On Tue, Jan 09, 2001 at 09:12:04PM +0100, Jens Axboe wrote:
> I haven't heard anything beyond the raised QUEUE_NR_REQUEST, so I'd like to
> see what you have pending so we can merge :-). The tiotest seek increase was
> mainly due to the elevator having 3000 requests to juggle and thus being able
>
On Wed, Jan 10 2001, Andrea Arcangeli wrote:
> On Tue, Jan 09, 2001 at 09:12:04PM +0100, Jens Axboe wrote:
> > I haven't heard anything beyond the raised QUEUE_NR_REQUEST, so I'd like to
> > see what you have pending so we can merge :-). The tiotest seek increase was
> > mainly due to the elevator
Hi,
On Tue, Jan 09, 2001 at 05:16:40PM +0100, Ingo Molnar wrote:
> On Tue, 9 Jan 2001, Stephen C. Tweedie wrote:
>
> i'm talking about kiovecs not kiobufs (because those are equivalent to a
> fragmented packet - every packet fragment can be anywhere). Initializing a
> kiovec involves touching a
Date: Tue, 9 Jan 2001 15:17:25 +
From: "Stephen C. Tweedie" <[EMAIL PROTECTED]>
Jes has also got hard numbers for the performance advantages of
jumbograms on some of the networks he's been using, and you ain't
going to get udp jumbograms through a page-by-page API, ever.
Again
On Monday January 1, [EMAIL PROTECTED] wrote:
> On Thu, Dec 21, 2000 at 12:05:41PM +1100, Neil Brown wrote:
> > So, I have started putting some patches together and they can be
> > found at
> > http://www.cse.unsw.edu.au/~neilb/patches/knfsd-2.2/
>
> I included the interesting ones in my tr
> The Mesa package in Red Hat 7 won't do DRI with recent XFree86 CVS.
Yep. Its Mesa 3.3/DRI 1.0. XFree86 CVS is Mesa 3.4/DRI 2.0. That has several
advantages including mostly working on Matrox cards which 1.0 never did (for
me anyway) and handling things that Mesa 3.3 tried to allocate the odd g
Why not use the limits from instead?
-d
Chris Mason wrote:
> On Wednesday, January 10, 2001 02:32:09 AM +0100 Marc Lehmann <[EMAIL PROTECTED]> wrote:
>
> >>> EIP; c013f911<=
> > Trace; c013f706
> > Trace; c0136e01
>
> The buffer reiserfs is sending to filldir is big enough for
> the
- Begin Hush Signed Message from [EMAIL PROTECTED] -
hello.
i just compiled a 2.4.0 kernel from stable sources from ftp.us.kernel.org,
including reiserfs support from the reiserfs patch (www.namesys.com) .
anyway, i compiled the ramfs (resizeable ramdisk) feature as a module, loaded
the
linux-2.4.1-pre1/drivers/md/xor.c calls the macro XOR_TRY_TEMPLATES,
which is defined in include/asm-i386/xor.h to use HAVE_XMM, which is
defined in include/asm-i386/processor.h to reference mmu_cr4_features.
So, to support compilation of raid5 as a module, i386_ksyms.c needs
to export mm
Please name a time or event when you would cal a setfeaturers command
without having a IDENTIFY page filled?
On Tue, 9 Jan 2001, Arnaldo Carvalho de Melo wrote:
> Hi,
>
> Please consider applying.
>
> - Arnaldo
>
> --- linux-2.4.0-ac4/drivers/ide/ide-features.cMon Jan 8 20:3
On Wed, 10 Jan 2001, Alan Cox wrote:
> > The Mesa package in Red Hat 7 won't do DRI with recent XFree86 CVS.
>
> Yep. Its Mesa 3.3/DRI 1.0. XFree86 CVS is Mesa 3.4/DRI 2.0. That has several
> advantages including mostly working on Matrox cards which 1.0 never did (for
> me anyway) and handling
This is valid that Paul is maintaining that subdriver as GADI is doing a
StartUp in Video stuff.
Cheers,
On Tue, 9 Jan 2001, Paul Bristow wrote:
> Linus, Alan,
>
> Could you please apply this patch to the MAINTAINERS file so that the
> 2.4.x
> IDE-FLOPPY maintainer is correctly identified as
On Tue, 9 Jan 2001, Benjamin C.R. LaHaise wrote:
> Do the math again: for transmitting a single page in a kiobuf only 64
> bytes needs to be initialized. If map_array is moved to the end of
> the structure, that's all contiguous data and is a single cacheline.
but you are comparing apples to o
On Tue, 9 Jan 2001, Stephen C. Tweedie wrote:
> > we do have SLAB [which essentially caches structures, on a per-CPU basis]
> > which i did take into account, but still, initializing a 600+ byte kiovec
> > is probably more work than the rest of sending a packet! I mean i'd love
> > to eliminate
Tim Waugh wrote:
> I'm having problems with using xsane to acquire a preview from an HP
> ScanJet 5P connected to an AHA-2940. 2.3.42 is the last kernel that
> works right for me.
>
> The symptom is that the scanner starts to make scanning sounds, then
> stops, and xsane says 'Error during read:
On Tue, 9 Jan 2001, Jens Axboe wrote:
> > > ever seen, this is why i quoted it - the talk was about block-IO
> > > performance, and Stephen said that our block IO sucks. It used to suck,
> > > but in 2.4, with the right patch from Jens, it doesnt suck anymore. )
> >
> > Thats fine. Get me 128K-5
Alan Cox wrote:
>
> > it might not be important to others, but we do hold one particular
> > SPECweb99 world record: on 2-way, 2 GB RAM, testing a load with a full
>
> And its real world value is exactly the same as the mindcraft NT values. Don't
> forget that.
In other words, devastating.
jjs
Date:Tue, 9 Jan 2001 17:14:33 -0800 (PST)
From: Dave Zarzycki <[EMAIL PROTECTED]>
On Tue, 9 Jan 2001, Ingo Molnar wrote:
> then you'll love the zerocopy patch :-) Just use sendfile() or specify
> MSG_NOCOPY to sendmsg(), and you'll see effective memory-to-card
> DMA-and
On Tue, 9 Jan 2001, Chris Mason wrote:
>
>
> On Wednesday, January 10, 2001 02:32:09 AM +0100 Marc Lehmann <[EMAIL PROTECTED]> wrote:
>
> >>> EIP; c013f911<=
> > Trace; c013f706
> > Trace; c0136e01
>
> The buffer reiserfs is sending to filldir is big enough for
> the huge file nam
Date: Tue, 9 Jan 2001 16:27:49 +0100 (CET)
From: Trond Myklebust <[EMAIL PROTECTED]>
OK, but can you eventually generalize it to non-stream protocols
(i.e. UDP)?
Sure, this is what MSG_MORE is meant to accomodate. UDP could support
it just fine.
Later,
David S. Miller
[EMAIL PROTEC
Anyone tried using these beasts on a x86?
Anyway, what's happening: In BIOS my USB keyboard works really poorly -
it almost seems scancodes get dropped left and right. Ok, so I don't mind
too much, i'm sure BIOS has a very limited driver. After booting
Microsoft's offerring, it would work fin
On Wed, 10 Jan 2001, David Woodhouse wrote:
>
> How does this affect embedded systems with no swap space at all?
The no-swap behaviour shoul dactually be pretty much identical, simply
because both 2.2 and 2.4 will do the same thing: just skip dirty pages in
the page tables because they cannot
Hi,
On Tue, Jan 09, 2001 at 04:00:34PM +0100, Ingo Molnar wrote:
>
> On Tue, 9 Jan 2001, Stephen C. Tweedie wrote:
>
> we do have SLAB [which essentially caches structures, on a per-CPU basis]
> which i did take into account, but still, initializing a 600+ byte kiovec
> is probably more work th
Date: Tue, 09 Jan 2001 20:23:17 -0500
From: Jeff Garzik <[EMAIL PROTECTED]>
Is there any value to supporting fragments in a driver which
doesn't do hardware checksumming? IIRC Alexey had a patch to do
such for Tulip, but I don't see it in the above patchset.
I'm actually consider
On Wed, 10 Jan 2001, Andrea Arcangeli wrote:
> On Tue, Jan 09, 2001 at 01:31:35PM -0800, Linus Torvalds wrote:
> > don't have to worry about undocumented extensions etc.
>
> Infact I don't blame gcc maintainers for that, but the standard. Ok, minor
> issue.
Yeah, and nothing we can do about i
Hello,
I have some issues on Linux-2.4.0:
During boot the (slightly modified, see later) kernel says:
<4>Linux version 2.4.0-NANO (root@elf) (gcc version 2.95.2 19991024 (release)) #1 Mon
Jan 8
22:04:48 MET 2001
[...]
<4>PCI: PCI BIOS revision 2.10 entry at 0xfb280, last bus=1
<4>PCI: Using c
Hi Linus,
Linus Torvalds <[EMAIL PROTECTED]> writes:
> I'd really like an opinion on whether this is truly legal or not? After
> all, it does change the behaviour to mean "pages are locked only if they
> have been mapped into virtual memory". Which is not what it used to mean.
>
> Arguably the
Hi,
I don't know if it's possible to make fd a read-only device if the
inserted media is write-protected, but I had a strange problem:
I had inserted a write protected floppy and accessed it via autofs as
vfat in 2.2.18. It worked. Some time later it had expired (and I'm not
sure whether I ha
I've been getting problems all along the pre-2.4 series and 2.4 itself
when I use NFS to play mp3 files with xmms.
The message in the logs is:
tulip.c: outl_CSR6 too many attempts,csr5=0x60208100
After a few times the network stops working and it only recovers with the
following sequence of com
On Tue, Jan 09, 2001 at 01:26:44PM -0800, Linus Torvalds wrote:
>
>
> On Tue, 9 Jan 2001, Christoph Hellwig wrote:
> > >
> > > Look at sendfile(). You do NOT have a "bunch" of pages.
> > >
> > > Sendfile() is very much a page-at-a-time thing, and expects the actual IO
> > > layers to do it's o
On Tue, 9 Jan 2001, Ingo Molnar wrote:
> On Mon, 8 Jan 2001, Rik van Riel wrote:
>
> > Having proper kiobuf support would make it possible to, for example,
> > do zerocopy network->disk data transfers and lots of other things.
>
> i used to think that this is useful, but these days it isnt.
this
On Tue, 9 Jan 2001, Alan Cox wrote:
> > > We have already shown that the IO-plugging API sucks, I'm afraid.
> >
> > it might not be important to others, but we do hold one particular
> > SPECweb99 world record: on 2-way, 2 GB RAM, testing a load with a full
>
> And its real world value is exactl
"Christopher E. Brown" wrote:
>
> Think VLANing switch clusters. Say 4 switches connected by
> GigE on 4 floors or in 4 separate building. Now, across these
> switches 20 VLANS are running, with the switches enforcing VLAN
> partitioning. The client PCs know nothing about it, as each
> > We have already shown that the IO-plugging API sucks, I'm afraid.
>
> it might not be important to others, but we do hold one particular
> SPECweb99 world record: on 2-way, 2 GB RAM, testing a load with a full
And its real world value is exactly the same as the mindcraft NT values. Don't
for
Nothing interesting or new, just merges up with the latest 2.4.1-pre1
patch from Linus.
ftp.kernel.org:/pub/linux/kernel/people/davem/zerocopy-2.4.1p1-1.diff.gz
I haven't had any reports from anyone, which must mean that it is
working perfectly fine and adds no new bugs, testers are thus in
nir
Paul Flinders <[EMAIL PROTECTED]> writes:
> Has anyone got either 2.2.x or 2.4.0 booted on the above motherboard?
I've got an MSI 694D Pro AI mainboard (ie non-raid), and both 2.2.x
and 2.4.0 work flawlessly here. I did manage to build a 2.4.0 kernel
which didn't boot, but it got much further b
On Wed, 10 Jan 2001, Christoph Hellwig wrote:
>
> Simple. Because I stated before that I DON'T even want the networking
> to use kiobufs in lower layers. My whole argument is to pass a kiovec
> into the fileop instead of a page, because it makes sense for other
> drivers to use multiple pages
On Tue, 9 Jan 2001, Andrea Arcangeli wrote:
> BTW, I noticed what is left in blk-13B seems to be my work (Jens's
> fixes for merging when the I/O queue is full are just been integrated
> in test1x). [...]
it was Jens' [i think those were implemented by Jens entirely]
batch-freeing changes that
Date: Tue, 9 Jan 2001 18:56:33 -0800 (PST)
From: dean gaudet <[EMAIL PROTECTED]>
is NFS receive single copy today?
With the zerocopy patches, NFS client receive is "single cpu copy" if
that's what you mean.
Later,
David S. Miller
[EMAIL PROTECTED]
-
To unsubscribe from this list: send
> ever seen, this is why i quoted it - the talk was about block-IO
> performance, and Stephen said that our block IO sucks. It used to suck,
> but in 2.4, with the right patch from Jens, it doesnt suck anymore. )
Thats fine. Get me 128K-512K chunks nicely streaming into my raid controller
and I'l
On Wednesday, January 10, 2001 12:42:01 AM +0100 Marc Lehmann
<[EMAIL PROTECTED]> wrote:
> We are still investigating, but there seems to be a major security problem
> in at least some versions of reiserfs. Since reiserfs is shipped with
> newer versions of SuSE Linux and the problem is too eas
Hi
Marc Lehmann wrote:
> We are still investigating, but there seems to be a major security problem
> in at least some versions of reiserfs. Since reiserfs is shipped with
> newer versions of SuSE Linux and the problem is too easy to reproduce and
> VERY dangerous I think alerting people to this
On Wed, Jan 10, 2001 at 12:42:01AM +0100, Marc Lehmann wrote:
>
> Basically, you do:
>
> mkdir "$(perl -e 'print "x" x 768')"
[jaqque@osiris:/tmp/chk]% uname -a
Linux osiris 2.2.18 [classified] Sat Jan 6 11:19:04 PST 2001 i586 unknown
[jaqque@osiris:/tmp/chk]% mkdir "$(perl -e 'prin
No oops maybe, BUT if you setup an evil script to make so many that the various kernel
structures got too full (or it filled the whole partition/disk up) then
And at 650Mhz my computer could do that quite easily...
DL
-
To unsubscribe from this list: send the line "unsubscribe linux-kerne
On Tue, 9 Jan 2001, Ingo Molnar wrote:
>
> On Tue, 9 Jan 2001, Stephen C. Tweedie wrote:
>
> > > please study the networking portions of the zerocopy patch and you'll see
> > > why this is not desirable. An alloc_kiovec()/free_kiovec() is exactly the
> > > thing we cannot afford in a sendfile()
I haven't tracked the IP storage group too closely, but was at the San Diego IETF
where there were some interesting debates about this issue.
There is a write-up at http://ips.pdl.cs.cmu.edu/mail/msg02598.html
Now I'm not sure if I agree with some of the assumptions. And I share your concern
a
Date:Tue, 9 Jan 2001 11:14:05 -0800 (PST)
From: Dan Hollis <[EMAIL PROTECTED]>
Just extend sendfile to allow any fd to any fd. sendfile already
does file->socket and file->file. It only needs to be extended to
do socket->file.
This is not what senfile() does, it sends (to
Date: Tue, 9 Jan 2001 19:18:53 -0800 (PST)
From: dean gaudet <[EMAIL PROTECTED]>
- NIC DMAs packet to memory
- CPU reads headers from memory, figures out it's NFS
- CPU copies data bytes from packet image in memory to pagecache
Yes, this is precisely what happens in the NFS client
We are still investigating, but there seems to be a major security problem
in at least some versions of reiserfs. Since reiserfs is shipped with
newer versions of SuSE Linux and the problem is too easy to reproduce and
VERY dangerous I think alerting people to this problem is in order.
We have te
On Tue, 9 Jan 2001, David S. Miller wrote:
>Just extend sendfile to allow any fd to any fd. sendfile already
>does file->socket and file->file. It only needs to be extended to
>do socket->file.
> This is not what senfile() does, it sends (to a network socket) a
> file (from the page ca
I can't reproduce this.
[root@vaio /root]# mkdir "$(perl -e 'print "x" x 768')"
[root@vaio /root]# ls
On Tue, 9 Jan 2001, Dan Hollis wrote:
> > This is not what senfile() does, it sends (to a network socket) a
> > file (from the page cache), nothing more.
>
> Ok in any case, it would be nice to have a generic sendfile() which works
> on any fd's - socket or otherwise.
it's a bad name in that ca
On Tue, 9 Jan 2001, David S. Miller wrote:
>Date: Tue, 9 Jan 2001 18:56:33 -0800 (PST)
>From: dean gaudet <[EMAIL PROTECTED]>
>
>is NFS receive single copy today?
>
> With the zerocopy patches, NFS client receive is "single cpu copy" if
> that's what you mean.
yeah sorry, i meant:
-
On Tue, Jan 09, 2001 at 12:05:59PM +0100, Ingo Molnar wrote:
>
> On Tue, 9 Jan 2001, Christoph Hellwig wrote:
>
> > > 2.4. In any case, the zerocopy code is 'kiovec in spirit' (uses
> > > vectors of struct page *, offset, size entities),
>
> > Yep. That is why I was so worried aboit the writepa
On Tue, Jan 09, 2001 at 03:53:02PM -0500, Douglas Gilbert wrote:
> by timeouts ** resulting in scsi bus resets. Anyway the problem
> seems to disappear with the recently released SANE 1.0.4 .
> [The original report was based on SANE 1.0.3 and earlier.]
In fact my report that the problem went awa
> fixed length headers). i've never investigated the actual protocols
> though so maybe the solution used was to just push a lot of the detail
> down into the controllers.
The stuff I have access to (MPT fusion) pushes the FC handling down onto the
board. Basically you talk scsi and IP to it (Se
On Tue, 9 Jan 2001, Christoph Hellwig wrote:
> I didn't want to suggest that - I'm to clueless concerning networking
> to even consider an internal design for network zero-copy IO. I'm just
> talking about the VFS interface to the rest of the kernel.
(well, i think you just cannot be clueless a
On Tue, 9 Jan 2001, David S. Miller wrote:
> Ignore Ingo's comments about the MSG_NOCOPY flag, I've not included
> those parts in the zerocopy patches as they are very controversial
> and require some VM layer support.
Okay, I talked to some kernel engineers where I work and they were (I
think)
Silviu Marin-Caea wrote:
> I have RedHat7, glibc-2.2-9, gcc-2.96-69.
>
> I can build 2.4.0 while running kernel 2.2.16.
>
> If I try to rebuild 2.4.0 while running the new kernel, I get random
> compiler errors.
Could you supply the text of the errors, and your .config?
I've been building 2.4.0
I faced the same problem when I patched 2.4.0test7 with reiserFS
support. On my further correspondence with Alan Cox, he wrote that he is
unwilling to listen about any "bug report for 2.4kernel", arising after
patching kernel with some foreign code...
Any comments?
Archan Paul
[EMAIL PROTECTED]
Archan Paul rearranged electrons thusly:
> I faced the same problem when I patched 2.4.0test7 with reiserFS
> support. On my further correspondence with Alan Cox, he wrote that he is
> unwilling to listen about any "bug report for 2.4kernel", arising after
> patching kernel with some foreign code
On Tue, Jan 09, 2001 at 07:38:28PM +0100, Ingo Molnar wrote:
>
> On Tue, 9 Jan 2001, Jens Axboe wrote:
>
> > > > ever seen, this is why i quoted it - the talk was about block-IO
> > > > performance, and Stephen said that our block IO sucks. It used to suck,
> > > > but in 2.4, with the right pat
On Tue, 9 Jan 2001, Stephen Frost wrote:
> Now, the interesting bit here is that the processes can grow to be
> pretty large (200M+, up as high as 500M, higher if we let it ;) ) and what
> happens with MOSIX is that entire processes get sent over the wire to
> other machines for work. MOS
"David S. Miller" wrote:
>
> Nothing interesting or new, just merges up with the latest 2.4.1-pre1
> patch from Linus.
>
> ftp.kernel.org:/pub/linux/kernel/people/davem/zerocopy-2.4.1p1-1.diff.gz
>
> I haven't had any reports from anyone, which must mean that it is
> working perfectly fine and
On Tue, Jan 09 2001, Andrea Arcangeli wrote:
> > > > Thats fine. Get me 128K-512K chunks nicely streaming into my raid controller
> > > > and I'll be a happy man
> > >
> > > No problem, apply blk-13B and you'll get 512K chunks for SCSI and RAID.
> >
> > i cannot agree more - Jens' patch did wonde
On Wed, Jan 10, 2001 at 12:34:35AM +0100, Jens Axboe wrote:
> Ah I see. It would be nice to base the QUEUE_NR_REQUEST on something else
> than a static number. For example, 3000 per queue translates into 281Kb
> of request slots per queue. On a typical system with a floppy, hard drive,
> and CD-RO
On Sun, 7 Jan 2001, Alan Cox wrote:
> > Um, what about people running their box as just a VLAN router/firewall?
> > That seems to be one of the principle uses so far. Actually, in that case
> > both VLAN and IP traffic would come through, so it would be a tie if VLAN
> > came first, but non-vlan
301 - 367 of 367 matches
Mail list logo
