FreeBSD Multimedia Resources http://www.FreeBSD.org/docs/multimedia.html Wed, 26 Nov 2008 21:43:14 EST http://cisx1.uma.maine.edu/~wbackman/bsdtalk//bsdtalk166.mp3 Wed, 26 Nov 2008 00:00:00 EST Asterisk Open Source Community Director John Todd - MP3 version<br>From: bsdtalk<br>Tags: bsdtalk, interview, john todd, asterisk, openbsd, mp3<br> An interview with Asterisk Open Source Community Director John Todd, who also happens to be a user of BSD. We talk about Asterisk on BSD, and his choice of OpenBSD for his systems. http://cisx1.uma.maine.edu/~wbackman/bsdtalk//bsdtalk166.ogg Wed, 26 Nov 2008 00:00:00 EST Asterisk Open Source Community Director John Todd - Ogg version<br>From: bsdtalk<br>Tags: bsdtalk, interview, john todd, asterisk, openbsd, ogg<br> An interview with Asterisk Open Source Community Director John Todd, who also happens to be a user of BSD. We talk about Asterisk on BSD, and his choice of OpenBSD for his systems. http://blog.springdaemons.com/assets/2008/11/23/text.pdf Mon, 24 Nov 2008 00:00:00 EST Server deployment in mass-hosting environment using FreeBSD Ports system by Stanislav Sedov (in russian) - PDF version<br>From: Hostobzor, the Russian conference of hosting provider<br>Tags: hostobzor, hostobzor12, freebsd, ports, stanislav sedov, russian, paper, pdf<br> <p> Recently I have been attending Hostobzor 12th, the Russian conference of hosting providers, beeing held at Raivola hotel near St. Petersburg. The event was great as always thanks to organizers. There was a number of intersting talks given, a lot of interesting discussions held, and, what I appreciate better, a lot of new people with great ideas met. </p><p> I gave a talk on using the FreeBSD Ports system to mange a large-scale virtual hosting installations based on Hosting Telesystems experience. I tried to describe in detail how we use the ports collection to deploy a large number of servers diverced by architecture and OS versions, how we build packages and distribute them among servers, talked about how we use Mercurial VCS to incrementally merge upstream changes into our modified ports collection and FreeBSD src trees. Hopefully, I've not screwed it much... At least, some people was interested a lot and asked interesting questions. </p> http://blog.springdaemons.com/assets/2008/11/23/slides.pdf Mon, 24 Nov 2008 00:00:00 EST Server deployment in mass-hosting environment using FreeBSD Ports system by Stanislav Sedov (in russian) - PDF version<br>From: Hostobzor, the Russian conference of hosting provider<br>Tags: hostobzor, hostobzor12, freebsd, ports, stanislav sedov, russian, slides, pdf<br> <p> Recently I have been attending Hostobzor 12th, the Russian conference of hosting providers, beeing held at Raivola hotel near St. Petersburg. The event was great as always thanks to organizers. There was a number of intersting talks given, a lot of interesting discussions held, and, what I appreciate better, a lot of new people with great ideas met. </p><p> I gave a talk on using the FreeBSD Ports system to mange a large-scale virtual hosting installations based on Hosting Telesystems experience. I tried to describe in detail how we use the ports collection to deploy a large number of servers diverced by architecture and OS versions, how we build packages and distribute them among servers, talked about how we use Mercurial VCS to incrementally merge upstream changes into our modified ports collection and FreeBSD src trees. Hopefully, I've not screwed it much... At least, some people was interested a lot and asked interesting questions. </p> http://www.squid-cache.org/~adrian/talks/20081007%20-%20NYCBSDCON%20-%20Disk%20IO.pdf Mon, 24 Nov 2008 00:00:00 EST New York City BSD Con 2008 - Adrian Chadd: High-throughput concurrent disk IO in FreeBSD.<br>From: New York City *BSD User Group<br>Tags: nycbsdcon2008, nycbsdcon, presentation, pdf, freebsd, high performance, adrian chadd<br> Slides of presentations given at New York City BSD Conference 2008. http://www.nycbsdcon.org/2008/files/dillon_hammer.tgz Mon, 24 Nov 2008 00:00:00 EST New York City BSD Con 2008 - Metthew Dillon: The HAMMER File System.<br>From: New York City *BSD User Group<br>Tags: nycbsdcon2008, nycbsdcon, presentation, html, hammer, metthew dillon<br> Slides of presentations given at New York City BSD Conference 2008. http://www.nycbsdcon.org/2008/files/magnusson_pcc.pdf Mon, 24 Nov 2008 00:00:00 EST New York City BSD Con 2008 - Anders Magnusson: Design and Implementation of the Portable C Compiler.<br>From: New York City *BSD User Group<br>Tags: nycbsdcon2008, nycbsdcon, presentation, pdf, pcc, anders magnusson<br> Slides of presentations given at New York City BSD Conference 2008. http://www.openbsd.org/papers/nycbsdcon08-pie/ Mon, 24 Nov 2008 00:00:00 EST New York City BSD Con 2008 - Kurt Miller: OpenBSD's Position Independent Executables (PIE) Implementation.<br>From: New York City *BSD User Group<br>Tags: nycbsdcon2008, nycbsdcon, presentation, html, openbsd, pie, kurt miller<br> Slides of presentations given at New York City BSD Conference 2008. http://www.silby.com/nycbsdcon08/NYCBSDCon-tcpdiff.pdf Mon, 24 Nov 2008 00:00:00 EST New York City BSD Con 2008 - Mike Silbersack: Detecting TCP regressions with tcpdiff.<br>From: New York City *BSD User Group<br>Tags: nycbsdcon2008, nycbsdcon, presentation, pdf, tcp regression, tcpdiff, mike silbersack<br> Slides of presentations given at New York City BSD Conference 2008. http://www.nycbsdcon.org/2008/files/wright_hardware-wrong.pdf Mon, 24 Nov 2008 00:00:00 EST New York City BSD Con 2008 - Jason L Wright: When Hardware Is Wrong, or "They can Fix It In Software".<br>From: New York City *BSD User Group<br>Tags: nycbsdcon2008, nycbsdcon, presentation, pdf, hardware, jason l wright<br> Slides of presentations given at New York City BSD Conference 2008. http://www.nycbsdcon.org/2008/files/vidal_atf.pdf Mon, 24 Nov 2008 00:00:00 EST New York City BSD Con 2008 - Julio M. Merino Vidal: An introduction to the Automated Testing Framework (ATF) for NetBSD.<br>From: New York City *BSD User Group<br>Tags: nycbsdcon2008, nycbsdcon, presentation, pdf, netbsd, atf, julio m merino vidal<br> Slides of presentations given at New York City BSD Conference 2008. http://cisx1.uma.maine.edu/~wbackman/bsdtalk//bsdtalk165.mp3 Fri, 21 Nov 2008 00:00:00 EST Julian Elischer - MP3 version<br>From: bsdtalk<br>Tags: bsdtalk, interview, julian elischer, ironport, mp3<br> An interview with Julian Elischer at MeetBSD in California. We talk about his early days with BSD and his work using BSD at various companies. He is currently with IronPort, which was bought by Cisco. http://cisx1.uma.maine.edu/~wbackman/bsdtalk//bsdtalk165.ogg Fri, 21 Nov 2008 00:00:00 EST Julian Elischer - Ogg version<br>From: bsdtalk<br>Tags: bsdtalk, interview, julian elischer, ironport, ogg<br> An interview with Julian Elischer at MeetBSD in California. We talk about his early days with BSD and his work using BSD at various companies. He is currently with IronPort, which was bought by Cisco. http://meetbsd.com/images/slides//slides_robert_watson_networking.pdf Wed, 19 Nov 2008 00:00:00 EST MeetBSD 2008 in California - Presentation - FreeBSD Network Stack Performance - Optimizations for Modern Hardware by Robert Watson<br>From: MeetBSD<br>Tags: meetbsd, meetbsd2008, freebsd, presentations, robert watson, network stack performance, modern hardware, pdf<br> MeetBSD 2008 at the Googleplex in Mountain View, California to celebrate FreeBSD's 15th Anniversary! http://meetbsd.com/images/slides//slides_brooks_davis.pdf Wed, 19 Nov 2008 00:00:00 EST MeetBSD 2008 in California - Presentation - Isolating Cluster Jobs for Performance and Predictability by Brooks Davis<br>From: MeetBSD<br>Tags: meetbsd, meetbsd2008, freebsd, presentations, brooks davis, cluster, pdf<br> MeetBSD 2008 at the Googleplex in Mountain View, California to celebrate FreeBSD's 15th Anniversary! http://meetbsd.com/images/slides//slides_warner_losh.pdf Wed, 19 Nov 2008 00:00:00 EST MeetBSD 2008 in California - Presentation - Embedding FreeBSD by M. Warner Losh<br>From: MeetBSD<br>Tags: meetbsd, meetbsd2008, freebsd, presentations, warner losh, embedding freebsd, pdf<br> MeetBSD 2008 at the Googleplex in Mountain View, California to celebrate FreeBSD's 15th Anniversary! http://meetbsd.com/images/slides//slides_dru_lavigne.pdf Wed, 19 Nov 2008 00:00:00 EST MeetBSD 2008 in California - Presentation - BSD Certification by Dru Lavigne<br>From: MeetBSD<br>Tags: meetbsd, meetbsd2008, freebsd, presentations, dru lavigne, bsd certification, pdf<br> MeetBSD 2008 at the Googleplex in Mountain View, California to celebrate FreeBSD's 15th Anniversary! http://meetbsd.com/images/slides//slides_kris_moore.pdf Wed, 19 Nov 2008 00:00:00 EST MeetBSD 2008 in California - Presentation - PC-BSD 7 - A Developer's Perspective by Kris Moore<br>From: MeetBSD<br>Tags: meetbsd, meetbsd2008, freebsd, presentations, kris moore, pc-bsd, pdf<br> MeetBSD 2008 at the Googleplex in Mountain View, California to celebrate FreeBSD's 15th Anniversary! http://meetbsd.com/images/slides//slides_pawel.pdf Wed, 19 Nov 2008 00:00:00 EST MeetBSD 2008 in California - Presentation - A closer look at the ZFS file system by Pawel Jakub Dawidek<br>From: MeetBSD<br>Tags: meetbsd, meetbsd2008, freebsd, presentations, pawel jakub dawidek, zfs, pdf<br> MeetBSD 2008 at the Googleplex in Mountain View, California to celebrate FreeBSD's 15th Anniversary! http://meetbsd.com/images/slides//slides_robert_watson_freebsd_foundation.pdf Wed, 19 Nov 2008 00:00:00 EST MeetBSD 2008 in California - Presentation - FreeBSD Foundation Update & Recognition by Robert Watson<br>From: MeetBSD<br>Tags: meetbsd, meetbsd2008, freebsd, presentations, robert watsom, freebsd foundation, pdf<br> MeetBSD 2008 at the Googleplex in Mountain View, California to celebrate FreeBSD's 15th Anniversary! http://meetbsd.com/images/slides//slides_philip_paeps.pdf Wed, 19 Nov 2008 00:00:00 EST MeetBSD 2008 in California - Presentation - Crypto Acceleration by Philip Paeps<br>From: MeetBSD<br>Tags: meetbsd, meetbsd2008, freebsd, presentations, philip paeps, crypto acecelaration, pdf<br> MeetBSD 2008 at the Googleplex in Mountain View, California to celebrate FreeBSD's 15th Anniversary! http://meetbsd.com/images/slides//slides_zach_loafman.pdf Wed, 19 Nov 2008 00:00:00 EST MeetBSD 2008 in California - Presentation - Isilon and FreeBSD by Zach Loafman<br>From: MeetBSD<br>Tags: meetbsd, meetbsd2008, freebsd, presentations, zach loafman, isilon, pdf<br> MeetBSD 2008 at the Googleplex in Mountain View, California to celebrate FreeBSD's 15th Anniversary! http://meetbsd.com/images/slides//slides_kris_kennaway.pdf Wed, 19 Nov 2008 00:00:00 EST MeetBSD 2008 in California - Presentation - "Help, my system is slow!" Profiling tools, tips and tricks by Kris Kennaway<br>From: MeetBSD<br>Tags: meetbsd, meetbsd2008, freebsd, presentations, kris kennaway, profiling, pdf<br> MeetBSD 2008 at the Googleplex in Mountain View, California to celebrate FreeBSD's 15th Anniversary! ftp://ftp.openbsd.org/pub/OpenBSD/songs//song44.mp3 Tue, 18 Nov 2008 00:00:00 EST OpenBSD 4.4 Release Song - "Source Wars - Episode IV - Trial of the BSD Knights" - MP3 version<br>From: OpenBSD<br>Tags: openbsd, artwork, mp3<br> <p> Nearly 10 years ago Kirk McKusick wrote a history of the Berkeley Unix distributions for the O'Reilly book "Open Sources: Voices from the Open Source Revolution". We recommend you read his story, entitled "Twenty Years of Berkeley Unix From AT&amp;T-Owned to Freely Redistributable" first, to see how Kirk remembers how we got here. Sadly, since it showed up in book form originally, this text has probably not been read by enough people. </p> <p> The USL(AT&amp;T) vs BSDI/UCB court case settlement documents were not public until recently; their disclosure has made the facts more clear. But the story of how three people decided to free the BSD codebase of corporate pollution -- and release it freely -- is more interesting than the lawsuit which followed. Sure, a stupid lawsuit happened which hindered the acceptance of the BSD code during a critical period. But how did a bunch of guys go through the effort of replacing so much AT&amp;T code in the first place? After all, companies had lots of really evil lawyers back then too -- were they not afraid? </p> <p> After a decade of development, most of the AT&amp;T code had already been replaced by university researchers and their associates. So Keith Bostic, Mike Karels and Kirk McKusick (the main UCB CSRG group) started going through the 4.3BSD codebase to cleanse the rest. Keith, in particular, built a ragtag team (in those days, USENIX conferences were a gold mine for such team building) and led these rebels to rewrite and replace all the Imperial AT&amp;T code, piece by piece, starting with the libraries and userland programs. Anyone who helped only got credit as a Contributor -- people like Chris Torek and a cast of .. hundreds more. </p> <p> Then Mike and Kirk purified the kernel. After a bit more careful checking, this led to the release of a clean tree called Net/2 which was given to the world in June 1991 -- the largest dump of free source code the world had ever received (for those days -- not modern monsters like OpenOffice). </p> <p> Some of these ragtags formed a company (BSDi) to sell a production system based on this free code base, and a year later Unix System Laboratories (basically AT&amp;T) sued BSDi and UCB. Eventually AT&amp;T lost and after a few trifling fixes (described in the lawsuit documents) the codebase was free. A few newer developments (and more free code) were added, and released in June 1994 as 4.4BSD-Lite. Just over 14 years later OpenBSD is releasing its own 4.4 release (and for a lot less than $1000 per copy). </p> <p> The OpenBSD 4.4 release is dedicated to Keith Bostic, Mike Karels, Kirk McKusick, and all of those who contributed to making Net/2 and 4.4BSD-Lite free. </p> ftp://ftp.openbsd.org/pub/OpenBSD/songs//song44.ogg Tue, 18 Nov 2008 00:00:00 EST OpenBSD 4.4 Release Song - "Source Wars - Episode IV - Trial of the BSD Knights" - Ogg version<br>From: OpenBSD<br>Tags: openbsd, artwork, ogg<br> <p> Nearly 10 years ago Kirk McKusick wrote a history of the Berkeley Unix distributions for the O'Reilly book "Open Sources: Voices from the Open Source Revolution". We recommend you read his story, entitled "Twenty Years of Berkeley Unix From AT&amp;T-Owned to Freely Redistributable" first, to see how Kirk remembers how we got here. Sadly, since it showed up in book form originally, this text has probably not been read by enough people. </p> <p> The USL(AT&amp;T) vs BSDI/UCB court case settlement documents were not public until recently; their disclosure has made the facts more clear. But the story of how three people decided to free the BSD codebase of corporate pollution -- and release it freely -- is more interesting than the lawsuit which followed. Sure, a stupid lawsuit happened which hindered the acceptance of the BSD code during a critical period. But how did a bunch of guys go through the effort of replacing so much AT&amp;T code in the first place? After all, companies had lots of really evil lawyers back then too -- were they not afraid? </p> <p> After a decade of development, most of the AT&amp;T code had already been replaced by university researchers and their associates. So Keith Bostic, Mike Karels and Kirk McKusick (the main UCB CSRG group) started going through the 4.3BSD codebase to cleanse the rest. Keith, in particular, built a ragtag team (in those days, USENIX conferences were a gold mine for such team building) and led these rebels to rewrite and replace all the Imperial AT&amp;T code, piece by piece, starting with the libraries and userland programs. Anyone who helped only got credit as a Contributor -- people like Chris Torek and a cast of .. hundreds more. </p> <p> Then Mike and Kirk purified the kernel. After a bit more careful checking, this led to the release of a clean tree called Net/2 which was given to the world in June 1991 -- the largest dump of free source code the world had ever received (for those days -- not modern monsters like OpenOffice). </p> <p> Some of these ragtags formed a company (BSDi) to sell a production system based on this free code base, and a year later Unix System Laboratories (basically AT&amp;T) sued BSDi and UCB. Eventually AT&amp;T lost and after a few trifling fixes (described in the lawsuit documents) the codebase was free. A few newer developments (and more free code) were added, and released in June 1994 as 4.4BSD-Lite. Just over 14 years later OpenBSD is releasing its own 4.4 release (and for a lot less than $1000 per copy). </p> <p> The OpenBSD 4.4 release is dedicated to Keith Bostic, Mike Karels, Kirk McKusick, and all of those who contributed to making Net/2 and 4.4BSD-Lite free. </p> http://cisx1.uma.maine.edu/~wbackman/bsdtalk//bsdtalk164.mp3 Tue, 18 Nov 2008 00:00:00 EST At MeetBSD with some of the FreeBSD Core Team - MP3 version<br>From: bsdtalk<br>Tags: bsdtalk, interview, freebsd core team, meetbsd2008, meetbsd, robert watson, brooks davis, kris kennaway, peter wemm, philip paeps, freebsd, subversion, mp3<br> A conversation with some of the FreeBSD Core Team at MeetBSD California 2008. I speak with Brooks Davis, Kris Kennaway, Robert Watson, Peter Wemm, and Philip Paeps about the recent core team election, FreeBSD 7.1 and 8, Developer Summits, and the move to Subversion. http://cisx1.uma.maine.edu/~wbackman/bsdtalk//bsdtalk164.ogg Tue, 18 Nov 2008 00:00:00 EST At MeetBSD with some of the FreeBSD Core Team - Ogg version<br>From: bsdtalk<br>Tags: bsdtalk, interview, freebsd core team, meetbsd2008, meetbsd, robert watson, brooks davis, kris kennaway, peter wemm, philip paeps, freebsd, subversion, ogg<br> A conversation with some of the FreeBSD Core Team at MeetBSD California 2008. I speak with Brooks Davis, Kris Kennaway, Robert Watson, Peter Wemm, and Philip Paeps about the recent core team election, FreeBSD 7.1 and 8, Developer Summits, and the move to Subversion. http://www.fetissov.org/public/nycbug/nycbug-11-05-08.mp3 Sun, 16 Nov 2008 00:00:00 EST Hardware Performance Monitoring Counters - MP3 version<br>From: New York City *BSD User Group<br>Tags: nycbug, presentation, george neville-neil, counters, mp3<br> <p> Many modern CPUs provide on chip counters for performance events such as retiring instructions and cache misses. The hwpmc driver and libraries in FreeBSD give systems administrators and programmers access to APIs which make it possible to measure performance without modifying source code and with minimal intrusion into application execution. This talk will be a brief introduction to HWPMC, and how to use it. </p><p> Bio: George Neville-Neil is the co-author with Kirk McKusick of The Design and Implementation of the FreeBSD Operating System. He works on networking an operating systems for fun and profit. </p> http://cisx1.uma.maine.edu/~wbackman/bsdtalk//bsdtalk163.mp3 Sun, 16 Nov 2008 00:00:00 EST A Tour of iXsystems - MP3 version<br>From: bsdtalk<br>Tags: bsdtalk, interview, ixsystems, mp3<br> A brief description of my visit to iXsystems in California prior to MeetBSD 2008. http://cisx1.uma.maine.edu/~wbackman/bsdtalk//bsdtalk163.ogg Sun, 16 Nov 2008 00:00:00 EST A Tour of iXsystems - Ogg version<br>From: bsdtalk<br>Tags: bsdtalk, interview, ixsystems, ogg<br> A brief description of my visit to iXsystems in California prior to MeetBSD 2008. http://cisx1.uma.maine.edu/~wbackman/bsdtalk//bsdtalk162.mp3 Sun, 16 Nov 2008 00:00:00 EST BSD on a eeePC 900A - MP3 version<br>From: bsdtalk<br>Tags: bsdtalk, eeepc, mp3<br> I look forward to attending MeetBSD this weekend. <br> A brief description of my first attempts to get BSD on a eeePC 900A. I try OpenBSD 4.4, DragonFlyBSD 2.0.1, PC-BSD 7.0.1, and FreeBSD 7. http://cisx1.uma.maine.edu/~wbackman/bsdtalk//bsdtalk162.ogg Sun, 16 Nov 2008 00:00:00 EST BSD on a eeePC 900A - Ogg version<br>From: bsdtalk<br>Tags: bsdtalk, eeepc, ogg<br> I look forward to attending MeetBSD this weekend. <br> A brief description of my first attempts to get BSD on a eeePC 900A. I try OpenBSD 4.4, DragonFlyBSD 2.0.1, PC-BSD 7.0.1, and FreeBSD 7. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2812&type=ogg Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Hauke Fath - Managing BSD desktop clients - Fencing in the herd - OGG<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, bsd, desktop, hauke fath, ogg<br> The members of the BSD family have traditionally prospered off the desktop, as operating systems on servers and embedded systems. The advent of MacOS X has marked a change, and moved the desktop more into focus. Modern desktop systems create a richer software landscape, with more diverse requirements, than their server counterparts. User demands, software package interdependencies and frequent security issues result in a change rate that can put a considerable load on the admin staff. Without central management tools, previously identical installations diverge quickly. This paper looks at concepts and strategies for managing tens to hundreds of modern, Unix-like desktop clients. The available management tools range from simple, image-based software distribution, mainly used for setting up uniform clients, to "intelligent" rule-based engines capable of search-and-replace operations on configuration files. We will briefly compare their properties and limitations, then take a closer look at Radmind, a suite for file level administration of Unix clients. Radmind has been in use in the Institute of Telecommunication at Technische Universitt Darmstadt for over three years, managing NetBSD and Debian Linux clients in the labs as well as faculty members' machines. We will explore the Radmind suite's underlying concepts and functionality. In order to see how the concept holds up, we will discuss real-world scenarios from the system life-cycle of Installation, configuration changes, security updates, component updates, and system upgrades. <br> Hauke Fath works as a systems administrator for the Institut fr Nachrichtentechnik (telecommunication) at Technische Universitt Darmstadt. He has been using NetBSD since 1994, when he first booted a NetBSD 1.0A kernel on a Macintosh SE/30. NetBSD helped shaping his career by causing a slow drift from application programmer's work towards systems and network administration. Hauke Fath holds a MS in Physics and became a NetBSD developer in late 2006. <br> Keywords: Managing Unix desktop clients, software distribution, tripwire http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2812&type=mp3 Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Hauke Fath - Managing BSD desktop clients - Fencing in the herd - MP3<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, bsd, desktop, hauke fath, mp3<br> The members of the BSD family have traditionally prospered off the desktop, as operating systems on servers and embedded systems. The advent of MacOS X has marked a change, and moved the desktop more into focus. Modern desktop systems create a richer software landscape, with more diverse requirements, than their server counterparts. User demands, software package interdependencies and frequent security issues result in a change rate that can put a considerable load on the admin staff. Without central management tools, previously identical installations diverge quickly. This paper looks at concepts and strategies for managing tens to hundreds of modern, Unix-like desktop clients. The available management tools range from simple, image-based software distribution, mainly used for setting up uniform clients, to "intelligent" rule-based engines capable of search-and-replace operations on configuration files. We will briefly compare their properties and limitations, then take a closer look at Radmind, a suite for file level administration of Unix clients. Radmind has been in use in the Institute of Telecommunication at Technische Universitt Darmstadt for over three years, managing NetBSD and Debian Linux clients in the labs as well as faculty members' machines. We will explore the Radmind suite's underlying concepts and functionality. In order to see how the concept holds up, we will discuss real-world scenarios from the system life-cycle of Installation, configuration changes, security updates, component updates, and system upgrades. <br> Hauke Fath works as a systems administrator for the Institut fr Nachrichtentechnik (telecommunication) at Technische Universitt Darmstadt. He has been using NetBSD since 1994, when he first booted a NetBSD 1.0A kernel on a Macintosh SE/30. NetBSD helped shaping his career by causing a slow drift from application programmer's work towards systems and network administration. Hauke Fath holds a MS in Physics and became a NetBSD developer in late 2006. <br> Keywords: Managing Unix desktop clients, software distribution, tripwire http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2812&type=pdf Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Hauke Fath - Managing BSD desktop clients - Fencing in the herd - PDF<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, bsd, desktop, hauke fath, pdf<br> The members of the BSD family have traditionally prospered off the desktop, as operating systems on servers and embedded systems. The advent of MacOS X has marked a change, and moved the desktop more into focus. Modern desktop systems create a richer software landscape, with more diverse requirements, than their server counterparts. User demands, software package interdependencies and frequent security issues result in a change rate that can put a considerable load on the admin staff. Without central management tools, previously identical installations diverge quickly. This paper looks at concepts and strategies for managing tens to hundreds of modern, Unix-like desktop clients. The available management tools range from simple, image-based software distribution, mainly used for setting up uniform clients, to "intelligent" rule-based engines capable of search-and-replace operations on configuration files. We will briefly compare their properties and limitations, then take a closer look at Radmind, a suite for file level administration of Unix clients. Radmind has been in use in the Institute of Telecommunication at Technische Universitt Darmstadt for over three years, managing NetBSD and Debian Linux clients in the labs as well as faculty members' machines. We will explore the Radmind suite's underlying concepts and functionality. In order to see how the concept holds up, we will discuss real-world scenarios from the system life-cycle of Installation, configuration changes, security updates, component updates, and system upgrades. <br> Hauke Fath works as a systems administrator for the Institut fr Nachrichtentechnik (telecommunication) at Technische Universitt Darmstadt. He has been using NetBSD since 1994, when he first booted a NetBSD 1.0A kernel on a Macintosh SE/30. NetBSD helped shaping his career by causing a slow drift from application programmer's work towards systems and network administration. Hauke Fath holds a MS in Physics and became a NetBSD developer in late 2006. <br> Keywords: Managing Unix desktop clients, software distribution, tripwire http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2823&type=ogg Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Yvan Vanhullebus - IPSec tools: past, present and future - OGG<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, ipsec, yvan vanhullebus, ogg<br> The first part will explain what have been major changes since Manu's presentation at Bale's EuroBSDCon, including more detailed informations on changes which have a significant impact on administrator's bad habits (why the common way of doing it is bad, why it was sometimes needed in the past, how to do it the good way now, why this is far better), on both the UserLand (ipsec-tools project) and maybe in [Free|Net]BSD kernels/ IPSec stacks. <br> The second part will talk about the future of the project. News of the next major version (which may be out or about to be out when we'll be ate EuroBSDCon), news works which are planned or which are done but not yet public, but also news about the team: it's new members, new tools, what we would like to do in tue future, a <br> Yvan VANHULLEBUS works as an R&D security engineer for NETASQ since 2000, where he works on FreeBSD OS. He started to work on KAME's IPSec stack in 2001, provided many patches for various parts of the stack, then became one of the maintainers of ipsec-tools project, a fork of KAME's userland daemon. He became a NetBSD developper when ipsec-tools was migrated to NetBSD's CVS. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2823&type=mp3 Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Yvan Vanhullebus - IPSec tools: past, present and future - MP3<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, ipsec, yvan vanhullebus, mp3<br> The first part will explain what have been major changes since Manu's presentation at Bale's EuroBSDCon, including more detailed informations on changes which have a significant impact on administrator's bad habits (why the common way of doing it is bad, why it was sometimes needed in the past, how to do it the good way now, why this is far better), on both the UserLand (ipsec-tools project) and maybe in [Free|Net]BSD kernels/ IPSec stacks. <br> The second part will talk about the future of the project. News of the next major version (which may be out or about to be out when we'll be ate EuroBSDCon), news works which are planned or which are done but not yet public, but also news about the team: it's new members, new tools, what we would like to do in tue future, a <br> Yvan VANHULLEBUS works as an R&D security engineer for NETASQ since 2000, where he works on FreeBSD OS. He started to work on KAME's IPSec stack in 2001, provided many patches for various parts of the stack, then became one of the maintainers of ipsec-tools project, a fork of KAME's userland daemon. He became a NetBSD developper when ipsec-tools was migrated to NetBSD's CVS. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2823&type=pdf Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Yvan Vanhullebus - IPSec tools: past, present and future - PDF<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, ipsec, yvan vanhullebus, pdf<br> The first part will explain what have been major changes since Manu's presentation at Bale's EuroBSDCon, including more detailed informations on changes which have a significant impact on administrator's bad habits (why the common way of doing it is bad, why it was sometimes needed in the past, how to do it the good way now, why this is far better), on both the UserLand (ipsec-tools project) and maybe in [Free|Net]BSD kernels/ IPSec stacks. <br> The second part will talk about the future of the project. News of the next major version (which may be out or about to be out when we'll be ate EuroBSDCon), news works which are planned or which are done but not yet public, but also news about the team: it's new members, new tools, what we would like to do in tue future, a <br> Yvan VANHULLEBUS works as an R&D security engineer for NETASQ since 2000, where he works on FreeBSD OS. He started to work on KAME's IPSec stack in 2001, provided many patches for various parts of the stack, then became one of the maintainers of ipsec-tools project, a fork of KAME's userland daemon. He became a NetBSD developper when ipsec-tools was migrated to NetBSD's CVS. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2827&type=ogg Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - George Neville-Neil - Multicast Performance in FreeBSD - OGG<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, multicast, freebsd, george neville-neil, ogg<br> In the past ten years most of the research in network protocols has gone into TCP, leaving UDP to languish as a local configuration protocol. While the majority of Internet traffic is TCP, UDP remains the only IP protocol that works over multicast and as such has some specific, and interesting uses in some areas of computing. In 2008 we undertook a study of the performance of UDP multicast on both 1Gbps and 10Gbps Ethernet networks in order to see if changing the physical layer of the network would give a linear decrease in packet latency. To measure the possible gains we developed a new network protocol test program, mctest, which is capable of recording packet round trip times from many hosts simultaneously and which we believe accurately represents how many environments use multicast. The mctest program has been integrated into FreeBSD and is now being used to verify the proper operation of multicast on various pieces of 10Gbps hardware. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2827&type=mp3 Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - George Neville-Neil - Multicast Performance in FreeBSD - MP3<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, multicast, freebsd, george neville-neil, mp3<br> In the past ten years most of the research in network protocols has gone into TCP, leaving UDP to languish as a local configuration protocol. While the majority of Internet traffic is TCP, UDP remains the only IP protocol that works over multicast and as such has some specific, and interesting uses in some areas of computing. In 2008 we undertook a study of the performance of UDP multicast on both 1Gbps and 10Gbps Ethernet networks in order to see if changing the physical layer of the network would give a linear decrease in packet latency. To measure the possible gains we developed a new network protocol test program, mctest, which is capable of recording packet round trip times from many hosts simultaneously and which we believe accurately represents how many environments use multicast. The mctest program has been integrated into FreeBSD and is now being used to verify the proper operation of multicast on various pieces of 10Gbps hardware. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2827&type=pdf Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - George Neville-Neil - Multicast Performance in FreeBSD - PDF<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, multicast, freebsd, george neville-neil, pdf<br> In the past ten years most of the research in network protocols has gone into TCP, leaving UDP to languish as a local configuration protocol. While the majority of Internet traffic is TCP, UDP remains the only IP protocol that works over multicast and as such has some specific, and interesting uses in some areas of computing. In 2008 we undertook a study of the performance of UDP multicast on both 1Gbps and 10Gbps Ethernet networks in order to see if changing the physical layer of the network would give a linear decrease in packet latency. To measure the possible gains we developed a new network protocol test program, mctest, which is capable of recording packet round trip times from many hosts simultaneously and which we believe accurately represents how many environments use multicast. The mctest program has been integrated into FreeBSD and is now being used to verify the proper operation of multicast on various pieces of 10Gbps hardware. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2810&type=ogg Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Brooks Davis - Isolating cluster jobs for performance and predictability - OGG<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, freebsd, cluster, brooks davis, ogg<br> The Aerospace Corporation operates a federally funded research and development center in support of national-security, civil and commercial space programs. Many of our 2400+ engineers use a variety of computing technologies to support their work. Applications range from small models which are easily handled by desktops to parameter studies involving thousands of cpu hours and traditional, large scale parallel codes such as computational fluid dynamics and molecular modeling applications. Our primary resources used to support these large applications are computing clusters. Our current primary cluster, the Fellowship cluster consists of 352 dual-processor nodes with a total of 14xx cores. Two additional clusters, beginning at 150 dual-processor nodes each are being constructed to augment Fellowship. As in In any multiuser computing environment with limited resources, user competition for resources is a significant burden. Users want everything they need to do their job, right now. Unfortunately, other users may need those resources at the same time. Thus, systems to arbitrate this resource contention are necessary. On Fellowship we have deployed the Sun Grid Engine scheduler which scheduled batch jobs across the nodes. In the next section we discuss the performance problems that can occur when sharing resources in a high performance computing cluster. We then discuss range of possibilities to address these problems. We then explain the solutions we are investigating and describe our experiments with them. We then conclude with a discussion of future work. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2810&type=mp3 Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Brooks Davis - Isolating cluster jobs for performance and predictability - MP3<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, freebsd, cluster, brooks davis, mp3<br> The Aerospace Corporation operates a federally funded research and development center in support of national-security, civil and commercial space programs. Many of our 2400+ engineers use a variety of computing technologies to support their work. Applications range from small models which are easily handled by desktops to parameter studies involving thousands of cpu hours and traditional, large scale parallel codes such as computational fluid dynamics and molecular modeling applications. Our primary resources used to support these large applications are computing clusters. Our current primary cluster, the Fellowship cluster consists of 352 dual-processor nodes with a total of 14xx cores. Two additional clusters, beginning at 150 dual-processor nodes each are being constructed to augment Fellowship. As in In any multiuser computing environment with limited resources, user competition for resources is a significant burden. Users want everything they need to do their job, right now. Unfortunately, other users may need those resources at the same time. Thus, systems to arbitrate this resource contention are necessary. On Fellowship we have deployed the Sun Grid Engine scheduler which scheduled batch jobs across the nodes. In the next section we discuss the performance problems that can occur when sharing resources in a high performance computing cluster. We then discuss range of possibilities to address these problems. We then explain the solutions we are investigating and describe our experiments with them. We then conclude with a discussion of future work. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2810&type=pdf Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Brooks Davis - Isolating cluster jobs for performance and predictability - PDF<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, freebsd, cluster, brooks davis, pdf<br> The Aerospace Corporation operates a federally funded research and development center in support of national-security, civil and commercial space programs. Many of our 2400+ engineers use a variety of computing technologies to support their work. Applications range from small models which are easily handled by desktops to parameter studies involving thousands of cpu hours and traditional, large scale parallel codes such as computational fluid dynamics and molecular modeling applications. Our primary resources used to support these large applications are computing clusters. Our current primary cluster, the Fellowship cluster consists of 352 dual-processor nodes with a total of 14xx cores. Two additional clusters, beginning at 150 dual-processor nodes each are being constructed to augment Fellowship. As in In any multiuser computing environment with limited resources, user competition for resources is a significant burden. Users want everything they need to do their job, right now. Unfortunately, other users may need those resources at the same time. Thus, systems to arbitrate this resource contention are necessary. On Fellowship we have deployed the Sun Grid Engine scheduler which scheduled batch jobs across the nodes. In the next section we discuss the performance problems that can occur when sharing resources in a high performance computing cluster. We then discuss range of possibilities to address these problems. We then explain the solutions we are investigating and describe our experiments with them. We then conclude with a discussion of future work. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2815&type=ogg Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Michael Dexter - Zen and the Art of Multiplicity Maintenance: An applied survey of BSD-licensed multiplicity strategies from chroot to mult - OGG<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, bsd, michael dexter, ogg<br> Many BSD-licensed strategies of various levels of maturity exist to implement multiplicity, herein defined as the introduction of plurality to traditionally singular computing environments via isolation, virtualization, or other method. For example, the chroot utility introduces an additional isolated root execution environment within that of the host; or an emulator provides highly-isolated virtual systems that can run complete native or foreign operating systems. Motivations for multiplicity vary, but a demonstrable desire exists for users to obtain root or run a foreign binary or operating system. We propose a hands-on survey of portable and integrated BSD-licensed multiplicity strategies applicable to the FreeBSD, OpenBSD, DragonFlyBSD and NetBSD operating systems on the i386 architecture. We will also address three oft-coupled disciplines: software storage devices, the installation of operating system and userlands in multiplicity environments plus the management of select multiplicity environments. Finally we will comment on each strategies potential limits of isolation, compatibility, independence and potential overhead in comparison to traditional systems. Keywords: multiplicity, virtualization, chroot, jail, hypervisor, xen, compat. <br> Michael Dexter has used Unix systems since 1991 and BSD-licensed multiplicity strategies for over five years. He is the Program Manager at the BSD Fund and Project Manager of the BSD.lv Project. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2815&type=mp3 Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Michael Dexter - Zen and the Art of Multiplicity Maintenance: An applied survey of BSD-licensed multiplicity strategies from chroot to mult - MP3<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, bsd, michael dexter, mp3<br> Many BSD-licensed strategies of various levels of maturity exist to implement multiplicity, herein defined as the introduction of plurality to traditionally singular computing environments via isolation, virtualization, or other method. For example, the chroot utility introduces an additional isolated root execution environment within that of the host; or an emulator provides highly-isolated virtual systems that can run complete native or foreign operating systems. Motivations for multiplicity vary, but a demonstrable desire exists for users to obtain root or run a foreign binary or operating system. We propose a hands-on survey of portable and integrated BSD-licensed multiplicity strategies applicable to the FreeBSD, OpenBSD, DragonFlyBSD and NetBSD operating systems on the i386 architecture. We will also address three oft-coupled disciplines: software storage devices, the installation of operating system and userlands in multiplicity environments plus the management of select multiplicity environments. Finally we will comment on each strategies potential limits of isolation, compatibility, independence and potential overhead in comparison to traditional systems. Keywords: multiplicity, virtualization, chroot, jail, hypervisor, xen, compat. <br> Michael Dexter has used Unix systems since 1991 and BSD-licensed multiplicity strategies for over five years. He is the Program Manager at the BSD Fund and Project Manager of the BSD.lv Project. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2815&type=pdf Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Michael Dexter - Zen and the Art of Multiplicity Maintenance: An applied survey of BSD-licensed multiplicity strategies from chroot to mult - PDF<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, bsd, michael dexter, pdf<br> Many BSD-licensed strategies of various levels of maturity exist to implement multiplicity, herein defined as the introduction of plurality to traditionally singular computing environments via isolation, virtualization, or other method. For example, the chroot utility introduces an additional isolated root execution environment within that of the host; or an emulator provides highly-isolated virtual systems that can run complete native or foreign operating systems. Motivations for multiplicity vary, but a demonstrable desire exists for users to obtain root or run a foreign binary or operating system. We propose a hands-on survey of portable and integrated BSD-licensed multiplicity strategies applicable to the FreeBSD, OpenBSD, DragonFlyBSD and NetBSD operating systems on the i386 architecture. We will also address three oft-coupled disciplines: software storage devices, the installation of operating system and userlands in multiplicity environments plus the management of select multiplicity environments. Finally we will comment on each strategies potential limits of isolation, compatibility, independence and potential overhead in comparison to traditional systems. Keywords: multiplicity, virtualization, chroot, jail, hypervisor, xen, compat. <br> Michael Dexter has used Unix systems since 1991 and BSD-licensed multiplicity strategies for over five years. He is the Program Manager at the BSD Fund and Project Manager of the BSD.lv Project. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2807&type=ogg Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - George Neville-Neil - Four years of summer of code - OGG<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, google soc, george neville-neil, ogg<br> The Google Summer of Code is a program designed to provide students with real world experience contributing to open source projects during the summer break in university studies. Each year Google selects a number of open source projects to act as mentoring organizations. Students are invited to submit project proposals for the open source projects that are most interesting to them. FreeBSD was one of the projects selected to participate in the inaugural Summer of Code in 2005 and we have participated each year since then. Over the past 4 years a total of 79 students have participated in the program and it has become a very significant source of new committers to FreeBSD. This talk will examine in detail the selection criteria for projects, the impact that successful projects have had, and some suggestions for how we can better leverage this program in the future. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2807&type=mp3 Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - George Neville-Neil - Four years of summer of code - MP3<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, google soc, george neville-neil, mp3<br> The Google Summer of Code is a program designed to provide students with real world experience contributing to open source projects during the summer break in university studies. Each year Google selects a number of open source projects to act as mentoring organizations. Students are invited to submit project proposals for the open source projects that are most interesting to them. FreeBSD was one of the projects selected to participate in the inaugural Summer of Code in 2005 and we have participated each year since then. Over the past 4 years a total of 79 students have participated in the program and it has become a very significant source of new committers to FreeBSD. This talk will examine in detail the selection criteria for projects, the impact that successful projects have had, and some suggestions for how we can better leverage this program in the future. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2807&type=pdf Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - George Neville-Neil - Four years of summer of code - PDF<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, google soc, george neville-neil, pdf<br> The Google Summer of Code is a program designed to provide students with real world experience contributing to open source projects during the summer break in university studies. Each year Google selects a number of open source projects to act as mentoring organizations. Students are invited to submit project proposals for the open source projects that are most interesting to them. FreeBSD was one of the projects selected to participate in the inaugural Summer of Code in 2005 and we have participated each year since then. Over the past 4 years a total of 79 students have participated in the program and it has become a very significant source of new committers to FreeBSD. This talk will examine in detail the selection criteria for projects, the impact that successful projects have had, and some suggestions for how we can better leverage this program in the future. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2822&type=ogg Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 Keynote - George Neville-Neil - Thinking about thinking code - OGG<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, george neville-neil, ogg<br> EuroBSDCon 2008 Keynote - George Neville-Neil - Thinking about thinking code http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2822&type=mp3 Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 Keynote - George Neville-Neil - Thinking about thinking code - MP3<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, george neville-neil, mp3<br> EuroBSDCon 2008 Keynote - George Neville-Neil - Thinking about thinking code http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2822&type=pdf Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 Keynote - George Neville-Neil - Thinking about thinking code - PDF<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, george neville-neil, pdf<br> EuroBSDCon 2008 Keynote - George Neville-Neil - Thinking about thinking code http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2826&type=ogg Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Pedro Giffuni - Working with Engineering Applications in FreeBSD - OGG<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, freebsd, engineering applications, pedro giffuni, ogg<br> In recent years, traditional branches of engineering like Civil, Chemical, Mechanical, Electrical and Industrial Engineering are requiring extensive computing facilities for their needs. Several well known labs (Sandia, Lawrence Livermore) rely on huge clusters to do all types of complex analysis that were unthinkable a couple of decades ago. While the free BSD variants share the environment with traditional UNIX systems, frequently used for such computations, it was not common to find adequate free software packages to carry complex calculations. Eventually commercial versions of important math related packages started to appear for the Linux platform. Even when the big packages were distant, the BSDs learned and adapted in resourceful ways: Matlab and Mathematica, running under Linux emulation, demanded functionality from the BSDs and NetBSD implemented a signal trampoline to be able to run AutoCAD with IRIX binary compatibility. A notable project that was always available under a free license was Berkeley's Spice circuit analysis program, however it was an exception rather than the rule. Even when the scientific community pressed for a while to get other important tools like NASA's FEA package Nastran under a free license, the objective of being able to access and enhance open scientific tools was elusive. About a decade ago the situation started to improve: FreeBSD's ports system started growing exponentially, first with a high content in the math category, afterwards with a CAD section and after sustained growth in those categories a science section was created. This growth was mostly pushed by Universities and their research projects and in general are not well known with respect to the commercial counterparts. I started porting math/engineering code for FreeBSD around 1996. Back then it was absolutely unthinkable for a Mechanical Engineer to depend only on FreeBSD for it's daily work. The situation nowadays is different: there are some very high quality engineering analysis packages like EDF's Code Aster, with more than 12 years of professional development, that just can't be ignored. A Finite Element package, like Code Aster, can easily cost 5000 US$, is priced according to the maximum problem size it can solve, can require yearly licenses, and is rarely available with source code. In NASTRAN's case the source code is only available for US citizens under a yearly fee. Free software does have serious limitations though; just like in office applications there are proprietary CAD formats or sometimes the package simply doesn't have the required functionality. Having the sources, of course, always has the advantage of being able to implement (or pay for) some specific functionality you might need. Many commercial packages have been recently ported to Linux, but even when they gain some of the advantages of an open environment they still have yet another limitation: they have been very slow to make use of the multicored features of the new processors in the market, a huge limitation now that the speed war between processors has been limited by the overheating problem. The objective of the talk is to give an overview of several CAD/CAE packages that have been made available recently as part of FreeBSD's ports system and the decisions that were made to port them. BRLCAD and Varkon are two CAD utilities that made a transition from closed source to an open environment and in the process in the process of getting ported to BSD have gained greater portability and general "bug" fixes critical for their consolidation as usable and maintainable projects. There are also some tricks that have not been well documented: it is possible to enable threads and some extra optimizations on some packages, and it is also possible to replace the standard BLAS library with the faster GOTO BLAS without rebuilding the package. It is also possible to build the packages optimized for a clustered environment, but perhaps what is most interesting of all is how all the packages interrelate with each other and can turn FreeBSD into a complete enginering environment. No OS distribution so far is offering all the engineering specific utilities offered through FreeBSD's ports system: from design to visualization, passing through analysis FreeBSD is becoming an option that can't be ignored, and best of all, it is an effort that will benefit not only FreeBSD but the wider audience. <br> Pedro F. Giffuni M. Sc. Industrial Engineering - University of Pittsburgh Mechanical Engineer - Universidad Nacional de Colombia I was born in Bogota, Colombia but I am an Italian citizen. My experience with computers started when I was about 12 years old With the TRS-80 Color Computer first using Basic and the OS-9. I studied electronics for 3 years but became tired of worrying about "whatever happened to electrons in there" and moved to Mechanical Engineering. For a while I rested from the computer world until the Internet came stepping along. I started using FreeBSD around 1995 and soon fell in love with the idea of being able to install a complete version of UNIX from the net with just one floppy. After submitting a the 999th port to the FreeBSD project Walnut Creek was kind enough to give me a subscription for several years to FreeBSD's CD-ROM. Since then I've been on and off porting software packages or fixing the bugs I have caused while porting them. Of course there has always been great respect for the other BSDs and their wonderful license and while I've given up on the idea of one day seeing a "UnifiedBSD" I am glad to see different approaches sharing ideas in a healthful environment. <br> Keywords: BSD, engineering, CAE, CAD, math, mechanical, FreeBSD ports http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2826&type=mp3 Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Pedro Giffuni - Working with Engineering Applications in FreeBSD - MP3<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, freebsd, engineering applications, pedro giffuni, mp3<br> In recent years, traditional branches of engineering like Civil, Chemical, Mechanical, Electrical and Industrial Engineering are requiring extensive computing facilities for their needs. Several well known labs (Sandia, Lawrence Livermore) rely on huge clusters to do all types of complex analysis that were unthinkable a couple of decades ago. While the free BSD variants share the environment with traditional UNIX systems, frequently used for such computations, it was not common to find adequate free software packages to carry complex calculations. Eventually commercial versions of important math related packages started to appear for the Linux platform. Even when the big packages were distant, the BSDs learned and adapted in resourceful ways: Matlab and Mathematica, running under Linux emulation, demanded functionality from the BSDs and NetBSD implemented a signal trampoline to be able to run AutoCAD with IRIX binary compatibility. A notable project that was always available under a free license was Berkeley's Spice circuit analysis program, however it was an exception rather than the rule. Even when the scientific community pressed for a while to get other important tools like NASA's FEA package Nastran under a free license, the objective of being able to access and enhance open scientific tools was elusive. About a decade ago the situation started to improve: FreeBSD's ports system started growing exponentially, first with a high content in the math category, afterwards with a CAD section and after sustained growth in those categories a science section was created. This growth was mostly pushed by Universities and their research projects and in general are not well known with respect to the commercial counterparts. I started porting math/engineering code for FreeBSD around 1996. Back then it was absolutely unthinkable for a Mechanical Engineer to depend only on FreeBSD for it's daily work. The situation nowadays is different: there are some very high quality engineering analysis packages like EDF's Code Aster, with more than 12 years of professional development, that just can't be ignored. A Finite Element package, like Code Aster, can easily cost 5000 US$, is priced according to the maximum problem size it can solve, can require yearly licenses, and is rarely available with source code. In NASTRAN's case the source code is only available for US citizens under a yearly fee. Free software does have serious limitations though; just like in office applications there are proprietary CAD formats or sometimes the package simply doesn't have the required functionality. Having the sources, of course, always has the advantage of being able to implement (or pay for) some specific functionality you might need. Many commercial packages have been recently ported to Linux, but even when they gain some of the advantages of an open environment they still have yet another limitation: they have been very slow to make use of the multicored features of the new processors in the market, a huge limitation now that the speed war between processors has been limited by the overheating problem. The objective of the talk is to give an overview of several CAD/CAE packages that have been made available recently as part of FreeBSD's ports system and the decisions that were made to port them. BRLCAD and Varkon are two CAD utilities that made a transition from closed source to an open environment and in the process in the process of getting ported to BSD have gained greater portability and general "bug" fixes critical for their consolidation as usable and maintainable projects. There are also some tricks that have not been well documented: it is possible to enable threads and some extra optimizations on some packages, and it is also possible to replace the standard BLAS library with the faster GOTO BLAS without rebuilding the package. It is also possible to build the packages optimized for a clustered environment, but perhaps what is most interesting of all is how all the packages interrelate with each other and can turn FreeBSD into a complete enginering environment. No OS distribution so far is offering all the engineering specific utilities offered through FreeBSD's ports system: from design to visualization, passing through analysis FreeBSD is becoming an option that can't be ignored, and best of all, it is an effort that will benefit not only FreeBSD but the wider audience. <br> Pedro F. Giffuni M. Sc. Industrial Engineering - University of Pittsburgh Mechanical Engineer - Universidad Nacional de Colombia I was born in Bogota, Colombia but I am an Italian citizen. My experience with computers started when I was about 12 years old With the TRS-80 Color Computer first using Basic and the OS-9. I studied electronics for 3 years but became tired of worrying about "whatever happened to electrons in there" and moved to Mechanical Engineering. For a while I rested from the computer world until the Internet came stepping along. I started using FreeBSD around 1995 and soon fell in love with the idea of being able to install a complete version of UNIX from the net with just one floppy. After submitting a the 999th port to the FreeBSD project Walnut Creek was kind enough to give me a subscription for several years to FreeBSD's CD-ROM. Since then I've been on and off porting software packages or fixing the bugs I have caused while porting them. Of course there has always been great respect for the other BSDs and their wonderful license and while I've given up on the idea of one day seeing a "UnifiedBSD" I am glad to see different approaches sharing ideas in a healthful environment. <br> Keywords: BSD, engineering, CAE, CAD, math, mechanical, FreeBSD ports http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2826&type=pdf Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Pedro Giffuni - Working with Engineering Applications in FreeBSD - PDF<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, freebsd, engineering applications, pedro giffuni, pdf<br> In recent years, traditional branches of engineering like Civil, Chemical, Mechanical, Electrical and Industrial Engineering are requiring extensive computing facilities for their needs. Several well known labs (Sandia, Lawrence Livermore) rely on huge clusters to do all types of complex analysis that were unthinkable a couple of decades ago. While the free BSD variants share the environment with traditional UNIX systems, frequently used for such computations, it was not common to find adequate free software packages to carry complex calculations. Eventually commercial versions of important math related packages started to appear for the Linux platform. Even when the big packages were distant, the BSDs learned and adapted in resourceful ways: Matlab and Mathematica, running under Linux emulation, demanded functionality from the BSDs and NetBSD implemented a signal trampoline to be able to run AutoCAD with IRIX binary compatibility. A notable project that was always available under a free license was Berkeley's Spice circuit analysis program, however it was an exception rather than the rule. Even when the scientific community pressed for a while to get other important tools like NASA's FEA package Nastran under a free license, the objective of being able to access and enhance open scientific tools was elusive. About a decade ago the situation started to improve: FreeBSD's ports system started growing exponentially, first with a high content in the math category, afterwards with a CAD section and after sustained growth in those categories a science section was created. This growth was mostly pushed by Universities and their research projects and in general are not well known with respect to the commercial counterparts. I started porting math/engineering code for FreeBSD around 1996. Back then it was absolutely unthinkable for a Mechanical Engineer to depend only on FreeBSD for it's daily work. The situation nowadays is different: there are some very high quality engineering analysis packages like EDF's Code Aster, with more than 12 years of professional development, that just can't be ignored. A Finite Element package, like Code Aster, can easily cost 5000 US$, is priced according to the maximum problem size it can solve, can require yearly licenses, and is rarely available with source code. In NASTRAN's case the source code is only available for US citizens under a yearly fee. Free software does have serious limitations though; just like in office applications there are proprietary CAD formats or sometimes the package simply doesn't have the required functionality. Having the sources, of course, always has the advantage of being able to implement (or pay for) some specific functionality you might need. Many commercial packages have been recently ported to Linux, but even when they gain some of the advantages of an open environment they still have yet another limitation: they have been very slow to make use of the multicored features of the new processors in the market, a huge limitation now that the speed war between processors has been limited by the overheating problem. The objective of the talk is to give an overview of several CAD/CAE packages that have been made available recently as part of FreeBSD's ports system and the decisions that were made to port them. BRLCAD and Varkon are two CAD utilities that made a transition from closed source to an open environment and in the process in the process of getting ported to BSD have gained greater portability and general "bug" fixes critical for their consolidation as usable and maintainable projects. There are also some tricks that have not been well documented: it is possible to enable threads and some extra optimizations on some packages, and it is also possible to replace the standard BLAS library with the faster GOTO BLAS without rebuilding the package. It is also possible to build the packages optimized for a clustered environment, but perhaps what is most interesting of all is how all the packages interrelate with each other and can turn FreeBSD into a complete enginering environment. No OS distribution so far is offering all the engineering specific utilities offered through FreeBSD's ports system: from design to visualization, passing through analysis FreeBSD is becoming an option that can't be ignored, and best of all, it is an effort that will benefit not only FreeBSD but the wider audience. <br> Pedro F. Giffuni M. Sc. Industrial Engineering - University of Pittsburgh Mechanical Engineer - Universidad Nacional de Colombia I was born in Bogota, Colombia but I am an Italian citizen. My experience with computers started when I was about 12 years old With the TRS-80 Color Computer first using Basic and the OS-9. I studied electronics for 3 years but became tired of worrying about "whatever happened to electrons in there" and moved to Mechanical Engineering. For a while I rested from the computer world until the Internet came stepping along. I started using FreeBSD around 1995 and soon fell in love with the idea of being able to install a complete version of UNIX from the net with just one floppy. After submitting a the 999th port to the FreeBSD project Walnut Creek was kind enough to give me a subscription for several years to FreeBSD's CD-ROM. Since then I've been on and off porting software packages or fixing the bugs I have caused while porting them. Of course there has always been great respect for the other BSDs and their wonderful license and while I've given up on the idea of one day seeing a "UnifiedBSD" I am glad to see different approaches sharing ideas in a healthful environment. <br> Keywords: BSD, engineering, CAE, CAD, math, mechanical, FreeBSD ports http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2828&type=ogg Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Paeps Philip - How-to embed FreeBSD - OGG<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, embed, freebsd, philip paeps, ogg<br> This paper provides a how-to embed FreeBSD. A console server built form an AT91RM9200 based ARM system will be explored. This paper will talk about the selection of hardware. It will explore creating images for the target system, as well as concentrate on different alternatives for deploying the system. A number of different options exist today, and no comprehensive guide for navigating through the choices exists today. This paper will explore the different alternatives that exist today for producing images targeted at different size requirements. The differing choices for storage in an embedded environment are explored. The techniques used to access rich debugging environments are discussed. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2828&type=mp3 Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Paeps Philip - How-to embed FreeBSD - MP3<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, embed, freebsd, philip paeps, mp3<br> This paper provides a how-to embed FreeBSD. A console server built form an AT91RM9200 based ARM system will be explored. This paper will talk about the selection of hardware. It will explore creating images for the target system, as well as concentrate on different alternatives for deploying the system. A number of different options exist today, and no comprehensive guide for navigating through the choices exists today. This paper will explore the different alternatives that exist today for producing images targeted at different size requirements. The differing choices for storage in an embedded environment are explored. The techniques used to access rich debugging environments are discussed. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2828&type=pdf Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Paeps Philip - How-to embed FreeBSD - PDF<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, embed, freebsd, philip paeps, pdf<br> This paper provides a how-to embed FreeBSD. A console server built form an AT91RM9200 based ARM system will be explored. This paper will talk about the selection of hardware. It will explore creating images for the target system, as well as concentrate on different alternatives for deploying the system. A number of different options exist today, and no comprehensive guide for navigating through the choices exists today. This paper will explore the different alternatives that exist today for producing images targeted at different size requirements. The differing choices for storage in an embedded environment are explored. The techniques used to access rich debugging environments are discussed. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2825&type=ogg Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Constantine Murenin - OpenBSD Hardware Sensors Framework - OGG<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, openbsd, hardware sensors, constantine murenin, ogg<br> In this talk, we will discuss the past and present history and the design principles of the OpenBSD hardware sensors framework. Sensors framework provides a unified interface for storing, registering and accessing information about hardware monitoring sensors. Sensor types include, but are not limited to, temperature, voltage, fan RPM, time offset and logical drive status. The framework spans sensor_attach(9), sysctl(3), sysctl(8), sensorsd(8), ntpd(8), snmpd(8) and more than 67 drivers, ranging from I2C temperature sensors and Super I/O hardware monitors to IPMI, RAID and SCSI enclosures. Several third-party tools are also available, for example, a plug-in for Nagios and ports/sysutils/symon. Originally based on some ideas from NetBSD, the framework has sustained many improvements in OpenBSD, and was ported and committed to FreeBSD and DragonFly BSD. <br> Constantine A. Murenin is an MMath graduate student at the David R. Cheriton School of Computer Science at the University of Waterloo (CA). Prior to his graduate appointment, Constantine attended and subsequently graduated from East Carolina University (US) and De Montfort University (UK), receiving two bachelor degrees in computer science, with honors and honours respectively. A FreeBSD Google Summer of Code 2007 Student, OpenBSD Committer and Mozilla Contributor, Constantine's interests range from standards compliance and usability at all levels, to quiet computing and hardware monitoring. <br> <a href="http://Constantine.SU/">http://Constantine.SU/</a> http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2825&type=mp3 Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Constantine Murenin - OpenBSD Hardware Sensors Framework - MP3<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, openbsd, hardware sensors, constantine murenin, mp3<br> In this talk, we will discuss the past and present history and the design principles of the OpenBSD hardware sensors framework. Sensors framework provides a unified interface for storing, registering and accessing information about hardware monitoring sensors. Sensor types include, but are not limited to, temperature, voltage, fan RPM, time offset and logical drive status. The framework spans sensor_attach(9), sysctl(3), sysctl(8), sensorsd(8), ntpd(8), snmpd(8) and more than 67 drivers, ranging from I2C temperature sensors and Super I/O hardware monitors to IPMI, RAID and SCSI enclosures. Several third-party tools are also available, for example, a plug-in for Nagios and ports/sysutils/symon. Originally based on some ideas from NetBSD, the framework has sustained many improvements in OpenBSD, and was ported and committed to FreeBSD and DragonFly BSD. <br> Constantine A. Murenin is an MMath graduate student at the David R. Cheriton School of Computer Science at the University of Waterloo (CA). Prior to his graduate appointment, Constantine attended and subsequently graduated from East Carolina University (US) and De Montfort University (UK), receiving two bachelor degrees in computer science, with honors and honours respectively. A FreeBSD Google Summer of Code 2007 Student, OpenBSD Committer and Mozilla Contributor, Constantine's interests range from standards compliance and usability at all levels, to quiet computing and hardware monitoring. <br> <a href="http://Constantine.SU/">http://Constantine.SU/</a> http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2825&type=pdf Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Constantine Murenin - OpenBSD Hardware Sensors Framework - PDF<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, openbsd, hardware sensors, constantine murenin, pdf<br> In this talk, we will discuss the past and present history and the design principles of the OpenBSD hardware sensors framework. Sensors framework provides a unified interface for storing, registering and accessing information about hardware monitoring sensors. Sensor types include, but are not limited to, temperature, voltage, fan RPM, time offset and logical drive status. The framework spans sensor_attach(9), sysctl(3), sysctl(8), sensorsd(8), ntpd(8), snmpd(8) and more than 67 drivers, ranging from I2C temperature sensors and Super I/O hardware monitors to IPMI, RAID and SCSI enclosures. Several third-party tools are also available, for example, a plug-in for Nagios and ports/sysutils/symon. Originally based on some ideas from NetBSD, the framework has sustained many improvements in OpenBSD, and was ported and committed to FreeBSD and DragonFly BSD. <br> Constantine A. Murenin is an MMath graduate student at the David R. Cheriton School of Computer Science at the University of Waterloo (CA). Prior to his graduate appointment, Constantine attended and subsequently graduated from East Carolina University (US) and De Montfort University (UK), receiving two bachelor degrees in computer science, with honors and honours respectively. A FreeBSD Google Summer of Code 2007 Student, OpenBSD Committer and Mozilla Contributor, Constantine's interests range from standards compliance and usability at all levels, to quiet computing and hardware monitoring. <br> <a href="http://Constantine.SU/">http://Constantine.SU/</a> http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2821&type=ogg Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Robert Watson - FreeBSD Network Stack Performance Optimizations for Modern Hardware - OGG<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, freebsd, network stack, hardware, robert watson, ogg<br> The arrival of high CPU core density, with commodity quad-core notebooks and 32-core servers, combined with 10gbps networking have transformed network design principles for operating systems. This talk will describe changes in the FreeBSD 6.x, 7.x, and forthcoming 8.x network stacks required to exploit multiple cores and serve 10gbps networks. The goal of the session will be to introduce the audience to general strategies used to improve performance, their rationales, and their impact on applications and users: <ul> <li>Introduction to the SMPng Project and the follow-on Netperf Project <li>Workloads and performance measurement <li>Efficient primitives to support modern network stacks <li>Multi-core and cache-aware network memory allocator <li>Fine-grained network stack locking <li>Load-balancing and contention-avoidance across multiple CPUs <li>CPU affinity for network stack data structures <li>TCP performance enhancements including TSO, LRO, and TOE <li>Zero-copy Berkely Packet Filter (BPF) buffers <li>Direct network stack dispatch from interrupt handlers <li>Multiple input and output queues </ul> <br> Robert Watson is a researcher at the University of Cambridge Computer Laboratory investinging operating system and network security. Prior to joining the Computer Laboratory to work on a PhD, he was Senior Principal Scientist at McAfee Research, now SPARTA ISSO, a leading security research and development organization, directing government and commercial research contracts for customers that include DARPA, the US Navy, and Apple Computer. His research interests include operating system security, network stack structure and performance, and windowing system structure. He is also a member of the FreeBSD Core Team and president of the FreeBSD Foundation. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2821&type=mp3 Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Robert Watson - FreeBSD Network Stack Performance Optimizations for Modern Hardware - MP3<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, freebsd, network stack, hardware, robert watson, mp3<br> The arrival of high CPU core density, with commodity quad-core notebooks and 32-core servers, combined with 10gbps networking have transformed network design principles for operating systems. This talk will describe changes in the FreeBSD 6.x, 7.x, and forthcoming 8.x network stacks required to exploit multiple cores and serve 10gbps networks. The goal of the session will be to introduce the audience to general strategies used to improve performance, their rationales, and their impact on applications and users: <ul> <li>Introduction to the SMPng Project and the follow-on Netperf Project <li>Workloads and performance measurement <li>Efficient primitives to support modern network stacks <li>Multi-core and cache-aware network memory allocator <li>Fine-grained network stack locking <li>Load-balancing and contention-avoidance across multiple CPUs <li>CPU affinity for network stack data structures <li>TCP performance enhancements including TSO, LRO, and TOE <li>Zero-copy Berkely Packet Filter (BPF) buffers <li>Direct network stack dispatch from interrupt handlers <li>Multiple input and output queues </ul> <br> Robert Watson is a researcher at the University of Cambridge Computer Laboratory investinging operating system and network security. Prior to joining the Computer Laboratory to work on a PhD, he was Senior Principal Scientist at McAfee Research, now SPARTA ISSO, a leading security research and development organization, directing government and commercial research contracts for customers that include DARPA, the US Navy, and Apple Computer. His research interests include operating system security, network stack structure and performance, and windowing system structure. He is also a member of the FreeBSD Core Team and president of the FreeBSD Foundation. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2821&type=pdf Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Robert Watson - FreeBSD Network Stack Performance Optimizations for Modern Hardware - PDF<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, freebsd, network stack, hardware, robert watson, pdf<br> The arrival of high CPU core density, with commodity quad-core notebooks and 32-core servers, combined with 10gbps networking have transformed network design principles for operating systems. This talk will describe changes in the FreeBSD 6.x, 7.x, and forthcoming 8.x network stacks required to exploit multiple cores and serve 10gbps networks. The goal of the session will be to introduce the audience to general strategies used to improve performance, their rationales, and their impact on applications and users: <ul> <li>Introduction to the SMPng Project and the follow-on Netperf Project <li>Workloads and performance measurement <li>Efficient primitives to support modern network stacks <li>Multi-core and cache-aware network memory allocator <li>Fine-grained network stack locking <li>Load-balancing and contention-avoidance across multiple CPUs <li>CPU affinity for network stack data structures <li>TCP performance enhancements including TSO, LRO, and TOE <li>Zero-copy Berkely Packet Filter (BPF) buffers <li>Direct network stack dispatch from interrupt handlers <li>Multiple input and output queues </ul> <br> Robert Watson is a researcher at the University of Cambridge Computer Laboratory investinging operating system and network security. Prior to joining the Computer Laboratory to work on a PhD, he was Senior Principal Scientist at McAfee Research, now SPARTA ISSO, a leading security research and development organization, directing government and commercial research contracts for customers that include DARPA, the US Navy, and Apple Computer. His research interests include operating system security, network stack structure and performance, and windowing system structure. He is also a member of the FreeBSD Core Team and president of the FreeBSD Foundation. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2817&type=ogg Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Aggelos Economopoulos - An MP-capable network stack for DragonFlyBSD with minimal use of locks - OGG<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, dragonflybsd, mp, network stack, aggelos economopoulos, ogg<br> Given the modern trend towards multi-core shared memory multiprocessors, it is inconceivable for production OS kernels not to be reentrant. The typical approach for allowing multiple execution contexts to simultaneously execute in kernel mode has been to use fine-grained locking for synchronising access to shared resources. While this technique has been proven efficient, empirical evidence suggests that the resulting locking rules tend to be cumbersome even for the experienced kernel programmer, leading to bugs that are hard to diagnose. Moreover, scaling to more processors requires extensive use of locks, which may impose unnecessary locking overhead for small scale multiprocessor systems. This talk will describe the typical approach and then discuss the alternative approach taken in the DragonFlyBSD network stack. We will give an overview of the various protocol threads employed for network I/O processing and the common-case code paths for packet reception and transmission. Additionally, we'll need to make a passing reference to DragonFlyBSD's message passing model. This should establish a baseline, allowing us to focus on the recent work by the author to eliminate use of the Big Giant Lock in the performance-critical paths for the TCP and UDP protocols. The decision to constrain this work on the two by far most widely-used transport protocols was made in order to (a) limit the amount of work necessary and (b) explore the effectiveness of the approach on the cases that matter at this point in time. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2817&type=mp3 Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Aggelos Economopoulos - An MP-capable network stack for DragonFlyBSD with minimal use of locks - MP3<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, dragonflybsd, mp, network stack, aggelos economopoulos, mp3<br> Given the modern trend towards multi-core shared memory multiprocessors, it is inconceivable for production OS kernels not to be reentrant. The typical approach for allowing multiple execution contexts to simultaneously execute in kernel mode has been to use fine-grained locking for synchronising access to shared resources. While this technique has been proven efficient, empirical evidence suggests that the resulting locking rules tend to be cumbersome even for the experienced kernel programmer, leading to bugs that are hard to diagnose. Moreover, scaling to more processors requires extensive use of locks, which may impose unnecessary locking overhead for small scale multiprocessor systems. This talk will describe the typical approach and then discuss the alternative approach taken in the DragonFlyBSD network stack. We will give an overview of the various protocol threads employed for network I/O processing and the common-case code paths for packet reception and transmission. Additionally, we'll need to make a passing reference to DragonFlyBSD's message passing model. This should establish a baseline, allowing us to focus on the recent work by the author to eliminate use of the Big Giant Lock in the performance-critical paths for the TCP and UDP protocols. The decision to constrain this work on the two by far most widely-used transport protocols was made in order to (a) limit the amount of work necessary and (b) explore the effectiveness of the approach on the cases that matter at this point in time. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2817&type=pdf Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Aggelos Economopoulos - An MP-capable network stack for DragonFlyBSD with minimal use of locks - PDF<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, dragonflybsd, mp, network stack, aggelos economopoulos, pdf<br> Given the modern trend towards multi-core shared memory multiprocessors, it is inconceivable for production OS kernels not to be reentrant. The typical approach for allowing multiple execution contexts to simultaneously execute in kernel mode has been to use fine-grained locking for synchronising access to shared resources. While this technique has been proven efficient, empirical evidence suggests that the resulting locking rules tend to be cumbersome even for the experienced kernel programmer, leading to bugs that are hard to diagnose. Moreover, scaling to more processors requires extensive use of locks, which may impose unnecessary locking overhead for small scale multiprocessor systems. This talk will describe the typical approach and then discuss the alternative approach taken in the DragonFlyBSD network stack. We will give an overview of the various protocol threads employed for network I/O processing and the common-case code paths for packet reception and transmission. Additionally, we'll need to make a passing reference to DragonFlyBSD's message passing model. This should establish a baseline, allowing us to focus on the recent work by the author to eliminate use of the Big Giant Lock in the performance-critical paths for the TCP and UDP protocols. The decision to constrain this work on the two by far most widely-used transport protocols was made in order to (a) limit the amount of work necessary and (b) explore the effectiveness of the approach on the cases that matter at this point in time. http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2806&type=ogg Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Anttii Kantee - Converting kernel file systems to services - OGG<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, anttii kantee, ogg<br> ABSD/UNIX operating system is traditionally split into two pieces: the kernel and userspace. Historically the reasons for this were clear: the UNIX kernel was a simple entity. However, over time the kernel has grown more and more complex. Currently, most of the same functionality is available both in userspace and the kernel, but under different names. Examples include synchronization routines and threading support. For instance, to lock a mutex in the NetBSD kernel, the call is mutex_enter(), while in userspace the routine which does exactly the same thing is known as pthread_mutex_enter(). Taking another classic example, a BSD style OS has malloc()/free() available both in userspace and the kernel, but with different linkage (the kernel malloc interface is currently being widely deprecated, though). This imposes a completely arbitrary division between the kernel and userspace. Most functionality provided by an opearating system should be treated as a service instead of explicitly pinning it down as a userspace daemon or a kernel driver. Currently, due to the arbitrarily difference in programming interface names, functionality must be explicitly ported between the kernel and userspace if it is to run in one or the other environment. By unifying the environments where possible, the arbitrary division is weakened and porting between these environments becomes simpler. <br> Antti Kantee has been a NetBSD developer for many many moons. He has managed to work on quite a few bits and pieces of a BSD system: userland utilities, the pkgsrc packaging system, networking, virtual memory, device drivers, hardware support and file systems. <br> See also <a href="http://www.netbsd.org/docs/puffs/rump.htm">http://www.netbsd.org/docs/puffs/rump.htm</a> http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2806&type=mp3 Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Anttii Kantee - Converting kernel file systems to services - MP3<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, anttii kantee, mp3<br> ABSD/UNIX operating system is traditionally split into two pieces: the kernel and userspace. Historically the reasons for this were clear: the UNIX kernel was a simple entity. However, over time the kernel has grown more and more complex. Currently, most of the same functionality is available both in userspace and the kernel, but under different names. Examples include synchronization routines and threading support. For instance, to lock a mutex in the NetBSD kernel, the call is mutex_enter(), while in userspace the routine which does exactly the same thing is known as pthread_mutex_enter(). Taking another classic example, a BSD style OS has malloc()/free() available both in userspace and the kernel, but with different linkage (the kernel malloc interface is currently being widely deprecated, though). This imposes a completely arbitrary division between the kernel and userspace. Most functionality provided by an opearating system should be treated as a service instead of explicitly pinning it down as a userspace daemon or a kernel driver. Currently, due to the arbitrarily difference in programming interface names, functionality must be explicitly ported between the kernel and userspace if it is to run in one or the other environment. By unifying the environments where possible, the arbitrary division is weakened and porting between these environments becomes simpler. <br> Antti Kantee has been a NetBSD developer for many many moons. He has managed to work on quite a few bits and pieces of a BSD system: userland utilities, the pkgsrc packaging system, networking, virtual memory, device drivers, hardware support and file systems. <br> See also <a href="http://www.netbsd.org/docs/puffs/rump.htm">http://www.netbsd.org/docs/puffs/rump.htm</a> http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2806&type=pdf Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Anttii Kantee - Converting kernel file systems to services - PDF<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, anttii kantee, pdf<br> ABSD/UNIX operating system is traditionally split into two pieces: the kernel and userspace. Historically the reasons for this were clear: the UNIX kernel was a simple entity. However, over time the kernel has grown more and more complex. Currently, most of the same functionality is available both in userspace and the kernel, but under different names. Examples include synchronization routines and threading support. For instance, to lock a mutex in the NetBSD kernel, the call is mutex_enter(), while in userspace the routine which does exactly the same thing is known as pthread_mutex_enter(). Taking another classic example, a BSD style OS has malloc()/free() available both in userspace and the kernel, but with different linkage (the kernel malloc interface is currently being widely deprecated, though). This imposes a completely arbitrary division between the kernel and userspace. Most functionality provided by an opearating system should be treated as a service instead of explicitly pinning it down as a userspace daemon or a kernel driver. Currently, due to the arbitrarily difference in programming interface names, functionality must be explicitly ported between the kernel and userspace if it is to run in one or the other environment. By unifying the environments where possible, the arbitrary division is weakened and porting between these environments becomes simpler. <br> Antti Kantee has been a NetBSD developer for many many moons. He has managed to work on quite a few bits and pieces of a BSD system: userland utilities, the pkgsrc packaging system, networking, virtual memory, device drivers, hardware support and file systems. <br> See also <a href="http://www.netbsd.org/docs/puffs/rump.htm">http://www.netbsd.org/docs/puffs/rump.htm</a> http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2814&type=ogg Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Nick Barkas - Dynamic memory allocation for dirhash in UFS2 - OGG<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, ufs2, nick barkas, ogg<br> Hello My name is Nick Barkas. I'm a master's student studying scientific computing at Kungliga Tekniska hgskolan (KTH) in Stockholm, Sweden. I have just begun work on a Google Summer of Code project with FreeBSD: Dynamic memory allocation for dirhash in UFS2 . I would like to present my results from this project at EuroBSDCon this year. This project is very much a work in progress now so it is a bit difficult to summarize what I would ultimately present. I will try to describe an outline, though. First I will give background information on dirhash: an explanation of the directory data structure in UFS2, how directory lookups in this structure necessitate a linear search, and how dirhash speeds these lookups up without having to change anything about the directory data structure. Next I will explain the current limitation that dirhash's maximum memory use must be manually specified by administrators, or left at a small conservative default of 2MB. I will explain some different methods I will have explored to try and make this maximum memory limit dynamically increase and decrease as the system has more or less free memory, and which method I will have ultimately settled on and implemented. Then I'll present some test results of performance of operations on very large directories with and without dynamic memory allocation enabled for dirhash. Next I will talk about how speed gains from dirhash are limited by the fact that the hash tables exist only in memory and must be recreated after each system boot, as big directories are scanned for the first time, or even have to be recreated for a directory that has not been scanned in some time if its dirhash has been discarded to free memory. These problems can be eliminated by using an on-disk index for directory entries. I will talk about some of the challenges of implementing on-disk indexing, such as remaining backwards compatible with older versions of UFS2 and interoperating properly with softupdates. Then, if my SoC project has permitted me time to work on this aspect of it, I will explain some possible methods for adding directory indexing to UFS2 that meets these challenges, and which of those ideas I will have implemented. Finally I will present results of some benchmarks on this filesystem with indices, and compare to performance with dirhash, and with no indices or dirhashes. <br> Keywords: dirhash, ufs2, filesystems, performance tuning http://audiovideocours.u-strasbg.fr/avc/courseaccess?id=2814&type=mp3 Wed, 22 Oct 2008 00:00:00 EST EuroBSDCon 2008 - Nick Barkas - Dynamic memory allocation for dirhash in UFS2 - MP3<br>From: EuroBSDCon<br>Tags: eurobsdcon, eurobsdcon2008, ufs2, nick barkas, mp3<br> Hello My name is Nick Barkas. I'm a master's student studying scientific computing at Kungliga Tekniska hgskolan (KTH) in Stockholm, Sweden. I have just begun work on a Google Summer of Code project with FreeBSD: Dynamic memory allocation for dirhash in UFS2 . I would like to present my results from this project at EuroBSDCon this year. This project is very much a work in progress now so it is a bit difficult to summarize what I would ultimately present. I will try to describe an outline, though. First I will give background information on dirhash: an explanation of the directory data structure in UFS2, how directory lookups in this structure necessitate a linear search, and how dirhash speeds these lookups up without having to change anything about the directory data structure. Next I will explain the current limitation that dirhash's maximum memory use must be manually specified by administrators, or left at a small conservative default of 2MB. I will explain some different methods I will have explored to try and make this maximum memory limit dynamically increase and decrease as the system has more or less free memory, and which method I will have ultimately settled on and implemented. Then I'll present some test results of performance of operations on very large directories with and without dynamic memory allocation enabled for dirhash. Next I will talk about how speed gains from dirhash are limited by the fact that the hash tables exist only in memory and must be recreated after each system boot, as big directories are scanned for the first time, or even have to be recreated for a directory that has not been scanned in some time if its dirhash has been discarded to free memory. These problems can be eliminated by using an on-disk index for directory entries. I will talk about some of the challenges of implementing on-disk indexing, such as remaining backwards compatible with older versions of UFS2 and interoperating properly with softupdates. Then, if my SoC project has permitted me time to work on this aspect of it, I will explain some possible methods for adding directory indexing to UFS2 that meets these challenges, and which of those ideas I will have implemented. Finally I will present results of some benchmarks on this filesystem with indices, and compare to performance with dirhash, and with no indices or dirhashes. <br> Keywords: dirhash, ufs2, filesystems, performance tuning