rgrinberg has joined #mirage
rgrinberg has quit [Quit: Leaving.]
rgrinberg has joined #mirage
rgrinberg has quit [Quit: Leaving.]
rgrinberg has joined #mirage
rgrinberg has quit [Quit: Leaving.]
rgrinberg has joined #mirage
thomasga has quit [Quit: Leaving.]
brson has quit [Quit: leaving]
brson has joined #mirage
brson_ has joined #mirage
brson_ has quit [Client Quit]
brson_ has joined #mirage
brson has quit [Ping timeout: 244 seconds]
tlockney is now known as tlockney_away
brson_ has quit [Ping timeout: 244 seconds]
hhugo has joined #mirage
bcg has quit [Ping timeout: 250 seconds]
hhugo has quit [Quit: Leaving.]
rgrinberg has quit [Quit: Leaving.]
englishm has joined #mirage
thomasga has joined #mirage
djs55 has joined #mirage
djs55 has quit [Client Quit]
djs55 has joined #mirage
andreas has joined #mirage
andreas1 has quit [Ping timeout: 272 seconds]
avsm has joined #mirage
dsheets has joined #mirage
jonludlam has joined #mirage
* avsm
replots graphs, lots of graphs
<
avsm>
dsheets: worth pulling together docker onto the jitsu graph?
<
dsheets>
avsm, maybe... depends on if i can get better numbers. i'm looking at straces now
<
dsheets>
i'd like to be able to see we at least know why it's slow
<
dsheets>
perhaps i can remove disk access
<
dsheets>
also, do you know which dhcp client puts network data into environment variables?
<
avsm>
the isc one i think
<
avsm>
i'm going to take a shot at a mirage dhcp client after this
<
avsm>
as in one that runs on unix
hhugo has joined #mirage
<
avsm>
yeah characterisign docker slowness would be useful — wonder if its just aufs
<
jonludlam>
a dhcp server would be nice
<
dsheets>
that would be absurd... i don't even use the fs
<
dsheets>
but there is probably startup overhead somehow
<
dsheets>
avsm, it's using devicemapper
<
avsm>
jonludlam: xen boot doesnt depend on udev does it?
<
avsm>
domain build
<
jonludlam>
shouldn't do
<
jonludlam>
not in the hacked version
<
avsm>
yes but before
<
avsm>
that might explain docker
<
jonludlam>
it doesn't need to - xl will call the hotplug scripts directly
<
avsm>
got it, so xend used to?
<
jonludlam>
so does xapi :-(
<
thomasga>
avsm: do you know what happens if we do too many printf without flushing the console?
<
thomasga>
(ie. printf* and no call to Console.log_s)
<
thomasga>
can it make the console ring explode?
<
avsm>
thomasga: not recommended for performance
<
avsm>
xenconsoled is a bit racy
<
avsm>
but it should work
<
avsm>
the log_S will just block
<
avsm>
but xenconsoled draining ring has been known to be buggy in the past, didnt think it was now
<
thomasga>
ok I'll remove all my printf then ...
<
thomasga>
seems to work ok at least
<
thomasga>
(but sometime, some random errors)
mort___ has joined #mirage
<
mort___>
hannes: another side channel attack (less relevant to tls perhaps but still :)
<
hannes>
mort___: interesting, again gnupg pays for not using blinding for rsa computation..
avsm has quit [Quit: Leaving.]
<
mort___>
<glib, uninformed>what we need is cdma applied to computation</glib, uninformed>
<
dsheets>
bah "MMC Device 0 not found\nspl: mmc device not found!!" if I try to boot a btrfs-enabled xenarm kernel
thomasga has quit [Quit: Leaving.]
mort___ has quit [Ping timeout: 245 seconds]
<
hannes>
(it's not only blinding, but also normalization -- compute first c' = c mod n before decryption)
bcg has joined #mirage
bcg has quit [Client Quit]
thomasga has joined #mirage
avsm has joined #mirage
<
dsheets>
Magnus3, it's... much faster
<
dsheets>
feels like at least 5x
<
dsheets>
(systemd vs upstart)
andreas has quit [Ping timeout: 245 seconds]
o_pax has joined #mirage
andreas has joined #mirage
thomasga has quit [Quit: Leaving.]
mort___ has joined #mirage
<
avsm>
mort___: that was a quick drive
thomasga has joined #mirage
<
mort___>
back in horizon
<
mort___>
not dirving south until ~4
<
mort___>
meetings+phd supervsiion first
<
avsm>
mort___: iml gave a bunch of feedback
<
avsm>
now reading nemesis paper :)
<
mort___>
the jsac one?
<
mort___>
his feedback usu good tho often highy compressed
<
mort___>
(you never read neemsis paper before? used to be compulsory in srg ;)
<
avsm>
trying to find detail about filesystem
<
mort___>
iap or smh (or poss even rolf) good people to ask
<
mort___>
nemesis was woefully under published
<
mort___>
think the fs stuff was done out of twente
mort___ has quit [Quit: Leaving.]
mort___ has joined #mirage
mort___ has quit [Remote host closed the connection]
mort___ has joined #mirage
<
mort___>
think the posix api layers above nemesis were done @ glasgow iirc
<
mort___>
(ask rolf)
o_pax has quit [Quit: o_pax]
thomasga has quit [Quit: Leaving.]
andreas has quit [Ping timeout: 244 seconds]
mort___ has quit [Quit: Leaving.]
thomasga has joined #mirage
o_pax has joined #mirage
djs55 has quit [Quit: Leaving.]
<
dsheets>
avsm, still doesn't cover the non-xen case, though
tlockney_away is now known as tlockney
<
avsm>
dsheets: just xen+docker is fine for now
philtom has joined #mirage
avsm has quit [Quit: Leaving.]
philtom has quit [Ping timeout: 260 seconds]
avsm has joined #mirage
djs55 has joined #mirage
djs55 has quit [Client Quit]
djs55 has joined #mirage
o_pax has quit [Quit: o_pax]
o_pax has joined #mirage
rgrinberg has joined #mirage
o_pax has quit [Quit: o_pax]
o_pax has joined #mirage
o_pax has quit [Client Quit]
o_pax has joined #mirage
rgrinberg has quit [Quit: Leaving.]
o_pax has quit [Client Quit]
o_pax has joined #mirage
andreas has joined #mirage
<
thomasga>
any idea what means: Cannot handle page request order 1!
<
thomasga>
memalign(4096, 4096) failed.?
rgrinberg has joined #mirage
<
djs55>
out of memory I think
<
djs55>
I can't remember if the malloc/memalign failure causes us to Gc.compact and free our unused Cstructs
<
thomasga>
ok thanks
<
thomasga>
I got some interesting "RX exn Invalid_argument("Cstruct.sub")" as well
<
djs55>
we need to do some work on backtrace printing :)
<
jonludlam>
djs55, what packages do you need to install in trunk to do a opam init --comp...?
<
djs55>
I usually do something like 'gcc m4 automake'
<
jonludlam>
it's running with just yum installing gcc so far.. it's not failed yet :-)
o_pax has quit [Quit: o_pax]
djs551 has joined #mirage
djs55 has quit [Ping timeout: 272 seconds]
avsm has quit [Quit: Leaving.]
thomasga has quit [Quit: Leaving.]
thomasga has joined #mirage
djs551 has quit [Quit: Leaving.]
yomimono has joined #mirage
avsm has joined #mirage
rgrinberg has quit [Quit: Leaving.]
brson has joined #mirage
rgrinberg has joined #mirage
tlockney is now known as tlockney_away
djs55 has joined #mirage
yomimono has quit [Ping timeout: 272 seconds]
thomasga has quit [Quit: Leaving.]
yomimono has joined #mirage
thomasga has joined #mirage
rgrinberg has quit [Quit: Leaving.]
rgrinberg has joined #mirage
rgrinberg has quit [Client Quit]
thomasga has quit [Quit: Leaving.]
rgrinberg has joined #mirage
thomasga has joined #mirage
boogie has joined #mirage
tlockney_away is now known as tlockney
hhugo has quit [Quit: Leaving.]
hhugo has joined #mirage
thomasga has quit [Ping timeout: 260 seconds]
rgrinberg has quit [Quit: Leaving.]
hhugo has quit [Quit: Leaving.]
avsm1 has joined #mirage
avsm has quit [Ping timeout: 260 seconds]
hhugo has joined #mirage
rgrinberg has joined #mirage
djs55 has quit [Quit: Leaving.]
dsheets has quit [Ping timeout: 245 seconds]
djs55 has joined #mirage
avsm has joined #mirage
avsm1 has quit [Read error: Connection reset by peer]
djs55 has quit [Quit: Leaving.]
yomimono has quit [Ping timeout: 260 seconds]
dsheets has joined #mirage
mcclurmc has quit [Remote host closed the connection]
rgrinberg has quit [Quit: Leaving.]
thomasga has joined #mirage
dsheets has quit [Ping timeout: 260 seconds]
thomasga has quit [Quit: Leaving.]
hhugo has quit [Quit: Leaving.]
hhugo has joined #mirage
yomimono has joined #mirage
boogie has quit [Remote host closed the connection]
hhugo has quit [Ping timeout: 260 seconds]