Linux Netfilter development
 help / color / mirror / Atom feed
From: Pablo Neira Ayuso <pablo@netfilter.org>
To: Florian Westphal <fw@strlen.de>
Cc: netfilter-devel@vger.kernel.org, Nadia Pinaeva <n.m.pinaeva@gmail.com>
Subject: Re: [PATCH nf-next] netfilter: nf_tables: store new sets in dedicated list
Date: Mon, 19 Aug 2024 18:33:30 +0200	[thread overview]
Message-ID: <ZsNz2lTEqLsiIn6R@calendula> (raw)
In-Reply-To: <20240710085835.1957-1-fw@strlen.de>

On Wed, Jul 10, 2024 at 10:58:29AM +0200, Florian Westphal wrote:
> nft_set_lookup_byid() is very slow when transaction becomes large, due to
> walk of the transaction list.
> 
> Add a dedicated list that contains only the new sets.
> 
> Before: nft -f ruleset 0.07s user 0.00s system 0% cpu 1:04.84 total
> After: nft -f ruleset 0.07s user 0.00s system 0% cpu 30.115 total
> 
> .. where ruleset contains ~10 sets with ~100k elements.
> The above number is for a combined flush+reload of the ruleset.
> 
> With previous flush, even the first NEWELEM has to walk through a few
> hundred thousands of DELSET(ELEM) transactions before the first NEWSET
> object. To cope with random-order-newset-newsetelem we'd need to replace
> commit_set_list with a hashtable.
> 
> Expectation is that a NEWELEM operation refers to the most recently added
> set, so last entry of the dedicated list should be the set we want.
> 
> NB: This is not a bug fix per se (functionality is fine), but with
> larger transaction batches list search takes forever, so it would be
> nice to speed this up for -stable too, hence adding a "fixes" tag.

applied to nf-next, thanks

      reply	other threads:[~2024-08-19 16:33 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-07-10  8:58 [PATCH nf-next] netfilter: nf_tables: store new sets in dedicated list Florian Westphal
2024-08-19 16:33 ` Pablo Neira Ayuso [this message]

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=ZsNz2lTEqLsiIn6R@calendula \
    --to=pablo@netfilter.org \
    --cc=fw@strlen.de \
    --cc=n.m.pinaeva@gmail.com \
    --cc=netfilter-devel@vger.kernel.org \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox