Re: [PATCH nf-next RFC 2/3] xt_statistic: do nth-mode accounting per CPU

[Florian Westphal <fw@strlen.de>]

Jesper Dangaard Brouer <hawk@kernel.org> wrote:
> The atomic cmpxchg operations for the nth-mode matching is a scaling
> concern, on our production servers with 192 CPUs. The iptables rules that
> does sampling of every 10000 packets exists on INPUT and OUTPUT chains.
> Thus, these nth-counter rules are hit for every packets on the system with
> high concurrency.
 
> Our use-case is statistical sampling, where we don't need an accurate packet
> across all CPUs in the system. Thus, we implement per-CPU counters for the
> nth-mode match.
> 
> This replaces the XT_STATISTIC_MODE_NTH, to avoid having to change userspace
> tooling. We keep and move atomic variant under XT_STATISTIC_MODE_NTH_ATOMIC
> mode, which userspace can easily be extended to leverage if this is
> necessary.

This patch seems acceptable to me (aside from the deliberate userspace
breakage).

But I do wonder why you can't move to random sampling instead, it
doesn't suffer from this problem (i.e. -m statistic --mode random).

I think a non-rfc version would have to add a new mode, plus the
userspace change, and an explanation why -m random can't be used,
esp.  because the changelog above implies to me that -m random would work
for this :-)