fche changed the topic of #systemtap to: http://sourceware.org/systemtap; email systemtap@sourceware.org if answers here not timely, conversations may be logged
hpt has joined #systemtap
sanoj has joined #systemtap
sanoj has quit [Ping timeout: 240 seconds]
mjw has joined #systemtap
sanoj has joined #systemtap
slowfranklin has joined #systemtap
<lightydo> Hi, appreciate your comments on the following stap snippet and results: https://tinyurl.com/ydy4p46e
<lightydo> the results vary with each run (stap) but remain significantly inferior (copied, 1.29942 s, 3.3 GB/s, copied, 1.47352 s, 2.9 GB/s)
darvon has quit [Ping timeout: 248 seconds]
orivej has quit [Ping timeout: 256 seconds]
darvon has joined #systemtap
slowfranklin has quit [Quit: slowfranklin]
<mjw> lightydo, Looks like a worst case scenario. I would play with the bs and count and see how it affects things. What happens for example of you swap them? bs=1M count=4K and/or use real files.
<lightydo> will try that..
hpt has quit [Quit: Lost terminal]
<lightydo> mjw, indeed you are right. the performance hit is much lower when inverting bs and count values
<mjw> but yeah, there is some overhead to probing, the example you use seems to insert 2 million probe interrupts, which is probably noticeable.
<mjw> If you swap the arguments there are probably only ~10000 probe interrupts, which should be less noticeable.
<mjw> stap -t will give you some statistics
scox has quit [Ping timeout: 240 seconds]
aryehw has joined #systemtap
orivej has joined #systemtap
orivej has quit [Ping timeout: 240 seconds]
gromero has joined #systemtap
slowfranklin has joined #systemtap
sanoj has quit [Ping timeout: 240 seconds]
slowfranklin has quit [Quit: slowfranklin]
orivej has joined #systemtap
wcohen has quit [Ping timeout: 260 seconds]
scox has joined #systemtap
wcohen has joined #systemtap
mbenitez has joined #systemtap
mbenitez has quit [Client Quit]
mbenitez has joined #systemtap
mbenitez has quit [Read error: Connection reset by peer]
mbenitez has joined #systemtap
mbenitez has quit [Remote host closed the connection]
mbenitez has joined #systemtap
slowfranklin has joined #systemtap
slowfranklin has quit [Client Quit]
<fche> it'd also help if the kernel offered tracepoints at the vfs operations, so we wouldn't have to suffer full kprobes hits
tromey has joined #systemtap
aryehw has quit [Ping timeout: 260 seconds]
gromero has quit [Quit: Leaving]
gromero has joined #systemtap
mbenitez has quit [Ping timeout: 260 seconds]
mbenitez has joined #systemtap
mjw has quit [Quit: Leaving]
orivej has quit [Ping timeout: 256 seconds]
tromey has quit [Read error: Connection reset by peer]
tromey has joined #systemtap
mbenitez has quit [Remote host closed the connection]
mbenitez has joined #systemtap
orivej has joined #systemtap
mbenitez has quit [Quit: Leaving]
wcohen has quit [Ping timeout: 256 seconds]
tromey has quit [Quit: ERC (IRC client for Emacs 26.1)]
scox has quit [Ping timeout: 265 seconds]
wcohen has joined #systemtap
gromero has quit [Ping timeout: 256 seconds]
orivej has quit [Ping timeout: 264 seconds]