[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <20240524135958.I_5-z_K6@linutronix.de>
Date: Fri, 24 May 2024 15:59:58 +0200
From: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
To: Jesper Dangaard Brouer <hawk@...nel.org>
Cc: Alexei Starovoitov <alexei.starovoitov@...il.com>,
Toke Høiland-Jørgensen <toke@...hat.com>,
LKML <linux-kernel@...r.kernel.org>,
Network Development <netdev@...r.kernel.org>,
"David S. Miller" <davem@...emloft.net>,
Boqun Feng <boqun.feng@...il.com>,
Daniel Borkmann <daniel@...earbox.net>,
Eric Dumazet <edumazet@...gle.com>,
Frederic Weisbecker <frederic@...nel.org>,
Ingo Molnar <mingo@...hat.com>, Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>,
Peter Zijlstra <peterz@...radead.org>,
Thomas Gleixner <tglx@...utronix.de>,
Waiman Long <longman@...hat.com>, Will Deacon <will@...nel.org>,
Alexei Starovoitov <ast@...nel.org>,
Andrii Nakryiko <andrii@...nel.org>,
Eduard Zingerman <eddyz87@...il.com>, Hao Luo <haoluo@...gle.com>,
Jiri Olsa <jolsa@...nel.org>,
John Fastabend <john.fastabend@...il.com>,
KP Singh <kpsingh@...nel.org>,
Martin KaFai Lau <martin.lau@...ux.dev>, Song Liu <song@...nel.org>,
Stanislav Fomichev <sdf@...gle.com>,
Yonghong Song <yonghong.song@...ux.dev>, bpf <bpf@...r.kernel.org>,
Arnaldo Carvalho de Melo <acme@...nel.org>
Subject: Re: [PATCH net-next 14/15 v2] net: Reference bpf_redirect_info via
task_struct on PREEMPT_RT.
On 2024-05-22 09:09:45 [+0200], Jesper Dangaard Brouer wrote:
> For this benchmark, to focus, I would reduce this to:
> # perf report --sort cpu,symbol --no-children
Keeping the bpf_net_ctx_set()/clear, removing the NULL checks (to align
with Alexei in his last email).
Perf numbers wise, I'm using
xdp-bench redirect-cpu --cpu 3 --remote-action drop eth1 -e
unpached:
| eth1->? 9,427,705 rx/s 0 err,drop/s
| receive total 9,427,705 pkt/s 0 drop/s 0 error/s
| cpu:17 9,427,705 pkt/s 0 drop/s 0 error/s
| enqueue to cpu 3 9,427,708 pkt/s 0 drop/s 8.00 bulk-avg
| cpu:17->3 9,427,708 pkt/s 0 drop/s 8.00 bulk-avg
| kthread total 9,427,710 pkt/s 0 drop/s 147,276 sched
| cpu:3 9,427,710 pkt/s 0 drop/s 147,276 sched
| xdp_stats 0 pass/s 9,427,710 drop/s 0 redir/s
| cpu:3 0 pass/s 9,427,710 drop/s 0 redir/s
| redirect_err 0 error/s
| xdp_exception 0 hit/s
Patched:
| eth1->? 9,557,170 rx/s 0 err,drop/s
| receive total 9,557,170 pkt/s 0 drop/s 0 error/s
| cpu:9 9,557,170 pkt/s 0 drop/s 0 error/s
| enqueue to cpu 3 9,557,170 pkt/s 0 drop/s 8.00 bulk-avg
| cpu:9->3 9,557,170 pkt/s 0 drop/s 8.00 bulk-avg
| kthread total 9,557,195 pkt/s 0 drop/s 126,164 sched
| cpu:3 9,557,195 pkt/s 0 drop/s 126,164 sched
| xdp_stats 0 pass/s 9,557,195 drop/s 0 redir/s
| cpu:3 0 pass/s 9,557,195 drop/s 0 redir/s
| redirect_err 0 error/s
| xdp_exception 0 hit/s
I think this is noise. perf output as suggested (perf report --sort
cpu,symbol --no-children).
unpatched:
| 19.05% 017 [k] bpf_prog_4f0ffbb35139c187_cpumap_l4_hash
| 11.40% 017 [k] ixgbe_poll
| 10.68% 003 [k] cpu_map_kthread_run
| 7.62% 003 [k] intel_idle
| 6.11% 017 [k] xdp_do_redirect
| 6.01% 003 [k] page_frag_free
| 4.72% 017 [k] bq_flush_to_queue
| 3.74% 017 [k] cpu_map_redirect
| 2.35% 003 [k] xdp_return_frame
| 1.55% 003 [k] bpf_prog_57cd311f2e27366b_cpumap_drop
| 1.49% 017 [k] dma_sync_single_for_device
| 1.41% 017 [k] ixgbe_alloc_rx_buffers
| 1.26% 017 [k] cpu_map_enqueue
| 1.24% 017 [k] dma_sync_single_for_cpu
| 1.12% 003 [k] __xdp_return
| 0.83% 017 [k] bpf_trace_run4
| 0.77% 003 [k] __switch_to
patched:
| 18.20% 009 [k] bpf_prog_4f0ffbb35139c187_cpumap_l4_hash
| 11.64% 009 [k] ixgbe_poll
| 7.74% 003 [k] page_frag_free
| 6.69% 003 [k] cpu_map_bpf_prog_run_xdp
| 6.02% 003 [k] intel_idle
| 5.96% 009 [k] xdp_do_redirect
| 4.45% 003 [k] cpu_map_kthread_run
| 3.71% 009 [k] cpu_map_redirect
| 3.23% 009 [k] bq_flush_to_queue
| 2.55% 003 [k] xdp_return_frame
| 1.67% 003 [k] bpf_prog_57cd311f2e27366b_cpumap_drop
| 1.60% 009 [k] _raw_spin_lock
| 1.57% 009 [k] bpf_prog_d7eca17ddc334d36_tp_xdp_cpumap_enqueue
| 1.48% 009 [k] dma_sync_single_for_device
| 1.47% 009 [k] ixgbe_alloc_rx_buffers
| 1.39% 009 [k] dma_sync_single_for_cpu
| 1.33% 009 [k] cpu_map_enqueue
| 1.19% 003 [k] __xdp_return
| 0.66% 003 [k] __switch_to
I'm going to repost the series once the merge window closes unless there
is something you want me to do.
> --Jesper
Sebastian
Powered by blists - more mailing lists