Hugh Dickins wrote:
On Mon, 21 Mar 2005, David S. Miller wrote:
On Tue, 22 Mar 2005 15:14:54 +1100
Nick Piggin <[EMAIL PROTECTED]> wrote:
Question, Dave: flush_tlb_pgtables after Hugh's patch is also
possibly not being called with enough range to cover all page
tables that have been f
Andrew Morton wrote:
With these six patches the ppc64 is hitting the BUG in exit_mmap():
BUG_ON(mm->nr_ptes);/* This is just debugging */
fairly early in boot.
No doubt Hugh will have this fixed before long... but if you
have time to spare, you may just try hitting it on the head
and ma
Arun Srinivas wrote:
Pls. help me. I went through the sched.c for kernel 2.6 and saw that it
supports
hyperthreading.I would be glad if someone could answer this question(if
am not wrong a HT processor has 2 architectural states and one execution
unit...i.e., two pipeline streams)
1)when the
Hugh Dickins wrote:
On Tue, 22 Mar 2005, David S. Miller wrote:
On Tue, 22 Mar 2005 19:36:46 + (GMT)
Hugh Dickins <[EMAIL PROTECTED]> wrote:
I notice that although both i386 and sparc64 use pgtable-nopud.h, the
i386 pud_clear does nothing at all and the sparc64 pud_clear resets to 0.
This was
David S. Miller wrote:
On Wed, 23 Mar 2005 10:32:10 +1100
Nick Piggin <[EMAIL PROTECTED]> wrote:
I think David's on the right track - I think there's something a
bit wrong at the top. In my reply to Andrew in this thread I
posted a patch which may at least get things working...
W
David S. Miller wrote:
On Tue, 22 Mar 2005 17:10:13 -0800
Andrew Morton <[EMAIL PROTECTED]> wrote:
Hugh Dickins <[EMAIL PROTECTED]> wrote:
On Tue, 22 Mar 2005, Luck, Tony wrote:
>
> But I'm still confused by all the math on addr/end at each
> level.
You think the rest of us are not ;-?
umm, give
Arun Srinivas wrote:
If the SMT (apart from SMP) support is enabled in the .config file,
does the kernel recogonize the 2 logical processor as 2 logical or 2
physical processors?
You shouldn't be able to select SMT if SMP is not enabled.
If SMT and SMP is selected, then the scheduler will recog
Nick Piggin wrote:
Something like the following (untested) extension of Bodo's work
could be the minimal fix for 2.6.11. As I've said though, I'd
consider it a hack and prefer to do something about the locking.
That could be done after 2.6.11 though. Depends how you feel.
I think th
Bodo Stroesser wrote:
Working with the new UML skas0 mode on my Xeon HT host, sporadically I saw
some processes on UML segfaulting.
In all cases, I could track this down to be caused by a gs segment
register,
that had the wrong contents.
This again is caused by a problem in the host linux: A ptra
Ingo Molnar wrote:
* Nick Piggin <[EMAIL PROTECTED]> wrote:
When a task is put to sleep, it is dequeued from the runqueue
while it is still running. The problem is that the runqueue
lock can be dropped and retaken in schedule() before the task
actually schedules off, and wait_task_inacti
Nick Piggin wrote:
Ingo Molnar wrote:
* Nick Piggin <[EMAIL PROTECTED]> wrote:
When a task is put to sleep, it is dequeued from the runqueue
while it is still running. The problem is that the runqueue
lock can be dropped and retaken in schedule() before the task
actually schedules of
Andrew Morton wrote:
Nick Piggin <[EMAIL PROTECTED]> wrote:
Bodo Stroesser wrote:
Nick Piggin wrote:
Bodo Stroesser wrote:
I don't see how this could help because AFAIKS, child->saving is only
set and cleared while the runqueue is locked. And the same runqueue lock
is taken by wait
Bodo Stroesser wrote:
Nick Piggin wrote:
Bodo Stroesser wrote:
I don't see how this could help because AFAIKS, child->saving is only
set and cleared while the runqueue is locked. And the same runqueue lock
is taken by wait_task_inactive.
Sorry, that not right. There are some routines c
Nick Piggin wrote:
Andrew Morton wrote:
Nick Piggin <[EMAIL PROTECTED]> wrote:
Andrew, IMO this is another bug to hold 2.6.11 for.
Sure. I wouldn't consider Bodo's patch to be the one to use though..
No. Something similar could be done that works on all architectures
and all wa
On Wed, 2005-02-02 at 14:09 +1100, Nick Piggin wrote:
> On Tue, 2005-02-01 at 18:49 -0800, Christoph Lameter wrote:
> > On Wed, 2 Feb 2005, Nick Piggin wrote:
> > I mean we could just speculatively copy, risk copying crap and
> > discard that later when we find that the
On Tue, 2005-02-01 at 11:01 -0800, Christoph Lameter wrote:
> On Tue, 1 Feb 2005, Nick Piggin wrote:
> > A per-pte lock is sufficient for this case, of course, which is why the
> > pte-locked system is completely free of the page table lock.
>
> Introducing pte locking
On Tue, 2005-02-01 at 17:20 -0800, Christoph Lameter wrote:
> On Wed, 2 Feb 2005, Nick Piggin wrote:
>
> > > The unmapping in rmap.c would change the pte. This would be discovered
> > > after acquiring the spinlock later in do_wp_page. Which would then lead to
> > &
Christoph Lameter wrote:
Slightly OT: are you still planning to move the update_mem_hiwater and
friends crud out of these fastpaths? It looks like at least that function
is unsafe to be lockless.
@@ -1316,21 +1318,27 @@ static int do_wp_page(struct mm_struct *
flush_cache_pa
Christoph Lameter wrote:
The page fault handler attempts to use the page_table_lock only for short
time periods. It repeatedly drops and reacquires the lock. When the lock
is reacquired, checks are made if the underlying pte has changed before
replacing the pte value. These locations are a good fit
Dinakar Guniguntala wrote:
On Mon, Feb 07, 2005 at 03:59:49PM -0800, Matthew Dobson wrote:
Sorry to reply a long quiet thread, but I've been trading emails with Paul
Jackson on this subject recently, and I've been unable to convince either
him or myself that merging CPUSETs and CKRM is as easy a
Martin J. Bligh wrote:
What about your proposed sched domain changes?
Cant sched domains be used handle the CPU groupings and the
existing code in cpusets that handle memory continue as is?
Weren't sched somains supposed to give the scheduler better knowledge
of the CPU groupings afterall ?
sched d
Matthew Dobson wrote:
Nick Piggin wrote:
I didn't really follow where that idea went, but I think at least
a few people thought that sort of functionality wasn't nearly
fancy enough! :)
Well, that's about how far the idea was supposed to go. ;) I think
named hierarchical sche
On Thu, 2005-02-10 at 18:09 -0800, Matt Mackall wrote:
> On Thu, Feb 10, 2005 at 04:47:27PM -0800, Chris Wright wrote:
> > * Matt Mackall ([EMAIL PROTECTED]) wrote:
> > > What happened to the RT rlimit code from Chris?
> >
> > I still have it, but I had the impression Ingo didn't like it as a long
On Thu, 2005-02-10 at 22:41 -0500, Paul Davis wrote:
> [ the best solution is ]
>
> [ my preferred solution is ... ]
>
> [ it would be better if ... ]
>
> [ this is a kludge and it should be done instead like ... ]
>
> did nobody read what andrew wrote and what JOQ pointed out?
>
On Fri, 2005-02-11 at 17:34 +1100, Peter Williams wrote:
> Nick Piggin wrote:
> > I can't say much about it because I'm not putting my hand up to
> > do anything. Just mentioning that rlimit would be better if not
> > for the userspace side of the equation. I think
On Mon, 2005-02-14 at 06:28 +0100, Willy Tarreau wrote:
> Hello Josh,
>
> On Sun, Feb 13, 2005 at 06:23:15PM -0600, Josh Aas wrote:
> > Hello,
> >
> > I have written an introduction to the Linux 2.6.8.1 CPU scheduler
> > implementation. It should help people to understand what is going on in
>
Benjamin Herrenschmidt wrote:
Hi !
When using 4level-fixup.h, a PMD page may end up beeing freed before the
matching PGD entry is cleared due to the way the compatibility macros
work. This can cause nasty races on some architectures.
This patch fixes it by defining pud_clear() to be pgd_clear(). Th
Benjamin Herrenschmidt wrote:
Index: linux-work/include/asm-generic/4level-fixup.h
===
--- linux-work.orig/include/asm-generic/4level-fixup.h 2005-01-24
17:09:49.0 +1100
+++ linux-work/include/asm-generic/4level-fixup.h
Some of you have seen this before. Just resending because
I based my next patch on top of this one.
Suggested by Linus: optimise a condition in the clear_p?d_range functions.
Results in one less conditional branch on i386 with gcc-3.4.4
Signed-off-by: Nick Piggin <[EMAIL PROTEC
I am pretty surprised myself that I was able to consolidate
all "page table range" functions into a single type of iterator
(well, there are a couple of variations, but it's not too bad).
I thought at least the functions which allocate new page tables
would have to be seperate from those which don'
(Note these are all obviously just RFCs, until after 2.6.11,
at which time I'll send them off to Andrew if they've proven
OK).
Anyway, here is the patch to fold the page table walkers
nicely for 2 and 3 level implementations... now we are getting
some good reasons why people should convert to the -
And lastly, redo this vital optimisation that David
had to remove earlier. Saves a few bytes.
---
linux-2.6-npiggin/include/asm-generic/pgtable-nopmd.h |2 ++
linux-2.6-npiggin/include/asm-generic/pgtable-nopud.h |2 ++
linux-2.6-npiggin/mm/memory.c |8 +
Linus Torvalds wrote:
On Fri, 18 Feb 2005, Nick Piggin wrote:
I am pretty surprised myself that I was able to consolidate
all "page table range" functions into a single type of iterator
(well, there are a couple of variations, but it's not too bad).
Ok, this is post-2.6.11 mate
Andi Kleen wrote:
On Thu, Feb 17, 2005 at 03:30:31PM -0800, David S. Miller wrote:
On Fri, 18 Feb 2005 00:03:42 +0100
Andi Kleen <[EMAIL PROTECTED]> wrote:
And to be honest we only have about 6 or 7 of these walkers
in the whole kernel. And 90% of them are in memory.c
While doing 4level I think I
Benjamin Herrenschmidt wrote:
All of them are slightly differently implemented, some check overflow,
some don't, some have redudant checking, some aren't even consistent
between all 3/4 loops of a given walk routine set, and we have seen the
tendency to introduce subtle bugs in one of them when the
Nick Piggin wrote:
Haven't yet pulled out a pre-4-level kernel to see how 3-level compares
I guess I'll do that now.
Close.
Before 4level: 119.5us, after folded walkers: 132.8us
I think most of this is now coming from clear_page_range, rather
than the actual traversing of the page table
On Wed, 2005-01-26 at 16:27 -0600, Jack O'Quin wrote:
> Ingo Molnar <[EMAIL PROTECTED]> writes:
>
> > - exported the current RT-average value to /proc/stat (it's the last
> >field in the cpu lines)
>
> > e.g. the issue Con and others raised: privileged tasks. By default, the
> > root user w
On Wed, 2005-01-26 at 20:31 -0600, Jack O'Quin wrote:
> Nick Piggin <[EMAIL PROTECTED]> writes:
>
> > I'm a bit concerned about this kind of policy and breakage of
> > userspace APIs going into the kernel. I mean, if an app is
> > succeeds in gaining S
On Wed, 2005-01-26 at 23:15 -0600, Jack O'Quin wrote:
> Nick Piggin <[EMAIL PROTECTED]> writes:
>
> > But the important elements are lost. The standard provides a
> > deterministic scheduling order, and a deterministic scheduling
> > latency
>
> Where
Zou Nan hai wrote:
There is a performance regression of lmbench
lat_proc fork result on ia64.
in
2.6.10
I got
Process fork+exit:164.8438 microseconds.
in 2.6.11-rc2
Process fork+exit:183.8621 microseconds.
I believe this regression was caused by
the 4-level page tables change.
Since most of
Andrew Morton wrote:
ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.11-rc2/2.6.11-rc2-mm2/
Changes since 2.6.11-rc2-mm1:
Just a couple of things:
+task_size-is-variable.patch
+use-mm_vm_size-in-exit_mmap.patch
I didn't hear back about my comments on this patch. I don't see
why M
On Tue, 2005-02-01 at 18:49 -0800, Christoph Lameter wrote:
> On Wed, 2 Feb 2005, Nick Piggin wrote:
>
> > Well yeah, but the interesting case is when that isn't a lock ;)
> >
> > I'm not saying what you've got is no good. I'm sure it would be fine
&g
On Thu, 2005-02-03 at 11:29 +0100, Terje FÃberg wrote:
> I recently upgraded my desktop from 2.4.28 to
> 2.6.10. Even under moderate memory pressure kswapd
> regularly eats almost all available cpu time
> whenever there is a little more IO throughput,
> like copying large files. The system is extr
Terje FÃberg wrote:
Terje FÃberg <[EMAIL PROTECTED]> skrev:
The kernel is compiling right now, but I cannot
reboot this machine until six or seven o'clock
tonight (CET). I will report then.
Well, well, I rebooted the same kernel, now with
MAGIC-SYSRQ enabled. At first the kswapd-effect
wouldn
Nick Piggin wrote:
Hmm, your DMA zone has no active pages, and pages_scanned (which
triggers all_unreclaimable)
is only incremented when scanning the active list. But I wonder, if the
pages can't be
freed, why aren't they being put on the active list?
Oh, attached should be a minimal
Andrew Morton wrote:
Nick Piggin <[EMAIL PROTECTED]> wrote:
Oh, attached should be a minimal fix if you would like to try it out.
...
--- linux-2.6/mm/vmscan.c~vmscan-minfix 2005-02-04 11:52:37.0 +1100
+++ linux-2.6-npiggin/mm/vmscan.c 2005-02-04 11:53:32.0 +1100
@@
On Thu, 2005-02-03 at 22:26 -0800, Christoph Lameter wrote:
> On Fri, 4 Feb 2005, Paul Mackerras wrote:
>
> > As has my scepticism about pre-zeroing actually providing any benefit
> > on ppc64. Nevertheless, the only definitive answer is to actually
> > measure the performance both ways.
>
> Of
Terje Fåberg wrote:
Terje Fåberg <[EMAIL PROTECTED]> skrev:
I'll continue to do the same things I did yesterday
before kswapd started to spin.
Looks very good so far. I am unable to reproduce the
bad kswapd behaviour with your patch, Nick.
To double-check I booted into the old kernel an hour
a
Hugh Dickins wrote:
On Sun, 20 Feb 2005, Nick Piggin wrote:
Open coding is probably the smaller evil.
And they're really not changed that often.
My opinion FWIW: I'm all for regularizing the pagetable loops to
work the same way, changing their variables to use the same names,
impro
On Tue, 2005-02-22 at 20:31 -0800, David S. Miller wrote:
> On Wed, 23 Feb 2005 02:06:28 + (GMT)
> Hugh Dickins <[EMAIL PROTECTED]> wrote:
>
> > I've not seen Dave's bitmap walking functions (for clearing?),
> > would they fit in better with my way?
>
Hugh: I'll have more of a look through y
On Tue, 2005-02-22 at 20:31 -0800, David S. Miller wrote:
> I just got also reminded that we walk these damn pagetables completely
> twice every exit, once to unmap the VMAs pte mappings, once again to
> zap the page tables. It might be fruitful to explore combining
> those two steps, perhaps not
Hugh Dickins wrote:
On Wed, 23 Feb 2005, Lee Revell wrote:
Thanks, your patch fixes the copy_pte_range latency.
clear_page_range is also problematic.
Yes, I saw that from your other traces too. I know there are plans
to improve clear_page_range during 2.6.12, but I didn't realize that
it had beco
Hugh Dickins wrote:
I'm off to bed, but since your appetite for looking at patches
is greater than mine, I'll throw what I'm currently testing over
the wall to you now. Against 2.6.11-rc4-bk9, but my starting point
was obviously your patches. Not yet split up, but clearly should be.
Yeah you've s
Lee Revell wrote:
On Thu, 2005-02-24 at 10:27 +1100, Nick Piggin wrote:
If you are using i386 with 2-level page tables (no highmem), then
the behaviour should be more or less identical. Odd.
IIRC last time I really tested this a few months ago, the worst case
latency on that machine was about
Lee Revell wrote:
On Thu, 2005-02-24 at 12:29 +1100, Nick Piggin wrote:
Lee Revell wrote:
IIRC last time I really tested this a few months ago, the worst case
latency on that machine was about 150us. Currently its 422us from the
same clear_page_range code path.
Well it should be pretty trivial to
On Thu, 2005-02-24 at 05:12 +, Hugh Dickins wrote:
> On Thu, 24 Feb 2005, Nick Piggin wrote:
> > OK after sleeping on it, I'm warming to your way.
> >
> > I don't think it makes something like David's modifications any
> > easier, but mine di
Hi,
I hope that you can include the following set of CPU scheduler
patches in -mm soon, if you have no other significant performance
work going on.
There are some fairly significant changes, with a few basic aims:
* Improve SMT behaviour
* Improve CMP behaviour, CMP/NUMA scheduling (ie. Opteron)
1/13
Some fixes for unsynchronised TSCs. A task's timestamp may have been set
by another CPU. Although we try to adjust this correctly with the
timestamp_last_tick field, there is no guarantee this will be exactly right.
Signed-off-by: Nick Piggin <[EMAIL PROTECTED]>
Index: linux
ancing faster, and ensure
the migration threads don't start running which is another problem
observed in the wild.
Signed-off-by: Nick Piggin <[EMAIL PROTECTED]>
Index: linux-2.6/kernel/sched.c
===
--- linux-2.6.
3/13
I have an updated userspace parser for this thing, if you
are still keeping it on your website.
Move balancing fields into struct sched_domain, so we can get more
useful results on systems with multiple domains (eg SMT+SMP, CMP+NUMA,
SMP+NUMA, etc).
Signed-off-by: Nick Piggin <[EM
4/13
Fix up a few small warts in the periodic multiprocessor rebalancing
code.
Signed-off-by: Nick Piggin <[EMAIL PROTECTED]>
Index: linux-2.6/kernel/sched.c
===
--- linux-2.6.orig/kernel/sched.c 2005-02-24 17:31:28.431609701
5/13
Cleanup find_busiest_group a bit. New sched-domains code
means we can't have groups without a CPU.
Signed-off-by: Nick Piggin <[EMAIL PROTECTED]>
Index: linux-2.6/kernel/sched.c
===
--- linux-2.6.orig/kernel/sched.c
7/13
Fix up active load balancing a bit so it doesn't get called when it shouldn't.
Reset the nr_balance_failed counter at more points where we have found
conditions to be balanced. This reduces too aggressive active balancing seen
on some workloads.
Signed-off-by: Nick Piggin <[EM
ance
tolerance is now set at half the domain's imbalance, so we get the
opportunity to do wake balancing before the more random periodic
rebalancing gets preformed.
Signed-off-by: Nick Piggin <[EMAIL PROTECTED]>
Index: linux-2.6/kernel/sched.c
=
ily increased).
So generally a higher number will result in more conservative balancing.
Signed-off-by: Nick Piggin <[EMAIL PROTECTED]>
Index: linux-2.6/include/asm-i386/topology.h
===
--- linux-2.6.orig/include/asm-i386/topology.
12/13
Add SCHEDSTAT statistics for sched-balance-fork.
Signed-off-by: Nick Piggin <[EMAIL PROTECTED]>
Index: linux-2.6/include/linux/sched.h
===
--- linux-2.6.orig/include/linux/sched.h 2005-02-24 17:39:07.616911007
10/13
Remove the very aggressive idle stuff that has recently gone into
2.6 - it is going against the direction we are trying to go. Hopefully
we can regain performance through other methods.
Signed-off-by: Nick Piggin <[EMAIL PROTECTED]>
Index: linux-2.6/include/asm-i386/topo
is for the new tasks to be
sent to a different socket, but more often than not, we would first load
up our sibling core, or fill two cores of a single remote socket before
selecting a new one.
This gives large improvements to STREAM on such systems.
Signed-off-by: Nick Piggin <[EMAIL PROTEC
13/13
Do some basic initial tuning.
Signed-off-by: Nick Piggin <[EMAIL PROTECTED]>
Index: linux-2.6/include/asm-x86_64/topology.h
===
--- linux-2.6.orig/include/asm-x86_64/topology.h 2005-02-24 17:39:07.615911131 +1100
+++
6/13
Remove the special casing for idle CPU balancing. Things like this are
hurting for example on SMT, where are single sibling being idle doesn't
really warrant a really aggressive pull over the NUMA domain, for example.
Signed-off-by: Nick Piggin <[EMAIL PROTECTED]>
Index: linux
On Thu, 2005-02-24 at 08:46 +0100, Ingo Molnar wrote:
> * Nick Piggin <[EMAIL PROTECTED]> wrote:
>
> > 1/13
> >
>
> ugh, has this been tested? It needs the patch below.
>
Yes. Which might also explain why I didn't see -ve intervals :(
Thanks Ingo.
Ingo Molnar wrote:
* Nick Piggin <[EMAIL PROTECTED]> wrote:
[PATCH 6/13] no aggressive idle balancing
[PATCH 8/13] generalised CPU load averaging
[PATCH 9/13] less affine wakups
[PATCH 10/13] remove aggressive idle balancing
they look fine, but these are the really scary ones :-) Maybe we
Hugh Dickins wrote:
On Thu, 24 Feb 2005, Nick Piggin wrote:
pud_addr_end?
next = pud_addr_end(addr, end);
Hmm, yes, I'll go with that, thanks (unless a better idea follows).
Something I do intend on top of what I sent before, is another set
of three macros, like
Ingo Molnar wrote:
* Nick Piggin <[EMAIL PROTECTED]> wrote:
[PATCH 11/13] sched-domains aware balance-on-fork
[PATCH 12/13] schedstats additions for sched-balance-fork
[PATCH 13/13] basic tuning
STREAMS numbers tricky. It's pretty much the only benchmark that 1)
relies on being able
Hugh Dickins wrote:
At one stage I was adding unlikelies to all the p??_bads, then it
seemed more sensible to hide that in a new macro (which of course
must do the none and bad tests inline, before going off to the function).
Yeah that sounds OK. I think (un)likely can propagate through
inline func
Rick Lindsley wrote:
I have an updated userspace parser for this thing, if you are still
keeping it on your website.
Sure, be happy to include it, thanks! Send it along. Is it for version
11 or version 12?
Version 12. I can send it to you next week. This was actually
directed at Andrew, w
Rick Lindsley wrote:
There is little help we get from userspace, and i'm not sure we want to
add scheduler overhead for this single benchmark - when something like a
_tiny_ bit of NUMAlib use within the OpenMP library would probably solve
things equally well!
There's has been a gene
Giovanni Tusa wrote:
If I am not wrong, the scheduler will choose it again (it will be still the
higher priority task, and the only of its priority list).
I have to add an explicit sleep to effectively relinquish the CPU for some
time, or the scheduler can deal with such a
situation in another way
Christian Schmid wrote:
I already tried with 300 KB and even used a perl-hash as a horrible-slow
buffer for a readahead-replacement. It still slowed down on the syswrite
to the socket. Thats the strange thing.
Do you have to use manual readahead though? What is the performance
like if you just l
Christian Schmid wrote:
This issue has been tracked down more. This bug does NOT appear if I
disable preemtive kernel.
Maybe this helps.
Yes, it may help - can you boot with profile=schedule and get
the results for say, a 30 second period while the application
is experiencing problems?
So:
start
Robert Hancock wrote:
Bernd Schubert wrote:
Oh no, not this page allocation problems again. In summer I already
posted problems with page allocation errors with 2.6.7, but to me it
seemed that nobody cared. That time we got those problems every
morning during the cron jobs and our main file serv
Andrew Theurer wrote:
Nick, can you describe the system you run the DB tests on? Do you have
any cpu idle time stats and hopefully some context switch rate stats?
Yeah, it is dbt3-pgsql on OSDL's 8-way STP machines. I think they're
PIII Xeons with 2MB L2 cache.
I had been having some difficulty r
Nick Piggin wrote:
Andrew Theurer wrote:
Nick, can you describe the system you run the DB tests on? Do you
have any cpu idle time stats and hopefully some context switch rate
stats?
Yeah, it is dbt3-pgsql on OSDL's 8-way STP machines. I think they're
PIII Xeons with 2MB L2 cache.
Corey Minyard wrote:
Arjan van de Ven wrote:
Just doing an atomic operation is not faster than doing a lock, an
atomic operation, then an unlock? Am I missing something?
if the lock and the atomic are on the same cacheline they're the same
cost on most modern cpus...
Ah, I see. Not likely
Corey Minyard wrote:
Nick Piggin wrote:
Is get_with_check actually going to be useful for anything? It
seems like it promotes complex and potentially unsafe schemes.
It is certainly more complex to use this, and I'm guessing that's why
Greg rejected it. Certainly a valid problem.
e
I've had a few queries about this, so by "popular" demand, I've
put my latest nicksched stuff here:
www.kerneltrap.org/~npiggin/2.6.11-nicksched.gz
It includes all the multiprocessor stuff that's in -mm, and also
my alternate scheduler policy.
Nick
-
To unsubscribe from this list: send the line "un
Andrew Morton wrote:
Jeff Garzik <[EMAIL PROTECTED]> wrote:
IMO too confusing.
2.6.even: bugfixes only
2.6.odd: bugfixes and features.
That doesn't even confuse me!
I actually second Matt's request; -RCs à la 2.4.
Then your above becomes:
2.6.x-rc: bugfixes only
2.6.x-pre: bugfixes and features
And
Andrew Morton wrote:
Christoph Lameter <[EMAIL PROTECTED]> wrote:
On Wed, 2 Mar 2005, Andrew Morton wrote:
Earlier releases back in September 2004 had some pte locking code (and
AFAIK Nick also played around with pte locking) but that
was less efficient than atomic operations.
How much less effici
Benjamin Herrenschmidt wrote:
However, if this pte_cmpxchg() thing is used for removing access, then
sparc64 can't use it. In such a case a race in the TLB handler would
result in using an invalid PTE. I could "spin" on some lock bit, but
there is no way I'm adding instructions to the carefully c
Benjamin Herrenschmidt wrote:
On Fri, 2005-03-04 at 04:19 +1100, Nick Piggin wrote:
You don't want to do that for all architectures, as I said earlier.
eg. i386 can concurrently set the dirty bit with the MMU (which won't
honour the lock).
So you then need an atomic lock, atomic pte
Andrew Morton wrote:
Thomas Gleixner <[EMAIL PROTECTED]> wrote:
I don't see that the releases are stable. They are defined stable by
proclamation.
If they were stable we'd release the darn things! *obviously* -rc kernels
are expected to still have problems.
Release the -rc kernel when it is st
[EMAIL PROTECTED] wrote:
Since installing 2.6.10 kswapd has decided to loop wildly on two
occations. Both occations happened after starting a big compiles.
Checking vmstat, I noticed a steady stream of io/bi figures ranging
between 2-5K (which is about what I can get out of this box during
normal o
Christian Schmid wrote:
Today I tested with 5000 sockets. The problem is the same like above but
the more sockets there come, it just doesnt claim more bandwidth as it
SHOULD of course do. It seems it doesn't slow down but it just doesnt
scale anymore. The badwidth doesnt go over 80 MB/Sec, no m
Ben Greear wrote:
Christian Schmid wrote:
Ben Greear wrote:
How many bytes are you sending with each call to write()/sendto()
whatever?
I am using sendfile-call every 100 ms per socket with the poll-api. So
basically around 40 kb per round.
My application is single-threaded, uses non-blocking
Siddha, Suresh B wrote:
By code inspection, I see an issue with this patch
[PATCH 10/13] remove aggressive idle balancing
Why are we removing cpu_and_siblings_are_idle check from active_load_balance?
In case of SMT, we want to give prioritization to an idle package while
doing active_load_
Willy Tarreau wrote:
On Mon, Mar 07, 2005 at 04:14:37PM +1100, Nick Piggin wrote:
I think you would have better luck in reproducing this problem if you
did the full sendfile thing.
I think it is becoming disk bound due to page reclaim problems, which
is causing the slowdown.
In that case
Nick Piggin wrote:
Willy Tarreau wrote:
thousands of sockets). I never had enough time to investigate more, so I
went back to 2.4.
I have heard other complaints about this, and they are definitely
related to the scheduler (not saying yours is, but it is very possible).
Oh, and if you could dig
Prakash Punnoor wrote:
Nick Piggin schrieb:
I've had a few queries about this, so by "popular" demand, I've
put my latest nicksched stuff here:
www.kerneltrap.org/~npiggin/2.6.11-nicksched.gz
It includes all the multiprocessor stuff that's in -mm, and also
my alternate sc
[EMAIL PROTECTED] wrote:
If you do 'echo 0 0 > /proc/sys/vm/lowmem_reserve_ratio' the kernel gets a
divide-by-zero.
Prevent that, and fiddle with some whitespace too.
Signed-off-by: Andrew Morton <[EMAIL PROTECTED]>
Can we instead have a patch that makes the value zero turn off the
lowmem reserve e
Siddha, Suresh B wrote:
Nick,
On Mon, Mar 07, 2005 at 04:34:18PM +1100, Nick Piggin wrote:
Active balancing should only kick in after the prescribed number
of rebalancing failures - can_migrate_task will see this, and
will allow the balancing to take place.
We are resetting the nr_balance_failed
501 - 600 of 1974 matches
Mail list logo