On 05/17/2011 01:35 PM, John Baldwin wrote:
...
Yeah, I already have a patch to do that, but hadn't added atomic ops to
critical_enter() and critical_exit(). But it also wasn't as fancy in the
critical_exit() case. Here is what I have and I think it might actually
be ok (it doesn't use an atomi
On 05/17/2011 09:56 AM, John Baldwin wrote:
On Tuesday, May 17, 2011 12:20:40 pm Max Laier wrote:
On 05/17/2011 05:16 AM, John Baldwin wrote:
...
Index: kern/kern_switch.c
===
--- kern/kern_switch.c (revision 221536)
+++ kern
On 05/17/2011 05:16 AM, John Baldwin wrote:
...
Index: kern/kern_switch.c
===
--- kern/kern_switch.c (revision 221536)
+++ kern/kern_switch.c (working copy)
@@ -192,15 +192,22 @@
critical_exit(void)
{
struct thread *td;
- int flags;
On Monday 16 May 2011 17:54:54 Attilio Rao wrote:
> 2011/5/16 Max Laier :
> > On Monday 16 May 2011 16:46:03 John Baldwin wrote:
> >> On Monday, May 16, 2011 4:30:44 pm Max Laier wrote:
> >> > On Monday 16 May 2011 14:21:27 John Baldwin wrote:
> >> > >
On Monday 16 May 2011 16:46:03 John Baldwin wrote:
> On Monday, May 16, 2011 4:30:44 pm Max Laier wrote:
> > On Monday 16 May 2011 14:21:27 John Baldwin wrote:
> > > Yes, we need to fix that. Humm, it doesn't preempt when you do a
> > > critical_exit() thou
On Monday 16 May 2011 14:21:27 John Baldwin wrote:
> On Monday, May 16, 2011 1:46:33 pm Max Laier wrote:
> > I'd like to propose that we move forward with fixing the race, before
> > redesigning the API - please.
> >
> > We agree that there is a problem with
I'd like to propose that we move forward with fixing the race, before
redesigning the API - please.
We agree that there is a problem with the exit rendezvous. Let's fix that.
We agree that the generation approach proposed by NetAPP is the right way to
go? Can we check it in, then? Again, I'
On Sunday 15 May 2011 11:16:03 John Baldwin wrote:
> On 5/15/11 10:53 AM, Andriy Gapon wrote:
> > on 15/05/2011 10:12 Andriy Gapon said the following:
> >> on 14/05/2011 18:25 John Baldwin said the following:
> >>> Hmmm, so this is not actually sufficient. NetApp ran into a very
> >>> similar race
onically increasing generation count
> to the rendezvous data set, which is cached in the rendezvous handler
> and to exit the last synchronization point if either smp_rv_waiters[2]
> is high enough, or the generation count has changed.
>
> I think this would also handle the case the T
On Friday 13 May 2011 11:50:57 Max Laier wrote:
> On Friday 13 May 2011 11:28:33 Andriy Gapon wrote:
> > on 13/05/2011 17:41 Max Laier said the following:
> > > this ncpus isn't the one you are looking for.
> >
> > Thank you!
>
> > Here's an up
On Friday 13 May 2011 11:28:33 Andriy Gapon wrote:
> on 13/05/2011 17:41 Max Laier said the following:
> > this ncpus isn't the one you are looking for.
>
> Thank you!
>
> Here's an updated patch:
Can you attach the patch, so I can apply it locally. This code
On Friday 13 May 2011 09:43:25 Andriy Gapon wrote:
> This is a change in vein of what I've been doing in the xcpu branch and
> it's supposed to fix the issue by the recent commit that (probably
> unintentionally) stress-tests smp_rendezvous in TSC code.
>
> Non-essential changes:
> - ditch initial
On Friday 13 May 2011 09:43:25 Andriy Gapon wrote:
> This is a change in vein of what I've been doing in the xcpu branch and
> it's supposed to fix the issue by the recent commit that (probably
> unintentionally) stress-tests smp_rendezvous in TSC code.
>
> Non-essential changes:
> - ditch initial
On Monday 23 August 2010 20:56:08 Simon L. B. Nielsen wrote:
> I can't think of what else to say, so that was probably it :-).
MD5/SHA256/SIZE?
Thank you!
Max
___
freebsd-current@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebs
On Tuesday 20 July 2010 04:33:01 Doug Barton wrote:
> On Mon, 19 Jul 2010, Chris Ruiz wrote:
> > On Mon, Jul 19, 2010 at 8:03 PM, Doug Barton wrote:
> >> I added options KDTRACE_HOOKS to my kernel config, built a new kernel,
> >> and rebooted. I decided to try your script before things went sidewa
On Monday 14 June 2010 23:22:42 Pawel Worach wrote:
> Here is a patch that fixes a couple of "warning: format string is not a
> string literal" and a couple of unused/never read variable "len" warnings
> in lib/libugidfw.
I'm not sure about the intention behind the len assignements in libugidfw -
suggest reading the OpenBSD FAQ about it:
http://www.openbsd.org/faq/pf/index.html
or if you prefer a summarize, check out the port status report:
http://www.freebsd.org/news/status/report-oct-2003-dec-2003.html#Porting-OpenBSD's-pf
--
Best regards, | [EMAIL
If I build attached kmod and kldload/-unload it on a GENERIC kernel w/
SMP & apic it'll error out:
"Zone was not empty (xx items). Lost X pages of memory."
w/o SMP & apic the problem disappears.
This is on a p4 HTT, but seems reproducible on "proper" SMP systems as
well. UP systems don't show it
>> Could a vinum guru please contact me via email?
>>
>> I've lost 2 vinum volumes as a result of the latest fiasco and naturally
>> am eager to figure out what's going on and recover the data.
EA> This isn't necessarily directed at you - I'm just using this email as a
EA> footstep to send this ge
Hello Andreas,
Monday, November 17, 2003, 8:11:47 AM, you wrote:
AK> #7 0xc05ed8a9 in ip_input (m=0x0) at
AK> /usr/src/sys/netinet/ip_input.c:364
AK> #8 0xc05e6292 in div_output (so=0xc2f11d20, m=0xc16d6600,
AK> sin=0xc2d834b0,
AK> control=0x0) at /usr/src/sys/netinet/ip_divert.c:364
AK> (
> I'll admit to being mostly a lurker here, but isn't the point of /sbin
> to be statically linked. That's what the 's' stands for?
> Second question. This seems to imply that /sbin and /bin both have to
> have the same behavior? I have no problem with /bin being dynamically
> linked, but what
Monday, November 10, 2003, 4:32:54 PM, you wrote:
AL> On Mon, 10 Nov 2003 13:12:42 +0100
AL> Tobias Roth <[EMAIL PROTECTED]> wrote:
>> the author of altq itself or the author of the freebsd port?
AL> I don't know the who's who, but I think it was the author of altq
AL> itself.
I certainly doubt
Monday, November 10, 2003, 5:29:34 AM, you wrote:
ML> I am looking for a solution to make QoS possible on my FreeBSD box. After
ML> searching for the internet, I found that there is a software called ALTQ
ML> that can do possibly what I want. However, I found that it is still not
ML> directly built
type
for CARP interfaces.
- Locking?!?
- You tell me!
Tests:
Very basic tests for IPv4 and IPv6 performed with OpenBSD as a "known
good" peer. I have very limited test environment at the moment.
Code:
http://pf4freebsd.love2party.net/carp.diff
Perforce: branch mlaier_carp
Hello Antoine,
Tuesday, November 4, 2003, 10:55:22 AM, you wrote:
AJ> I just migrated a 4.8 server to -CURRENT and I have one question.
AJ> At boot time I get the following message:
AJ>
AJ> module_register: module if_tun already exists!
AJ> Module
Hello,
this just a short "yes, we are aware of things" message. As OpenBSD
3.4 was released three days ago, we will release pf 2.0 soon. However,
before that can take place there are some issues that have to be
resolved beforehand:
1) As you may know, Brooks Davis has finally brought if_xname t
Hello Andre,
Monday, October 20, 2003, 4:07:40 AM, you wrote:
> I was just wondering if anyone was currently having a look at the
> possibility of porting OpenBSD's CARP. I have a bit of free time on my
> hands but wouldn't want to duplicate anyone's work...
we are working on a pf / pfsync port.
Hello Andrey,
Wednesday, October 15, 2003, 1:29:21 PM, you wrote:
AC> Due to increased activity of SPAM harvesters what are our plans to hide
AC> our addresses from public WWW? I mean all browseable mailing lists,
AC> FreeBSD site, CVS via WWW, PRs, ports and docs.
AC> As I think, simple form wi
Hello Michael,
Tuesday, October 14, 2003, 2:03:51 PM, you wrote:
>> I see it's patched and contains altq-code, but trying to apply the classic
>> ack-prioritizing ruleset gives me "pfctl: tun0: driver does not support
>> altq". Is this expected?
MN> Okay, it seems pf didn't like the fact that my
JR> Do you have P4's with hyper threading?
Why? Are there particular issues with HT and ULE? The normal scheduler
doesn't seem to utilize the second "virtual" processor at all (as long
as I trust in what top tells me). Any suggestions how to build a desktop
system (i.e. with X, audio/video etc.) k
Hello Clau,
C> i removed the last "/" from "/kern/" and now it seems it can find the
C> directory.
C> i don't know if this is a general problem, or it is just in the case of
C> my system.
Same here. Setting SYSDIR helped for now. But the last commit message to
kmod.mk:
"Revert rev. 1.86, I've fix
Hello Eivind,
Thursday, September 25, 2003, 4:12:59 PM, you wrote:
EO> /usr/src/sys/contrib/ipfilter/netinet/ip_fil.c: In function `fr_check_wrapper':
EO> /usr/src/sys/contrib/ipfilter/netinet/ip_fil.c:319: error:
EO> `PFIL_OUT' undeclared (first use in this function)
This seems to be a problem w
32 matches
Mail list logo
