Chris Wedgwood wrote:
>
> You can measure this latency; and it's indeed very low (lmbench gives
> 28 usecs on one of my machines).
>
> If you don't see this I would suspect an application bug -- can you
> use strace or some such and confirm this is not the case?
OK, two new data points (thanks
Dan Maas wrote:
>
> > OK, if this is the case, how do I alter the scheduling class?
>
> man sched_setscheduler
>
> Set SCHED_FIFO or SCHED_RR; you'll need to be root to do this AFAIK.
>
> I do agree though, Linux's scheduler (for SCHED_OTHER processes) is much
> less "ruthless" than, say, the
2.4.1-pre9 changes to drivers/char/drm/drm.h are incorrect.
Please reverse this small change to compile correctly.
r128_drv.c:124: `DRM_IOCTL_R128_PACKET' undeclared here (not in a function)
r128_drv.c:124: nonconstant array index in initializer for `r128_ioctls'
make[3]: *** [r128_drv.o] Error
On Fri, 19 Jan 2001, Mark I Manning IV wrote:
>
> Two spaces are perfect, they delineate the blocks very nicely and dont
> eat up the comments real estate.
WHAT "comments real estate". You have tons of real estate - up and down.
Don't try to move it sideways where it won't fit anyway.
Write
Hello,
How do I compile a PPPoE client into the kernel? I have read a book about
compiling modules into the kernel but it doesn't give me a good idea about
it.
Thank you,
Simon Liu
_
Get Your Private, Free E-mail from
On Fri, Jan 19, 2001, Miles Lane <[EMAIL PROTECTED]> wrote:
> Johannes Erdfelt wrote:
>
> > TODO
> >
> > - The PCI DMA architecture is horribly inefficient on x86 and ia64. The
> > result is a page is allocated for each TD. This is evil. Perhaps a slab
> > cache internally? Or modify
In article <[EMAIL PROTECTED]>,
Albert D. Cahalan <[EMAIL PROTECTED]> wrote:
>> Tabs are 8 characters so NO tabs should be used in ANY source file what
>...
>> Rationale: Tabs force your code out to the right edge of the display
>> leaving no room for comments. You don't need great big gaping
Hi,
I did compile my new kernel 2.4 on a Red Hat 6.0 Linux
system. My Linux System was installed so that it can
boot from a floppy.
So on the boot floppy, I have LILO (On the hard drive,
there's also LILO).
For booting my new kernel (/boot/vmlinuz-2.4.0), I added
following stanza to
David Schwartz wrote:
>
> How can you tell when select wakes up the process? What you are seeing has
> nothing whatsoever to do with select and simply has to do with the fact that
> the kernel does not give the CPU to a process the second that process may
> want it.
I guess I can't. But
Hi guys ...
new to the list. need help ?
can anyone please guide to me to an how-to or documentation on how to make a
custom boot.img & initrd.img ?
thanks in advance..
parag mehta
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL
On Sat, 20 Jan 2001, Rik van Riel wrote:
> Is there ever a reason NOT to do the best possible IO
> clustering at write time ?
>
> Remember that disk writes do not cost memory and have
> no influence on the resident set ... completely unlike
> read clustering, which does need to be limited.
Announcing 802.1Q VLAN version 1.0.0 for Linux.
802.1Q VLAN is an industry standard that allows you to run multiple
Virtual LANs over a single ethernet wire/interface. It also supports
priority settings. To user-space code, this VLAN patch makes VLAN
devices look like Ethernet devices.
The
> Thanks CW and DS for the prompt replies. However, although each
> addressed the (flawed) example I included, neither addressed the
> problem described in the text.
>
> I wrote:
> > > If select() is waiting for data to become available on a
> > > TCP socket FD, and
> > > data becomes available,
Em Fri, Jan 19, 2001 at 09:53:06PM -0500, Billy Harvey escreveu:
> /usr/src/linux/drivers/sound
>
> cs46xx.c:4238: banner causes a section type conflict
probably one __initdata is a const char? get rid of the const keyword and
try again. No patch as I've not yet downloaded -ac10
- Arnaldo
-
To
On Fri, 19 Jan 2001, Marcelo Tosatti wrote:
> The write clustering issue has already been discussed (mainly at Miami)
> and the agreement, AFAIK, was to implement the write clustering at the
> per-address-space writepage() operation.
>
> IMO there are some problems if we implement the write
Jeff Hartmann wrote:
>
> >> There is also a known issue with U160 modes and the currently
> >> embedded aic7xxx driver.
> >
> >
> > That's true the problem is the TCQ command seems to be sequencing wrong.
> >
> >
> >> You might want to try the Adaptec
> >> supported driver from here:
> >>
> >>
/usr/src/linux/drivers/sound
cs46xx.c:4238: banner causes a section type conflict
Billy
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
Please read the FAQ at http://www.tux.org/lkml/
On Friday 19 January 2001 19:27, Jeff Garzik wrote:
> Steven Cole wrote:
> > I got the following errors building 2.4.0-ac10:
> > The first three digits are the line number in the build log.
>
> Always run 'make mrproper' before building.
>
> Alan's patch accidentally includes some files that are
Steven Cole wrote:
>
> I got the following errors building 2.4.0-ac10:
> The first three digits are the line number in the build log.
Always run 'make mrproper' before building.
Alan's patch accidentally includes some files that are generated by the
build system.
Jeff
--
Jeff
Thanks CW and DS for the prompt replies. However, although each
addressed the (flawed) example I included, neither addressed the
problem described in the text.
I wrote:
> > If select() is waiting for data to become available on a
> > TCP socket FD, and
> > data becomes available, it doesn't
Frank Davis wrote:
>
> Hello,
>I just applied 2.4.0-ac10 to 2.4.0(patch -p1 and include/iinux/autoconf.h and include/linux/modversion.h didn't apply cleanly. I
>received .rej files.
make mrproper, those files are generated by the build
--
Jeff Garzik | "You see, in this world
Hi,
I'm starting to implement a generic write clustering scheme and I would
like to receive comments and suggestions.
The write clustering issue has already been discussed (mainly at Miami)
and the agreement, AFAIK, was to implement the write clustering at the
per-address-space writepage()
I got the following errors building 2.4.0-ac10:
The first three digits are the line number in the build log.
855 make[3]: Entering directory `/usr/src/linux-2.4.0-ac10/drivers/acpi'
856 make[3]: warning: -jN forced in submake: disabling jobserver mode.
857 gcc -D__KERNEL__
Hello,
I just applied 2.4.0-ac10 to 2.4.0(patch -p1 http://www.tux.org/lkml/
After starting X I get a kernel opps always on the xfs process,
System is RedHat 7.0+patches+linus 2.4.0 compiled with 'kgcc' (egcs-2.91.66)
Linux limelight 2.4.0 #1 Sat Jan 6 23:05:38 EST 2001 i686 unknown
9:06pm up 4:34, 6 users, load average: 0.08, 0.16, 0.09
^was stable since compiled,
ftp://ftp.kernel.org/pub/linux/kernel/people/alan/2.4/
2.4.0-ac10
o Merge Linus 2.4.1-8
o Add s->s_maxbytes to reiserfs (me)
o Remove EHASHCOLLISION and make reiserfs thus(me)
compatible with existing glibc/apps
o Clean
David Ford wrote:
> > One other thing. Allot of people neglect to brace a statement if
> > it has a single line body. This is VERY bad, always brace your
> > statements
> >
> > if (x = 1)
> >if (y = 2)
> > if (z = 3)
> >for (i = 1; i < 10; i++)
> > if
> >
> Tabs are 8 characters so NO tabs should be used in ANY source file what
...
> Rationale: Tabs force your code out to the right edge of the display
> leaving no room for comments. You don't need great big gaping spaces to
> delineate the start and end of a block, TWO spaces do this just fine.
I'm sorry I can't be more descriptive than that, but there aren't any
errors ever displayed. What happened was after about a day of uptime, I
began seeing IO errors when trying to access files. I realized that the
IO errors occurred on any file I had created. I rebooted since the
computer
Really amazing...
1280x1024 scrolling with matroxfb was awfully slow...
With mga and agpgart it's as fast as consoles are
normally.
Next I'll try changing modes without changing to 1024x768
on loading modules and then acceleration.
Mirko Kloppstech
-
To unsubscribe from this list: send the
Mark I Manning IV wrote:
> Tabs are 8 characters so NO tabs should be used in ANY source file what
> so ever. There are some silly people that insist on hitting the tab key
> when they should really be hitting the SPACE key (and for your info Linus
> PI is EXACTLY 3... ish :)
If one is
> What version of the raidtools to I need for 2.2.18 software raid?
> Documentation/md.txt has a non-functional URL in it.
0.90
http://www.kernel.org/pub/linux/kernel/people/mingo/raid-patches/
http://www.kernel.org/pub/linux/daemons/raid/alpha/
--
| Work like you don't need the money.
As promised, here are some numbers for low thread counts from the
benchmark Andrew and Davide provided. I ran the benchmark for
1,2,4 and 8 threads. I ran the test 5 times for each thread count
and used 60 seconds as the measure time in each case.
2.4.0
-
1 1785408
snpe wrote:
> Hello,
>
> Is there ibcs2 or abi for kernel 2.4.x ?
>
> regards
> haris peco
> [EMAIL PROTECTED]
Been discussed - Check this out:
http://marc.theaimsgroup.com/?l=linux-kernel=97149702506290=2
--
=== Never ask a geek why, just nod your head and slowly back away.===
On Sat, 1 Jan 2000, Pavel Machek wrote:
>> --
>> Mike A. Harris - Linux advocate - Free Software advocate
>> This message is copyright 2001, all rights reserved.
>> Views expressed are my own, not necessarily
On Friday 19 January 2001 15:23, Mike Kravetz wrote:
> On Fri, Jan 19, 2001 at 02:03:06PM -0800, Davide Libenzi wrote:
>
>
> > > voidoneatwork(int thr)
> > > {
> > > int i;
> > > while (!start) /* don't disturb pthread_create() */
> > >
> If select() is waiting for data to become available on a
> TCP socket FD, and
> data becomes available, it doesn't return until the next clock tick.
If your application has scheduling requirements, you need to communicate
them to the scheduler.
> #include
> #include
>
Hi ppl.. This is my first posting here and it will probably generate
MORe flames than any previous posting but that isnt realy my intent,.
The attached doccument is My answer to teh linux Coding Style doc as
found in teh kernel sources bz2. It is done in parody of teh original
doc and is meant
Hello Paul,
(you CC'ed your original post to vger.rutgers.edu, I shamelessly corrected
this for this reply)
> I have (finally) merged your patch in with the ide-floppy driver and
> have it working with devfs here on my laptop for a PCMCIA Clik drive.
Have you merged my patch in literate or in
Hi folks,
In porting our file system to Linux, we discovered a discrepancy in the
old and new method of returning directory entries to programs. This
exists in 2.2.x and 2.4.x kernels (and maybe older ones too?)
fs/readdir.c:filldir(), used by most (?) programs, expects the
directory entry
Can this be confirmed?
Shawn Starr wrote:
> Just a while ago, my system just started acting funny. I couldn't use w,
> top, ps, and then some of my X applications started to freeze too.
> I couldn't even kill those hung processes because they'd hang too. So
> When i tried to restart
There have been a few reports on oopses in smbfs on 2.4 boxes with highmem
support enabled. This patch tries to fix that.
The patch replaces the smbfs dir cache code with something based on the
ncpfs code. Petr should recognize almost all of it. And the ntfs code has
contributed with new time
On Fri, Jan 19, 2001 at 02:03:06PM -0800, Davide Libenzi wrote:
> > voidoneatwork(int thr)
> > {
> > int i;
> > while (!start) /* don't disturb pthread_create() */
> > usleep(1);
> >
> > actthreads++;
> > while (!stop)
> > {
>
What version of the raidtools to I need for 2.2.18 software raid?
Documentation/md.txt has a non-functional URL in it.
Thanks.
-M
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
Please read the FAQ at
On Friday 19 January 2001 13:59, Mike Kravetz wrote:
> On Fri, Jan 19, 2001 at 12:49:21PM -0800, Mike Kravetz showed his lack
>
> of internet slang understanding and wrote:
> > It was my intention to post IIRC numbers for small thread counts today.
> > However, the benchmark (not the system)
In message <[EMAIL PROTECTED]> y
ou write:
> I got this in my logs:
>
> ip_conntrack: maximum limit of 16368 entries exceeded
It's OK, it just means that you have *alot* of connections going
through your box (or maybe you don't route both ways through your box,
which you need to do for
Hi!
> struct safe_kpointer {
> void *kaddr;
> unsigned long fingerprint[4];
> };
>
> the kernel can validate kaddr by 1) validating the pointer via the master
> fingerprint (every valid kernel pointer must point to a structure that
> starts with the
I have a similar problem with a Thinkpad 600e:
The machine has RedHat6.2, and the original kernel
(2.2.14-5) as well as every 2.4.0-test* kernel I've
tried (test5, test9, test10 and test12) have had
no trouble with the PCMCIA (actually Cardbus)
card I use (a 3Com 3C575, but I don't think it
has
Hi!
> > And no, I don't actually hink that sendfile() is all that hot. It was
> > _very_ easy to implement, and can be considered a 5-minute hack to give
> > a feature that fit very well in the MM architecture, and that the Apache
> > folks had already been using on other architectures.
>
> The
Hi!
> --
> Mike A. Harris - Linux advocate - Free Software advocate
> This message is copyright 2001, all rights reserved.
> Views expressed are my own, not necessarily shared by my employer.
>
On Fri, Jan 19, 2001 at 11:42:01AM -0500, John O'Donnell wrote:
> Vojtech Pavlik wrote:
> >
> > On Thu, Jan 18, 2001 at 11:42:25PM +, Howard Johnson wrote:
> > > On Thu, Jan 18, 2001 at 06:32:39PM -0500, John O'Donnell wrote:
> > > > Matthew Fredrickson wrote:
> > > >
> > > > I have the ASUS
On Fri, Jan 19, 2001 at 12:49:21PM -0800, Mike Kravetz showed his lack
of internet slang understanding and wrote:
>
> It was my intention to post IIRC numbers for small thread counts today.
> However, the benchmark (not the system) seems to hang on occasion. This
> occurs on both the unmodified
In article <[EMAIL PROTECTED]>,
<[EMAIL PROTECTED]> wrote:
>Hello!
>
>> It's about direct i/o from/to pages,
>
>Yes. Formally, there are no problems to send to tcp directly from io space.
Actually, as long as there is no "struct page" there _are_ problems.
This is why the NUMA stuff was brought
> Look: http-1.1, asynchronous one, the first request is sent, but not acked.
> Time to send the second one, but it is blocked by Nagle. If there is no
> third request, the pipe stalls. Seems, this situation will be usual,
> when http-1.1 will start to be used by clients, because of dependencies
On Fri, Jan 19, 2001 at 09:18:04PM +0300, [EMAIL PROTECTED] wrote:
> Hello!
>
> > The "uncork" won't push the last skb on the wire if there is not acknowledged
> > data in the write_queue and the payload of the last skb in the write_queue
> > isn't large MSS. This because the `uncork' will only
>> There is also a known issue with U160 modes and the currently
>> embedded aic7xxx driver.
>
>
> That's true the problem is the TCQ command seems to be sequencing wrong.
>
>
>> You might want to try the Adaptec
>> supported driver from here:
>>
>> http://people.FreeBSD.org/~gibbs/linux/
On Fri, Jan 19, 2001 at 08:52:53PM +0300, [EMAIL PROTECTED] wrote:
> Hello!
>
> > I thought setsockopt is meant to set an option in the socket,
>
> It is not.
The manpage disagrees with you:
getsockopt, setsockopt - get and set options on sockets
On Thu, Jan 18, 2001 at 05:34:35PM -0800, Mike Kravetz wrote:
> On Fri, Jan 19, 2001 at 02:30:41AM +0100, Andrea Arcangeli wrote:
> > On Thu, Jan 18, 2001 at 04:52:25PM -0800, Mike Kravetz wrote:
> > > was less than the number of processors. I'll give the tests a try
> > > with a smaller number
[1.] select() sleeps for 1 tick even if data available
[2.] Full description of the problem/report:
If select() is waiting for data to become available on a TCP socket FD,
and
data becomes available, it doesn't return until the next clock tick.
This
produces large
On Fri, 19 Jan 2001, Bob Frey wrote:
> On Thu, Jan 18, 2001 at 11:24:54PM +, Stephen Kitchener wrote:
> > The only thing that might be odd is that the scanner's scsi card and the
> > display card are using the same IRQ, but I thought that IRQ sharing was ok in
> > the new kernels. The
On Fri, Jan 19, 2001 at 03:12:11PM -0500, Mark Hahn wrote:
> > incurred in the current implementation. To maintain existing
> > scheduler behavior, we look at all CPU specific runqueues to find
> > the highest priority (goodness) task in the system. Therefore,
>
> do you have cpu-affinity?
Hello!
> It's about direct i/o from/to pages,
Yes. Formally, there are no problems to send to tcp directly from io space.
But could someone explain me one thing. Does bus-mastering
from io really work? And if it does, is it enough fast?
At least, looking at my book on pci, I do not understand
Hello!
> the business about the last 1100ish bytes of a 4096 byte send being
> delayed by nagle only implies that the stack's implementation of nagle
> was broken and interpreting it on a per-segment rather than a per-send
> basis.
+
> software, or the host TCP stack. otherwise, the persistent
On 19 Jan 01 at 18:18, [EMAIL PROTECTED] wrote:
> I have a Matrox G450 and Kernel 2.4.0.
> Vesafb works fine, however not matroxfb.
> First, matroxfb.o does not exist.
Why do you think that matroxfb.o should exist?
> Any other module in the matrox directory doesn't do anything.
> strace fbset
dean gaudet wrote:
>
> On Wed, 17 Jan 2001, Rick Jones wrote:
>
> > > actually the problem isn't nagle... nagle needs to be turned off for
> > > efficient servers anyhow.
> >
> > i'm not sure I follow that. could you expand on that a bit?
>
> the problem which caused us to disable nagle in
Hi,
This is not just a reiserfs/raid problem. Corruption has been reported on
the kernel mailing list with software raid 5 and ext2...
Ed
On Friday 19 January 2001 16:27, Edward wrote:
> Reiserfs in linux-2.4.1-pre8 does not properly with the RAID5 code that
> is in that kernel. It is easy
On Fri, Jan 19, 2001 at 01:03:05PM -0500, Hubertus Franke wrote:
>
> Mike sounds good, we will do all our measurements from now on with thread
> count for the entire range from 1 to 16 and
> then in power of twos upto 2048 and for maxcpus=1,2,4,6,8. Do you think
> that 4096 is overkill ? So far
Hello!
> The "uncork" won't push the last skb on the wire if there is not acknowledged
> data in the write_queue and the payload of the last skb in the write_queue
> isn't large MSS. This because the `uncork' will only re-evaluate the
> write_queue in function of the _nagle_ algorithm, quite
Many oopses appeared, among others gcc closed with signal 11.
One output:
Jan 19 18:45:12 john kernel: Unable to handle kernel paging request at virtual a
Jan 19 18:45:12 john kernel: printing eip:
Jan 19 18:45:12 john kernel: c0123b27
Jan 19 18:45:12 john kernel: *pde =
Jan 19
I have a Matrox G450 and Kernel 2.4.0.
Vesafb works fine, however not matroxfb.
First, matroxfb.o does not exist.
Any other module in the matrox directory doesn't do anything.
strace fbset -s returns -ENOSYS for /dev/fb0, which exists.
Loading matroxfb_base.o crashes the computer immediately.
Reiserfs in linux-2.4.1-pre8 does not properly with the RAID5 code that
is in that kernel. It is easy to get corrupted filesystem on device in
less than 1 minute. Please, do not use it (reiserfs) on RAID5 devices.
We are trying to figure out what is wrong.
Edward
-
To unsubscribe from this
"Justin T. Gibbs" wrote:
>
> >This is a temporary patch to keep the scsi driver from eating
> >your data I am working on a real fix
> >
> >Leslie Donaldson
>
> What is the firmware revision of your Seagate drives?
Not using seagate drives this is with quantum
see bottom
> There
Mike sounds good, we will do all our measurements from now on with thread
count for the entire range from 1 to 16 and
then in power of twos upto 2048 and for maxcpus=1,2,4,6,8. Do you think
that 4096 is overkill ? So far the numbers you got and we got over here are
the same. Andi suggested that
>This is a temporary patch to keep the scsi driver from eating
>your data I am working on a real fix
>
>Leslie Donaldson
What is the firmware revision of your Seagate drives? There
were several models shipped in the recent past with firware that
would cause the drive to drop off the bus
Torrey Hoffman ([EMAIL PROTECTED]) said:
> Here's an lspci -v dump. The machine is a set top box, pretty much a
> standard PC, but with hardware parts that are rarely seen in normal
> desktops. (The graphics card, ethernet card, and MPEG decoder chip
> all required non-standard Linux and X
Hello!
> I thought setsockopt is meant to set an option in the socket,
It is not.
setsockopt() is simply a bit more clever extension to ioctl(),
which is adapted (in bsd style though) to understand layering
and has an explicit length to data.
It is prefered for all the operations on sockets,
Bill Nottingham said:
>Torrey Hoffman ([EMAIL PROTECTED]) said:
>> Does anyone know of a driver for the Crystal 4299 sound chip?
>
>It's not something there's one particular sound driver for (it's just
>an ac97 codec chip, as you saw). Most likely you want to use something
>like the i810_audio
This is a temporary patch to keep the scsi driver from eating
your data I am working on a real fix
Leslie Donaldson
*** linux/drivers/scsi/aic7xxx.c.2.4.0-12 Sat Jan 6 21:55:47 2001
--- linux/drivers/scsi/aic7xxx.cSat Jan 6 22:08:12 2001
***
*** 7073,7078
Hi Linus,
On Sun, 14 Jan 2001, Linus Torvalds wrote:
> Well, as the new shm code doesn't return 1 any more, the whole
> locked page handling should just be deleted. ramfs always just
> re-marked the page dirty in its own "writepage()" function, so it
> was only shmfs that ever returned this
Linus Torvalds wrote:
> > I wrote a driver for a zoran-chipset frame-grabber card. The "natural"
> > way to save a video stream was exactly the way it came out of the
> > card. And the card was structured that you could put on an "mpeg
> > decoder" (or encoder) chip, and you could DMA the stream
On Fri, Jan 19, 2001 at 10:47:06AM -0500, Hubertus Franke wrote:
> What you can see from these numbers is that MQ does an awesome job up to
> 1024 threads. When measuring in the future, we will take from now on the
> general concern about low number of threads into account. Your points are
>
Hi Nick,
you can't run with <512K L2 for >2-way on Intel. The 256K L2 cache cumine
procs only support 2-way SMP. For 4-way and greater, you have to use Xeon
procs, and they come in three flavours - 512K, 1M, and 2M. The machine that
Mike is using has 1M parts (which are fairly common at the
Hello,
kernel is 2.4.1-pre8
missing check after kmalloc in drivers/video/sbus.c, possible memory leak
in case of sbusfb_init_fb() failure, unnesesary compare (memset to area
before).
best explanation is a patch, look:
--- drivers/video/sbusfb.c.orig Fri Jan 19 19:14:22 2001
+++
Vojtech Pavlik wrote:
>
> On Thu, Jan 18, 2001 at 11:42:25PM +, Howard Johnson wrote:
> > On Thu, Jan 18, 2001 at 06:32:39PM -0500, John O'Donnell wrote:
> > > Matthew Fredrickson wrote:
> > >
> > > I have the ASUS CUV4X.
> > > VIA vt82c686a (cf/cg) IDE UDMA66 controller on pci0:4.1
> > > I
I've been working on automatic assignment of unique class handles inside of
a system call. I came across the function qdisc_alloc_handle in
net/sch_api.c, and I tried to use that. it didn't work, and I'm sure I'm
missing something obvious. I don't think I clearly understand how handles
are
In the sched_yield benchmark case this is not a problem , because the
threads don't have any memory footprint, all cloned.
The chatroom, I agree with you. However, I assume that these big irons
(8-ways) will be pretty much loaded with at least 1MB cache. Maybe at this
point another cite with an
On Fri, Jan 19, 2001 at 09:39:13AM -0700, Ian S. Nelson wrote:
> is this a bug?
>
> We have a number of machines running 2.4.0 and /proc/meminfo says we're
> sharing no memory. top says that also, probably because it just reads
> /proc/meminfo, or at least I assume that's how it works.All
[Paul Mackerras and linux-ppp added to the cc list]
It seems that the MPPP reconstruction queue got corrupted:
ppp_mp_reconstruct() called kfree_skb(), and within kfree_skb() the call
to skb->destructor() crashed:
skb->destructor was 0x01010101.
>
>
> I reported this a few months ago
is this a bug?
We have a number of machines running 2.4.0 and /proc/meminfo says we're
sharing no memory. top says that also, probably because it just reads
/proc/meminfo, or at least I assume that's how it works.All the
individual procs show the memory they are sharing though.
thanks,
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Today, Michael Rothwell ([EMAIL PROTECTED]) wrote:
> Mo McKinlay wrote:
>
> > Nono, that's not what I mean - each of the filesystems fails if it
> > doesn't support what you're trying to do, that's given - but having a
> > different
On Friday 19 January 2001 07:59, Bill Hartner wrote:
> Just a couple of notes on the sched_test_yield benchmark.
> I posted it to the mailing list in Dec. I have a todo to get
> a home for it. There are some issues though. See below.
>
> (1) Beware of the changes in sys_sched_yield() for
You might want to rerun the tests with less cache heavy procs. The 2meg
xeons you are using could distort things from what the average linux user
would see (running with 256-512k cache).
Nick
On Fri, 19 Jan 2001, Hubertus Franke wrote:
>
> Sure, we are measuring that as well.
> We are
On Fre, 19 Jan 2001 you wrote:
> On Fri, 19 Jan 2001, RobertKaiser wrote:
>
> > On Thu Jan 18 16:30:30 2001 [EMAIL PROTECTED] wrote
> > > Has anyone had any luck getting a 2.4 kernel to run on Cobalt x86
> > > hardware? It doesn't even seem to start (I get nothing on the screen from
> > >t he
Sure, we are measuring that as well.
We are running all these benchmarks and configurations that I mentioned in
my previous message on
1-2-4-6- and 8 way configurations.
We have posted some preliminary results on older kernels on the website:
http://lse.sourceforge.net/scheduling/prelim.html
On Fri, Jan 19, 2001 at 08:05:41AM +0530, [EMAIL PROTECTED] wrote:
> Shouldn't we have an error / status field too ?
Might make sense.
Christoph
--
Of course it doesn't work. We've performed a software upgrade.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel"
Mo McKinlay wrote:
> Nono, that's not what I mean - each of the filesystems fails if it
> doesn't support what you're trying to do, that's given - but having a
> different delimeter registered by the filesystem (and hence the
> possibility of every single filesystem using a different delimeter)
another thing that would be interesting is what is the overhead on UP or
small (2-4 way) SMP machines
David Lang
On Thu, 18 Jan 2001, Mike Kravetz wrote:
> Date: Thu, 18 Jan 2001 16:52:25 -0800
> From: Mike Kravetz <[EMAIL PROTECTED]>
> To: Andrea Arcangeli <[EMAIL PROTECTED]>
> Cc: [EMAIL
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Today, Michael Rothwell ([EMAIL PROTECTED]) wrote:
> Oh, undoubtedly. But NTFS already disallows several characters in valid
> filenames. This also violates the "consistent abstract interface." But
> it's reality.
Nono, that's not what I
2.4.0 + aic7xxx (http://people.FreeBSD.org/~gibbs/linux/ patch)
+ 2GB RAM (CONFIG_HIGHMEM4G=y, CONFIG_HIGHMEM=y) crashed.
Before the crash, I observed zombie bdflush for some time.
This is the first crash fingerprint in kern.log:
Jan 17 15:25:25 jerolim kernel: kernel BUG at page_alloc.c:74!
Mo McKinlay wrote:
>
> -BEGIN PGP SIGNED MESSAGE-
> Hash: SHA1
>
> Today, Michael Rothwell ([EMAIL PROTECTED]) wrote:
>
> > The filesystem, when registering that it supports the "named streams"
> > namespace, could specify its preferred delimiter to the VFS as well.
> > Ext4
1 - 100 of 269 matches
Mail list logo