fche changed the topic of #systemtap to: http://sourceware.org/systemtap; email systemtap@sourceware.org if answers here not timely, conversations may be logged
khaled has quit [Quit: Konversation terminated!]
derek088_ has joined #systemtap
derek0883 has quit [Remote host closed the connection]
derek088_ has quit [Remote host closed the connection]
derek0883 has joined #systemtap
derek0883 has quit [Remote host closed the connection]
derek0883 has joined #systemtap
orivej has quit [Ping timeout: 258 seconds]
derek0883 has quit [Remote host closed the connection]
derek0883 has joined #systemtap
derek0883 has quit [Remote host closed the connection]
derek0883 has joined #systemtap
_whitelogger has joined #systemtap
derek0883 has quit [Remote host closed the connection]
derek0883 has joined #systemtap
derek0883 has quit [Remote host closed the connection]
derek0883 has joined #systemtap
orivej has joined #systemtap
derek0883 has quit [Remote host closed the connection]
derek0883 has joined #systemtap
sscox has quit [Ping timeout: 256 seconds]
orivej has quit [Ping timeout: 246 seconds]
orivej has joined #systemtap
derek0883 has quit [Remote host closed the connection]
orivej has quit [Ping timeout: 260 seconds]
derek0883 has joined #systemtap
derek0883 has quit [Remote host closed the connection]
khaled has joined #systemtap
derek0883 has joined #systemtap
derek0883 has quit [Ping timeout: 244 seconds]
khaled has quit [Quit: Konversation terminated!]
mjw has joined #systemtap
khaled has joined #systemtap
lijunlong has quit [Ping timeout: 265 seconds]
lijunlong has joined #systemtap
derek0883 has joined #systemtap
hpt has quit [Ping timeout: 246 seconds]
derek0883 has quit [Ping timeout: 260 seconds]
derek0883 has joined #systemtap
orivej has joined #systemtap
derek0883 has quit [Ping timeout: 265 seconds]
zamba has quit [Ping timeout: 258 seconds]
zamba has joined #systemtap
orivej has quit [Ping timeout: 246 seconds]
amerey has joined #systemtap
tromey has joined #systemtap
sscox has joined #systemtap
derek0883 has joined #systemtap
irker971 has joined #systemtap
<irker971> systemtap: alizhang systemtap.git:azhang/pr13838 * release-4.3-93-g4232485ed / runtime/softfloat.c testsuite/buildok/floatingpoint.stp: modifications on string to float function and fix bugs in buildok floatingpoint script
DTEIT_ has joined #systemtap
DTEIT has quit [Ping timeout: 256 seconds]
DTEIT_ has quit [Ping timeout: 240 seconds]
DTEIT has joined #systemtap
orivej has joined #systemtap
derek0883 has quit [Ping timeout: 240 seconds]
derek0883 has joined #systemtap
sscox has quit [Ping timeout: 260 seconds]
<irker971> systemtap: fche systemtap.git:azhang/pr13838 * release-4.3-94-gbf4c677a1 / runtime/softfloat.c: softfloat: fix stackoverflow url
sscox has joined #systemtap
derek0883 has quit [Remote host closed the connection]
derek0883 has joined #systemtap
derek0883 has quit [Read error: Connection reset by peer]
derek0883 has joined #systemtap
derek0883 has quit [Remote host closed the connection]
orivej has quit [Ping timeout: 256 seconds]
orivej has joined #systemtap
<irker971> systemtap: smakarov systemtap.git:master * release-4.3-86-ge85ffdcf4 / testsuite/systemtap.onthefly/kprobes_onthefly.exp: PR26755 temporary kprobes_onthefly.exp: also disable m* on ppc
derek0883 has joined #systemtap
<agentzh> fche: kerneltoast has made more tweaks and fixes in his patch for the LRU locks: https://gist.github.com/agentzh/76baa805746c46d52c3adbcfba975c44
<agentzh> if it looks good, i can push to master.
<agentzh> the CPU improvement is orders of magnitude.
<agentzh> i'll prepare some graphs for comparison.
<agentzh> i'll put these graphs to the commit log too.
<agentzh> it's running the same stap ko against the same target processes with identical fake load.
<agentzh> *stap script
<agentzh> there's still room for optimizations, but that'll be another optimization and another patch.
derek0883 has quit [Remote host closed the connection]
derek0883 has joined #systemtap
<agentzh> fche: also added a NEWS entry as suggested to the patch: https://gist.github.com/agentzh/76baa805746c46d52c3adbcfba975c44
tromey has quit [Quit: ERC (IRC client for Emacs 27.1.50)]
mjw has quit [Quit: Leaving]
orivej has quit [Ping timeout: 240 seconds]
<fche> sounds good
<fche> thanks a lot guys
<fche> I'm not sure this optimization will hit smaller scale users too, but might
<fche> but am glad it's helping you guys
<agentzh> great, thanks
derek0883 has quit [Ping timeout: 240 seconds]
<irker971> systemtap: sultan systemtap.git:master * release-4.3-87-g4b937c5e9 / runtime/linux/runtime.h runtime/task_finder_vma.c: task_finder_vma: rewrite using RCU to fix performance issues
<agentzh> fche: the remaining 2/3 CPU time is in another spinlock around task_utrace_lock, and kerneltoast will look into it.
<fche> ok
<agentzh> the left-hand-side tower is in task_utrace_struct().
derek0883 has joined #systemtap
<agentzh> taking about 2/3 of the total ko CPU time.
<agentzh> not seeing the vma map hash table lookups any more.
<fche> ok
<agentzh> kerneltoast noticed that this lock can be replaced with RCU locks as well.
<agentzh> so we may kill this part as well :)
<agentzh> fche: btw, what do you think of this small patch? https://gist.github.com/agentzh/e05586565b77e6c791b41e6350a5df29
<agentzh> the current hash table size is too small.
<agentzh> and not configurable.
<agentzh> it helps reducing the hash conflicts.
<agentzh> in my tests.
<agentzh> *our
<fche> sure
<agentzh> thanks
<irker971> systemtap: yichun systemtap.git:master * release-4.3-88-g03bcbc766 / runtime/task_finder_vma.c: Optimize: increase the default size of the vma map hash table
amerey has quit [Remote host closed the connection]
khaled has quit [Quit: Konversation terminated!]
orivej has joined #systemtap
derek0883 has quit [Remote host closed the connection]