fche changed the topic of #systemtap to: http://sourceware.org/systemtap; email systemtap@sourceware.org if answers here not timely, conversations may be logged
scox has joined #systemtap
hpt has joined #systemtap
srikar_away is now known as srikar
hpt has quit [Quit: leaving]
lzap has quit [Ping timeout: 276 seconds]
hpt has joined #systemtap
lzap has joined #systemtap
hkshaw has quit [Quit: Leaving.]
irker712 has quit [Quit: transmission timeout]
hkshaw has joined #systemtap
srikar is now known as srikar_away
ananth has joined #systemtap
ravi has joined #systemtap
ego has joined #systemtap
nkambo2 has joined #systemtap
nkambo1 has quit [Ping timeout: 246 seconds]
hchiramm has joined #systemtap
naveen has joined #systemtap
ego has quit [Ping timeout: 244 seconds]
srikar_away is now known as srikar
nkambo2 has quit [Ping timeout: 246 seconds]
ego has joined #systemtap
srikar is now known as srikar_away
srikar_away is now known as srikar
hpt has quit [Ping timeout: 250 seconds]
nkambo has joined #systemtap
hpt has joined #systemtap
ton31337_ is now known as ton31337
wakatana2 has joined #systemtap
ravi has quit [Remote host closed the connection]
ravi has joined #systemtap
ego has quit [Ping timeout: 260 seconds]
hpt has quit [Ping timeout: 260 seconds]
hpt has joined #systemtap
cap_ has joined #systemtap
hpt has quit [Ping timeout: 244 seconds]
ego has joined #systemtap
mjw has joined #systemtap
hkshaw has quit [Read error: Connection reset by peer]
hkshaw has joined #systemtap
hkshaw has quit [Quit: Leaving.]
hkshaw has joined #systemtap
nkambo has quit [Ping timeout: 260 seconds]
nkambo has joined #systemtap
scox has quit [Ping timeout: 244 seconds]
ego has quit [Ping timeout: 244 seconds]
nkambo has quit [Ping timeout: 252 seconds]
nkambo has joined #systemtap
pmuldoon_ has joined #systemtap
pmuldoon has quit [Remote host closed the connection]
ego has joined #systemtap
naveen has quit [Quit: Leaving.]
ravi has quit [Quit: Leaving]
ananth has quit [Ping timeout: 260 seconds]
nkambo1 has joined #systemtap
nkambo has quit [Ping timeout: 276 seconds]
nkambo1 has quit [Ping timeout: 260 seconds]
nkambo1 has joined #systemtap
nkambo2 has joined #systemtap
nkambo has joined #systemtap
srikar is now known as srikar_away
nkambo1 has quit [Ping timeout: 246 seconds]
wcohen has quit [Ping timeout: 260 seconds]
nkambo2 has quit [Ping timeout: 276 seconds]
nkambo1 has joined #systemtap
nkambo has quit [Ping timeout: 240 seconds]
hkshaw has quit [Ping timeout: 250 seconds]
nkambo2 has joined #systemtap
nkambo1 has quit [Read error: Connection reset by peer]
nkambo1 has joined #systemtap
nkambo2 has quit [Ping timeout: 260 seconds]
hkshaw has joined #systemtap
nkambo1 has quit [Ping timeout: 252 seconds]
ego has quit [Ping timeout: 246 seconds]
ravi has joined #systemtap
hchiramm has quit [Ping timeout: 246 seconds]
ego has joined #systemtap
scox has joined #systemtap
flu_ has joined #systemtap
ravi has quit [Ping timeout: 244 seconds]
ravi has joined #systemtap
ravi has quit [Client Quit]
ravi has joined #systemtap
mbenitez has joined #systemtap
ego has quit [Ping timeout: 260 seconds]
wcohen has joined #systemtap
nili has joined #systemtap
nili is now known as Guest6282
tromey has joined #systemtap
drsmith has joined #systemtap
nkambo has joined #systemtap
nkambo1 has joined #systemtap
ravi has quit [Ping timeout: 276 seconds]
nkambo has quit [Ping timeout: 276 seconds]
nkambo1 has quit [Remote host closed the connection]
naveen has joined #systemtap
srikar_away is now known as srikar
brolley has joined #systemtap
naveen has quit [Quit: Leaving.]
srikar is now known as srikar_away
will has joined #systemtap
will is now known as otherwill
<otherwill> hi guys, I'm trying to get parameters values from calls, using the para-callgraph.stp script, but all floating point variables are being show as ? . Does anyone know if there's a way to solve it?
<jistone> otherwill, generally speaking - kernel code can't use floating point hardware
<jistone> if stap will let you take the address of the parameter then you may be able to read it like an integer, dump the raw ieee 754 hex
<jistone> it must be in memory for that, not a register
<otherwill> I'm using $$parms$$ to get everything
<jistone> right - that's not going to be smart enough here, unfortunately
<otherwill> well, at least now I know what is wrong. I'll try another approach
<jistone> ^ a bug on this topic, but no real activity to speak of
<otherwill> jistone: you helped me a lot, I'm on this for 3 days now
<otherwill> I'll see what I can do, if I find something, I'll answer this bug thread
cap_ has quit [Quit: .]
<jistone> otherwill, please feel free to ask sooner next time!
<jistone> I appreciate the effort of trying on your own, but I wouldn't want folks struggling toward a dead end
<jistone> but hey, if you actually find something to solve that bug, it won't be a dead end after all
<otherwill> I think I'll try another software
<otherwill> before I was using Intel PIN, but there was a lot of problems trying to access unauthorized memory when I needed pointer values
<otherwill> maybe I can use PIN together with Stap
<otherwill> I'll see
<jistone> we also have systemtap --runtime=dyninst
<jistone> we possibly could use floating point directly there
<otherwill> sorry to be so noob, but I tried to activate dyninst in my OS (Arch Linux), but I could not find out how to do it
<jistone> I don't know if the Arch build is configured with dyninst by default
<otherwill> ERROR: --runtime=dyninst unavailable; this build lacks DYNINST feature
<otherwill> this is the message I got
<jistone> then it seems not
<jistone> "stap -V" will also tell features, should have DYNINST listed
<otherwill> DYNINST is not
<jistone> I think dyninst was in AUR though
<otherwill> it was, but it's not anymore
<jistone> huh
<jistone> I guess you're left to compile it on your own then, sorry
<jistone> or come use Fedora, it's nice too :)
<fche> we hardly ever bite
<jistone> anyway, floating point currently won't work in stap --dyninst either, but it might be a lower barrier to get that going
<fche> (wonder if we could try -msoft-float!)
<otherwill> fche: it's a lot of reconfigurations to do, but it could be an option to consider. Maybe in a VM :)
<otherwill> sorry, -msoft-float is a compiler option?
<jistone> yes
<fche> yeah. was talking more to josh, thinking out loud
<otherwill> let me try
<jistone> that might be just one piece of the puzzle
<jistone> e.g. the other dependent bug, we don't even parse any floating point DWARF right now
<fche> otherwill, it definitely won't work now
<fche> I'm speculating it might be a path toward this in the future
<otherwill> yes, I can confirm that doesn't work
<otherwill> huahua
<otherwill> I did not tried, but is it possible to get the values of $$parms individually, as an array?
<jistone> not so generically, but you can access particular named parameters
<fche> & $parma
<jistone> perhaps @cast(& $my_f64, "int64_t")
<otherwill> is there any other type than floats that I'll get as "?" ?
<jistone> "?" may simply come up if the dwarf is incomplete in any way, e.g. a parameter optimized out
<otherwill> my PIN output was very similar to the Stap callgraph
<otherwill> I think I can merge the outputs
nkambo has joined #systemtap
irker109 has joined #systemtap
<irker109> systemtap: flu systemtap.git:refs/heads/master * release-3.0-78-g5d27641 / NEWS cmdline.h elaborate.cxx man/stap.1.in session.cxx session.h testsuite/systemtap.base/timeout.exp: new -T timeout option http://tinyurl.com/z428d8e
<fche> that was quick
<fche> flu_, my main reason for asking for that option was that we use -c sleep XXX quite a bit in the testsuite, even when not really appropriate
<fche> could you review such cases, esp. in the systemtap.examples set, and convert them to -T ?
<flu_> sure
<fche> nice work btw, didn't even have to remind about the NEWS! :)
mjw has quit [Quit: Leaving]
mnaser has left #systemtap ["Textual IRC Client: www.textualapp.com"]
nkambo has quit [Quit: Good day !]
<otherwill> guys, tks for help, bye
otherwill has quit [Quit: Bye]
chris2 has quit [Ping timeout: 260 seconds]
tromey has quit [Quit: ERC (IRC client for Emacs 25.0.93.1)]
wcohen has quit [Ping timeout: 276 seconds]
scox has quit [Ping timeout: 246 seconds]
<irker109> systemtap: jistone systemtap.git:refs/heads/master * release-3.0-79-g37a3892 / tapsets.cxx: tapsets: use levenshtein_suggest for kprobe.function http://tinyurl.com/jcq9k85
mbenitez has quit [Quit: Leaving]
iJ1eirae_ has joined #systemtap
modem has quit [Disconnected by services]
iJ1eirae_ has quit [Quit: leaving]
modem_ has joined #systemtap
<fche> thanks josh
modem_ has quit [Client Quit]
drsmith has left #systemtap [#systemtap]
modem has joined #systemtap
wcohen has joined #systemtap
brolley has left #systemtap [#systemtap]
modem has quit [Changing host]
modem has joined #systemtap
modem has quit [Remote host closed the connection]
modem has joined #systemtap
modem has quit [Remote host closed the connection]
<jistone> thanks fche
<jistone> fche, what do you think of start an auto-pocalypse? http://paste.fedoraproject.org/367742/63522949
<jistone> (converted most blah<blah,blah>::iterator in tapsets.cxx)
modem has joined #systemtap
<fche> go for it
<fche> will put in a word to management to start paying you by removed characters
<jistone> heh
<jistone> hmm, can git-diff summarize the character-delta too?
<fche> we will find a way
<irker109> systemtap: jistone systemtap.git:refs/heads/master * release-3.0-80-gb4662f6 / tapsets.cxx: tapsets.cxx iterator auto-pocalypse http://tinyurl.com/h45e5vn
wakatana2 has quit [Remote host closed the connection]
scox has joined #systemtap