Am Montag, den 15.01.2018, 08:42 -0800 schrieb Laura Abbott:
> On 01/11/2018 06:17 PM, Peter Robinson wrote:
> > > I just noticed, there is a difference in the default value of
> > > `/proc/sys/net/core/optmem_max` on armv7l:
> > >
> > > On all arches it is 20480, but on armv7l it is 10240.
> > >
> > > Is there any specific reason for limiting the maximum ancillary
> > > buffer
> > > size allowed per socket on this arch?
> >
> > No specific reason, I think that would be an upstream kernel
> > default,
> > I'm not aware we tweak that setting on any of the architectures so
> > it
> > should be the arch default.
>
> The actual root cause is that the default is based off of
> sizeof(unsigned long) which is different on 32-bit targets.
I just checked and found `unsigned long` to be 32 bits on %{arm},
only. All other arches (even %{ix86}) have it set to 64 bits.
unsigned long long seems to be at least 64-bit on all arches.
> This has been the setting for a very long
> time, is there a reason changing it via sysctl is not an option?
Well, yes… One cannot change it using sysctl (or using other ways)
without being root (and thus isn't an option for Koji builds).
The preset can be changed to be the same on all arches (based on
changing that in systemd) by adding `net.core.optmem_max = 20480` to
`/usr/lib/sysctl.d/50-default.conf`, tho.
Any ideas towards that?
Let's keep the further discussion in [1].
Cheers,
Björn
[1] https://bugzilla.redhat.com/show_bug.cgi?id=1534620_______________________________________________
kernel mailing list -- kernel@xxxxxxxxxxxxxxxxxxxxxxx
To unsubscribe send an email to kernel-leave@xxxxxxxxxxxxxxxxxxxxxxx
