On Wed, 22 Nov 2017, Masanobu SAITOH wrote:
Date: Wed, 22 Nov 2017 11:41:59 +0900
From: Masanobu SAITOH
To: 6b...@6bone.informatik.uni-leipzig.de
Cc: msai...@execsw.org, tech-kern@NetBSD.org
Subject: Re: increase softint_bytes
On 2017/11/21 15:35, Masanobu SAITOH wrote:
On 2017/11/20 17:28
On Thu, Nov 16, 2017 at 10:25:54PM +0100, Jarom??r Dole??ek wrote:
>
> If I count correctly, with current 8192 bytes the system supports some 100
> softints, which seems to be on quite low side - more advanced hardware and
> drivers usually use queue and softint per cpu, so it can quickly run out
On 2017/11/21 15:35, Masanobu SAITOH wrote:
On 2017/11/20 17:28, Masanobu SAITOH wrote:
On 2017/11/17 18:42, 6b...@6bone.informatik.uni-leipzig.de wrote:
On Thu, 16 Nov 2017, Masanobu SAITOH wrote:
Hi, all.
Some device drivers now allocate a lot of softints.
See:
http://mail-index.netbs
On 2017/11/21 17:03, matthew green wrote:
It'll take a little time to write this change. And, it's low level
and important code, so it will take a time to test the stability
before sending pullup request. So,
0) Apply the following change to -current.
Inde
> It'll take a little time to write this change. And, it's low level
> and important code, so it will take a time to test the stability
> before sending pullup request. So,
>
> 0) Apply the following change to -current.
>
>
> Index: kern_softint.c
> ==
On Tue, Nov 21, 2017 at 03:45:26PM +0900, Masanobu SAITOH wrote:
> 0) Apply the following change to -current.
>
>
> Index: kern_softint.c
> ===
> RCS file: /cvsroot/src/sys/kern/kern_softint.c,v
> ret
On 2017/11/20 17:28, Masanobu SAITOH wrote:
On 2017/11/17 18:42, 6b...@6bone.informatik.uni-leipzig.de wrote:
On Thu, 16 Nov 2017, Masanobu SAITOH wrote:
Hi, all.
Some device drivers now allocate a lot of softints.
See:
http://mail-index.netbsd.org/current-users/2017/11/09/msg032581.html
can't this be fixed by making it dynamic?
It's not easy because the return value of softint_establish() is
made from this area's address. As you know, the value is keep by each driver.
I'm sorry. I misread kern_softint.c. The return value is not directly point to
the area, but it's offse
On 2017/11/17 18:42, 6b...@6bone.informatik.uni-leipzig.de wrote:
On Thu, 16 Nov 2017, Masanobu SAITOH wrote:
Hi, all.
Some device drivers now allocate a lot of softints.
See:
http://mail-index.netbsd.org/current-users/2017/11/09/msg032581.html
To avoid this panic, I wrote the following
On Thu, 16 Nov 2017, Masanobu SAITOH wrote:
Hi, all.
Some device drivers now allocate a lot of softints.
See:
http://mail-index.netbsd.org/current-users/2017/11/09/msg032581.html
To avoid this panic, I wrote the following patch:
http://www.netbsd.org/~msaitoh/softint-20171116
Hi, all.
On 2017/11/17 15:35, Masanobu SAITOH wrote:
Hi, mrg.
On 2017/11/17 5:05, matthew green wrote:
Masanobu SAITOH writes:
Hi, all.
Some device drivers now allocate a lot of softints.
See:
http://mail-index.netbsd.org/current-users/2017/11/09/msg032581.html
To avoid this pani
On Fri, Nov 17, 2017 at 03:35:48PM +0900, Masanobu SAITOH wrote:
> bridge, agr, strip, sl, stf, ppp, l2tp, gre and maybe some other
> pseudo interfaces which is created by ifconfig command allocate
> softint. Some of them may be created tens, hundreds or more.
> So I think it's worth to check the c
On Fri, Nov 17, 2017 at 03:43:57PM +0900, Masanobu SAITOH wrote:
> Each driver which call softint_establish() keep the return value, so
> it's very hard without big modification.
We could make the "void *cookie" returned by softint_establish(9) an
index (internally) instead (w/o changing ABI or A
softint_establish() already fails if there is no space, and prints a
WARNING in this case. The caller however needs to check for the failure,
which ixgbe(4) mostly doesn't. Not sure if that is really the root cause,
the panic seems to be actually in different area, and I didn't actually see
the war
On 2017/11/17 6:25, Jaromír Doleček wrote:
softint_establish() already fails if there is no space, and prints a WARNING in
this case. The caller however needs to check for the failure, which ixgbe(4)
mostly doesn't.
No. ixgbe() checks the return value of if_initialize() and return
correctly.
Hi, mrg.
On 2017/11/17 5:05, matthew green wrote:
Masanobu SAITOH writes:
Hi, all.
Some device drivers now allocate a lot of softints.
See:
http://mail-index.netbsd.org/current-users/2017/11/09/msg032581.html
To avoid this panic, I wrote the following patch:
http://www
Masanobu SAITOH writes:
> Hi, all.
>
> Some device drivers now allocate a lot of softints.
> See:
>
> http://mail-index.netbsd.org/current-users/2017/11/09/msg032581.html
>
> To avoid this panic, I wrote the following patch:
>
> http://www.netbsd.org/~msaitoh/softint-20171116-0.
Hi, all.
Some device drivers now allocate a lot of softints.
See:
http://mail-index.netbsd.org/current-users/2017/11/09/msg032581.html
To avoid this panic, I wrote the following patch:
http://www.netbsd.org/~msaitoh/softint-20171116-0.dif
Summary:
- Increase the def
18 matches
Mail list logo
