Re: [PATCH] softirq: let ksoftirqd do its job

From	Rick Jones <rick.jones2@hpe.com>
Newsgroups	linux.kernel
Subject	Re: [PATCH] softirq: let ksoftirqd do its job
Date	2016-09-01 01:40 +0200
Message-ID	<scngR-sq-13@gated-at.bofh.it> (permalink)
References	(9 earlier) <sckCm-7aI-11@gated-at.bofh.it> <sclI6-7NG-31@gated-at.bofh.it> <scmb7-8fs-5@gated-at.bofh.it> <scmut-8mg-19@gated-at.bofh.it> <scmXv-kA-5@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On 08/31/2016 04:11 PM, Eric Dumazet wrote:
> On Wed, 2016-08-31 at 15:47 -0700, Rick Jones wrote:
>> With regard to drops, are both of you sure you're using the same socket
>> buffer sizes?
>
> Does it really matter ?

At least at points in the past I have seen different drop counts at the 
SO_RCVBUF based on using (sometimes much) larger sizes.  The hypothesis 
I was operating under at the time was that this dealt with those 
situations where the netserver was held-off from running for "a little 
while" from time to time.  It didn't change things for a sustained 
overload situation though.

>> In the meantime, is anything interesting happening with TCP_RR or
>> TCP_STREAM?
>
> TCP_RR is driven by the network latency, we do not drop packets in the
> socket itself.

I've been of the opinion it (single stream) is driven by path length. 
Sometimes by NIC latency.  But then I'm almost always measuring in the 
LAN rather than across the WAN.

happy benchmarking,

rick

Thread

[PATCH] softirq: let ksoftirqd do its job Eric Dumazet <eric.dumazet@gmail.com> - 2016-08-31 19:50 +0200
  Re: [PATCH] softirq: let ksoftirqd do its job Jesper Dangaard Brouer <jbrouer@redhat.com> - 2016-08-31 21:50 +0200
    Re: [PATCH] softirq: let ksoftirqd do its job Eric Dumazet <eric.dumazet@gmail.com> - 2016-08-31 22:50 +0200
      Re: [PATCH] softirq: let ksoftirqd do its job Jesper Dangaard Brouer <jbrouer@redhat.com> - 2016-09-01 00:00 +0200
        Re: [PATCH] softirq: let ksoftirqd do its job Eric Dumazet <eric.dumazet@gmail.com> - 2016-09-01 00:30 +0200
          Re: [PATCH] softirq: let ksoftirqd do its job Rick Jones <rick.jones2@hpe.com> - 2016-09-01 00:50 +0200
            Re: [PATCH] softirq: let ksoftirqd do its job Eric Dumazet <eric.dumazet@gmail.com> - 2016-09-01 01:20 +0200
              Re: [PATCH] softirq: let ksoftirqd do its job Rick Jones <rick.jones2@hpe.com> - 2016-09-01 01:40 +0200
                Re: [PATCH] softirq: let ksoftirqd do its job Jesper Dangaard Brouer <brouer@redhat.com> - 2016-09-01 12:40 +0200
                Re: [PATCH] softirq: let ksoftirqd do its job Eric Dumazet <eric.dumazet@gmail.com> - 2016-09-01 15:10 +0200
        Re: [PATCH] softirq: let ksoftirqd do its job Jesper Dangaard Brouer <brouer@redhat.com> - 2016-09-01 13:10 +0200
          Re: [PATCH] softirq: let ksoftirqd do its job Hannes Frederic Sowa <hannes@redhat.com> - 2016-09-01 13:20 +0200
          Re: [PATCH] softirq: let ksoftirqd do its job Peter Zijlstra <peterz@infradead.org> - 2016-09-01 14:00 +0200
            Re: [PATCH] softirq: let ksoftirqd do its job Jesper Dangaard Brouer <brouer@redhat.com> - 2016-09-01 14:40 +0200
              Re: [PATCH] softirq: let ksoftirqd do its job Jesper Dangaard Brouer <brouer@redhat.com> - 2016-09-01 14:40 +0200
                Re: [PATCH] softirq: let ksoftirqd do its job Peter Zijlstra <peterz@infradead.org> - 2016-09-01 14:50 +0200
                Re: [PATCH] softirq: let ksoftirqd do its job Jesper Dangaard Brouer <brouer@redhat.com> - 2016-09-01 15:40 +0200
                Re: [PATCH] softirq: let ksoftirqd do its job Peter Zijlstra <peterz@infradead.org> - 2016-09-01 17:30 +0200
                Re: [PATCH] softirq: let ksoftirqd do its job Jesper Dangaard Brouer <brouer@redhat.com> - 2016-09-02 10:40 +0200
                Re: [PATCH] softirq: let ksoftirqd do its job Eric Dumazet <eric.dumazet@gmail.com> - 2016-09-01 15:10 +0200
                Re: [PATCH] softirq: let ksoftirqd do its job Hannes Frederic Sowa <hannes@redhat.com> - 2016-09-01 15:10 +0200
                Re: [PATCH] softirq: let ksoftirqd do its job Eric Dumazet <eric.dumazet@gmail.com> - 2016-09-01 15:30 +0200
      Re: [PATCH] softirq: let ksoftirqd do its job Hannes Frederic Sowa <hannes@redhat.com> - 2016-09-01 14:10 +0200
        Re: [PATCH] softirq: let ksoftirqd do its job Eric Dumazet <eric.dumazet@gmail.com> - 2016-09-01 15:00 +0200
  Re: [PATCH] softirq: let ksoftirqd do its job Hannes Frederic Sowa <hannes@redhat.com> - 2016-09-01 14:10 +0200
  Re: [PATCH] softirq: let ksoftirqd do its job David Miller <davem@davemloft.net> - 2016-09-02 08:40 +0200

csiph-web