Introduce generic structures and routines for
resource accounting.
Each resource accounting container is supposed to
aggregate it, container_subsystem_state and its
resource-specific members within.
diff -upr linux-2.6.20.orig/include/linux/res_counter.h
This includes setup of RSS container within generic
process containers, all the declarations used in RSS
accounting, and core code responsible for accounting.
diff -upr linux-2.6.20.orig/include/linux/rss_container.h
linux-2.6.20-0/include/linux/rss_container.h
---
Adds needed pointers to mm_struct and page struct,
places hooks to core code for mm_struct initialization
and hooks in container_init_early() to preinitialize
RSS accounting subsystem.
diff -upr linux-2.6.20.orig/include/linux/mm.h linux-2.6.20-0/include/linux/mm.h
---
Pages are charged to their first touchers which are
determined using pages' mapcount manipulations in
rmap calls.
diff -upr linux-2.6.20.orig/fs/exec.c linux-2.6.20-0/fs/exec.c
--- linux-2.6.20.orig/fs/exec.c 2007-02-04 21:44:54.0 +0300
+++ linux-2.6.20-0/fs/exec.c2007-03-06
* container_try_to_free_pages() walks containers
page list and tries to shrink pages. This is based
on try_to_free_pages() and Co code.
Called from core code when no resource left at the
moment of page touching.
* container_out_of_memory() selects a process to be
killed which mm_struct
Small and simple - each fork()/clone() is accounted
and rejected when limit is hit.
diff -upr linux-2.6.20.orig/include/linux/numproc_container.h
linux-2.6.20-0/include/linux/numproc_container.h
--- linux-2.6.20.orig/include/linux/numproc_container.h 2007-03-06
13:39:17.0 +0300
+++
Simple again - increment usage counter at file open and
decrement at file close. Reject opening if limit is hit.
diff -upr linux-2.6.20.orig/fs/Makefile linux-2.6.20-0/fs/Makefile
--- linux-2.6.20.orig/fs/Makefile 2007-02-04 21:44:54.0 +0300
+++ linux-2.6.20-0/fs/Makefile 2007-03-06
Ingo Molnar wrote:
* Gerd Hoffmann [EMAIL PROTECTED] wrote:
So in the end you would still have two different hypervisor ABI's,
the VMI ROM just hides that.
oh, but that way i have cleverly pushed the problem out of Linux and
into the VMI-ROM's domain ;) Which is all i care about.
Fine, so
Ingo Molnar wrote:
legacy support has to be ensured, but it does not hugely matter in terms
of the designing our future. What matters is that once we change some
fundamental aspect of Linux, we can adopt lguest/KVM immediately. With
'external' hypervisors there is no such compulsory forward
Ingo Molnar wrote:
i think you are missing my point.
paravirt_ops is a Linux-internal abstraction that tries to make our life
easier but it has no relevance whatsoever to an external hypervisor - be
that Xen, VMWare/ESX or Windows/Longhorn.
Of course it has relevance. Linux is an
* Jeremy Fitzhardinge [EMAIL PROTECTED] wrote:
The whole point of pv_ops is to allow the hypervisors interfaces to
evolve at their own pace without having to constrain the core kernel's
development
unfortunately that's a self-serving oxymoron, contradicted by real life
;) Pretty much the
Anthony Liguori wrote:
Ingo Molnar wrote:
* Gerd Hoffmann [EMAIL PROTECTED] wrote:
So in the end you would still have two different hypervisor ABI's,
the VMI ROM just hides that.
oh, but that way i have cleverly pushed the problem out of Linux
and into the VMI-ROM's domain ;) Which is all
* Jeremy Fitzhardinge [EMAIL PROTECTED] wrote:
My suggestion would be for Linux to make only a /single/ external
ABI promise: VMI. (and we can extend it with higher-level paravirt
ops, etc.)
VMI is not a promise, it's just three letters. It doesn't even mean
the same thing now as
Nakajima, Jun wrote:
Anthony Liguori wrote:
Ingo Molnar wrote:
* Gerd Hoffmann [EMAIL PROTECTED] wrote:
So in the end you would still have two different hypervisor ABI's,
the VMI ROM just hides that.
oh, but that way i have cleverly pushed the problem out of
Ingo Molnar wrote:
* Jeremy Fitzhardinge [EMAIL PROTECTED] wrote:
My suggestion would be for Linux to make only a /single/ external
ABI promise: VMI. (and we can extend it with higher-level paravirt
ops, etc.)
VMI is not a promise, it's just three letters. It doesn't even mean
Zachary Amsden wrote:
Yes, I don't have a problem with your patch, I just wish I had been
cc'd on it. Fixing this is rather tricky, but I believe no strange
build magic is required, it can be done in kernel init code. Still
building my SUSE 9.0 guest to test. SUSE 9.0 is one of those that
* Ingo Molnar ([EMAIL PROTECTED]) wrote:
yes - but de-facto contradicted by the Xen paravirt_ops patches sent to
lkml ;)
There's no intrinsic value to the Xen on VMI approach that's superior
to Xen on pv_ops (not to mention the complications that it causes).
What are you driving at? You seem
* Chris Wright [EMAIL PROTECTED] wrote:
What are you driving at? You seem to be arguing that abstractions are
bad unless done via ABI's. [...]
i'm still arguing the same: that doing the same thing via overlapping,
conflicting, redundant ABIs is crazy and contrary to the basic interests
of
* Nakajima, Jun [EMAIL PROTECTED] wrote:
I think a KVM Linux would benefit more from paravirt ops, rather than
VMI. The higher-level interface such as the one in Xen, espeically for
I/O, interrupt controllers, timer, SMP, etc. actually simplifies the
implementation of the VMM, and improve
* Ingo Molnar ([EMAIL PROTECTED]) wrote:
* Chris Wright [EMAIL PROTECTED] wrote:
What are you driving at? You seem to be arguing that abstractions are
bad unless done via ABI's. [...]
i'm still arguing the same: that doing the same thing via overlapping,
conflicting, redundant ABIs
Ingo Molnar wrote:
maybe we are talking past each other because i dont really disagree with
that: i mentioned it right at beginning that higher-level APIs would
have to be added to VMI. What i'd like to avoid is the ABI duplication
for the lowlevel stuff /and/ for the highlevel stuff. Since
* Chris Wright [EMAIL PROTECTED] wrote:
i'm still arguing the same: that doing the same thing via
overlapping, conflicting, redundant ABIs is crazy and contrary to
the basic interests of Linux. It's like having 5 different, parallel
variants of sys_open(), interfaced via a convoluted
On 03/06/2007 02:59 AM, Thomas Gleixner wrote:
On Tue, 2007-03-06 at 00:55 -0800, Zachary Amsden wrote:
a proper CE device also has the added bonus of making high-res timers
guests work automatically. It should be simple: just pass it through to
your hypervisor, a hyper-CE-device, like a
* Jeremy Fitzhardinge [EMAIL PROTECTED] wrote:
If you're seriously talking about an ABI, [...]
HELLO, this isnt a hypothetical!! The moment there's a xen_paravirt_ops,
Linux has DE FACTO committed itself to the Xen ABI: whatever
functionality the hypercall_page call table plus the int $0x82
Ingo Molnar wrote:
so trying to argue as if there was no ABI imposed on Linux by hiding the
Xen ABI behind paravirt_ops, and whistling into the air as if nothing
happened is misguided at best.
How is the situation even slightly different with a unified hypervisor ABI?
J
-
To
* Jeremy Fitzhardinge [EMAIL PROTECTED] wrote:
so trying to argue as if there was no ABI imposed on Linux by hiding
the Xen ABI behind paravirt_ops, and whistling into the air as if
nothing happened is misguided at best.
How is the situation even slightly different with a unified
I believe this was just a quick fix in response to Ingo breaking the VMI
build yesterday by disabling NO_IDLE_HZ on us. There is no technical
reason why NO_IDLE_HZ=y can't coexist with NO_HZ.
Well it's nasty that you force NO_IDLE_HZ on all of paravirt ops users.
I think the right solution
* Ingo Molnar ([EMAIL PROTECTED]) wrote:
with the big freaking difference that the 5 parallel implementations of
inode-i_op are:
_internal to Linux_
Granted. Until it's modprobe xen.ko, vmware.ko, viridian.ko...that's
not going to go away, even with the VMI.
Doh. There's only a
On 03/06/2007 02:21 PM, Andi Kleen wrote:
I believe this was just a quick fix in response to Ingo breaking the VMI
build yesterday by disabling NO_IDLE_HZ on us. There is no technical
reason why NO_IDLE_HZ=y can't coexist with NO_HZ.
Well it's nasty that you force NO_IDLE_HZ on all of
Ingo Molnar wrote:
* Nakajima, Jun [EMAIL PROTECTED] wrote:
I think a KVM Linux would benefit more from paravirt ops, rather than
VMI. The higher-level interface such as the one in Xen, espeically
for I/O, interrupt controllers, timer, SMP, etc. actually simplifies
the implementation of the
On Tue, 2007-03-06 at 22:24 +0100, Miklos Szeredi wrote:
I'm not liking this, its not a constant operation as the name implies.
OK, I'll think of something better.
And it style is a bit out of line with the rest of rmap.
The thing it actually does is page_mkclean(), all it doesn't do
This adds two sysfs attributes to /sys/bus/ibmebus which can
be used to notify the ebus driver of added / removed ebus
devices in the OF device tree.
We are seeing several build errors when attempting to apply this to
2.6.21-rc2:
CC arch/powerpc/kernel/ibmebus.o
arch/powerpc/kernel/ibmebus.c:
Hi Bill,
On Tue, Mar 06, 2007 at 04:37:37PM -0500, Bill Davidsen wrote:
(...)
The point is that no one CPU scheduler will satisfy the policy needs of
all users, any more than one i/o scheduler does so. We have realtime
scheduling, preempt both voluntary and involuntary, why should we not
The tlclk driver is going on the MPCBL005 so I need to make the Kconfig
more more generic. Just some text changes.
--mgross
Signed-off-by: Mark Gross [EMAIL PROTECTED]
diff -urN -X linux-2.6.21-rc2/Documentation/dontdiff
linux-2.6.21-rc2/drivers/char/Kconfig
Pavel Machek wrote:
Timetraveling, sorry.
Pavel
Sure confuses Thunderbird. It shows one unread message but
N does not do anything...
-
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to [EMAIL
Hi.
On Tue, 2007-03-06 at 21:31 +0100, Rafael J. Wysocki wrote:
Hi,
On Tuesday, 6 March 2007 01:30, Johannes Berg wrote:
On Tue, 2007-02-27 at 22:51 +0100, Rafael J. Wysocki wrote:
For 2.6.21-rc1 I've invented the appended workaround (works for me,
waiting for
Johannes to
On Tuesday 06 March 2007 12:50 pm, Alessandro Zummo wrote:
On Tue, 6 Mar 2007 11:32:28 -0800
David Brownell [EMAIL PROTECTED] wrote:
on then... My dmesg says, related to rtc :
...
rtc_cmos 00:03: rtc core: registered rtc_cmos as rtc0
I think the RTC core shouldn't emit this
Hi,
On Tuesday, 6 March 2007 23:25, Nigel Cunningham wrote:
On Tue, 2007-03-06 at 21:31 +0100, Rafael J. Wysocki wrote:
On Tuesday, 6 March 2007 01:30, Johannes Berg wrote:
On Tue, 2007-02-27 at 22:51 +0100, Rafael J. Wysocki wrote:
For 2.6.21-rc1 I've invented the appended
Adrian Bunk wrote:
On Tue, Mar 06, 2007 at 12:46:22PM -0500, Bill Davidsen wrote:
Adrian Bunk wrote:
This patch contains the scheduled removal of the OBSOLETE_OSS options
for 2.6.22.
If these are drivers for which there are thought to be useful ALSA
drivers, would it be
On 3/6/07, Alexey Dobriyan [EMAIL PROTECTED] wrote:
+static int __init i2c_bfin_twi_init(void)
+{
+ rc = request_irq(twi_iface.irq, bfin_twi_interrupt_entry, SA_INTERRUPT,
i2c-bfin-twi, twi_iface);
+ if (rc) {
+ printk(KERN_ERR i2c-bfin-twi: can't get IRQ %d !\n,
The MPSC serial driver assumes that interrupt is always on to pick up
the DMA transmit ops that aren't submitted while the DMA engine is active.
However when irqs are off for a period of time such as operations under kernel
crash dump console messages do not show up due to additional DMA ops are
Hello everyone.
IMHO, ACPI disabled due to DMI failure or blacklisted year should be
noted, as is done with other ACPI blacklisting.
This will help people troubleshoot when ACPI isn't working. Status
quo is a mysterious ACPI Disabled message without explanation on
BIOS that implements ACPI but
From: Venkatesh Pallipadi [EMAIL PROTECTED]
This patch fixes a build breakage with !CONFIG_HOTPLUG_CPU and
CONFIG_CPU_IDLE.
Signed-off-by: Venkatesh Pallipadi [EMAIL PROTECTED]
Signed-off-by: Adrian Bunk [EMAIL PROTECTED]
---
This patch was sent by Venkatesh Pallipadi on:
- 2 Mar 2007
---
On Mon, Mar 05, 2007 at 01:36:55PM +, David Howells wrote:
Adrian Bunk [EMAIL PROTECTED] wrote:
OK, what about the patch below?
How many goats did you have to sacrifice to get that to work?
I'd say it was quite straightforward. :-)
I like it with
just one very minor niggle: if
If CONFIG_ZONE_DMA is ever undefined, ZONE_DMA will also not be defined,
and setup.c won't compile. This wraps it with an #ifdef.
Signed-off-by: Andres Salomon [EMAIL PROTECTED]
diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c
index 0b476e1..b69626e 100644
---
On Wed, 7 Mar 2007 00:24:35 +0200
Sami Farin [EMAIL PROTECTED] wrote:
On Tue, Mar 06, 2007 at 23:53:49 +0200, Sami Farin wrote:
...
And I found bug in gcc-4.1.2, it gave 0 for ncubic results
when doing 1000 loops test... gcc-4.0.3 works.
Found it.
--- cbrt-test.c~ 2007-03-07
From: Stephen Hemminger [EMAIL PROTECTED]
Date: Tue, 6 Mar 2007 16:00:55 -0800
On Wed, 7 Mar 2007 00:24:35 +0200
Sami Farin [EMAIL PROTECTED] wrote:
On Tue, Mar 06, 2007 at 23:53:49 +0200, Sami Farin wrote:
...
And I found bug in gcc-4.1.2, it gave 0 for ncubic results
when doing
On Tue, Mar 06, 2007 at 16:00:55 -0800, Stephen Hemminger wrote:
...
Now Linux 2.6 does not have memory in fls, maybe it causes
some gcc funnies some people are seeing.
That code was copy-paste from:
include/asm-x86_64/bitops.h
So shouldn't both fls() and ffs() be fixed there
On Tue, 2007-03-06 at 14:10 +0100, Ingo Molnar wrote:
* Rusty Russell [EMAIL PROTECTED] wrote:
Currently x86 (similar to x84-64) has a special per-cpu structure
called i386_pda which can be easily and efficiently referenced via
the %fs register. An ELF section is more flexible than a
On Tue, 2007-03-06 at 14:15 +0100, Ingo Molnar wrote:
* Rusty Russell [EMAIL PROTECTED] wrote:
Xen wants page-aligned GDT (and PDA must not cross a page-boundary,
but that doesn't happen at the moment since it's so close to start of
page). Let's allow page-alignment in general for
On Tue, 2007-03-06 at 14:20 +0100, Ingo Molnar wrote:
* Rusty Russell [EMAIL PROTECTED] wrote:
+/* The boot Global Descriptor Table: after boot we allocate a per-cpu copy
*/
.align L1_CACHE_BYTES
ENTRY(boot_gdt_table)
- .fill GDT_ENTRY_BOOT_CS,8,0
- .quad
On Wed, 28 Feb 2007 15:25:54 +0100
Joerg Roedel [EMAIL PROTECTED] wrote:
From: Joerg Roedel [EMAIL PROTECTED]
This patch simplifies the get_cycles_sync() function by removing the
#ifdefs from it. Further it introduces an optimization for AMD
processors. There the RDTSCP instruction is used
On Tue, 2007-03-06 at 10:17 -0800, Jeremy Fitzhardinge wrote:
Rusty Russell wrote:
diff -r 213b1ec27001 arch/alpha/kernel/vmlinux.lds.S
--- a/arch/alpha/kernel/vmlinux.lds.S Tue Mar 06 19:01:59 2007 +1100
+++ b/arch/alpha/kernel/vmlinux.lds.S Tue Mar 06 19:02:03 2007 +1100
@@
On Tue, 2007-03-06 at 20:34 +0100, Andi Kleen wrote:
Sigh -- i had hoped this had settled down because it was a
merging nightmare last time. Ok.
Indeed, that's why I waited until everything else was fully merged and
accepted.
+#define percpu_to_op(op,var,val) \
+
This patch is the same as the v3 posted before, and removes multiple
passes over the ready set.
--
ChangeLog:
v3) Removed the revents field from the epoll item structure, as
suggested by Eric Dumazet
v2) In v1, I was trying to avoid to get the spinlock twice WRT yesterday
patch,
This patch add an anonymous inode source, to be used for files that need
and inode only in order to create a file*. We do not care of having an
inode for each file, and we do not even care of having different names in
the associated dentries (dentry names will be same for classes of file*).
This patch cuts out lots of code from epoll, by reusing the anonymous
inode source of patch 2/3.
Signed-off-by: Davide Libenzi davidel@xmailserver.org
- Davide
eventpoll.c | 174 +---
1 file changed, 3 insertions(+), 171
Rusty Russell wrote:
If we used __thread, then gcc could do this optimization for us when it
knows an rvalue is needed, however:
1) gcc wants to use %gs, not %fs, which is measurably slower for the
kernel,
2) gcc wants to use huge offsets to store the address of the per-cpu
space, and
On Tue, 6 Mar 2007, Avi Kivity wrote:
Right. For kvmfs this isn't a problem as there's a 1:1 relationship
between synthetic inodes and dentries. Perhaps d_alloc_anon() could be
extended to avoid the scan if it's a problem.
I currently have the dentry to carry the name of the file* class
Chen, Dongliang wrote:
There are lots of functions in the Linux kernel that are declared as
unsigned long, but the return value is negative integer while error
occurred. An example of these functions is do_mmap_pgoff in mm/mmap.c,
which is defined as:
unsigned long do_mmap_pgoff()
In this
Rusty Russell wrote:
AFAICT, we could save the wasted partial page in three ways: by trying
to link it first, if it's only a case of one file, by having a special
page-aligned percpu data section, or by having a smarter linker.
We already do the second of those for conventional data, so it
[ Al Viro added to Cc: as the arbiter of good taste in the VFS layer. He
has veto powers even over my proposals ;^]
On Tue, 6 Mar 2007, Davide Libenzi wrote:
I currently have the dentry to carry the name of the file* class it is
linked to. I'd prefer to keep it that way, unless there are
On Tue, 6 Mar 2007, Linus Torvalds wrote:
[ Al Viro added to Cc: as the arbiter of good taste in the VFS layer. He
has veto powers even over my proposals ;^]
On Tue, 6 Mar 2007, Davide Libenzi wrote:
I currently have the dentry to carry the name of the file* class it is
linked
To fix the following compile error by enclosing it in ifndef
__ASSEMBLY__/endif.
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
include/asm-generic/bug.h
include/asm-generic/bug.h: Assembler messages:
include/asm-generic/bug.h:7: Error: Unrecognized opcode:
To fix the following compile error by replacing the deleted structure
member is_continuous with flags.
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
arch/powerpc/kernel/time.c
arch/powerpc/kernel/time.c:938: error: unknown field 'is_continuous' specified
in
To fix the following compile error.
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
kernel/irq/manage.c: In function 'irq_set_affinity':
kernel/irq/manage.c:81: error: invalid type argument of '-'
kernel/irq/manage.c:82: error: invalid type argument of '-'
- - -
To fix the following compile error by adding dummy functions for now.
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
include/asm-powerpc/futex.h
kernel/built-in.o: In function `fixup_pi_state_owner64':
kernel/futex.c:2380: undefined reference to
To fix the following compile error by changing names from
__{read,write}_trylock to ___raw_{read,write}_trylock in asm-powerpc/spinlock.h
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
include/asm-powerpc/spinlock.h
include/linux/spinlock_api_smp.h:49: error:
To fix the following compile error by adding necessary macro definitions
(mostly taken from asm-generic/percpu.h).
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
include/asm-powerpc/percpu.h
In file included from include/asm/tlb.h:52,
from
To fix the following compile error by changing local_irq_restore()
to raw_local_irq_restore().
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
include/asm-powerpc/hw_irq.h
In file included from include/asm/system.h:9,
from
Hi Ingo,
Please apply.
This series of patches fixes build breakage on arch/powerpc with realtime
preempt patch. This applies on top of linux-2.6.20 and patch-2.6.20-rt8.
Although there has been some efforts to port realtime-preempt patch to
powerpc, build breakage still exists for
On Tue, 6 Mar 2007, Davide Libenzi wrote:
I'm OK with everything that avoid code duplication due to those fake
inodes. The change can be localized inside the existing API, so it doesn't
really affect me externally.
Can you try with the first patch version that doesn't do anything special
Hi Ingo,
Please consider for inclusion in your rt tree.
This series of patches fixes boot and runntime errors/warnings for
powerpc (esp. 64 bit). This applies to linux-2.6.20, patch-2.6.20-rt8
and previous my patch set;
http://ozlabs.org/pipermail/linuxppc-dev/2007-March/032640.html
To add preemption checks for the NEED_RESCHED_DELAYED flag.
Signed-off-by: Tsutomu Owa [EMAIL PROTECTED]
-- owa
diff -rup linux-rt8/include/asm-powerpc/thread_info.h
rt/include/asm-powerpc/thread_info.h
--- linux-rt8/include/asm-powerpc/thread_info.h 2007-02-20 14:30:40.0
+0900
+++
This patch series implements a new signalfd() system call. I took part of
the original Linus code (and you know how badly it can be broken :), and I
added even more breakage ;)
The patch had to be almost completely changed. This patch allows multiple
signalfd to listen for signals on the same
This patch wire the signalfd system call the the i386 arch.
Signed-off-by: Davide Libenzi davidel@xmailserver.org
- Davide
arch/i386/kernel/syscall_table.S |1 +
include/asm-i386/unistd.h|3 ++-
2 files changed, 3 insertions(+), 1 deletion(-)
Index:
This patch wire the signalfd system call the the x86_64 arch.
Signed-off-by: Davide Libenzi davidel@xmailserver.org
- Davide
arch/x86_64/ia32/ia32entry.S |6 --
include/asm-x86_64/unistd.h |4 +++-
2 files changed, 7 insertions(+), 3 deletions(-)
Index:
The new signalfd system call requires compat code for the sigset_t. This
patch implements it in fs/compat.c
Signed-off-by: Davide Libenzi davidel@xmailserver.org
- Davide
fs/compat.c | 20
1 file changed, 20 insertions(+)
Index: linux-2.6.20.ep2/fs/compat.c
To convert the spinlocks into the raw onces to fix the following
warnings/errors.
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Badness at arch/powerpc/kernel/entry_64.S:651
Call Trace:
[C06133E0] [C000FAAC] show_stack+0x68/0x1b0 (unreliable)
To fix the following runtime warning.
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
BUG: using smp_processor_id() in preemptible [] code: init/371
caller is .pgtable_free_tlb+0x2c/0x14c
Call Trace:
[CFF6B770] [C000FAAC] .show_stack+0x68/0x1b0
What follows is the same patch series that constitutes the RDSL Rotating
Staircase DeadLine cpu scheduler resynced for 2.6.21-rc2-mm2.
A rollup patch that can be applied directly to 2.6.21-rc2-mm2 is here:
http://ck.kolivas.org/patches/staircase-deadline/2.6.21-rc2-mm2-sched-rsdl.patch
and the
Add a list_splice_tail variant of list_splice.
Patch-by: Peter Zijlstra [EMAIL PROTECTED]
Signed-off-by: Con Kolivas [EMAIL PROTECTED]
---
include/linux/list.h | 42 ++
1 file changed, 42 insertions(+)
Index: linux-2.6.21-rc2-mm2/include/linux/list.h
Remove the sleep_avg field from proc output as it will be removed from the
task_struct.
Signed-off-by: Con Kolivas [EMAIL PROTECTED]
---
fs/proc/array.c |2 --
1 file changed, 2 deletions(-)
Index: linux-2.6.21-rc2-mm2/fs/proc/array.c
To fix the following runtime warnings when entering xmon.
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Entering xmon
BUG: using smp_processor_id() in preemptible [] code: khvcd/280
caller is .xmon_core+0xb8/0x8ec
Call Trace:
[CFD737C0]
Modify the sched_find_first_bit function to work on a 180bit long bitmap.
Signed-off-by: Con Kolivas [EMAIL PROTECTED]
---
include/asm-generic/bitops/sched.h | 10 ++
include/asm-s390/bitops.h | 12 +---
2 files changed, 7 insertions(+), 15 deletions(-)
Index:
Remove the TASK_NONINTERACTIVE flag as it will no longer be used.
Signed-off-by: Con Kolivas [EMAIL PROTECTED]
---
fs/pipe.c |7 +--
include/linux/sched.h |3 +--
2 files changed, 2 insertions(+), 8 deletions(-)
Index: linux-2.6.21-rc2-mm2/fs/pipe.c
Implement the Rotating Staircase DeadLine RSDL cpu scheduler policy.
Signed-off-by: Con Kolivas [EMAIL PROTECTED]
---
include/linux/init_task.h |2
include/linux/sched.h | 32 -
kernel/sched.c| 1186 ++
3 files changed, 594
On Tue, 6 Mar 2007, Davide Libenzi wrote:
This patch series implements a new signalfd() system call. I took part of
the original Linus code (and you know how badly it can be broken :), and I
added even more breakage ;)
I forgot to add that this requires the anonymous inode source contained
Add comprehensive documentation of the RSDL cpu scheduler design.
Signed-off-by: Con Kolivas [EMAIL PROTECTED]
---
Documentation/sched-design.txt | 273 -
1 file changed, 267 insertions(+), 6 deletions(-)
Index:
To fix the following boot time error by removing ack member added by
the rt patch.
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Processor 1 found.
Brought up 2 CPUs
[ cut here ]
kernel BUG at arch/powerpc/platforms/cell/interrupt.c:86!
pu 0x1:
To fix the following boot time warnings by setting soft_enabled and
hard_enabled.
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Freeing unused kernel memory: 248k freed
BUG: scheduling with irqs disabled: rc.sysinit/0x/373
caller is user_work+0x14/0x2c
Call
On Tue, 6 Mar 2007, Linus Torvalds wrote:
On Tue, 6 Mar 2007, Davide Libenzi wrote:
I'm OK with everything that avoid code duplication due to those fake
inodes. The change can be localized inside the existing API, so it doesn't
really affect me externally.
Can you try with the
On Tue, 06 Mar 2007 18:52:59 -0500
Andres Salomon [EMAIL PROTECTED] wrote:
If CONFIG_ZONE_DMA is ever undefined, ZONE_DMA will also not be defined,
and setup.c won't compile. This wraps it with an #ifdef.
I guess if anyone tries to disable ZONE_DMA on i386 they'll pretty quickly
discover
On Tue, 6 Mar 2007, Hugh Dickins wrote:
This comes from Oliver's commit 94bebf4d1b8e7719f0f3944c037a21cfd99a4af7
Driver core: fix race in sysfs between sysfs_remove_file() and read()/write()
in 2.6.21-rc1. It looks to me like sysfs_write_file downs buffer-sem
while calling
On 3/6/07, Mockern [EMAIL PROTECTED] wrote:
hi,
Is there a way how to make kernel thread more faster?
I put some of my code to the kthread, but I noticed that kthread sends data
more slow
than original driver without kthread.
Please post a link to your driver source code.
Lee
-
To
On Tue, 6 Mar 2007, Davide Libenzi wrote:
This patch is the same as the v3 posted before, and removes multiple
passes over the ready set.
Can you put a nicer Subject: message, rather than giving all three patches
the same Subject.
I'm assuming this will all go through Andrew anyway, but
On Tue, 6 Mar 2007, Linus Torvalds wrote:
On Tue, 6 Mar 2007, Davide Libenzi wrote:
This patch is the same as the v3 posted before, and removes multiple
passes over the ready set.
Can you put a nicer Subject: message, rather than giving all three patches
the same Subject.
I'm
[PATCH] SLUB The unqueued slab allocator v4
V3-V4
- Rename /proc/slabinfo to /proc/slubinfo. We have a different format after
all.
- More bug fixes and stabilization of diagnostic functions. This seems
to be finally something that works wherever we test it.
- Serialize kmem_cache_create and
Unlimited kmalloc size and removal of general caches =4.
We can directly use the page allocator for all allocations 4K and larger. This
means that no general slabs are necessary and the size of the allocation passed
to kmalloc() can be arbitrarily large. Remove the useless general caches over
Guarantee a mininum number of objects per slab
The number of objects per slab is important for SLUB because it determines
the number of allocations that can be performed without having to consult
per node slab lists. Add another boot option min_objects=xx that
allows the configuration of the
901 - 1000 of 1194 matches
Mail list logo