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
hchiramm_ has quit [Ping timeout: 250 seconds]
hchiramm has quit [Ping timeout: 244 seconds]
srikar_away is now known as srikar
hpt has quit [Ping timeout: 246 seconds]
hpt has joined #systemtap
hkshaw has quit [Quit: Leaving.]
hchiramm has joined #systemtap
hchiramm_ has joined #systemtap
hpt has quit [Ping timeout: 276 seconds]
hpt has joined #systemtap
irker893 has quit [Quit: transmission timeout]
hkshaw has joined #systemtap
ananth has joined #systemtap
ravi_ has joined #systemtap
srikar is now known as srikar_away
hchiramm has quit [Read error: Connection reset by peer]
hchiramm_ has quit [Read error: Connection reset by peer]
hpt has quit [Quit: Lost terminal]
hpt has joined #systemtap
hchiramm_ has joined #systemtap
hpt has quit [Ping timeout: 250 seconds]
hchiramm has joined #systemtap
hpt has joined #systemtap
nkambo has joined #systemtap
ego has joined #systemtap
cbzx has joined #systemtap
cbzx has quit [Client Quit]
ego has quit [Ping timeout: 244 seconds]
srikar_away is now known as srikar
naveen has joined #systemtap
ego has joined #systemtap
hpt has quit [Ping timeout: 252 seconds]
nkambo has quit [Read error: Connection reset by peer]
ego has quit [Ping timeout: 264 seconds]
hpt has joined #systemtap
ego has joined #systemtap
hpt has quit [Ping timeout: 244 seconds]
hpt has joined #systemtap
hpt has quit [Ping timeout: 240 seconds]
ego has quit [Ping timeout: 264 seconds]
mjw has joined #systemtap
hchiramm has quit [Read error: Connection reset by peer]
hchiramm_ has quit [Read error: Connection reset by peer]
ravi_ has quit [Remote host closed the connection]
hkshaw has quit [Ping timeout: 240 seconds]
hchiramm has quit [Ping timeout: 244 seconds]
hchiramm_ has quit [Ping timeout: 260 seconds]
srikar is now known as srikar_away
<modem>
heya
<modem>
fche, hi
<modem>
I am needed something that I think is not implemented as a tapset function in systemtap
<modem>
I am willing do add it in a tapset but a little advices would be needed
<modem>
basically I need to like have a conditionnal breakpoint when i am hit from a special path
hchiramm_ has joined #systemtap
hchiramm has joined #systemtap
<modem>
also, I do not want this breakpoint to be hit by any thread/CPU, only if the current running thread just got from my special path
<modem>
so actually this is very much more like the @entry() does
<modem>
only it is not linked to an "entry point"
<modem>
but the condition of being from a special path is exactly the same
<modem>
I'd like to add two function
<modem>
entry_open ()
<modem>
and entry_reset ()
<modem>
the later will always reset the entry_open() and need to be call each time entry_open() has been called
<modem>
but also because you sometime don't know if you came here from your special path, the entry_reset() also could be a no-op is entry_open() has not been started
<modem>
entry_reset() would return a bool, if its true then you are from the entry_open()'s path, otherwise you just did a no-op
<modem>
Any advices or where to look at the runtime code for the TID+cpu()+etc combo to apply that are welcome :-) Ty
ananth has quit [Quit: Leaving]
<modem>
btw there is a print_regs () but no dump_stack ()
<modem>
that be cool to have an dump_stack () { hex_display (register ("rsp"), 64); } or some kind of it
<fche>
hi modem
<modem>
fche, hi, i just implemented my own dump_stack ()
<fche>
re. your conditional probe ... probably use normal probes and conditionals within them
<modem>
fche, it's a bit complex
<fche>
or even the on-the-fly syntax probe first_probe { activate_second[tid()] = 1 } probe second_probe if activate_second[tid()] { } (if we allow tid() in there)
<modem>
fche, could be easier with the entry()-framework
<modem>
well yeah i could do that
<fche>
that bit is provided by the kernel, and only assists with keeping a place for holding the data from entry to exit
<fche>
but we can't trigger it at arbitrary points, only .return
<modem>
fche, btw, how to retrieve sizeof(long) in .stp ?
<modem>
fche, ah ok it's part of the kprobe framework
<modem>
i thought it was systemtap-feature
drsmith has joined #systemtap
<fche>
sizeof(long) ? couple of ways -- %{ sizeof(long) %} in an expression context (using embedded-C)
tromey has quit [Quit: ERC (IRC client for Emacs 25.0.91.2)]
ego has quit [Quit: Leaving]
tromey has joined #systemtap
tromey has quit [Quit: ERC (IRC client for Emacs 25.0.92.1)]
tromey has joined #systemtap
ajakop has joined #systemtap
hkshaw has quit [Quit: Leaving.]
srikar is now known as srikar_away
mjw has quit [Quit: Leaving]
flu_ has quit [Read error: Connection reset by peer]
hchiramm has quit [Ping timeout: 244 seconds]
hchiramm_ has quit [Ping timeout: 244 seconds]
<irker111>
systemtap: ajakop systemtap.git:refs/heads/ajakop/13608 * release-2.9-364-gdab6460 / testsuite/systemtap.server/server_req_size.exp: PR13608: compare the tested output to a short string http://tinyurl.com/hq6b782
<irker111>
systemtap: ajakop systemtap.git:refs/heads/ajakop/13608 * release-2.9-365-gb6368aa / testsuite/lib/systemtap.exp: PR13608: poll checking if the stap server started http://tinyurl.com/h3tmwas
<irker111>
systemtap: ajakop systemtap.git:refs/heads/master * release-2.9-408-g8c074dc / man/stap-server.8 stap-server stap-serverd.cxx: PR13608: fixed comments and docs to make more sense http://tinyurl.com/h7nlcq3
<irker111>
systemtap: ajakop systemtap.git:refs/heads/master * release-2.9-409-g1946a94 / testsuite/systemtap.server/server_req_size.exp: PR13608: test compile server request size options http://tinyurl.com/j3eqtku
<irker111>
systemtap: ajakop systemtap.git:refs/heads/master * release-2.9-410-gc1531f3 / testsuite/lib/systemtap.exp: PR13608: poll checking if the stap server started http://tinyurl.com/jbjk224
<fche>
thanks abe!
<ajakop>
fche, you're welcome
flu_ has joined #systemtap
tromey has quit [Quit: ERC (IRC client for Emacs 25.0.92.1)]