Hi guys,
Considering performance issue, I think we need to start asking questions
and try to figure it out more in detail. Consider an enterprise including
all architectural elements, systems / sub-systems / components / modules /
processes and all the way down to functional units which plenty of
resources (tangible and intangible) dedicated to make it happen. Let's take
this as a holographic universe in our mind and ask "Could there be a demand
for a performance monitoring pattern to get fit in that enterprise without
having major impacts? If there could be a demand, as a Hypothesis, how it
could be rejected? If not, what we are going to exchange for this
opportunity or what would be the opportunity cost for such decision
making?..."
It is not only about "inproc" which could be used in local structural
pattern building but it is about designing in a SMART way. Ans you already
know about that! Measurement as one of its core elements shine out when we
encounter bottle-necks by which whole enterprise could experience risk that
no compensation overseen for it.
Are you paying attention?
It is not always about speed. How fast is fast? Is it really fast? Speed is
just one of the problem solvents in solution space.
Omid Shahraki
------------------------------------------------------------------
On Jan 6, 2017 22:25, "Karan, Cem F CIV USARMY RDECOM ARL (US)" <
cem.f.karan.civ@xxxxxxxx> wrote:
Sounds good. I agree that arrays are the fastest method, and I suspect
that once subscriptions are set up, they will stay stable over long time
periods. So, yes, **in theory** an array is worse than a Patricia tree,
etc., but I expect that in practice the arrays will win big.
Thanks,
Cem Karan
-----Original Message-----On Behalf Of Garrett D'Amore
From: nanomsg-bounce@xxxxxxxxxxxxx [mailto:nanomsg-bounce@xxxxxxxxxxxxx]
Sent: Friday, January 06, 2017 1:33 PMthe identity of the sender, and confirm the authenticity of all links
To: nanomsg@xxxxxxxxxxxxx
Subject: [nanomsg] Re: [Non-DoD Source] status update libnng
All active links contained in this email were disabled. Please verify
contained within the message prior to copying and pasting the address toa Web browser.
that using an array, I can use a binary search to get filtering
________________________________
Oh, I convinced myself that an array is better. What’s even cooler, is
operations back to O(log(n)). Changing subscriptions will still besomewhat expensive, but I think that won’t be too bad since I can reduce
it to the cost of memcpy(), where the size being copied is basically apointer and a size (at most 16 bytes total typically) per subscription.
This means if you have 1000 subscriptions I might have to memcpy 16kwhen you change the subscription. But most of the time we’ll be
looking at shuffling around a couple of hundred bytes at most.(Allocations are still an issue, but I think I can keep that down to minimum
— preallocating 16 slots or so to start, and doubling each we find weneed more.)
<cem.f.karan.civ@xxxxxxxx < Caution-
On Fri, Jan 6, 2017 at 10:19 AM, Karan, Cem F CIV USARMY RDECOM ARL (US)
mailto:cem.f.karan.civ@xxxxxxxx ;> > wrote:simpler testing; whether or not an array/list/Patricia tree are
I agree with what you're saying, but I was thinking of somewhat
better in the real world. The higher-order stuff is, as you point out,really, really complicated to test.
nanomsg-bounce@xxxxxxxxxxxxx > [Caution-mailto:nanomsg-
Thanks,
Cem Karan
> -----Original Message-----
> From: nanomsg-bounce@xxxxxxxxxxxxx < Caution-mailto:
bounce@xxxxxxxxxxxxx < Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx ;> ]On Behalf Of Garrett D'Amore
> Sent: Friday, January 06, 2017 11:30 AMverify the identity of the sender, and confirm the authenticity of all
> To: nanomsg@xxxxxxxxxxxxx < Caution-mailto:nanomsg@xxxxxxxxxxxxx
> Subject: [nanomsg] Re: [Non-DoD Source] status update libnng
>
> All active links contained in this email were disabled. Please
linksaddress to a Web browser.
> contained within the message prior to copying and pasting the
>to use generically.
>
> ________________________________
>
>
>
> Performance statistics are hard to gather somewhat, and harder
>latency; really you want to modify the wire protocol to carry
> The difficulty of gathering is that you need to measure entire
timestamps.are so wildly different that what might be perfectly normal for
> Some performance data we can report, such as queue depth, etc.
>
> The difficulty of use is that everyone’s system and applications
one userperformance-related bug analysis, I can recall precisely one user over he
> might be tragically bad for another.
>
> In actuality, there has been very little demand for
years
griping“I don’t care”. (Because inproc performance was never
> about inproc performance vs. ZMQ. My response at the time was
terriblyand I also had bigger fish to fry around trying to fix the MT-
> important to me since I don’t think it sees much real world use,
safety things infigure out how to make libnanomsg’s inproc completely thread-safe
> inproc. libnng is me basically giving up on that. I couldn’t
withoutpassing data across the different sockets (which had different
> completely trashing the performance. The FSM architecture made
lockARL (US) <cem.f.karan.civ@xxxxxxxx < Caution-
> hierarchies) too damned difficult.
>
> On Fri, Jan 6, 2017 at 7:00 AM, Karan, Cem F CIV USARMY RDECOM
mailto:cem.f.karan.civ@xxxxxxxx ;> < Caution-cem.f.karan.civ@xxxxxxxx > > > wrote:
> Caution-mailto:cem.f.karan.civ@xxxxxxxx ;< Caution-mailto:
>statistics gathering code; have you considered adding code that
>
> You were mentioning that you were planning on adding
gathersbug reports that include those statistics, which would let you
> performance statistics as well? As end users we could send you
know if it’s ananomsg-bounce@xxxxxxxxxxxxx > < Caution-Caution-
> problem or not.
>
> Thanks,
> Cem Karan
>
> > -----Original Message-----
> > From: nanomsg-bounce@xxxxxxxxxxxxx < Caution-mailto:
mailto:nanomsg-bounce@xxxxxxxxxxxxx ;< Caution-mailto:nanomsg-bounce@freelists.org > > [Caution-Caution-mailto:nanomsg- ;<
Caution-mailto:nanomsg- ;>Caution-Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx ;<
> bounce@xxxxxxxxxxxxx < Caution-mailto:bounce@xxxxxxxxxxxxx ;> <
Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx ;> > ] On Behalf Of GarrettD'Amore
> > Sent: Thursday, January 05, 2017 1:37 PMfreelists.org > < Caution-Caution-mailto:nanomsg@xxxxxxxxxxxxx ;<
> > To: nanomsg@xxxxxxxxxxxxx < Caution-mailto:nanomsg@
Caution-mailto:nanomsg@xxxxxxxxxxxxx ;> >libnng
> > Subject: [nanomsg] Re: [Non-DoD Source] status update
> >Please verify the identity of the sender, and confirm the authenticity
> > All active links contained in this email were disabled.
of allpasting the address to a Web browser.
> links
> > contained within the message prior to copying and
> >a few hundred of these things, I’ll switch to an array.
> >
> > ________________________________
> >
> >
> >
> > I could certainly make it an array. :-)
> >
> > If it seems to be universal that nobody needs more than
> >was about the O(n) vs O(log(n)) thing though. If we know that O(n)
> > I wasn’t so much worried about list traversal times as I
issuperior. One thing about an array, is that if I keep it sorted, then
> good
> > enough, then certainly an array is probably going to be
> subscribeto shuffle on average half the items in the array. I’m assuming
> > operations will become more expensive, since I’ll have
> subscription(I’d really like to know if anyone has an application where changes to
> > changes occur less frequently than messages arrive.
> subscriptions —operation.)
> > subscribe/unsubscribe — is a performance sensitive
> >danielcccc@xxxxxxxxx < Caution-mailto:danielcccc@xxxxxxxxx ;> < Caution-
> > - Garrett
> >
> >
> > On Thu, Jan 5, 2017 at 10:23 AM, Daniel C <
Caution-mailto:danielcccc@xxxxxxxxx ;< Caution-mailto:danielcccc@gmail.com > > < Caution-
> Caution-Caution-mailto:danielcccc@xxxxxxxxx ;< Caution-mailto:danielcccc@xxxxxxxxx > < Caution-Caution-
mailto:danielcccc@xxxxxxxxx ;< Caution-mailto:danielcccc@xxxxxxxxx ;> >definitely less than 10 or 20 in my case.
wrote:> >
> >
> > I agree with Jason; an array would be faster. N
> >j.e.aten@xxxxxxxxx < Caution-mailto:j.e.aten@xxxxxxxxx ;> < Caution-
> >
> > Dan
> >
> >
> > On Thu, Jan 5, 2017 at 7:58 AM, Jason E. Aten <
Caution-mailto:j.e.aten@xxxxxxxxx ;< Caution-mailto:j.e.aten@xxxxxxxxxj.e.aten@xxxxxxxxx > < Caution-Caution-
> < Caution-
> Caution-Caution-mailto:j.e.aten@xxxxxxxxx ;< Caution-mailto:
mailto:j.e.aten@xxxxxxxxx ;< Caution-mailto:j.e.aten@xxxxxxxxx ;> > > >wrote:
> >array to be much faster than a linked list.
> >
> > For a small N < 10, I would expect an
> >D'Amore <garrett@xxxxxxxxxx < Caution-mailto:garrett@xxxxxxxxxx ;>
> > My typical use is for small N, about 3.
> >
> > On Thu, Jan 5, 2017 at 4:52 AM, Garrett
< Caution-Caution-mailto:garrett@xxxxxxxxxx ;< Caution-mailto:garrett@xxxxxxxxxx > > <
Caution-mailto:garrett@xxxxxxxxxx ;> < Caution-Caution-
> Caution-Caution-Caution-mailto:garrett@xxxxxxxxxx ;<
mailto:garrett@xxxxxxxxxx ;< Caution-mailto:garrett@xxxxxxxxxx ;> > > >wrote:
> >accept() is such a non-portable nightmare. I almost went down the path of
> >
> > TCP works now. OMG, close() vs.
> > pthread cancellation. Thankfully, that crisis is nowaverted. I never realized just how broken the use of UNIX file
descriptors inworking now . Thank goodness for shutdown(2) and dup2().
> the face of
> > close() and multiple threads really are. But its
> >inproc, and I’ve started PUB/SUB. Sub is actually done, untested.
> > There’s a test suite for TCP and
> >up the remaining protocols and IPC before the weekend.
> > I give 50/50 odds on me finishing
> >weekend is writing the eventing framework (necessary for file descriptor
> > What won’t happen before the
basedAnd Windows will probably happen next week. I’ve designed this such
> > notifications for example), or statistics framework.
that Ifor now used a simple sorted linked list for subscriptions. My instinct is
> think I
> > will be able to crank out Windows stuff super fast.
> >
> > One question about PUB/SUB. I’ve
thatsufficient, but probably superior to a patricia tree; I think most of us
> > for the vast vast majority of folks, this is not only
only
> maintainany given time. That said, I’m keen to hear of actual uses of
> > around a dozen or so subscriptions on any subscriber at
nanomsgseveral hundred active subscriptions on a given end node. (Note
> where the
> > patricia tree makes a real difference — cases with over
thatclients — thousands — each having dozens of subscriptions — with
> this is only
> > on the the end node; a server can service many many
zerothat filtering messages is now an O(n) instead of O(log(n)) operation (where
> negative
> > impact in my design.)
> >
> > To be clear, the linked list means
n issmall values of n, the linked list approach I’ve taken is faster. I have
> > the number of active subscriptions); I suspect that for
> implementedin a patricia tree if there is need. (I didn’t yank Martin’s old code
> > this way for now for expediency, but I’m open to pulling
> because I wantit into the new code base — I haven’t had time to be certain of that
> > to make sure I thoroughly understand it before I bring
yet.Garrett D'Amore <garrett@xxxxxxxxxx < Caution-
> >
> >
> > On Wed, Jan 4, 2017 at 2:18 AM,
mailto:garrett@xxxxxxxxxx ;> < Caution-Caution-mailto:garrett@xxxxxxxxxx< Caution-mailto:garrett@xxxxxxxxxx ;> >
Caution-mailto:garrett@xxxxxxxxxx ;> < Caution-Caution-
> < Caution-Caution-Caution-mailto:garrett@xxxxxxxxxx ;<
mailto:garrett@xxxxxxxxxx ;< Caution-mailto:garrett@xxxxxxxxxx ;> > >initial swag at TCP. Turns out it was bit more code than anticipated, as I
> > > wrote:
> >
> >
> > I’ve just committed the
want to
> > support TCPv4 and TCPv6, and properly support differentplatforms that might have different ways to resolve names, or
handlethe winsock code later.
> low level
> > TCP details. This should make it really fast to write
> >abstract the details so that transports that want to build on top of TCP
> > I’ve also tried to
(e.g. websocket
> > or TLS) can do so easily.can look at the last commit if you want to see what I’m up to. The main
> >
> >
> > Totally untested, but you
missingsupport for some of the richer TCP options — e.g. KEEPALIVEs etc. I am
> > thing (besides testing that it actually works) is
disablingbusiness wanting Nagle turned on. (And I’ve taken care to use
> Nagle by
> > default, because I think 99% of nanomsg users have no
writev topossible. This is something that sadly isn’t possible using Go….)
> avoid
> > splitting writes up across separate packets when
> >10:54 AM, Karan, Cem F CIV USARMY RDECOM ARL (US)
> > On Tue, Jan 3, 2017 at
> > <cem.f.karan.civ@xxxxxxxx < Caution-mailto:cem.f.karan.civ@xxxxxxxx > < Caution-Caution-
mailto:cem.f.karan.civ@xxxxxxxx ;< Caution-mailto:cem.f.karan.civ@xxxxxxxx > > < Caution-Caution-Caution-
mailto:cem.f.karan.civ@xxxxxxxx ;< Caution-mailto:cem.f.karan.civ@xxxxxxxx > <
> Caution-Caution-mailto:cem.f.karan.civ@xxxxxxxx ;<Caution-mailto:cem.f.karan.civ@xxxxxxxx ;> > > > wrote:
> >glitched and forgot that inproc is a thing; for some reason I thought you
> >
> > Got it, my brain
were
> > building out your own TCP stack, which would have mademe... concerned. ;)
> >Message-----
> > Thanks,
> > Cem Karan
> >
> > > -----Original
> > > From:nanomsg-bounce@xxxxxxxxxxxxx < Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx
<nanomsg-bounce@xxxxxxxxxxxxx > > < Caution-
Caution-Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx ;< Caution-mailto:
> Caution-Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx ;<Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx ;> < Caution-Caution-
mailto:nanomsg-bounce@xxxxxxxxxxxxx ;< Caution-mailto:nanomsg-bounce@freelists.org > > >
> > [Caution-Caution-Caution-mailto:nanomsg-bounce@freelists.org < Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx ;> <
Caution-Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx ;< Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx > > < Caution-Caution-
> Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx ;< Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx > < Caution-Caution-
mailto:nanomsg-bounce@xxxxxxxxxxxxx ;< Caution-mailto:nanomsg-bounce@freelists.org > > > ] On Behalf Of Garrett D'Amore
> > > Sent: Tuesday,January 03, 2017 1:23 PM
>nanomsg@xxxxxxxxxxxxx < Caution-mailto:nanomsg@xxxxxxxxxxxxx ;> <
> > > To:
Caution-Caution-
mailto:nanomsg@xxxxxxxxxxxxx ;< Caution-mailto:nanomsg@xxxxxxxxxxxxx ;>freelists.org > < Caution-Caution-
< Caution-Caution-
> Caution-mailto:nanomsg@xxxxxxxxxxxxx ;< Caution-mailto:nanomsg@
mailto:nanomsg@xxxxxxxxxxxxx ;< Caution-mailto:nanomsg@xxxxxxxxxxxxx ;>[nanomsg] Re: [Non-DoD Source] status update libnng
>
> > > Subject:
> > >contained in this email were disabled. Please verify the identity of the
> > > All active links
sender,
> > and confirm the authenticity of all linksthe message prior to copying and pasting the address to a Web browser.
> > > contained within
> > >________________________________
> > >
> > >
> > >hours from having TCP working. Right now the TCP transport is not written,
> > >
> > >
> > > I’m about 24
> > though I’ve written a fair bit of it locally.pattern is working now, as is PAIR, and inproc is working quit well and
> > >
> > > The REQ/REP
totally
> > thread safe.lockless algorithms go — I’m a big believer in mutexes. I need mutexes and
> > >
> > > As far as
condition
> > variables to make things work well, and inthey are used sensibly (with minimal contention), they do not significantly
> > > my experience if
> > impact performance.lockless data structures are superior, but you have to have use cases that
> > >
> > > For some things
work
> > for them; with mutexes and condvars Ithink about this; they Just Work.
> > > don’t have to
> > >to look at alternative designs for that in the future, but I’m only going
> > > It may be useful
to do
> > that once I’ve demonstrated a clear need ormaybe someone else will contribute at that point). Until then, I need to
> > > benefit (or
focus on
> > getting the code working with a sensibleprematurely optimizing things.
> > > design and avoid
> > >2017 at 6:45 AM, Karan, Cem F CIV USARMY RDECOM ARL (US)
> > > - Garrett
> > >
> > >
> > > On Tue, Jan 3,
>civ@xxxxxxxx > < Caution-Caution-
> > <cem.f.karan.civ@xxxxxxxx < Caution-mailto:cem.f.karan.
mailto:cem.f.karan.civ@xxxxxxxx ;< Caution-mailto:cem.f.karan.civ@xxxxxxxx > > < Caution-Caution-Caution-
mailto:cem.f.karan.civ@xxxxxxxx ;< Caution-mailto:cem.f.karan.civ@xxxxxxxx > <
> Caution-Caution-mailto:cem.f.karan.civ@xxxxxxxx ;<Caution-mailto:cem.f.karan.civ@xxxxxxxx ;> > > < Caution-
> > >Caution-Caution-Caution-mailto:cem.f.karan.civ@xxxxxxxx ;< Caution-
mailto:cem.f.karan.civ@xxxxxxxx ;> < Caution-Caution-mailto:cem.f.karan.civ@xxxxxxxx < Caution-mailto:cem.f.karan.civ@xxxxxxxx ;> > <
> Caution-Caution-Caution-mailto:cem.f.karan.civ@xxxxxxxx ;<Caution-mailto:cem.f.karan.civ@xxxxxxxx ;> < Caution-Caution-
mailto:cem.f.karan.civ@xxxxxxxx ;< Caution-mailto:cem.f.karan.civ@xxxxxxxx > > > > >
> > wrote:-----Original Message-----
> > >
> > >
> > > >
> > > > From:nanomsg-bounce@xxxxxxxxxxxxx < Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx
<nanomsg-bounce@xxxxxxxxxxxxx > > <
Caution-Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx ;< Caution-mailto:
> Caution-Caution-Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx ;<Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx ;> < Caution-
Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx ;< Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx > > >
> > < Caution-Caution-Caution-Caution-mailto:nanomsg-bounce@freelists.org < Caution-mailto:nanomsg-
bounce@xxxxxxxxxxxxx > < Caution-Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx < Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx ;> >
<
Caution-Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx ;> < Caution-Caution-
> Caution-Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx ;<
mailto:nanomsg-bounce@xxxxxxxxxxxxx ;< Caution-mailto:nanomsg-bounce@freelists.org > > > > [Caution-Caution-
> > Caution-Caution-mailto:nanomsg- ;< Caution-mailto:nanomsg- > < Caution-Caution-mailto:nanomsg- ;< Caution-
mailto:nanomsg- ;> > < Caution-Caution-Caution-mailto:nanomsg- ;<Caution-mailto:nanomsg- ;> < Caution-Caution-mailto:nanomsg- ;<
Caution-mailto:nanomsg- ;> > >bounce@xxxxxxxxxxxxx < Caution-mailto:bounce@xxxxxxxxxxxxx ;> <
> > >
Caution-Caution-
mailto:bounce@xxxxxxxxxxxxx ;< Caution-mailto:bounce@xxxxxxxxxxxxx ;> >< Caution-Caution-
> Caution-mailto:bounce@xxxxxxxxxxxxx ;< Caution-mailto:bounce@freelists.org > < Caution-Caution-mailto:bounce@xxxxxxxxxxxxx ;<
Caution-mailto:bounce@xxxxxxxxxxxxx ;> > > < Caution-Caution-Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx ;> < Caution-
> > Caution-Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx ;<
Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx ;< Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx > > < Caution-Caution-
> Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx ;< Caution-mailto:nanomsg-bounce@xxxxxxxxxxxxx > < Caution-Caution-
mailto:nanomsg-bounce@xxxxxxxxxxxxx ;< Caution-mailto:nanomsg-bounce@freelists.org > > > > ] On Behalf Of Garrett D'Amore
> > > > Sent:Monday, December 26, 2016 2:46 AM
> >nanomsg@xxxxxxxxxxxxx < Caution-mailto:nanomsg@xxxxxxxxxxxxx ;> <
> > > > To:
Caution-Caution-
mailto:nanomsg@xxxxxxxxxxxxx ;< Caution-mailto:nanomsg@xxxxxxxxxxxxx ;>freelists.org > < Caution-Caution-
< Caution-Caution-
> Caution-mailto:nanomsg@xxxxxxxxxxxxx ;< Caution-mailto:nanomsg@
mailto:nanomsg@xxxxxxxxxxxxx ;< Caution-mailto:nanomsg@xxxxxxxxxxxxx ;>Caution-mailto:nanomsg@xxxxxxxxxxxxx ;> < Caution-Caution-
> < Caution-Caution-
> > Caution-Caution-mailto:nanomsg@xxxxxxxxxxxxx ;<
mailto:nanomsg@xxxxxxxxxxxxx ;< Caution-mailto:nanomsg@xxxxxxxxxxxxx ;>freelists.org > < Caution-Caution-
< Caution-Caution-
> Caution-mailto:nanomsg@xxxxxxxxxxxxx ;< Caution-mailto:nanomsg@
mailto:nanomsg@xxxxxxxxxxxxx ;< Caution-mailto:nanomsg@xxxxxxxxxxxxx ;>[Non-DoD Source] [nanomsg] status update libnng
> >
>
> > > > Subject:
> > > >brief Christmas (western) update…
> > > > Just a
> > > >is now managing connections. There’s a lot more to this than you’d think —
> > > > libnng
and a
> > lot of details that I’ve written underexpect that by New Years I’ll have it in a functional state for TCP for
> > > the hood.
> > > >
> > > > I
POSIX systems, for
> > at least the primary patterns /really only a couple of hours from that point.
> > > protocols. TBH,
> > > > I’m
> > > >that the current code base is pretty much crash-immune with respect to
> > > > Note
things that
> > caused grief in libnanomsg — e.g.will not impact libnng. The whole approach has been from a “correct
> > > ENOMEM
> > > > errors
first”, so I
> > expect we will have fewer problems oncestart using this.
> > > we
> > > > actually
> > > >are moving apace… quite quickly actually.
> > > > Things
> > > >anyone is so inclined to review or give feedback on teh existing code, I’m
> > > > If
now at the
> > point to receive it, understanding thatlarge swathes still unimplemented. You can’t use it for TCP for example.
> > > there are
> > > > still
But at this
> > point I’d rather solicit feedback earlyDon’t tell me what’s missing, but if you see problems with what’s already
> > > rather than
> > > > late.
there,
> > please *do* let me know.going on a ski trip for the next several days, but will probably work in
> > > >
> > > > I’m
the evenings
> > getting the thing to a state where otherplaying with for actual experimentation.
> > > folks can
> > > > start
> > > >really looking forward to benchmarking this thing. I think we’re gonna
> > > > I’m
blow the doors
> > off libnanomsg, at least for platformsnon-crappy pthreads. :-)
> > > that have
> > > >
> > > >Christmas everyone! :-)
> > > > Merry
> > >for all your hard work!
> > > Thank you
> > >you say that you can't use it for TCP, what exactly do you mean?
> > > BTW, when
> > >
> > > Thanks,
> > > Cem Karan
> > >
> > >
> > >
> >
> >
> >
> >
> >
> >
> >
>
>
>