Re: [GNHLUG] GNHLUG is turning 15! Let's have a party!
And streaming video so that the geographically challenged can participate! (Luckily, my broadband provider here in WNC doesn't cap aggregate bandwidth, but shortly I'll be returning to the Comcast dungeon in SoFla). --- On Tue, 10/6/09, Ben Scott wrote: > From: Ben Scott > Subject: Re: [GNHLUG] GNHLUG is turning 15! Let's have a party! > To: "Greater NH Linux User Group" > Date: Tuesday, October 6, 2009, 12:39 PM > On Tue, Oct 6, 2009 at 12:15 PM, Bill > McGonigle > wrote: > > On 10/06/2009 12:33 AM, Ben Scott wrote: > >> Manch-Vegas is centrally located amongst most of > NH's population > >> centers (sorry, Bill!) > > > > Just to be pedantic, "and the other 108 members of > DLSLUG". > > Clearly what is needed here is *two* parties, > connected with a FOSS > video conferencing system ;-) > > -- Ben > ___ > gnhlug-discuss mailing list > gnhlug-discuss@mail.gnhlug.org > http://mail.gnhlug.org/mailman/listinfo/gnhlug-discuss/ > ___ gnhlug-discuss mailing list gnhlug-discuss@mail.gnhlug.org http://mail.gnhlug.org/mailman/listinfo/gnhlug-discuss/
Parallel sockets or?
The TCP connection to my FFT server is not performing anywhere near the link speed. (14%) I've scoured the net (and this list, probably to your annoyance) looking for ways to optimize the link speed. Having tried most of them, (including jumbo frames, interrupt coalescence, tuning socket sizes to BDP, wmem_max, etc.) and only realizing at most a 10% increase of speed over default setting has me frustrated. However, it has given me a great deal of respect for the great work that others have put into the OS and TCP. Reading some papers about increasing WAN performance between super computers mentioned the use of parallel sockets to increase TCP network throughput. The parallel sockets with default TCP settings had higher throughput than a single "highly tuned" socket. There are quite a few papers explaining how this can be. Apparently this parallel socket technology is using in several products, like filezilla, and there is a plugin for Firefox to increase download speed. Supposedly there is a psocket library. psockets are supposed to "look" like BSD sockets. So the programming did not look too bad. I went to sourceforge and found a project that had been set up and apparently abandoned. Nothing to download, at least not directly. The originators of psock were at cesnet.cz, there is a link to the library at http://www.cesnet.cz/project/qosip The make doesn't finish. Several compile errors. I played about a bit, but did not make much headway... I've sent an email to Dr. Sven Ubik at cesnet.cz but have not heard from him... Anyone find a good download site for psockets? I did find UDT, which looks interesting. For the main transport it uses UDP, with overhead to make it "reliable". Supposedly it is very fast. I did try the test code, at least the project compiled, and I managed to send data at 650Mbps, across my local network, if I believe its diagnostics. Unfortunately for me, it is written all in C++, which makes it hard for me to understand how to use it. If at all possible, I'd like to use simpler, C libraries and TCP. Suggestions, comments, where do I go from here??? Regards, Bruce Bruce Labitt Autoliv Electronics 1011B Pawtucket Blvd, PO Box 1858 Lowell, MA 01853 Email: bruce.lab...@autoliv.com. Tel: (978) 674-6526 Fax: (978) 674-6581 ** Neither the footer nor anything else in this E-mail is intended to or constitutes an electronic signature and/or legally binding agreement in the absence of an express statement or Autoliv policy and/or procedure to the contrary.This E-mail and any attachments hereto are Autoliv property and may contain legally privileged, confidential and/or proprietary information.The recipient of this E-mail is prohibited from distributing, copying, forwarding or in any way disseminating any material contained within this E-mail without prior written permission from the author. If you receive this E-mail in error, please immediately notify the author and delete this E-mail. Autoliv disclaims all responsibility and liability for the consequences of any person who fails to abide by the terms herein. ** ___ gnhlug-discuss mailing list gnhlug-discuss@mail.gnhlug.org http://mail.gnhlug.org/mailman/listinfo/gnhlug-discuss/
Re: Parallel sockets or?
bruce.lab...@autoliv.com wrote: > The TCP connection to my FFT server is not performing anywhere near the > link speed. (14%) I've scoured the net (and this list, probably to your > annoyance) looking for ways to optimize the link speed. Having tried most > of them, (including jumbo frames, interrupt coalescence, tuning socket > sizes to BDP, wmem_max, etc.) and only realizing at most a 10% increase of > speed over default setting has me frustrated. However, it has given me a > great deal of respect for the great work that others have put into the OS > and TCP. > > Reading some papers about increasing WAN performance between super > computers mentioned the use of parallel sockets to increase TCP network > throughput. The parallel sockets with default TCP settings had higher > throughput than a single "highly tuned" socket. There are quite a few > papers explaining how this can be. > > Apparently this parallel socket technology is using in several products, > like filezilla, and there is a plugin for Firefox to increase download > speed. > > Supposedly there is a psocket library. psockets are supposed to "look" > like BSD sockets. So the programming did not look too bad. I went to > sourceforge and found a project that had been set up and apparently > abandoned. Nothing to download, at least not directly. > > The originators of psock were at cesnet.cz, there is a link to the library > at http://www.cesnet.cz/project/qosip > > The make doesn't finish. Several compile errors. I played about a bit, > but did not make much headway... > > I've sent an email to Dr. Sven Ubik at cesnet.cz but have not heard from > him... Anyone find a good download site for psockets? > > I did find UDT, which looks interesting. For the main transport it uses > UDP, with overhead to make it "reliable". Supposedly it is very fast. I > did try the test code, at least the project compiled, and I managed to > send data at 650Mbps, across my local network, if I believe its > diagnostics. Unfortunately for me, it is written all in C++, which makes > it hard for me to understand how to use it. If at all possible, I'd like > to use simpler, C libraries and TCP. > > Suggestions, comments, where do I go from here??? > > Regards, > Bruce > > Bruce Labitt > Autoliv Electronics > 1011B Pawtucket Blvd, PO Box 1858 > Lowell, MA 01853 > > Email: bruce.lab...@autoliv.com. > Tel: (978) 674-6526 > Fax: (978) 674-6581 > > ** > Neither the footer nor anything else in this E-mail is intended to or > constitutes an electronic signature and/or legally binding agreement in > the absence of an express statement or Autoliv policy and/or procedure to > the contrary.This E-mail and any attachments hereto are Autoliv property > and may contain legally privileged, confidential and/or proprietary > information.The recipient of this E-mail is prohibited from distributing, > copying, forwarding or in any way disseminating any material contained > within this E-mail without prior written permission from the author. If > you receive this E-mail in error, please immediately notify the author > and delete this E-mail. Autoliv disclaims all responsibility and > liability for the consequences of any person who fails to abide by the > terms herein. > ** > > ___ > gnhlug-discuss mailing list > gnhlug-discuss@mail.gnhlug.org > http://mail.gnhlug.org/mailman/listinfo/gnhlug-discuss/ > > There is another way to radically increase communication speed that is very popular in the cluster world. Basically hardware is added to allow memory to memory writing. One node communicates with another by writing into this device which is mapped to the other nodes memory controller (a 50,000 foot simplification but useful). Here is an article that describes "cluster interconnects": http://www.clustermonkey.net//content/view/124/34/ You might find this useful for more than your current project. -Alex ___ gnhlug-discuss mailing list gnhlug-discuss@mail.gnhlug.org http://mail.gnhlug.org/mailman/listinfo/gnhlug-discuss/
I want my KDiff3
I can't get KDiff3 to use it's excellent "preprocessor command" which can eliminate noise -- the type of noise that is easily introduced by SVN keywords -- when trying to do diffs on source. For example, this command works as expected on the command line: cat about.php | /bin/sed 's/\$\(LastChangedRevision\|HeadURL\|LastChangedBy\|LastChangedDate\).*\$/\$\1\$/' When I plug the same sed command into KDiff3's preference window (kdiff3 Version 0.9.94 Using KDE 4.2.4 (KDE 4.2.4)), it tells me that pre-processing has failed and sure enough - I get tons of false positives in a directory compare and individual files whose only difference is some SVN keyword (fully expanded) e.g. * @since $LastChangedDate: 2006-06-24 22:03:16 -0400 (Sat, 24 Jun 2006) $ Yes, I can use Meld, but like the song says: I want my MTV I want my KDiff3 Greg Rundlett nbpt 978-225-8302 m. 978-764-4424 -skype/aim/irc/twitter freephile http://profiles.aim.com/freephile ___ gnhlug-discuss mailing list gnhlug-discuss@mail.gnhlug.org http://mail.gnhlug.org/mailman/listinfo/gnhlug-discuss/
Re: I want my KDiff3 [SOLVED] pre-processor command
On Wed, Oct 7, 2009 at 3:06 PM, Greg Rundlett (freephile) wrote: > I can't get KDiff3 to use it's excellent "preprocessor command" which > can eliminate noise -- the type of noise that is easily introduced by > SVN keywords -- when trying to do diffs on source. OK, so apparently KDiff3 doesn't accept single quotes, but works with double quotes so perl -p -e "s/(.*)/foo/" works but perl -p -e 's/(.*)/foo/' doesn't ___ gnhlug-discuss mailing list gnhlug-discuss@mail.gnhlug.org http://mail.gnhlug.org/mailman/listinfo/gnhlug-discuss/
Re: I want my KDiff3
Greg Rundlett (freephile) writes: > Yes, I can use Meld, but like the song says: I > want my MTV I want my KDiff3 Hmm. I don't know if Meld does what you want here, but I am a big fan of Meldit's the prettiest diff too I've ever used. I'm also a big fan of ediff mode in X?Emacs. Regards, --kevin -- GnuPG ID: B280F24EGod, I loved that Pontiac. alumni.unh.edu!kdc-- Tom Waits http://kdc-blog.blogspot.com/ ___ gnhlug-discuss mailing list gnhlug-discuss@mail.gnhlug.org http://mail.gnhlug.org/mailman/listinfo/gnhlug-discuss/
Re: I want my KDiff3
On Wed, Oct 7, 2009 at 3:06 PM, Greg Rundlett (freephile) wrote: > Yes, I can use Meld, but like the song says: I > want my MTV I believe the song you are thinking of is "Money For Nothing", by the band Dire Straits. :) Unfortunately, this does not help you with your KDiff3 problem. ;-) -- Ben ___ gnhlug-discuss mailing list gnhlug-discuss@mail.gnhlug.org http://mail.gnhlug.org/mailman/listinfo/gnhlug-discuss/
Re: I want my KDiff3
Ben Scott writes: > > On Wed, Oct 7, 2009 at 3:06 PM, Greg Rundlett (freephile) > wrote: > > Yes, I can use Meld, but like the song says: I > > want my MTV > > I believe the song you are thinking of is "Money For Nothing", by > the band Dire Straits. :) And I believe the phrase in question was actually voiced by Sting :) But maybe Greg can be forgiven for thinking that it was ZZ Top-- that was presumably due to the ZZ-Top-esque guitar part; Wikipedia's `Money for Nothing' article says: Production Knopfler modelled his guitar sound for the recorded track after ZZ Top guitarist Billy Gibbons' trademark guitar tone, as ZZ Top's music videos were already a staple of early MTV. Gibbons later told a Musician magazine interviewer in 1986 that Knopfler had solicited Gibbons on how to replicate the tone -- Don't be afraid to ask (Lf.((Lx.xx) (Lr.f(rr. ___ gnhlug-discuss mailing list gnhlug-discuss@mail.gnhlug.org http://mail.gnhlug.org/mailman/listinfo/gnhlug-discuss/
Re: I want my KDiff3
On Wed, Oct 7, 2009 at 4:53 PM, Joshua Judson Rosen wrote: > Ben Scott writes: > > > > On Wed, Oct 7, 2009 at 3:06 PM, Greg Rundlett (freephile) > > wrote: > > > Yes, I can use Meld, but like the song says: I > > > want my MTV > > > > I believe the song you are thinking of is "Money For Nothing", by > > the band Dire Straits. :) > > And I believe the phrase in question was actually voiced by Sting :) > > But maybe Greg can be forgiven for thinking that it was ZZ Top-- > that was presumably due to the ZZ-Top-esque guitar part; > Wikipedia's `Money for Nothing' article says: > >Production > >Knopfler modelled his guitar sound for the recorded track after ZZ >Top guitarist Billy Gibbons' trademark guitar tone, as ZZ Top's >music videos were already a staple of early MTV. Gibbons later >told a Musician magazine interviewer in 1986 that Knopfler had >solicited Gibbons on how to replicate the tone > > And if it was done today he'd get sued. As it was, Sting dropped in to do the voice "because he thought it would be cool" and created a fit for the lawyers... ___ gnhlug-discuss mailing list gnhlug-discuss@mail.gnhlug.org http://mail.gnhlug.org/mailman/listinfo/gnhlug-discuss/
Re: I want my KDiff3
On Wed, Oct 7, 2009 at 4:57 PM, Tom Buskey wrote: > > > On Wed, Oct 7, 2009 at 4:53 PM, Joshua Judson Rosen > wrote: >> >> Ben Scott writes: >> > >> > On Wed, Oct 7, 2009 at 3:06 PM, Greg Rundlett (freephile) >> > wrote: >> > > Yes, I can use Meld, but like the song says: I >> > > want my MTV >> > >> > I believe the song you are thinking of is "Money For Nothing", by >> > the band Dire Straits. :) Doh, Of COURSE it was Dire Straights and Mark Knopfler on the the guitar!! Jeesh, I must be getting old when nostalgia means you misremember things :-O Nah, I was just more focused on my problem than my music. /me turning 43 years young this month. I still love Dire Straights and ZZ Top songs the MTV video of "Money For Nothing" by Dire Straights: http://www.mtv.com/videos/dire-straits/18177/money-for-nothing.jhtml better quality on MTV.com http://www.youtube.com/watch?v=Po1TsgvOoOY YouTube version p.s. I did send a request to the KDE documentation team to update the docs for KDiff3 because all the examples in the docs use single quotes which the current application does not support. Greg Rundlett nbpt 978-225-8302 m. 978-764-4424 -skype/aim/irc/twitter freephile http://profiles.aim.com/freephile ___ gnhlug-discuss mailing list gnhlug-discuss@mail.gnhlug.org http://mail.gnhlug.org/mailman/listinfo/gnhlug-discuss/