|
| |
| | Interview: Ingo Molnar |
 | | Ingo Molnar: Intel is obviously interested, and so were a number of kernel developers, and users as well. | | | Ingo Molnar: well, i'm in the fortunate position that the two are a perfect match. | | | Ingo Molnar: only Intel AFAIK - Hyper-Threading is an Intel trademark iirc. |
|
http://kerneltrap.org/node.php?id=517
(6695 words)
|
|
| |
| | Sample Contracts - Independent Contractor Agreement - Red Hat Software Inc. and Ingo Molnar - Competitive Intelligence ... |
| | Molnar shall establish and maintain sufficient office space, computer hardware, Internet access, and other equipment and services necessary to enable it to perform its obligations under this Agreement in a professional and timely fashion. | | | Molnar shall perform software development and consulting work as follows: 1. | | | In the event that Molnar requires additional computer hardware in order to perform its responsibilities under this Agreement, Red Hat will purchase or reimburse Molnar for the cost of such hardware. |
|
http://contracts.onecle.com/redhat/molnar.consult.1998.08.17.shtml
(1810 words)
|
|
| |
| | Linux Kernel 2.6: It's Worth More! |
| | Molnar's rough estimate found it would cost $176M (US) to redevelop the Linux kernel using traditional proprietary approaches. | | | So, what Molnar did was perfectly reasonable for getting a rough order of magnitude of effort. | | | The answer is that SLOCCount presumes that it's dealing with an "average" piece of software (i.e., a typical application) unless it's given parameters that tell it otherwise. |
|
http://www.dwheeler.com/essays/linux-kernel-cost.html
(3704 words)
|
|
| |
| | Bloglines Citations |
| | Molnar writes: (Summary) But i'd expect 64-bit userspace to work just fine too. | | | Molnar writes: (Summary) Changes since -U2: - build fix: fixes the latency.c compilation error reported by Adam Heath. | | | Molnar writes: (Summary) - fix the x64 compilation bug reported by thewade - fix the menuconfig duplicate entry bug noticed by Florian |
|
http://www.bloglines.com/citations?siteid=287548&itemid=7
(350 words)
|
|
| |
| | RealtimePreemption - CE Linux Public |
| | Ingo said this about how well this works on Un-processor (UP) systems versus SMP systems. | | | Recent patches from Ingo include a (large) number of technologies for improving preemption and debugging preemption issues with the Linux kernel. | | | Here is a list of things that could be worked on for this feature: |
|
http://tree.celinuxforum.org/CelfPubWiki/RealtimePreemption
(993 words)
|
|
| |
| | CS 3210 Operating System Design (Linux) |
| | This will require that you thoroughly understand the existing scheduler and that you develop an understanding of the fundamental improvements in the 2.5 scheduler. | | | You should develop a simple technique to retain this functionality in the modified scheduler. | | | Things You Don’t Need to Do Notice that Ingo’s scheduler has lots of enhancements beyond the O(1) feature. |
|
http://www.cc.gatech.edu/computing/classes/AY2003/cs3210_fall/p1.html
(1118 words)
|
|
| |
| | Slashdot Answers From Planet TUX: Ingo Molnar Responds |
| | Now that I've seen Ingo's answers, I think that the question about versions of TUX for other OSes turned out to be phrased poorly. | | | TUX itself can be safer than user-space webservers, simply due to the fact that the kernel is a much more controlled, predictable and dedicated programming environment. | | | It would be a reasonable and natural extension of the GET_OBJECT mechanizm to fetch objects from a cache hierarchy or from origin servers, yes. |
|
http://slashdot.org/interviews/00/07/20/1440204.shtml
(5255 words)
|
|
| |
| | LWN: On corporate PR and proper credit |
| | This enhancement was subsequently incorporated into the preempt real-time project maintained by Molnar. | | | On June 8, 2005, MontaVista open sourced an enhancement to the interrupt sub-system facilitating deterministic interrupt response. | | | MontaVista Software open sourced a working prototype of the real-time kernel in October 2004. |
|
http://lwn.net/Articles/145954
(1895 words)
|
|
| |
| | [No title] |
| | Technically Molnar's algorithm is O(1) while the old version was O(n). | | | His goal was to design an efficient algorithm that kept the strengths of the current version and improved its performance. | | | CS 380 Linux scheduler for kernel version 2.6.8.1 In 2002 Ingo Molnar decided to rewrite the process scheduler for Linux. |
|
http://www.cbu.edu/~yanushka/os/skdLnx.0
(987 words)
|
|
| |
| | Red Hat overhauls flagship Linux CNET News.com |
| | Their work was spurred in part by IBM, which began its own Linux threading project but dropped it after Linux leader Linus Torvalds expressed his preference for the Red Hat approach. | | | Improved Java performance could make Linux run better on a class of lower-end and midrange servers where it hasn't fared well thus far: "application servers" that run Java programs. | | | Unix products long have been able to gracefully handle many threads, but Linux lagged behind until two Red Hat programmers--Ulrich Drepper and Ingo Molnar--came up with new threading software. |
|
http://news.com.com/Red+Hat+overhauls+flagship+Linux/2100-7344_3-5094774.html
(2193 words)
|
|
| |
| | [No title] |
| | DESC 4G/4G: remove debug code EDESC The debug code in do_page_fault gets in the way of BUG handling, and triggers in the boot-time buggy wp test probe. | | | But it might even work on a real i386, if no other bugs get in the way. | | | 2.6.0-test2-mm4 DESC 4g4g: fpu emulation fix EDESC From: Ingo Molnar |
|
http://www.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.4/2.6.4-mm1/broken-out/4g-2.6.0-test2-mm2-A5.patch
(6359 words)
|
|
| |
| | [No title] |
| | Rapid Reaction Linux is not related to the well known KURT Linux [KURT98], except for the UTIME patch, both systems are relying on. | | | Rapid Reaction Linux combines two well known patches to achieve this goal on the Intel x86 architecture using processors like Intel Pentium or any newer descendant. | | | The 'Low Latency' kernel Patch created by Ingo Molnar [Molnar00] introduces about 50 additional Preemption Points into the standard Linux kernel code at positions where long latencies, f.ex. |
|
http://www.linuxshowcase.org/2001/full_papers/heursch/heursch_html
(5722 words)
|
|
| |
| | [No title] |
| | - seq_file /proc/interrupts for x86 too (Ingo Molnar) - fix memory leak in ia64 exec of ia32 binaries - check tgid not pid in scm_check_creds() (David Miller) - VM fixes: shm swap priority, zeromap_page_range - workaround VFS limitations for VXFS NFS export * Fri Aug 22 2003 Rik van Riel | | | - various XAPIC related fixes (Ingo Molnar) - correct context switch and iowait stats with HT shared runqueues - ext3 obscure deadlock fixes (Stephen Tweedie) - knfsd fixes: blocked lock, symlink error & missing bkl (Steve Dickson) * Wed Aug 5 2003 Rik van Riel | | | - nfs patches (Steve Dickson) - xapic improvements, summit support (Ingo Molnar) - fix core dump name for multithreaded programs (Roland McGrath) * Fri Jun 20 2003 Rik van Riel |
|
http://www.freevps.com/download/make_rpm/freevps-kernel-1.3.spec
(3895 words)
|
|
| |
| | Linux Real-Time Benchmarking Framework (LRTBF) |
| | Initially, the LRTBF was used for evaluating Ingo Molnar's PREEMPT_RT patches and Philippe Gerum's I-pipe (previously part of Adeos.) | | | It has already been used for publishing two sets of performance data evaluating Ingo Molnar's PREEMPT_RT and Philippe Gerum's I-pipe. | | | This is the initial release of the LRTBF. |
|
http://www.opersys.com/lrtbf
(809 words)
|
|
| |
| | Diary for DV |
| | Libxml make a very heavy use of the libc allocator, this might be the cause, dunno if I should analyze that as the Linux libc being optimized for single threaded perfs while Solaris one is more balanced in its choices. | | | I will make sure to always keep a CD-ROM reader even on server because trying to salvage a broken LILO on a root ext3 partition based on a SCSI card when the only input peripheral is a floppy drive ain't fun... | | | Having fun with Ingo Molnar testing TUX for FTP, until yesterday where the fr.rpmfind.net server used as the playground had serious filesystem problems. |
|
http://www.advogato.org/person/DV/diary.html?start=64
(2159 words)
|
|
| |
| | Linux-kernel mailing list archive 2002-29, by date |
| | Re: [patch] "big IRQ lock" removal, 2.5.27-A5 Ingo Molnar | | | Re: [patch] "big IRQ lock" removal, 2.5.27-A1 Ingo Molnar | | | Re: [patch] "big IRQ lock" removal, 2.5.27-A9 Ingo Molnar |
|
http://www.cs.helsinki.fi/linux/linux-kernel/2002-29/date.html
(5730 words)
|
|
| |
| | [No title] |
| | What is it, how it works, operations taken when opening a file or mounting a file system and description of important data structures explaining the purpose of each of their entries. | | | * Title: "The Linux RAID-1, 4, 5 Code" Author: Ingo Molnar, Gadi Oxman and Miguel de Icaza. | | | Here is it's abstract: "A description of the implementation of the RAID-1, RAID-4 and RAID-5 personalities of the MD device driver in the Linux kernel, providing users with high performance and reliable, secondary-storage capability using software". |
|
http://www.signaltonoise.net/library/kernel-docs.txt
(3601 words)
|
|
| |
| | Exec Shield - Wikipedia, the free encyclopedia |
| | Exec Shield attempts to flag data memory as non-executable and program memory as non-writeable. | | | If the CS limit is raised, for example by calling mprotect() to make higher memory executable, then the protections are lost below that limit. | | | Fortunately, most applications are fairly sane at this; the stack (the important part) at least winds up above any mapped libraries, so doesn't become executable except by explicit calls by the application. |
|
http://en.wikipedia.org/wiki/Exec_Shield
(351 words)
|
|
| |
| | Kernel Traffic #104 For 26 Jan 2001 |
| | Ingo replied, "math-FPU emulation takes up quite some space in the kernel image, so this could indeed be the case. | | | The fix was to remove the incorrect loop, it was a programming error." (see Issue #97, Section #6 (28 Nov 2000: 'modprobe' Infinite Loop On Buggy Drivers)) Ingo Oeser asked for an in-depth explanation, and Keith obliged: | | | Even if it could have loaded them, it would have been impossible to unload, both modules would have had a use count on the other. |
|
http://www.kerneltraffic.net/kernel-traffic/kt20010126_104.html
(4909 words)
|
|
| |
| | Linux IA64 Archives: By Thread |
| | Re: Add prefetch switch stack hook in scheduler function Russell King (29 Jul 2005) | | | Re: Add prefetch switch stack hook in scheduler function Nick Piggin (28 Jul 2005) |
|
http://www.gelato.unsw.edu.au/archives/linux-ia64/0507
(4251 words)
|
|
| |
| | Gmane -- Mail To News And Back Again |
| | This means that if the softlockup watchdog triggers, it has truly observed a longer than 10 seconds scheduling delay of a SCHED_FIFO prio 99 task. | | | (the patch also turns off the softlockup detector during the initial bootup phase and does small style fixes) Signed-off-by: Ingo Molnar ---- include/linux/sched.h |
|
http://article.gmane.org/gmane.linux.kernel/382655
(122 words)
|
|
| |
| | Linux Kernel mailing list Archive: Nach Thread |
| | Re: [PATCH][plugsched 0/28] Pluggable cpu scheduler framework Ingo Molnar | | | Re: [patch] Real-Time Preemption, -RT-2.6.9-mm1-V0.5 (networking problems) Ingo Molnar |
|
http://www.stunet.tu-freiberg.de/~hypermail/lkml/2004/11
(5963 words)
|
|
| |
| | SGI TPL View (Software-RAID-HOWTO) |
| | The howto was originally written by Jakob Østergaard based on a large number of emails between the author and Ingo Molnar (mingo@chiara.csoma.elte.hu) -- one of the RAID developers --, the linux-raid mailing list (linux-raid@vger.kernel.org) and various other people. | | | This HOWTO describes how to use Software RAID under Linux. | | | This is the RAID layer that is the standard in Linux-2.4, and it is the version that is also used by Linux-2.2 kernels shipped from some vendors. |
|
http://techpubs.sgi.com/tpl.cgi/view/linux/HOWTO/Software-RAID-HOWTO
(13000 words)
|
|
| |
| | [SDL] Fwd: lowlatency letter to linus |
| | > > We understand that we could try to maintain a version of Ingo's low latency > patches in parallel to the current kernel. | | | > > * what design goals you have in mind when you talk about > doing low latency "right", rather than "wrong, as in > Ingo's approach" ? | | | CPU and disk performance has improved to the point where we are > on the threshold of a revolution in the way that sound synthesis and > processing is done, and many of us want to ride Linux into the heart of that > revolution. |
|
http://www.libsdl.org/pipermail/sdl/2000-June/028593.html
(1060 words)
|
|
| |
| | Bloglines Citations |
| | Molnar writes: (Summary) [...] that should read: http://kernel.org/pub/linux/kernel/v2.6/linux-2.6.9.tar.bz2 http://kernel.org/pub/linux/kernel/v2.6/testing/patch-2.6.10-rc2.bz2 | | | Molnar writes: (Summary) i have released the -U10 Real-Time Preemption patch, which can be downloaded from: http://redhat.com/~mingo/realtime-preempt/ | | | Molnar writes: (Summary) i have released the -V0.7.33-0 Real-Time Preemption patch, which can be downloaded from the usual place: http://redhat.com/~mingo/realtime-preempt/ |
|
http://www.bloglines.com/citations?siteid=287548&itemid=9
(409 words)
|
|
| |
| | Linux-kernel mailing list archive 2002-01, by thread |
| | Re: Hardware Inventory [was: Re: ISA slot detection on PCI systems?] Alexander Viro | | | Re: MTBF Was: Two hdds on one channel - why so slow? | | | Re: [PATCH] Athlon XP 1600+ and _mmx_memcpy symbol in modules Athanasius |
|
http://www.cs.helsinki.fi/linux/linux-kernel/2002-01
(8004 words)
|
|
| |
| | Incoming to linuxppc-2.5 |
| | Without this patch, once a CPU is offlined and then later onlined, it becomes "more or less" useless (does not run any task other than its idle task!) Ingo said: The __setscheduler() call is (technically) incorrect because in the SCHED_NORMAL case the prio should be zero. | | | ChangeSet@1.497.4094.14, 2004-05-25 08:36:46-07:00, akpm@osdl.org [PATCH] Fix the mangled-oops-output-on-SMP problem From: Ingo Molnar printk currently does if (oops_in_progres) bust_printk_locks(); which means that once we oops, the printk locking is 100% ineffective and multiple CPUs make an unreadable mess on a serial console. | | | ChangeSet@1.497.4094.59, 2004-05-25 08:45:13-07:00, akpm@osdl.org [PATCH] Subject: Re: Help understanding slow down Signed-off-by: Ingo Molnar Add a warning that "idle=poll" is a performance hit on hyperthreaded CPUs. |
|
http://source.mvista.com/pipermail/linuxppc-commit/2004-May/003899.html
(4328 words)
|
|
| |
| | Linux scheduling latency |
| | Those patches use the same algorithmic approach as the ones here, and these patches borrow a few bits and pieces from Ingo's. | | | Ingo Molnar wrote Linux's first low-latency scheduling patches. | | | If something goes wrong and you start seeing scheduling latencies, please try to investigate the source using the above tools (mainly rtc_debug and amlat) and let me know what you're doing to cause this. |
|
http://www.zip.com.au/~akpm/linux/schedlat.html
(946 words)
|
|
| |
| | The Old Joel on Software Forum - The Joy of Linux |
| | Ingo's response to the logical followup question, "why so many threads, the answer is because we can :)" | | | In comparison, with the 2.5.31 kernel (prior to Ingo's recent threading work), such a test would have taken around 15 minutes. | | | Ingo Molnar explained that with the current stock 2.5 kernel such a test requires roughly 1GB RAM, and the act of starting and stopping all 100,000 threads in parallel takes only 2 seconds. |
|
http://discuss.fogcreek.com/joelonsoftware?cmd=show&ixPost=38288
(1790 words)
|
|
| |
| | Importing The Kernel Into git, Merging :: OSDir.com :: Open Source, Linux News & Software |
| | Thomas noted that the archive, which contains 3 years of development history, is comprised of 500,000 objects using 3.2 GiB of disk space. | | | Thomas worked using BitKeeper to export and create his tree, while Ingo used only the CVS tree as a source. | | | Over the weekend, Thomas Gleixner and Ingo Molnar both managed to separately import the complete kernel history into git format. |
|
http://osdir.com/Article5108.phtml
(107 words)
|
|
| |
| | Linux-Kernel Archive: By Thread |
| | Re: Swap on RAID; was: Re: the new VM Ingo Molnar | | | Re: 1023rd thread crashes 2.4.0-test8 from non-root user Ingo Molnar |
|
http://www.ussg.iu.edu/hypermail/linux/kernel/0009.3
(3908 words)
|
|
| |
| | Change Log of ATL QoS Web Pages |
| | Also enhanced jitter comparator to display below the graph the values that are above the last bin in the jitter histogram. | | | Results for Ingo Molnar Real-time Kernel 2.6.14-rtXX (where "XX" stands for the "rt" version number) have been posted. | | | For jitter both the nanosleep() and select() jitters are now posted. |
|
http://www.atl.lmco.com/projects/QoS/changelog.html
(679 words)
|
|
| |
| | Linux Valley - ENCYCLOPEDIA |
| | -pre1: - Chris Mason: reiserfs, another null bytes bug - Andrea Arkangeli: make SMP Athlon build - Alexander Zarochentcev: reiserfs directory fsync SMP locking fix - Jeff Garzik: PCI network driver updates - Alan Cox: continue merging - Ingo Molnar: fix RAID AUTORUN ioctl, scheduling improvements | | | -pre8: - Paul Mackerras: PPC update for thread-safe page table handling - Ingo Molnar: x86 PAE update for thread-safe page table handling - Jeff Garzik: network driver updates, i810 rng driver, and "alloc_etherdev()" network driver insert race condition fix. |
|
http://www.linuxvalley.com/encyclopedia/meteokernel/kernel24/prepatch.php
(444 words)
|
|
| |
| | Linux: Improving Interactivity |
| | I didn't actually even verify that UNIX domain sockets will | | | On Thu, 2003-03-06 at 17:11, Ingo Molnar wrote: | | | Continuing an earlier thread [story] on the lkml in which Ingo Molnar [interview] had announced his latest "HT scheduler" work, the conversation become heavily focused on interactivity. |
|
http://kerneltrap.org/node.php?id=603
(8194 words)
|
|
| |
| | [No title] |
| | arch/x86_64/mm/numa.c: In function `numa_setup': arch/x86_64/mm/numa.c:332: error: `numa_fake' undeclared (first use in this function) arch/x86_64/mm/numa.c:332: error: (Each undeclared identifier is reported only once arch/x86_64/mm/numa.c:332: error: for each function it appears in.) Signed-off-by: Ingo Molnar | | | Just make it synonymous with CONFIG_X86_IO_APIC - Move the definition of irq_mis_count over to io_apic.c Signed-off-by: Ingo Molnar |
|
http://www.kernel.org/pub/linux/kernel/v2.6/snapshots/old/patch-2.6.9-bk1.log
(6749 words)
|
|
| |
| | GROKLAW |
| | Where a source file was worked on by many programmers, only the principle authors are listed." | | | 60 kernel/timer.c 1992 Linus Torvalds; Ingo Molnar, Red Hat; David S Miller; Alexey Kuznetsov | | | 592 arch/i386/kernel/smp.c 1995 Alan Cox, Red Hat; 2000 Ingo Molnar, Red Hat |
|
http://radio.weblogs.com/0120124/2003/08/19.html
(3055 words)
|
|
| |
| | Linux-Kernel Archive by thread |
| | Re: AVL trees vs. Red-Black trees Ingo Molnar | | | Re: [patch] smp-2.3.30-A1, mb(), wmb(), rmb() Ingo Molnar | | | Re: [patch] new spinlock variant, spinlock-2.3.30-A4 Ingo Molnar |
|
http://www.ussg.iu.edu/hypermail/linux/kernel/9911.3
(3481 words)
|
|
| |
| | LWN.net weekly edition |
| | Ingo Molnar recently posted a patch adding a new set of system calls which will bind a process to a subset of the available CPUs on a system. | | | Ingo has also posted chaff, a tool for changing processor affinities of running processes. | | | Momchil Velikov has posted a new page cache implementation which is intended to be more scalable. |
|
http://lwn.net/2001/1129/bigpage.php3
(9938 words)
|
|
| |
| | NX bit - LearnThis.Info Enclyclopedia |
| | Exec Shield's legacy CPU support approximates (Ingo Molnar's word for it) NX emulation by tracking the upper code segment limit. | | | Linux itself supports standard hardware NX, now in 32 bit mode on 64-bit CPUs via Ingo Molnar's NX enabler patch as well as in 64 bit mode on CPUs that support it (these include current 64-bit CPUs of AMD and future CPUs announced by Intel, Transmeta and VIA). | | | Redhat kernel developer Ingo Molnar released a Linux kernel patch named Exec shield to approximate and utilize NX functionality on 32-bit x86 CPUs. |
|
http://encyclopedia.learnthis.info/n/nx/nx_bit.html
(1722 words)
|
|
| |
| | A preemptible Kernel for Ingo Molnar's latest scheduler [KernelTrap] |
| | The latest news and announcements about Linux based embedded applications... | | | The actually scheduling support is less, due to the simplified schedule and schedule_tail, although there is added code for making the per-CPU runqueues preempt-safe.' " | | | Ingo Molnar's recent O(1) scheduler has also looked attractive, but I've been waiting until it was compatible with Robert's patch before trying it. |
|
http://www.linuxdevices.com/news/NS9964337683.html
(320 words)
|
|
| |
| | KernelTimerSystems - CE Linux Public |
| | Ingo Molnar did an in-depth explanation about the performance of the current "timer wheel" implementation of timers. | | | This was part of a series of messages trying to justify the addition of ktimers (which have different characteristics). | | | 6 Ingo Molnar's explanation of timer wheel performance |
|
http://www.celinuxforum.org/pubwiki/moin.cgi/KernelTimerSystems
(425 words)
|
|
| |
| | Kernel Traffic |
| | Ingo tried doing some code revisions that turned out to blow up in his face, leaking dentries all over the place. | | | Without changing the design of the ext3 system, I don't think there is a clean patch. | | | It seemed that progress was being made, with folks like Steven Rostedt working round the clock on patch implementations; but ultimately the solution was not as forthcoming as folks would have liked. |
|
http://www.kerneltraffic.org/kernel-traffic/kt20050411_306.xml
(3051 words)
|
|
| |
| | LWN: Re: Ingo Molnar and Con Kolivas 2.6 scheduler patches |
| | Another note: I have not tested Davide's patch, nor have I read it in detail, or Ingo's scheduling code for that matter. | | | To make this work properly you need a double constraint: as well as guaranteeing maximum latency, you need a guarantee that real-time processes cannot totally exclude interactive processes. | | | By keeping this firmly in mind we will end up with better interactive performance, excellent audio reproduction, and simpler, better code overall. |
|
http://lwn.net/Articles/41639
(842 words)
|
|
| |
| | Magyar Linux levelezési lista archívum |
| | SunOS 4.1.3 kontra Linux 1.3.74 Ingo Molnar | | | tobb mint 6 virtualis terminal Ingo Molnar |
|
http://www.cab.u-szeged.hu/linux/lista/www/96.marc/3.het
(323 words)
|
|
| |
| | Re: [patch] Real-Time Preemption, -RT-2.6.13-rc6-V0.7.53-11 |
| | Ingo Molnar | | | That would cause some minimal runtime overhead for irqsafe locks though. | | | ] Ingo - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@[EMAIL PROTECTED] majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ |
|
http://www.talkaboutsoftware.com/group/linux.kernel/messages/209333.html
(767 words)
|
|
| |
| | Gmane -- Mail To News And Back Again |
| | * Paolo Ciarrocchi wrote: > 2005/7/26, Ingo Molnar : > [...] > > [back from KS/OLS] > > > > indeed. | | | > > > > Acked-by: Ingo Molnar > > Ingo, Lee, Andreas, > the patch seems to be quite simple and is a fix for a regression. | | | The effect of the bug is that RLIMIT_RTPRIO is completely > > non-functional in 2.6.12. |
|
http://article.gmane.org/gmane.linux.kernel/321027
(158 words)
|
|
|
