linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: David Miller <davem@davemloft.net>
To: fw@strlen.de
Cc: linux@stwm.de, netdev@vger.kernel.org,
	steffen.klassert@secunet.com, linux-kernel@vger.kernel.org,
	torvalds@linux-foundation.org, christophe.gouault@6wind.com
Subject: Re: Regression: kernel 4.14 an later very slow with many ipsec tunnels
Date: Thu, 13 Sep 2018 14:12:39 -0700 (PDT)	[thread overview]
Message-ID: <20180913.141239.123063658850697631.davem@davemloft.net> (raw)
In-Reply-To: <20180913210325.5usfj2rorvuvtyc7@breakpoint.cc>

From: Florian Westphal <fw@strlen.de>
Date: Thu, 13 Sep 2018 23:03:25 +0200

> I am staring at b58555f1767c9f4e330fcf168e4e753d2d9196e0
> but can't figure out how to configure that away from the
> 'no hashing for prefixed policies' default or why we even have
> policy_inexact in first place :/
> 
> I'll look at this again tomorrow.

The inexact list exists to handle prefixed input keys.

At the time that I wrote all of the control plane hash table
stuff, configurations I could find consisted of:

1) Entires with non-prefixed keys, which are easy to hash.
   The number of entries could be large (e.g. cell phone
   network)

2) A very small number of prefixed policies.

So hashing, when possible, falling back to the linked list
for prefixed stuff.

Beforehand we only had the linked list :-)

  reply	other threads:[~2018-09-13 21:12 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-09-13 11:30 Wolfgang Walter
2018-09-13 13:58 ` Florian Westphal
2018-09-13 15:46   ` Wolfgang Walter
2018-09-13 16:38     ` Florian Westphal
2018-09-13 17:23       ` David Miller
2018-09-13 21:03         ` Florian Westphal
2018-09-13 21:12           ` David Miller [this message]
2018-09-14  5:06           ` Steffen Klassert
2018-09-14  5:54             ` Florian Westphal
2018-09-14  6:01               ` Steffen Klassert
2018-09-14  8:01                 ` Christophe Gouault
2018-09-14 11:49               ` Wolfgang Walter
2018-10-02 14:45               ` Wolfgang Walter
2018-10-02 14:56                 ` Florian Westphal
2018-10-02 17:34                   ` Wolfgang Walter
2018-10-02 21:35                     ` Florian Westphal
2018-10-04 13:57                       ` Wolfgang Walter
2018-10-25  9:38                         ` Wolfgang Walter
2018-10-25 17:34                           ` David Miller
2018-10-25 19:24                             ` Florian Westphal
2018-10-26 12:18                             ` Wolfgang Walter
2018-10-25 22:45                           ` Florian Westphal

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=20180913.141239.123063658850697631.davem@davemloft.net \
    --to=davem@davemloft.net \
    --cc=christophe.gouault@6wind.com \
    --cc=fw@strlen.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux@stwm.de \
    --cc=netdev@vger.kernel.org \
    --cc=steffen.klassert@secunet.com \
    --cc=torvalds@linux-foundation.org \
    --subject='Re: Regression: kernel 4.14 an later very slow with many ipsec tunnels' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).