Re: new syscons screensaver
On Wed, May 02, 2001 at 12:50:00AM -0500, Andy Sloane wrote: > Hello, > > I just wrote a new syscons screensaver which I think is much more > interesting than the other ones, while still being relatively easy on the > CPU (much less CPU intensive than "fire", anyway). Please review it and > let me know what you think. > > It's the bsd daemon logo (with much editing, thanks to my coworker Waylon) > floating (with a realtime shadow!) above a bunch of tiled spheres which > move around and morph. It's only one palette change per frame, until the > bsd daemon moves. > > http://fear.incarnate.net/~andude/balls.tar.gz > > I'm not on this list, so please reply directly to me. Thanks. > > -Andy First, you should know that I absolutely love your first name. :) The screensaver isn't bad, and it gets pretty trippy when you focus at infinity and let the 3D-Illusions (TM) effect set in. If I were to make one suggestion, it would be to animate Beastie, so that he walks around the screen rather than teleporting everywhere. However, I'm quite fond of the green_saver module, which shuts down my monitor after 15 minutes. Other screensavers are really just for entertainment; I think green_saver is the only one that serves a really good purpose. -- Andrew Hesford [EMAIL PROTECTED] To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
new syscons screensaver
Hello, I just wrote a new syscons screensaver which I think is much more interesting than the other ones, while still being relatively easy on the CPU (much less CPU intensive than "fire", anyway). Please review it and let me know what you think. It's the bsd daemon logo (with much editing, thanks to my coworker Waylon) floating (with a realtime shadow!) above a bunch of tiled spheres which move around and morph. It's only one palette change per frame, until the bsd daemon moves. http://fear.incarnate.net/~andude/balls.tar.gz I'm not on this list, so please reply directly to me. Thanks. -Andy To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Mini Config.
Hi, I'm working on creating the smallest config I can get to compile as an "experiment" and to basically move to KLM's overall (once I get this working properly, I'll send-pr it to see if anyone wants it in the next release possibly). I have a question about how I would get some of the options into the kernel, wether it be sysctl or they would need to be in the kernel config. Things like: options NFS_ROOT options IPFIREWALL_VERBOSE options IPFIREWALL_VERBOSE_LIMIT=10 etc etc. If I kldload nfs.ko, will the NFS_ROOT option be available if I don't specify it in the kernel or do I need to specify it in the kernel if I want it to be usable as root when the NFS module is loaded? Can I do this via sysctls? Same goes for IPFIREWALL_* Thanks, Daryl To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Re: cdr and cdrw with 4.3 release
In message <[EMAIL PROTECTED]> Doug Ambrisko writes: : Any generic PCMCIA IDE based thing should work. I might stop using an Other than flash, I have 5 different PCMCIA IDE based things, and they all work. Warner To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Re: x86-64 Hammer and IA64 Itainium
On Fri, Apr 27, 2001 at 07:37:15AM +0200, Leif Neland wrote: > From: "Sergey Babkin" <[EMAIL PROTECTED]> > > Anothing interesting point is that the optimisation for IA-64 > > seems to be highly processor-specific: the code optimized for > > Itanium won't be optimal for McKinley and vice versa. I've heard > > an estimation of about 1.5 times speed increase due to the > > model-specific optimisation. > > > Perhaps commercial software will need to come in (encrypted) > source and be compiled to the the current processor... What else is .NET? (OK, it's a bunch of other stuff too, but processors like the Itanium that introduce serious system specific performance issues (like memory and cache latencies) are a very good reason to persue dynamic recompilation technologies like HotSpot, Dynamo, FX-86, Transmetta and .NET.) -- Andrew To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Re: Bootable CD IV
From: Rick Duvall <[EMAIL PROTECTED]> Subject: Bootable CD IV Date: Tue, 1 May 2001 12:03:21 -0700 (PDT) > So, let me get this straight: To make a bootable CD, you need to: > [steps alided] That will essentially work, yes, though I've never seen someone use /usr directly as a scratch directory before. :-) > Okay, got that far. But, it will load the kernel, then hang and say that > it cannot mount root device /dev/fd0. This doesn't make any sense to me > becuase I specifically told fstab on the cd to use the cdrom as root. Am > I stupid or something? Not stupid, just not thinking this all the way through. The root mounting code runs well ahead of anything which looks into /etc/fstab; how indeed could it even find fstab if it didn't know where the root partition was? You need to change the kernel's mind about where to find its root partition, something which can be accomplished in a variety of ways. In the case of the boot floppy, we don't even try; we just use MFS for the root partition and mount the CD elsewhere. Of all the options, this is in fact the simplest. - Jordan To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
cy0: port not found
Hi, I need some advice to build dial-in server. I've Cyclades Cyclom 32 YeP and FreeBSD 4.3. This is first time for me to Install multiport Serial. I'm trying to look at FreeBSD 4.3 manual : # man cy and I follow to add the lines to my kernel options, recompile it, and restart the computer. But reported : cy0: port not found What should I do ??? Thank's. Q -- Email ini dikirim oleh PlasaCom : http://www.plasa.com Cepat di-download via TelkomNet Instan http://www.plasa.com/instan Rindukah Anda bertemu dengan ex teman-teman satu sekolah dulu ? Kunjungilah mereka (47.033 anggota) di KSI : http://ksi.plasa.com -- To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Re: Bootable CD IV
So, you mean I need to create that rootmfs.gz thing that is on the second floppy of the freebsd install, then mount cdrom as something other than root? I do actually have a copy of my / on my cd, so, I don't see why it's failing to mount root. The only thing I can see is if I create the mfsroot.gz and get it compressed with kernel.gz like it is in the 2.88M boot.flp image. I just wish I knew what files to put in the root image, and how to get it to merge with kernel.gz. Thanks... Sincerely, Rick Duvall On Wed, 2 May 2001, Sven Huster wrote: > *This message was transferred with a trial version of CommuniGate(tm) Pro* > Hi > > i think it tries to mount root before it reads fstab, which is > on root. > > the problem i see, is that boot from cdrom simulates a floppy. > so the system will try to use the simulated floppy for the root device. > > i think you will need at least a minmal root fs on this bootable image, > you use to create the cdrom. > > regards > Sven > > At 12:03 01.05.01 -0700, you wrote: > >*This message was transferred with a trial version of CommuniGate(tm) Pro* > >So, let me get this straight: To make a bootable CD, you need to: > > > >1. compile a kernel (generic will work) > >2. gzip the kernel to kernel.gz > >3. vnconfig -s labels -c vn0 boot.flp (from /cdrom/floppies/boot.flp) > >4. mount /dev/vn0a /mnt > >5. cp kernel.gz /mnt/kernel.gz > >6. cp /boot/boot0 /mnt/boot/boot0;cp /boot/loader.4th > >/mnt/boot/loader.4th > >7. umount /dev/vn0a;vnconfig -u vn0 > >8. mkdir /usr/cd;cp boot.flp /usr/cd > >9. cp -R /bin /usr/cd;cp -R /etc /usr/cd;cp -R /sbin /usr/cd > >10. pico -w /usr/cd/etc/fstab to mount acd0 as root. > >11. mkisofs -o burnthis.iso -b boot.flp cd > >12. Burn the ISO to a CD. > >13. boot the CD. > > > >Okay, got that far. But, it will load the kernel, then hang and say that > >it cannot mount root device /dev/fd0. This doesn't make any sense to me > >becuase I specifically told fstab on the cd to use the cdrom as root. Am > >I stupid or something? > > > >Thanks. > > > >Sincerely, > > > >Rick Duvall > > > > > >To Unsubscribe: send mail to [EMAIL PROTECTED] > >with "unsubscribe freebsd-questions" in the body of the message > > > To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Re: Fetching an index of an FTP site using fetch...
Sean Chittenden <[EMAIL PROTECTED]> writes: > Does anyone have any ideas as far as a way in which it'd be > possible to fetch a directory index using fetch? No. It's not intended for that purpose, though it would be a nice addition. > PS I've looked through the source of fetch and libfetch, and > it seems like there's some stub code that hasn't been flushed out > completely. Anyone know of any plans to finish this up? Feel free to send patches :) DES -- Dag-Erling Smorgrav - [EMAIL PROTECTED] To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Bootable CD IV
So, let me get this straight: To make a bootable CD, you need to: 1. compile a kernel (generic will work) 2. gzip the kernel to kernel.gz 3. vnconfig -s labels -c vn0 boot.flp (from /cdrom/floppies/boot.flp) 4. mount /dev/vn0a /mnt 5. cp kernel.gz /mnt/kernel.gz 6. cp /boot/boot0 /mnt/boot/boot0;cp /boot/loader.4th /mnt/boot/loader.4th 7. umount /dev/vn0a;vnconfig -u vn0 8. mkdir /usr/cd;cp boot.flp /usr/cd 9. cp -R /bin /usr/cd;cp -R /etc /usr/cd;cp -R /sbin /usr/cd 10. pico -w /usr/cd/etc/fstab to mount acd0 as root. 11. mkisofs -o burnthis.iso -b boot.flp cd 12. Burn the ISO to a CD. 13. boot the CD. Okay, got that far. But, it will load the kernel, then hang and say that it cannot mount root device /dev/fd0. This doesn't make any sense to me becuase I specifically told fstab on the cd to use the cdrom as root. Am I stupid or something? Thanks. Sincerely, Rick Duvall To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Re: cdr and cdrw with 4.3 release
Terry Lambert writes: | Tom wrote: | > | > Does anyone know if it is possible to use a cdr/cdrw | > with 4.3 release? I want to use it with my sony vaio | > f580 (notebook). I have the option of usb or pcmcia. | > Can you tell me which models are known to work? Thanks | > for your help. Please mail all responses to | > [EMAIL PROTECTED] Thanks again.. Tom | | I use the internal CDRW with my Vaio PCG-XG29. I believe | that it is the same model which is used in the F580 and | similar F-series notebooks. | | I don't use an external CDRW off a USB or PCMCIA dongle. | | A person I used to work with has a PCG-XG28; they use a | PCMCIA based CDRW with success, but the card has to be | there, and the drive on, at boot time. That is strange. I definitely don't see such problems. I do such thing several times. I try to avoid booting my laptop and just suspend and resume it. So I have several cards come and go over one boot cycle. Any generic PCMCIA IDE based thing should work. I might stop using an external CDRW things once combo DVD & CDRW become more available/cheaper. Also internal bits are harder to share. Doug A. To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Re: Set up loader to boot cd
maillist> What about creating a mfsroot.gz as part of that boot floppy maillist> image, and mounting that as root, then mounting the cd as maillist> /usr on top of that? Simply 'mount -t cd9660 /dev/cd0a /usr' (or whatever CD device) after booting a kernel is not enough for you? I've not tried yet, but there is no reason to fail (if it fails, it means that you cannot install FreeBSD from your CD drive.) maillist> I don't quite understand how loader works, though Obviously, mounting a filesystem is not a loader(8)'s job :-) -- - Makoto `MAR' MATSUSHITA To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Re: vm balance
:I think we need to remember that we do not always have a :backing object, nor is a backing object always desirable. : :The performance of an mmap'ed file, or swap-backed anonymous :region is _significantly_ below that of unbacked objects. : :-- Terry This is not true, Terry. There is no performance degredation with swap verses unbacked storage, and no performance degredation with file-backed storage if you use MAP_NOSYNC to adjust the write flushing characteristics of the map. Additionally, there is no 'write through' in the VM layer per-say -- the filesystem syncer has to come along and actually look for dirty pages to sync to the backing store (and with MAP_NOSYNC it doesn't bother). The VM layers do not touch the backing store at all until they absolutely have to. For example, swap is not allocated until the pagedaemon actually decides to page something out. This leaves only the pageout daemon which operates as it always has... if you are not squeezed for memory, it won't try to page anything out. And you can always use madvise(), msync(), and mlock() on top of everything else to adjust the VM characteristics of a section of memory (though personally speaking I don't think mlock() is necessary with 4.x's VM system unless you need realtime). In short, mmap()'s backing store is not an issue in 4.x. Read the manual page for mmap for more information, I fleshed it out a long time ago to explain all of this. -Matt To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Re: Set up loader to boot cd
What about creating a mfsroot.gz as part of that boot floppy image, and mounting that as root, then mounting the cd as /usr on top of that? Let me know if you think that will work I don't quite understand how loader works, though Handbook doesn't tell me enough. Thanks. Sincerely, Rick Duvall On Wed, 2 May 2001, Makoto MATSUSHITA wrote: > > maillist> 4.2-20010119-STABLE > > My sample ISO image (using latest 4-stable) works very fine, booting > from CD and mount CD as root partition. It works pretty well. > > If you have enough bandwidth to fetch 160MB ISO image file, try: > >ftp://current.jp.FreeBSD.org/pub/FreeBSD/snapshots/i386/ISO-IMAGES/live-releng4.iso> > > Also, I've tried to do with 5-current, kernel *can't* mount CD as a > root partition. If you wanna try how it goes to fail, try: > >ftp://current.jp.FreeBSD.org/pub/FreeBSD/snapshots/i386/ISO-IMAGES/live-current.iso> > > I've sent a email before to [EMAIL PROTECTED], does anybody know why > 5-current kernel can't mount my CD-ROM as a root partition? > > -- - > Makoto `MAR' MATSUSHITA > > To Unsubscribe: send mail to [EMAIL PROTECTED] > with "unsubscribe freebsd-hackers" in the body of the message > To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Re: Set up loader to boot cd
maillist> 4.2-20010119-STABLE My sample ISO image (using latest 4-stable) works very fine, booting from CD and mount CD as root partition. It works pretty well. If you have enough bandwidth to fetch 160MB ISO image file, try: ftp://current.jp.FreeBSD.org/pub/FreeBSD/snapshots/i386/ISO-IMAGES/live-releng4.iso> Also, I've tried to do with 5-current, kernel *can't* mount CD as a root partition. If you wanna try how it goes to fail, try: ftp://current.jp.FreeBSD.org/pub/FreeBSD/snapshots/i386/ISO-IMAGES/live-current.iso> I've sent a email before to [EMAIL PROTECTED], does anybody know why 5-current kernel can't mount my CD-ROM as a root partition? -- - Makoto `MAR' MATSUSHITA To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Re: Set up loader to boot cd
4.2-20010119-STABLE On Tue, 1 May 2001, Makoto MATSUSHITA wrote: > > maillist> So, do I need to vnconfig the boot.flp and put my own custom > maillist> loader in it or what? I don't want to be puting -C in every > maillist> time I boot. Also, when I put in -C, the kernel will load, > maillist> but then can't find the CD device > > Which FreeBSD version you are using, 5-current or [43]-stable ? > > -- - > Makoto `MAR' MATSUSHITA > > To Unsubscribe: send mail to [EMAIL PROTECTED] > with "unsubscribe freebsd-hackers" in the body of the message > To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Re: Set up loader to boot cd
maillist> So, do I need to vnconfig the boot.flp and put my own custom maillist> loader in it or what? I don't want to be puting -C in every maillist> time I boot. Also, when I put in -C, the kernel will load, maillist> but then can't find the CD device Which FreeBSD version you are using, 5-current or [43]-stable ? -- - Makoto `MAR' MATSUSHITA To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Fetching an index of an FTP site using fetch...
Does anyone have any ideas as far as a way in which it'd be
possible to fetch a directory index using fetch? If I try to toss it
into mirror mode (-m|-M), it returns the following error:
fetch: fetch.out: Syntax error, command unrecognized
Anyone have any ideas? The full command that I was trying is:
fetch -p -m ftp://ftp.freebsd.org/pub/FreeBSD/CERT/advisories/
fetch -m ftp://ftp.freebsd.org/pub/FreeBSD/CERT/advisories/
fetch ftp://ftp.freebsd.org/pub/FreeBSD/CERT/advisories/
No dice on any of them. It seems like it should be possible
to get an INDEX file of sorts out of fetch, but aparently not.
::sigh:: -sc
PS I've looked through the source of fetch and libfetch, and
it seems like there's some stub code that hasn't been flushed out
completely. Anyone know of any plans to finish this up?
/*
* List a directory
*/
extern void warnx(char *, ...);
struct url_ent *
fetchListFTP(struct url *url, char *flags)
{
warnx("fetchListFTP(): not implemented");
return NULL;
}
--
Sean Chittenden
PGP signature
Re: Proposed struct file (was Re: vm balance)
Matt Dillon wrote: > > This is all preliminary. The question is whether we can > cover enough bases for this to be viable. > > Here is a proposed struct file. Make f_data opaque (or > more opaque), add f_object, extend fileops (see next > structure), Added f_vopflags to indicate the presence > of a vnode in f_data, allowing extended filesystem ops > (e.g. rename, remove, fchown, etc etc etc). 1) struct fileops is evil; adding to it contributes to its inherent evil-ness. 2) The new structure is too large. 3) The old structure is too large; I have a need for 1,000,000 open files for a particular application, and I'm not willing to give up that much memory. -- Terry To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Re: Problem with device rl
-BEGIN PGP SIGNED MESSAGE-
On Mon, 30 Apr 2001, Matthew Emmerton wrote:
Thank you,this patch is working
> *** if_rl.c.orig Sun Mar 25 19:08:34 2001
> --- if_rl.c Sun Mar 25 23:14:00 2001
> ***
> *** 149,154
> --- 149,156
> "Delta Electronics 8139 10/100BaseTX" },
> { ADDTRON_VENDORID, ADDTRON_DEVICEID_8139,
> "Addtron Technolgy 8139 10/100BaseTX" },
> + { DLINK_VENDORID, DLINK_DEVICEID_530TXPLUS,
> + "D-Link DFE-530TX+ 10/100BaseTX" },
> { 0, 0, NULL }
> };
> ***
> *** 898,904
> rl_read_eeprom(sc, (caddr_t)&rl_did, RL_EE_PCI_DID, 1, 0);
>
> if (rl_did == RT_DEVICEID_8139 || rl_did == ACCTON_DEVICEID_5030 ||
> ! rl_did == DELTA_DEVICEID_8139 || rl_did == ADDTRON_DEVICEID_8139)
> sc->rl_type = RL_8139;
> else if (rl_did == RT_DEVICEID_8129)
> sc->rl_type = RL_8129;
> --- 903,910
> rl_read_eeprom(sc, (caddr_t)&rl_did, RL_EE_PCI_DID, 1, 0);
>
> if (rl_did == RT_DEVICEID_8139 || rl_did == ACCTON_DEVICEID_5030 ||
> ! rl_did == DELTA_DEVICEID_8139 || rl_did == ADDTRON_DEVICEID_8139 ||
> ! rl_did == DLINK_DEVICEID_530TXPLUS)
> sc->rl_type = RL_8139;
> else if (rl_did == RT_DEVICEID_8129)
> sc->rl_type = RL_8129;
>
> *** if_rlreg.h.orig Sun Mar 25 19:08:34 2001
> --- if_rlreg.h Sun Mar 25 19:10:12 2001
> ***
> *** 433,438
> --- 433,448
> #define ADDTRON_DEVICEID_8139 0x1360
>
> /*
> + * D-Link vendor ID.
> + */
> + #define DLINK_VENDORID 0x1186
> +
> + /*
> + * D-Link DFE-530TX+ device ID
> + */
> + #define DLINK_DEVICEID_530TXPLUS 0x1300
> +
> + /*
>* PCI low memory base and low I/O base register, and
>* other PCI registers.
>*/
>
>
>
>
Vojislav Milunovic
[EMAIL PROTECTED]
-BEGIN PGP SIGNATURE-
Version: PGPfreeware 5.0i for non-commercial use
Charset: noconv
iQEVAwUBOu6A1i3gPLld8IkLAQH6Vgf9GKRPN5J2Wt6ty/I/dLyTmYkrUDU+TlLK
eS+o+dpvaDGKAGRDx+5yuxYfoxb40ZFar/mu29JSfCZ4SzLm8NJGWMi6Fshkt7Hn
ECdtZfZHOxVey51jobD1h+ipr33taj+8Wz8RMLMigE8wID3eQ/bY4TveXxYkal/B
aMOhHXy0SWIGLHp0AzyWomxByW0m8ye8BwiEktOx2Z7pAlBAl9FVd8TfgHzs+hJd
LVc2Goi4VCZ7vhhCpB097ier46tgcAH9eGavR4BPfT/RYOrmgOwsROW4B8bn7NI/
2CpHNGn7tY7gt1/kUSk+SYFr5Ot49Z1Ua7TrLV4o3hVXGNuPE+bcsQ==
=TdYO
-END PGP SIGNATURE-
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-hackers" in the body of the message
Re: arp_rtrequest error
Hi, Michael Jon Vigodda wrote on Mon, Apr 30, 2001 at 03:29:13PM -0400: > Hello. I saw your post on the FreeBSD-hackers mailing list and have the same >problem. I was wondering what fix you came up with for this as, months later, I am >scouring the mail lists to see if there is a fix and also cannot find one. > > I, too, have many aliases with the 0xfff netmask and am running routed. > > Any help or insights you can offer are greatly appreciated. Since I'm not familiar with the routing code, I switched over to gated, which did not cause these problems. Just a workaround, no real solution, but at least something. Best regards, Daniel -- IRCnet: Mr-Spock - signs of absurd developments in the net community: #42: - "Wurstbrot gehoert m.E. zum Fruehstuecks-botnet von Cartoon" - *Daniel Lang * [EMAIL PROTECTED] * +49 89 289 25735 * http://www.leo.org/~dl/* To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Re: x86-64 Hammer and IA64 Itainium
In message <[EMAIL PROTECTED]>, Terry Lambert writes: >"Michael C . Wu" wrote: >> I have been hearing about GaAs since the beginning of my college >> career. One chemistry professor put it rather well, "Gallium >> Arsenide based semiconductors are considered the future of >> semiconductors, and always will be the future of semiconductors." > >Hitachi has a GaAs SPARC chip; it is used in Satellites. > >The CRAY-3 was GaAs based, if I'm not mistaken. And Convex made a GaAs based supercomputer, the 3800 I belive. -- Poul-Henning Kamp | UNIX since Zilog Zeus 3.20 [EMAIL PROTECTED] | TCP/IP since RFC 956 FreeBSD committer | BSD since 4.3-tahoe Never attribute to malice what can adequately be explained by incompetence. To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Re: x86-64 Hammer and IA64 Itainium
Jeremiah Gowdy wrote: > Now think about this. Microsoft Visual C++ will be *the* > industry compiler for Itainium. Their compiler is already > working and has ILP support. Plus Intel makes its own > compiler which plugs into Visual Studio. Both the Microsoft > and Intel compilers for ILP are going to kick the crap out > of gcc and I think we all know it. So then what, you're > going to have FreeBSD and Linux compiled with an inferior > compiler compared to Windows with their compilers ? The > first thing that will happen is Microsoft will pay for a > benchmark showing Windows beating the living crap out of > Linux and BSD. And this time they won't have to fake it. > Not having proper ILP support is like intentionally stalling > pipes constantly. The whole design of this new cpu is the > ILP. Without it, the GNU compiled programs aren't going to > have much to show for. FWIW, I have been hearing increasing rumors about Intel donating their compiler to the FSF in order to ensure that benchmarks compiled with GCC run best on Intel. We have seen similar motions from Compaq, in their making Alpha compiler technology available without charge. These people sell hardware, not compilers; compilers are marketing tools for hardware, and have been, ever since free tools became "good enough" for most uses... -- Terry To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Re: x86-64 Hammer and IA64 Itainium
"Michael C . Wu" wrote: > I have been hearing about GaAs since the beginning of my college > career. One chemistry professor put it rather well, "Gallium > Arsenide based semiconductors are considered the future of > semiconductors, and always will be the future of semiconductors." Hitachi has a GaAs SPARC chip; it is used in Satellites. The CRAY-3 was GaAs based, if I'm not mistaken. -- Terry To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Re: vm balance
Poul-Henning Kamp wrote: > > In message <[EMAIL PROTECTED]>, Kirk > McKusick writes: > > >Every vnode in the system has an associated object. > > No: device vnodes dont... > > I think the correct solution to that is to move devices away from > vnodes and into the fdesc layer, just like fifo's and sockets. This is really, likewise, a bad idea. The "struct fileops" has been a problem from day one. It exists for devices because we still have "specfs", and have not moved over to a "devfs" that uses vnodes instead of using strategy routines invoked from a "struct fileops *" dereference. The code was smeared into the FIFO/socket/IPC code as a poor man's integration to get something working. When that happened, the ability to do normal things like set ownership, permissions, etc., on things like FIFOs disappeared. FreeBSD is much poorer with regard to full compliance with POSIX semantics on things like F_ fcntl() arguments and the like when applied to sockets. Linux, Solaris, AIX, and other POSIX and Single UNIX Specification compliant OSs don't suffer these same problems. Perhaps one of the most annoying things about FreeBSD is the inability to perform advisory locking on anything by true vnode objects... and then only if the underlying VFS has an advisory lock chain hung off of some private structure, which can't be rescued except through the evils of POSIX locking semantics. Many applications use advisory lock chains off of devices to communicate region protection information not directly related to really protecting the resource. Similarly, "struct fileops" is the main culprit, to my mind, behind the inability of FreeBSD to support cloning devices, such as that needed for multiple virtual machine instances in vmware to work as it does in Linux and other first-class host OSs. -- Terry To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
RE: write() vs aio_write()
-Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]]On Behalf Of 'Alfred Perlstein' Sent: Tuesday, May 01, 2001 8:36 AM To: Charles Randall Cc: ªL^¶W; Freebsd-Hackers Subject: Re: write() vs aio_write() * Charles Randall <[EMAIL PROTECTED]> [010430 10:26] wrote: > Regarding aio_*, Alfred Perlstein writes: > >It's a good idea to use it for disk IO, probably not a good > >idea for network IO. > > Could you elaborate? Sure. Network IO can be done without blocking (unless you take a fault on the source address of your data). Hence the additional context switching required by aio is not needed. Disk IO probably stands a good chance of blocking your application, if you can offload that blocking to a kernel thread you should be able to continue serving content. By the way. I think synchonous I/O include blocking and non-blocking I/O and asynchonous I/O is non-blocking I/O, but it is signal-driven. Am I right -- -Alfred Perlstein - [[EMAIL PROTECTED]] Instead of asking why a piece of software is using "1970s technology," start asking why software is ignoring 30 years of accumulated wisdom. To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
Re: vm balance
[ ... merging vnode and vm_object_t ... ] Kirk McKusick wrote: > Every vnode in the system has an associated object. Every object > backed by a file (e.g., everything but anonymous objects) has an > associated vnode. So, the performance of one is pretty tied to the > performance of the other. Matt is right that the VM does locking > on a page level, but then has to get a lock on the associated > vnode to do a read or a write, so really is pretty tied to the > vnode lock performance. Merging the two data structures is not > likely to change the performance characteristics of the system for > either better or worse. But it will save a lot of headaches having > to do with lock ordering that we have to deal with at the moment. I really, really dislike the idea of a merge of these objects, still, and not just because it will be nearly impossible to macke object coherency work in a stack of two or more VFS layers if this change ever goes through. When John Dyson originally wrote the FreeBSD unified VM and buffer cache code under contract for Oracle for use in their Oracle 8i and FreeBSD based NC server platform, he did so in such a way to allow anonymous objects, which did not have backing store associated with them. This was the memory pulled off of /dev/zero, and the memory in SYSVSHM. The main benefit of doing this is that it saves an incredible amount of write-through, which would otherwise be necessary to maintain coherency with the backing object (vnode). I think we need to remember that we do not always have a backing object, nor is a backing object always desirable. The performance of an mmap'ed file, or swap-backed anonymous region is _significantly_ below that of unbacked objects. -- Terry To Unsubscribe: send mail to [EMAIL PROTECTED] with "unsubscribe freebsd-hackers" in the body of the message
