From: Eric Dumazet <edumazet@google.com>
To: moshe@mellanox.com
Cc: Tariq Toukan <tariqt@mellanox.com>,
Eric Dumazet <eric.dumazet@gmail.com>,
aring@mojatatu.com, David Miller <davem@davemloft.net>,
netdev <netdev@vger.kernel.org>, Florian Westphal <fw@strlen.de>,
Herbert Xu <herbert@gondor.apana.org.au>,
Thomas Graf <tgraf@suug.ch>,
Jesper Dangaard Brouer <brouer@redhat.com>,
Alexander Aring <alex.aring@gmail.com>,
Stefan Schmidt <stefan@osg.samsung.com>,
Kirill Tkhai <ktkhai@virtuozzo.com>,
Eran Ben Elisha <eranbe@mellanox.com>
Subject: Re: [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag
Date: Thu, 31 May 2018 10:05:10 -0400 [thread overview]
Message-ID: <CANn89iJh4_urk440UAWYxr0RvVLjBJ+d4B-hDovSJ+d_0oWfMw@mail.gmail.com> (raw)
In-Reply-To: <0bb2faec-ba8d-51d7-0c1a-12520b9168e8@mellanox.com>
On Thu, May 31, 2018 at 8:18 AM Moshe Shemesh <moshe@mellanox.com> wrote:
>
>
>
> I do see big improvement after changing the 3 parameters as Eric suggested:
> /proc/sys/net/ipv6/ip6frag_time set to 2
> /proc/sys/net/ipv6/ip6frag_low_thresh set to 104857600
> /proc/sys/net/ipv6/ip6frag_high_thresh set to 78643200
>
>
> [root@reg-l-vrt-67100-104 linux-stable]# netperf -H
> fe80::7efe:90ff:fed5:bb48%ens9,inet6 -t udp_stream --
> MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to
> fe80::7efe:90ff:fed5:bb48%ens9 () port 0 AF_INET6
> Socket Message Elapsed Messages
> Size Size Time Okay Errors Throughput
> bytes bytes secs # # 10^6bits/sec
>
> 212992 65507 10.00 156387 0 8194.60
> 212992 10.00 76901 4029.57
>
> #kernel
> Ip6InReceives 7107999 0.0
> Ip6InDelivers 114126 0.0
> Ip6OutRequests 47 0.0
> Ip6ReasmTimeout 5115 0.0
> Ip6ReasmReqds 7107987 0.0
> Ip6ReasmOKs 114114 0.0
> Ip6ReasmFails 1714146 0.0
> ...
> Udp6InDatagrams 112486 0.0
> Udp6InErrors 1629 0.0
> Udp6RcvbufErrors 1629 0.0
> ...
>
> While before these parameters settings I got:
> [root@reg-l-vrt-67100-104 ~]# netperf -H
> fe80::e61d:2dff:feca:c7c3%ens9,inet6 -t udp_stream --
> MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to
> fe80::e61d:2dff:feca:c7c3%ens9 () port 0 AF_INET6
> Socket Message Elapsed Messages
> Size Size Time Okay Errors Throughput
> bytes bytes secs # # 10^6bits/sec
>
> 212992 65507 10.00 145419 0 7620.35
> 212992 10.00 285 14.93
>
> #kernel
> Ip6InReceives 6665965 0.0
> Ip6InDelivers 300 0.0
> Ip6OutRequests 9 0.0
> Ip6ReasmReqds 6665950 0.0
> Ip6ReasmOKs 285 0.0
> Ip6ReasmFails 6650890 0.0
> ...
> Udp6InDatagrams 286 0.0
>
>
> however, before the patchset, I got much better results:
> [root@reg-l-vrt-67100-104 linux-stable]# netperf -H
> fe80::7efe:90ff:fed5:bb48%ens9,inet6 -t udp_stream --
> MIGRATED UDP STREAM TEST from ::0 (::) port 0 AF_INET6 to
> fe80::7efe:90ff:fed5:bb48%ens9 () port 0 AF_INET6
> Socket Message Elapsed Messages
> Size Size Time Okay Errors Throughput
> bytes bytes secs # # 10^6bits/sec
>
> 212992 65507 10.00 158935 0 8328.32
> 212992 10.00 144652 7579.88
>
>
> #kernel
> Ip6InReceives 7088903 0.0
> Ip6InDelivers 154117 0.0
> Ip6OutRequests 9 0.0
> Ip6ReasmReqds 7088889 0.0
> Ip6ReasmOKs 154103 0.0
> ...
> Udp6InDatagrams 144653 0.0
> Udp6InErrors 9451 0.0
> Udp6RcvbufErrors 9451 0.0
>
>
Hi Moshe
Your environment seems to be very lossy.
Frags and packets losses do not mix well, there is nothing really
magic we can do with that,
unless we can reserve GB of memory for frags.
Which is exactly was the reason for my patches in the first place.
Thanks.
next prev parent reply other threads:[~2018-05-31 14:05 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-03-31 19:58 [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 01/19] ipv6: frag: remove unused field Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 02/19] inet: frags: change inet_frags_init_net() return value Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 03/19] inet: frags: add a pointer to struct netns_frags Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 04/19] inet: frags: refactor ipv6_frag_init() Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 05/19] inet: frags: refactor lowpan_net_frag_init() Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 06/19] inet: frags: refactor ipfrag_init() Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 07/19] rhashtable: add schedule points Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 08/19] inet: frags: use rhashtables for reassembly units Eric Dumazet
2018-04-16 12:54 ` Stefan Schmidt
2018-03-31 19:58 ` [PATCH v4 net-next 09/19] inet: frags: remove some helpers Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 10/19] inet: frags: get rif of inet_frag_evicting() Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 11/19] inet: frags: remove inet_frag_maybe_warn_overflow() Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 12/19] inet: frags: break the 2GB limit for frags storage Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 13/19] inet: frags: do not clone skb in ip_expire() Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 14/19] ipv6: frags: rewrite ip6_expire_frag_queue() Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 15/19] rhashtable: reorganize struct rhashtable layout Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 16/19] inet: frags: reorganize struct netns_frags Eric Dumazet
2018-03-31 19:58 ` [PATCH v4 net-next 17/19] inet: frags: get rid of ipfrag_skb_cb/FRAG_CB Eric Dumazet
2018-04-01 3:02 ` kbuild test robot
2018-03-31 19:58 ` [PATCH v4 net-next 18/19] ipv6: frags: get rid of ip6frag_skb_cb/FRAG6_CB Eric Dumazet
2018-03-31 19:59 ` [PATCH v4 net-next 19/19] inet: frags: get rid of nf_ct_frag6_skb_cb/NFCT_FRAG6_CB Eric Dumazet
2018-04-01 3:25 ` [PATCH v4 net-next 00/19] inet: frags: bring rhashtables to IP defrag David Miller
2018-05-28 9:12 ` Tariq Toukan
2018-05-28 14:52 ` Alexander Aring
2018-05-28 16:09 ` Eric Dumazet
2018-05-30 7:20 ` Tariq Toukan
2018-05-30 7:36 ` Eric Dumazet
2018-05-30 14:42 ` Tariq Toukan
2018-05-31 12:18 ` Moshe Shemesh
2018-05-31 14:05 ` Eric Dumazet [this message]
2018-05-30 9:20 ` Jesper Dangaard Brouer
2018-05-30 10:36 ` Eric Dumazet
2018-05-30 10:56 ` Eric Dumazet
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CANn89iJh4_urk440UAWYxr0RvVLjBJ+d4B-hDovSJ+d_0oWfMw@mail.gmail.com \
--to=edumazet@google.com \
--cc=alex.aring@gmail.com \
--cc=aring@mojatatu.com \
--cc=brouer@redhat.com \
--cc=davem@davemloft.net \
--cc=eranbe@mellanox.com \
--cc=eric.dumazet@gmail.com \
--cc=fw@strlen.de \
--cc=herbert@gondor.apana.org.au \
--cc=ktkhai@virtuozzo.com \
--cc=moshe@mellanox.com \
--cc=netdev@vger.kernel.org \
--cc=stefan@osg.samsung.com \
--cc=tariqt@mellanox.com \
--cc=tgraf@suug.ch \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.