Alexander Viro wrote:
We _have_ VM pressure there. However, such loads had never been used, so
there's no wonder that system gets unbalanced under them.
I suspect that simple replacement of goto next; with continue; in the
fs/dcache.c::prune_dcache() may make situation seriously better.
gcc -D__KERNEL__ -I/usr/local/src/linux/include -Wall -Wstrict-prototypes -O
2 -fomit-frame-pointer -fno-strict-aliasing -pipe -mpreferred-stack-boundary
=2 -march=i686 -DMODULE -DMODVERSIONS -include
/usr/local/src/linux/include/linux/modversions.h -c -o nbd.o nbd.c
nbd.c: In function
Hi,
Any pointers ? Patches to apply ?
Don't you people hate to followup yourself ..
Anyway it's updated RH70 on 2.4.3 kernel !
You didn't mention what type of 6500 it is? PPro? PII? PIII? How man
processors installed?
COMPAQ Proliant 6500 (P11), two PIII -
processor :
Hi,
I know I'm late, but Configure.help in 2.2.19 says:
..."The TCO (Total Cost of Ownership) timer is a watchdog"...
I know TCO meaning that, but I can't believe it for a mainboard
component. Should the user then throw the PC away, or what? Or is it
more safe to reboot frequently. What has
Al writes:
We _have_ VM pressure there. However, such loads had never been used, so
there's no wonder that system gets unbalanced under them.
I suspect that simple replacement of goto next; with continue; in the
fs/dcache.c::prune_dcache() may make situation seriously better.
Yes, it
Some uniprocessor configurations require the following patch in order to
build 2.4.4-pre2 at all...
--
Jeff Garzik | Sam: "Mind if I drive?"
Building 1024 | Max: "Not if you don't mind me clawing at the dash
MandrakeSoft | and shrieking like a cheerleader."
Index:
* All three interfaces do progressive disclosure -- the user only sees
questions he/she needs to answer (no more hundreds of greyed-out menu
entries for irrelevant drivers!).
Well, that sucks. The greyed-out menu entries were the only good
thing about xconfig. Such entries provide a clue
On Thu, 12 Apr 2001, Jeff Garzik wrote:
Alexander Viro wrote:
We _have_ VM pressure there. However, such loads had never been used, so
there's no wonder that system gets unbalanced under them.
I suspect that simple replacement of goto next; with continue; in the
Below are the errors generated from "make" for 2.4.4-pre2
I've no problem compiling 2.4.4-pre1.
___
gcc -D__KERNEL__ -I/u2/src/linux/include -Wall -Wstrict-prototypes -O2
-fomit-frame-pointer -fno-strict-aliasing -pipe
On Thu, 12 Apr 2001, Andreas Dilger wrote:
Al writes:
We _have_ VM pressure there. However, such loads had never been used, so
there's no wonder that system gets unbalanced under them.
I suspect that simple replacement of goto next; with continue; in the
fs/dcache.c::prune_dcache()
Here you are my today doubt:
setting up a traffic shaper with a linux box is very easy and after this
you have in your hands a powerful toy. Of course, due the great flexibility of
linux networking system there are many ways to achieve your goal.
In particular, which is the boost you gain if
Alexander Viro writes:
If nobody objects I'll go for test_bit/set_bit/clear_bit here.
Be sure to make d_flags an unsigned long when you do this! :-)
Later,
David S. Miller
[EMAIL PROTECTED]
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to
On Thu, 12 Apr 2001, David S. Miller wrote:
Alexander Viro writes:
If nobody objects I'll go for test_bit/set_bit/clear_bit here.
Be sure to make d_flags an unsigned long when you do this! :-)
Oh, fsck... Thanks for reminder - I've completely forgotten about
that.
Linus Torvalds wrote:
On Wed, 11 Apr 2001, Bernd Schmidt wrote:
See? Do you see why a "memory" clobber is _not_ comparable to a "ax"
clobber? And why that non-comparability makes a memory clobber equivalent
to a read-modify-write cycle?
I had to think about this, so I'll explain it a
John Alvord wrote:
I bumped into a funny non-optimization a few years ago. A system with
a timer queue like the above had been "optimized" by keeping old timer
elements... ready for new tasks to link onto and activate. The
granularity was 1 millsecond. Over time, all timer values from 0 to
Still experimenting with my SDT-9000... tried connecting it to another
controller
(2940AU in place of 2904, sorry but I've only Adaptec stuff :). Same
problem.
Tried with another tape (even with an old DDS-2 tape). Same. Even tried
another
cable/removing the CDWR drive from the bus.
It seems
watermodem wrote:
As somebody who is now debating how to measure latencies in a
giga-bit ethernet environment with several components doing
L3 switching in much less than 10 micro-seconds ... (hardware)
I agree that some method is need to achieve higher resolutions.
(Sigh... I will
"Albert D. Cahalan" wrote:
* All three interfaces do progressive disclosure -- the user only sees
questions he/she needs to answer (no more hundreds of greyed-out menu
entries for irrelevant drivers!).
Well, that sucks. The greyed-out menu entries were the only good
thing about
Hello,
I use RedHat 6.2 with 2.2.16 kernel and 4 NICs in my lab at school.
3 of NICs are private network 172.x.x.x, and the other is public 140.o.o.o
But when I use this box, I got following messages...
card3: response no resource
card3: Too much work at interrupt, status = 0x4050
card2:
I remember sometime in the late 80's a fellow at UniSoft
named Don whose last name escapes me just now told me about a
paper presented at a Usenix symposium that had some measurements
that purported that copy-on-write was a performance lose and
better performance would be achieve by
Albert D. Cahalan wrote:
* All three interfaces do progressive disclosure -- the user only sees
questions he/she needs to answer (no more hundreds of greyed-out menu
entries for irrelevant drivers!).
Well, that sucks. The greyed-out menu entries were the only good
thing about
Alexander Viro writes:
OK, how about wider testing? Theory: prune_dcache() goes through the
list of immediately killable dentries and tries to free given amount.
It has a "one warning" policy - it kills dentry if it sees it twice without
lookup finding that dentry in the interval.
óÒÄ, 11 áÐÒ 2001 × ÓÏÏÂÝÅÎÉÉ ÎÁ ÔÅÍÕ "Re: 2.4.3 compile error No 3" ÷Ù ÎÁÐÉÓÁÌÉ:
diff -urdN linux/net/ipx/Makefile linux/net/ipx/Makefile
Petr, first of all I save text of patch you sent me to file
"ipx-makefile.patch" in /usr/src and try to patch.
Result:
On Wed, Apr 11, 2001 at 05:36:42PM -0500, Steven Walter wrote:
It would appear that way, if not for something I neglected to mention in
my first message--the ioctl is on the fd for the opened serial port.
This succeeds in other version of the kernel (as described in my
original posting) and
Hi ,
The RTC interrupt is programmable from 2 Hz to 8192 Hz, in powers of 2. So the
interrupts that you
could get are one of the following: 0.122ms, .244ms, .488ms, .977ms,
1.953ms, 3.906ms, 7.813ms, and so on.Is there any workaround , so that i
can use RTC
for meeting my
I just spotted these messages in my xconsole:
Apr 12 11:22:19 emma1 kernel: hda: status error: status=0x50 { DriveReady SeekComplete
}
Apr 12 11:22:19 emma1 kernel: hda: no DRQ after issuing MULTWRITE
Apr 12 11:22:19 emma1 kernel: hda: ide_set_handler: handler not null; old=c01acc04,
On Wed, Apr 11, 2001 at 11:40:36PM +0200, Christoph Hellwig wrote:
In article [EMAIL PROTECTED] you wrote:
Hello all,
Is anyone aware of ongoing development to provide the capability
to take a snapshot of a block device?
It's part of Linux-LVM since version 0.8 and thus part of
hi all,
please help me to know how the proc file system is
created/implemented.
What are the source files,documentation related?
thanks in advance
bye
srinivas
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More
Hi.
I got a "current undefined" error when I try to compile the 2.4.2 linux
kernel with SMP support on a K7/Athlon platform.
I also got a "smp_num_cpus undefined" error when I don't une the SMP
option.
My kernel config uses lots of modules for various hardware plug-in
cards.
The attached file
On Wed, 11 Apr 2001, Jamie Lokier wrote:
Think of the original 64k and 256k VGA cards. I think some of those
didn't have an irq, but did have a way to read the progress of the
raster, which you could PLL to using timer interrupts. Some video games
still look fine at 320x200 :-)
The
But, as a separate issue, the CML2 design *could* be reworked to support
a multiple-apex tree, if there were any advantage to doing so. I don't
see one. Do you?
Enough to justify the work - no
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message
I know TCO meaning that, but I can't believe it for a mainboard
component. Should the user then throw the PC away, or what? Or is it
more safe to reboot frequently. What has this to do with costs?
Its a watchdog timer. It reduces the buzzwordTCO/buzzword by letting you
arrange for your
On 11 Apr 01 at 14:55, Chris Meadors wrote:
I would like to see this fixed as much as anyone (even complained to the
XFree people from SuSE last ALS). But I don't think the fix should be in
the kernel. XF4 needs to be fixed. The problem doesn't just effect the
maxtroxfb, but also the
Albert D. Cahalan [EMAIL PROTECTED]:
* All three interfaces do progressive disclosure -- the user only sees
questions he/she needs to answer (no more hundreds of greyed-out menu
entries for irrelevant drivers!).
Well, that sucks. The greyed-out menu entries were the only good
thing
[1.] One line summary of the problem:
Linux 2.2.19 system crash with Oops in scsi_do_cmd during mirror rebuild
on megaraid
[2.] Full description of the problem/report:
Seconds after starting a rebuild of a mirrored partition on a megaraid
controller, the
system crashed. It might be
[1.] One line summary of the problem:
Linux 2.2.19 system crash with Oops in scsi_do_cmd during mirror rebuild
on megaraid
Can you duplicate it without the intel modules being loaded that boot
Before I attempted to rebuild the mirror set, I got several kernel
messages like this
Hi,
I have been playing around with patches that fix this problem. What seems to happen is
that the VM code is pretty efficent at avoiding the calls to shrink the caches. When
they
do get called its a case of to little to late. This is espically bad in lightly
loaded
systems. The
On Wed, 11 Apr 2001 [EMAIL PROTECTED] wrote:
Unfortunately, I'm fairly sure that finishing gcml would take long
enough to render the point moot, because by the time it was done the
average Linux machine would have sped up enough for the Python
implementation not to be laggy anymore :-).
jeff millar [EMAIL PROTECTED]:
From what's in the various documentation and reading about 1% of the cml2
traffic... cml2's various "make *config" invocations use config.out as a
database for remembering configuration, and then on exit they all generate a
fresh copy of .config.
Actually
I'm not a list member so IF you respond to this mail please CC me.
I've been looking at the archives and see some problems with the 2.3.x
kernel versions and affs support. I havn't tried any 2.3.x versions but
starting with 2.4.0 I can no longer mount an affs file system. No matter
if loopback
Hello! In kernel 2.4.3, I think I found a minor error in the file:
include/linux/ghash.h
On line 109, it says:
int ix = hashfn(pos);\
and it should say:
int ix = HASHFN(pos);\
Out of curiosity, is there a reason that this hash table doesn't seem to
be used anywhere
Hi Guys,
Niraj wrote:
The RTC interrupt is programmable from 2 Hz to 8192 Hz, in
powers of 2. So the interrupts that you could get are one
of the following: 0.122ms, .244ms, .488ms, .977ms,
1.953ms, 3.906ms, 7.813ms, and so on.Is there any
workaround , so that i can use RTC for
For anyone who is interested, I have produced a list of all
of the .data variables that contain all zeroes and could be moved to
.bss within the kernel and all of the modules (all of the modules
that we build at Yggdrasil for x86, which is almost all). These
are global or static
"Adam J. Richter" [EMAIL PROTECTED] said:
[...]
I suppose that running the child first also has a minor
advantage for clone() in that it should make programs that spawn lots
of threads to do little bits of work behave better on machines with a
small number of processors, since the
[EMAIL PROTECTED] wrote:
It seems that the tape is written incorrectly. I wrote some large file
(300MB)
and read it back four time. The read copies are all the same. They differ
from the original only in 32 consecutive bytes (the replaced values SEEM
random). Of course, 32 bytes in 300MB
I'm wondering if anyone in the Linux kernel development community has
any ideas about some problems I'm having with Digi Xem boards.
We've got a Digi Xem board (two different PCI boards and an ISA board
were tested) in a Linux 2.2.19 machine to provide logins to Wyse
terminals. When logged into
On 12 Apr 01 at 12:49, info wrote:
/usr/src/linux/arch/i386/lib/lib.a /usr/src/linux/lib/lib.a
/usr/src/linux/arch/i386/lib/lib.a \
--end-group \
-o vmlinux
net/network.o(.data+0x2c84): undefined reference to `sysctl_ipx_pprop_broadcasting'
Yes. This error is
On Thursday 12 April 2001 06:07, Dave Jones wrote:
On Wed, 11 Apr 2001 [EMAIL PROTECTED] wrote:
Unfortunately, I'm fairly sure that finishing gcml would take long
enough to render the point moot, because by the time it was done the
average Linux machine would have sped up enough for the
I get this when I try to compile 2.4.4-pre2
(I'm assuming the list is working this morning, since I've received no
messages).
Thanks.
-- todd --
$ make bzImage
gcc -D__KERNEL__ -I/var/src/linux-2.4.3/include -Wall -Wstrict-prototypes -O2
-fomit-frame-pointer -fno-strict-aliasing -pipe
Hi Guys,
I made some errors in my last code here's the correction
Niraj wrote:
The RTC interrupt is programmable from 2 Hz to 8192 Hz, in
powers of 2. So the interrupts that you could get are one
of the following: 0.122ms, .244ms, .488ms, .977ms,
1.953ms, 3.906ms, 7.813ms, and so on.
Hi
Regarding the patch
I don't have experience with the linux kernel internals but could this patch
not lead to a run-loop condition as the only thing that can break our of the
for(;;) loop is the tmp==dentry_unused statement. So if the required number
of dentries does not exist and
Marcin Kowalski [EMAIL PROTECTED] writes:
Hi
Regarding the patch
I don't have experience with the linux kernel internals but could this patch
not lead to a run-loop condition as the only thing that can break our of the
for(;;) loop is the tmp==dentry_unused statement. So if the
Petr Vandrovec wrote:
On 11 Apr 01 at 14:55, Chris Meadors wrote:
I would like to see this fixed as much as anyone (even complained to the
XFree people from SuSE last ALS). But I don't think the fix should be in
the kernel. XF4 needs to be fixed. The problem doesn't just effect the
On Wed, 11 Apr 2001, Bret Indrelee wrote:
Current generation PCs can easily handle 1000s of
interrupts a second if you keep the overhead small.
the PC centric implementation of the ticked system is one of its major flaws.
there are architectures which the cost of a fixed interval is the same
On Thu, 12 Apr 2001, Steven Cole wrote:
Excuse me, but this seems to be something of a red herring.
...
Adding seconds or tens of seconds at this time on 2001 hardware will
seem very moot by the time 2.5/2.6 is at the point 2.4.x is now.
Adding tens of seconds per build is not acceptable
On Thu, 12 Apr 2001, Mark Salisbury wrote:
On Wed, 11 Apr 2001, Bret Indrelee wrote:
Current generation PCs can easily handle 1000s of
interrupts a second if you keep the overhead small.
the PC centric implementation of the ticked system is one of its major flaws.
there are
I want to take a moment to thank everyone who is participating in the debate
about CML2's slowness, language type, single- vs. multiple-apex tree, UI, and
so forth. Even the harshest critics.
While I continue to believe my design choices have been basically sound ones,
you are all doing an
Digi's engineering staff _may_ look at this problem but since they don't
officially support kernels not released by RedHat, we have no
guarantees. Any ideas out there?
Well if its what I think their driver probably doesnt work with 2.2.16 either.
The API for tty interfaces changed during 2.2
First the 2.4.3 tries to prefer the child.
Only does it in half of the cases though (odd counter numbers).
Your patch seems a bit radical for what you want to do.
Taking away all tokens from the parents will require that it has to wait
until the next recalculate loop.
Since (p) and (current)
On Thu, 12 Apr 2001, Rafael E. Herrera wrote:
But only users using matroxfb complains to me and/or to linux-kernel ;-)
You know, it worked last week, but it does not work anymore today. And
only thing I changed was kernel. So it must be in kernel...
I thought I had seen at least one other
On Thu, 12 Apr 2001, Marcin Kowalski wrote:
Hi
Regarding the patch
I don't have experience with the linux kernel internals but could this patch
not lead to a run-loop condition as the only thing that can break our of the
for(;;) loop is the tmp==dentry_unused statement. So if
i have two network connections.
one is to my company with the lan useing the 192.168.0.0 subnet,
and the other is to a client using the same subnet.
i wanted to know if it was possible to setup some kind of nating on my laptop
in such a way, that will translate the client's entire 192.168.0.0
On Thu, Apr 12, 2001 at 01:45:08AM -0400, Alexander Viro wrote:
On Wed, 11 Apr 2001, Andreas Dilger wrote:
I just discovered a similar problem when testing Daniel Philip's new ext2
directory indexing code with bonnie++. I was running bonnie under single
user mode (basically nothing else
Shouldn't a compiler be able to deal with this instead?
(Just a thought.)
/Johan
- Original Message -
From: Adam J. Richter [EMAIL PROTECTED]
To: [EMAIL PROTECTED]
Sent: Thursday, April 12, 2001 2:36 PM
Subject: List of all-zero .data variables in linux-2.4.3 available
For anyone who
hi,
the default MAX_ORDER is 10. as i don't know anything about
page usage, i did some tests to see how it affects performance
(with the infamous kernel compile time).
here it is (all +6m):
1st test2nd testmean
2 40.153
3 38.543
4 38.065
Just an interesting data point here.
A while back (8-10 months ago), I'd thought I'd blown my ps2 mouse port on
my motherboard and was using a serial mouse. Having just moved and
reconnecting everything, I decided to give it a try again.
Built kernel 2.4.2.
Basically, I got the problem down
On Thu, 12 Apr 2001, Jan Harkes wrote:
But the VM pressure on the dcache and icache only comes into play once
the system still has a free_shortage _after_ other attempts of freeing
up memory in do_try_to_free_pages.
I don't think that it's necessary bad.
sync_all_inodes, which is called
On Thu, 12 Apr 2001, Ed Tomlinson wrote:
I have been playing around with patches that fix this problem. What
seems to happen is that the VM code is pretty efficent at avoiding the
calls to shrink the caches. When they do get called its a case of to
little to late. This is espically bad in
On Thu, Apr 12, 2001 at 04:44:48PM +0200, [EMAIL PROTECTED] wrote:
Shouldn't a compiler be able to deal with this instead?
(Just a thought.)
Search the lkml archives for discussion on this topic around Christmas.
--
Russell King ([EMAIL PROTECTED])The developer of ARM Linux
I've seen the same scenario about 2-3 times a week. kswapd and one or
more processes all CPU bound, totalling to 100%. I've had 'esdplay' hung
on several occasions, and 2-3 times it's been xscreensaver (3.29) hung.
The 'hung' processes are consistently immune to kill -9, even as root, which
hi,
when trying to scan with xsane and "agfa snapscan 1236s", i get the
following message:
Attached scsi generic sg2 at scsi0, channel 0, id 5, lun 0, type 6
sym53c895-0-5,*: target did not report SYNC.
sym53c895-0-5,0: extraneous data discarded.
sym53c895-0-5,0: COMMAND FAILED (89 0)
Hi,
I think that it is the bug of FAT-fs.
Please try the following patch.
thanks a lot, the patch fixes the problem
--
-ulrich lauther
Ulrich Lauther ph: +49 89 636 48834 fx: ... 636 42284
This patch (made against linux-2.4.4-pre2) takes Anton Blanchard's suggestions
and abstracts out the rwsem implementation somewhat. This makes the following
general files:
include/linux/rwsem.h - general RW semaphore wrapper
include/linux/rwsem-spinlock.h - rwsem
On Thu, 12 Apr 2001, Alexander Viro wrote:
On Thu, 12 Apr 2001, Jan Harkes wrote:
But the VM pressure on the dcache and icache only comes into play once
the system still has a free_shortage _after_ other attempts of freeing
up memory in do_try_to_free_pages.
I don't think that it's
I've seen the same scenario about 2-3 times a week. kswapd and one or
more processes all CPU bound, totalling to 100%. I've had 'esdplay' hung
on several occasions, and 2-3 times it's been xscreensaver (3.29) hung.
The 'hung' processes are consistently immune to kill -9, even as root, which
On Thu, 12 Apr 2001, Rik van Riel wrote:
On Thu, 12 Apr 2001, Ed Tomlinson wrote:
I have been playing around with patches that fix this problem. What
seems to happen is that the VM code is pretty efficent at avoiding the
calls to shrink the caches. When they do get called its a case
i've noticed that i can't seem to enable DMA on my IDE disk under
2.4.2-ac18. this works under 2.2.19pre14 (the last 2.2 kernel i
built). i've been slogging through lk archives but can't seem to find
where this got changed.
when i do 'hdparm -d 1 /dev/hda', i get
/dev/hda:
setting using_dma
I've been attempting to use Donald Becker's DP83815 driver (version
1.0.7) under the 2.2.18 kernel.
Firstly, I found that when the driver was compiled into the kernel instead
of being compiled as a module, it was redetecting the same cards
repeatedly and reregistering them. This meant that the
Hi all !!
This is just to reinforce the message below.
This crash is ver easy to reproduce.
Use bootldr (with the last patch from Nico) [it also happens with
Redboot]
+
Lunix 2.4.0 + patch rmk2 + diff rmk2-np2
+ a ramdisk.
Once logged in Linux, type these commands :
SHELL mknod /dev/dsp c
On Thu, 12 Apr 2001, Rik van Riel wrote:
Please take a look at Ed Tomlinson's patch. It also puts pressure
on the dcache and icache independent of VM pressure, but it does
so based on the (lack of) pressure inside the dcache and icache
themselves.
The patch looks simple, sane and it
Hi
I have applied this(Tom's) patch as well as the small change to
dcache.c(thanx Andreas, David, Alexander and All), I ran some tests and so
far so good, both the dcache and inode cache entries in slabinfo are keeping
nice and low even though I tested by creating thousands of files and then
On Thu, 12 Apr 2001 [EMAIL PROTECTED] wrote:
Shouldn't a compiler be able to deal with this instead?
(Just a thought.)
/Johan
The compiler does deal with it. That's why you have a choice when
you write code.
The defacto standard has been that initialized data, regardless of
whether it's
//Linux really needs a clean basis for asynchronous and
//unbuffered i/o libraries. Something like the fork/thread
//clone(), but to replace select() and aio_* polling. This
//might be a start. And it is just a file and very like a
//pipe or socket.
//Suppose we add /dev/qio with 64 byte
On Wed, Apr 11, 2001 at 06:29:30PM -0700, Anton Blanchard wrote:
This patch provides a very good performance improvement in file
descriptor management for SMP linux kernel on a 4-way machine with the
expectation of even higher gains on higher end machines. The patch uses the
On Thu, 12 Apr 2001 [EMAIL PROTECTED] wrote:
I've seen the same scenario about 2-3 times a week. kswapd and one or
more processes all CPU bound, totalling to 100%. I've had 'esdplay' hung
on several occasions, and 2-3 times it's been xscreensaver (3.29) hung.
The 'hung' processes are
On Thu, 12 Apr 2001, Alexander Viro wrote:
Bad idea. If you do loops over directory contents you will almost
permanently have almost all dentries freeable. Doesn't make freeing
them a good thing - think of the effects it would have.
Simple question: how many of dentries in
On Thu, 12 Apr 2001 16:12:55 BST, Alan Cox said:
I've seen the same scenario about 2-3 times a week. kswapd and one or
more processes all CPU bound, totalling to 100%. I've had 'esdplay' hung
on several occasions, and 2-3 times it's been xscreensaver (3.29) hung.
The 'hung' processes
On Thu, 12 Apr 2001, Alexander Viro wrote:
IOW. keeping dcache/icache size low is not a good thing, unless you
have a memory pressure that requires it. More agressive kupdate _is_
a good thing, though - possibly kupdate sans flushing buffers, so that
it would just keep the icache clean and
On Wed, Apr 11 2001, Josh McKinney wrote:
I had the almost exact same thing happen to me just yesterday, I started up
xcdroast, and cdda2wav and kswapd went crazy, backed out of X and all was
well, and still is.
Same kernel as you too.
I can tell you why this happens. Earlier kernels
Hi,
Base (2.4.2) -
100 Average Throughput = 39.628 MB/sec
200 Average Throughput = 22.792 MB/sec
Base + files_struct patch -
100 Average Throughput = 39.874 MB/sec
200 Average Throughput = 23.174 MB/sec
I found this value quite less
2.4.3-pre6 quietly made a very significant change there:
it used to say "if (!order) goto try_again;" and now just
says "goto try_again;". Which seems very sensible since
__GFP_WAIT is set, but I do wonder if it was a safe change.
We have mechanisms for freeing pages (order 0), but whether
Hi there,
We think we might have encountered a problem with the cpu load
calculation in Linux (2.2.x). The current calculation is based on
dividing the jiffies to user, system and idle jiffies according to the
process the timer hardware interrupt interrupts.
In our case the timer interrupt
Hubertus Franke wrote:
In the recent optimizations to sys_sched_yield a bug was introduced.
In the current implementation of sys_sched_yield()
the aligned_data and idle_tasks are indexed by logical cpu-#.
They should however be indexed by physical cpu-#.
Since logical==physical on the
Hi CJ,
you should really read the thread titled "Linux's implementation of
poll() not scalable?" in the LKML archives, here is a link:
http://www.uwsg.iu.edu/hypermail/linux/kernel/0010.3/0003.html
There are many problems with the /dev/something interface for events and
all is described in that
ftp://ftp.kernel.org/pub/linux/kernel/people/alan/2.4/
Intermediate diffs are available from
http://www.bzimage.org
The merges are tricky in places so this one is to make sure I got the merges
right.
2.4.3-ac5
o Merge Linus 2.4.4pre1
o
On Thu, 12 Apr 2001, Alan Cox wrote:
2.4.3-pre6 quietly made a very significant change there:
it used to say "if (!order) goto try_again;" and now just
says "goto try_again;". Which seems very sensible since
__GFP_WAIT is set, but I do wonder if it was a safe change.
We have
Hi All,
I am trying to implement a client using sockets in a Linux module,
and not having much success with it. Does anyone have some suggesstions
on how do i go about it?
If anyone has an example, it would be great.
Thanks in Advance,
-Sharath.
-
To unsubscribe from this list: send the
Folks, IMO ext2-dir-patch got to the stable stage. Currently
it's against 2.4.4-pre2, but it should apply to anything starting with
2.4.2 or so.
Ted, could you review it for potential inclusion into 2.4 once
it gets enough testing? It's ext2-only (the only change outside of
ext2
On Thu, Apr 12, 2001 at 05:16:33PM +0200, Cyrille Ngalle wrote:
This is just to reinforce the message below.
And why is it of interest to LKML? I can think if no one here who'd
be interested in it.
This crash is ver easy to reproduce.
Use bootldr (with the last patch from Nico) [it also
There is a great article here:
http://www.linux-mag.com/2000-12/gear_01.html
Here is what I got out of it...
http://www.jukie.net/~bart/kernel/kserv/
Bart.
On Thu, 12 Apr 2001, Sharath Kumar wrote:
Hi All,
I am trying to implement a client using sockets in a Linux module,
and
1 - 100 of 435 matches
Mail list logo