Re: increase softint_bytes

[Masanobu SAITOH <msaitoh%execsw.org@localhost>]

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. That panic is not in ixgbe(4) driver but in ip_input.c::ip_init().


 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 warning in the dmesg.
> Making softint size fully dynamic is unfortunately not straighforward, it would need to reallocate the softint memory on all CPUs in a way that any serviced softints would continue working during this time.

 Each driver which call softint_establish() keep the return value, so
it's very hard without big modification.

> It would be simple however to adjust it based on % of physical memory, instead of fixed value.

It might be good, but it's only small area, so fixed value might be OK.
And not so many people create a lot of pseudo interface, so I think it's
OK to make the max value as a kernel option to increase.

> 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 system with e.g. 32 cores.
>
> I agree that the sysctl seems somewhat unnecessary, since the limit is only relevant during boot anyway,

As I wrote, it's incorrect because ifconfig xxxN create allocates softint.


> so it's not very helpful.
> Jaromir
>
> 2017-11-16 21:05 GMT+01:00 matthew green <mrg%eterna.com.au@localhost <mailto:mrg%eterna.com.au@localhost>>:
>
>     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 <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 <http://www.netbsd.org/~msaitoh/softint-20171116-0.dif>
>     >
>     > Summary:
>     >
>     >       - Increase the default size from 8192 bytes to 32768 bytes.
>     >       - Add new option SOFTINT_BYTES to change the value.
>     >       - Add two new read-only sysctls kern.softint.{max,count}
>     >
>     > Any comment?
>
>     can't this be fixed by making it dynamic?  ie, fix it properly so
>     that it never has this problem again -- if in 10 years we're adding
>     5x as many softints as today, we'll hit it again.
>
>     i also don't see why the crash can't be fixed to become an error.
>     the code tries to avoid adding more than it can, but soemthing must
>     be wrong for the crash to occur anyway.  ie, at worst we'd fix it
>     to return an error instead of crashing.
>
>     if that is done, the sysctl exports seem unneccesary as well.
>
>     thanks.
>
>
>     .mrg.


--
-----------------------------------------------
                SAITOH Masanobu (msaitoh%execsw.org@localhost
                                 msaitoh%netbsd.org@localhost)