[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <e224073d-4c92-9a11-5385-4c38b06e6d15@kernel.org>
Date: Thu, 12 Jan 2023 21:03:55 -0700
From: David Ahern <dsahern@...nel.org>
To: Jon Maxwell <jmaxwell37@...il.com>, davem@...emloft.net
Cc: edumazet@...gle.com, kuba@...nel.org, pabeni@...hat.com,
yoshfuji@...ux-ipv6.org, martin.lau@...nel.org,
joel@...lfernandes.org, paulmck@...nel.org, eyal.birger@...il.com,
netdev@...r.kernel.org, linux-kernel@...r.kernel.org,
Andrea Mayer <andrea.mayer@...roma2.it>
Subject: Re: [net-next v2] ipv6: remove max_size check inline with ipv4
On 1/11/23 6:25 PM, Jon Maxwell wrote:
> v2: Correct syntax error in net/ipv6/route.c
>
> In ip6_dst_gc() replace:
>
> if (entries > gc_thresh)
>
> With:
>
> if (entries > ops->gc_thresh)
>
> Sending Ipv6 packets in a loop via a raw socket triggers an issue where a
> route is cloned by ip6_rt_cache_alloc() for each packet sent. This quickly
> consumes the Ipv6 max_size threshold which defaults to 4096 resulting in
> these warnings:
>
> [1] 99.187805] dst_alloc: 7728 callbacks suppressed
> [2] Route cache is full: consider increasing sysctl net.ipv6.route.max_size.
> .
> .
> [300] Route cache is full: consider increasing sysctl net.ipv6.route.max_size.
>
> When this happens the packet is dropped and sendto() gets a network is
> unreachable error:
>
> # ./a.out -s
>
> remaining pkt 200557 errno 101
> remaining pkt 196462 errno 101
> .
> .
> remaining pkt 126821 errno 101
>
> Implement David Aherns suggestion to remove max_size check seeing that Ipv6
> has a GC to manage memory usage. Ipv4 already does not check max_size.
>
> Here are some memory comparisons for Ipv4 vs Ipv6 with the patch:
>
> Test by running 5 instances of a program that sends UDP packets to a raw
> socket 5000000 times. Compare Ipv4 and Ipv6 performance with a similar
> program.
>
> Ipv4:
>
> Before test:
>
> # grep -e Slab -e Free /proc/meminfo
> MemFree: 29427108 kB
> Slab: 237612 kB
>
> # grep dst_cache /proc/slabinfo
> ip6_dst_cache 1912 2528 256 32 2 : tunables 0 0 0
> xfrm_dst_cache 0 0 320 25 2 : tunables 0 0 0
> ip_dst_cache 2881 3990 192 42 2 : tunables 0 0 0
>
> During test:
>
> # grep -e Slab -e Free /proc/meminfo
> MemFree: 29417608 kB
> Slab: 247712 kB
>
> # grep dst_cache /proc/slabinfo
> ip6_dst_cache 1912 2528 256 32 2 : tunables 0 0 0
> xfrm_dst_cache 0 0 320 25 2 : tunables 0 0 0
> ip_dst_cache 44394 44394 192 42 2 : tunables 0 0 0
>
> After test:
>
> # grep -e Slab -e Free /proc/meminfo
> MemFree: 29422308 kB
> Slab: 238104 kB
>
> # grep dst_cache /proc/slabinfo
> ip6_dst_cache 1912 2528 256 32 2 : tunables 0 0 0
> xfrm_dst_cache 0 0 320 25 2 : tunables 0 0 0
> ip_dst_cache 3048 4116 192 42 2 : tunables 0 0 0
>
> Ipv6 with patch:
>
> Errno 101 errors are not observed anymore with the patch.
>
> Before test:
>
> # grep -e Slab -e Free /proc/meminfo
> MemFree: 29422308 kB
> Slab: 238104 kB
>
> # grep dst_cache /proc/slabinfo
> ip6_dst_cache 1912 2528 256 32 2 : tunables 0 0 0
> xfrm_dst_cache 0 0 320 25 2 : tunables 0 0 0
> ip_dst_cache 3048 4116 192 42 2 : tunables 0 0 0
>
> During Test:
>
> # grep -e Slab -e Free /proc/meminfo
> MemFree: 29431516 kB
> Slab: 240940 kB
>
> # grep dst_cache /proc/slabinfo
> ip6_dst_cache 11980 12064 256 32 2 : tunables 0 0 0
> xfrm_dst_cache 0 0 320 25 2 : tunables 0 0 0
> ip_dst_cache 3048 4116 192 42 2 : tunables 0 0 0
>
> After Test:
>
> # grep -e Slab -e Free /proc/meminfo
> MemFree: 29441816 kB
> Slab: 238132 kB
>
> # grep dst_cache /proc/slabinfo
> ip6_dst_cache 1902 2432 256 32 2 : tunables 0 0 0
> xfrm_dst_cache 0 0 320 25 2 : tunables 0 0 0
> ip_dst_cache 3048 4116 192 42 2 : tunables 0 0 0
>
> Tested-by: Andrea Mayer <andrea.mayer@...roma2.it>
> Signed-off-by: Jon Maxwell <jmaxwell37@...il.com>
> ---
> include/net/dst_ops.h | 2 +-
> net/core/dst.c | 8 ++------
> net/ipv6/route.c | 13 +++++--------
> 3 files changed, 8 insertions(+), 15 deletions(-)
>
Thanks for the data in the commit message.
Reviewed-by: David Ahern <dsahern@...nel.org>
Powered by blists - more mailing lists