linux-kernel - Re: [PATCH net-next v3] arm: eBPF JIT compiler

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Sat, 19 Aug 2017 19:11:51 -0700
From:   Alexei Starovoitov <ast@...com>
To:     Shubham Bansal <illusionist.neo@...il.com>
CC:     Russell King - ARM Linux <linux@...linux.org.uk>,
        David Miller <davem@...emloft.net>,
        Network Development <netdev@...r.kernel.org>,
        Daniel Borkmann <daniel@...earbox.net>,
        <linux-arm-kernel@...ts.infradead.org>,
        LKML <linux-kernel@...r.kernel.org>,
        Kees Cook <keescook@...omium.org>, Andrew Lunn <andrew@...n.ch>
Subject: Re: [PATCH net-next v3] arm: eBPF JIT compiler

On 8/19/17 2:46 PM, Shubham Bansal wrote:
> test_pkt_access:PASS:ipv4 271 nsec
> test_pkt_access:PASS:ipv6 297 nsec
> test_xdp:PASS:ipv4 961517 nsec     <--- Here is the difference.
> test_xdp:PASS:ipv6 615855 nsec     <--- Here is the difference.

yes. this is expected. These two numbers are single run
on cold cache, so there will be run-to-run variation.

> test_l4lb:PASS:ipv4 3049 nsec
> test_l4lb:PASS:ipv6 3906 nsec

These two and the first two were the ones I was interested in,
since they do many iterations over the same set and
the best to compare code gen changes.
The delta % is actually better than I expected judging by test_bpf
micro-benchmarks, so the results are very encouraging.

Thanks!