ggherdov` has quit [Excess Flood]
mbenitez has quit [Quit: Leaving]
tromey has quit [Quit: ERC (IRC client for Emacs 26.0.91)]
wcohen has quit [Ping timeout: 265 seconds]
slowfranklin has quit [Quit: slowfranklin]
gromero has quit [Ping timeout: 240 seconds]
ggherdov` has joined #systemtap
ggherdov` has quit [Excess Flood]
wcohen has joined #systemtap
ggherdov` has joined #systemtap
ggherdov` has quit [Excess Flood]
amerey has quit [Quit: Leaving]
extra has joined #systemtap
<extra> SystemTap and gdb should be able to be used at the same time, right?
<fche> yup
<fche> one place where conflicts have occurred is when a systemtap userspace probe and a gdb session are targeting the same process
<fche> sometimes ISTR gdb getting confused about extra sigtraps
<eklitzke> yeah i've seen gdb get stuck
<extra> alright... yeah, gdb seems to bite the dust after using systemtap with -x <pid of process being debugged>
<eklitzke> when i used stap on a process gdb was already attached to it got stuck, but when i gdb attached to a process that was already stapped it's fine
<extra> interesting... I wonder why that is - does SystemTap use ptrace behind the scenes?
<fche> nope
<fche> hmm. wait yes, very briefly, to synchronize startup
<eklitzke> you can't have two processes ptrace attached at the same time
<eklitzke> so how does that work?
<fche> hm, actually I don't think we do that any more;
<fche> WORKAROUND_BZ467568 ... ancient thing that's not turned o
<fche> on
<fche> hm, looking at that pastebin, can't think of a reason for that off the top of my head
<fche> no such process -- did it die?
<extra> no, it is still running
<extra> the process was stopped at a breakpoint when I started stap, though... I wonder what happens when stap is started while it's running