From: Patrick McHardy <kaber@trash.net>
To: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Thomas Graf <tgraf@suug.ch>,
David Laight <David.Laight@ACULAB.COM>,
"davem@davemloft.net" <davem@davemloft.net>,
"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
"paulmck@linux.vnet.ibm.com" <paulmck@linux.vnet.ibm.com>,
"edumazet@google.com" <edumazet@google.com>,
"john.r.fastabend@intel.com" <john.r.fastabend@intel.com>,
"josh@joshtriplett.org" <josh@joshtriplett.org>,
"netfilter-devel@vger.kernel.org"
<netfilter-devel@vger.kernel.org>
Subject: Re: [PATCH 7/9] rhashtable: Per bucket locks & deferred expansion/shrinking
Date: Fri, 16 Jan 2015 21:31:56 +0000 [thread overview]
Message-ID: <20150116213156.GA7109@acer.localdomain> (raw)
In-Reply-To: <20150116204921.GA14833@gondor.apana.org.au>
On 17.01, Herbert Xu wrote:
> On Fri, Jan 16, 2015 at 07:35:57PM +0000, Patrick McHardy wrote:
> >
> > Well, rhashtable (or generally resizing) will make it a lot worse.
> > Usually we at worst miss entries which were added during the dump,
> > which is made up by the notifications.
> >
> > With resizing we might miss anything, its completely undeterministic.
>
> Correct. If you want to have a stable dump you will need to have
> data structure outside the hash table. For example, with xfrm_state
> we do it with a linked list.
That's certainly one possibility, however since we might have a huge
number of elements, its very undesirable to use even a little memory
for this.
I'm tending towards deferring resize operations while dumps are in
progress. Since we only allow dumps by root, it seems the worst
thing that can happen is that we run using a non optimal hash,
which is comparable to having a badly structured ruleset.
next prev parent reply other threads:[~2015-01-16 21:32 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <cover.1418647641.git.tgraf@suug.ch>
2014-12-15 12:51 ` [PATCH 1/9] rhashtable: Do hashing inside of rhashtable_lookup_compare() Thomas Graf
2014-12-15 12:51 ` [PATCH 5/9] nft_hash: Remove rhashtable_remove_pprev() Thomas Graf
2014-12-15 12:51 ` [PATCH 7/9] rhashtable: Per bucket locks & deferred expansion/shrinking Thomas Graf
2015-01-16 15:34 ` Patrick McHardy
2015-01-16 15:58 ` Thomas Graf
2015-01-16 16:03 ` Patrick McHardy
2015-01-16 16:15 ` Thomas Graf
2015-01-16 16:32 ` Patrick McHardy
2015-01-16 16:38 ` Thomas Graf
2015-01-16 16:51 ` Patrick McHardy
2015-01-16 16:43 ` David Laight
2015-01-16 16:53 ` Thomas Graf
2015-01-16 18:36 ` Patrick McHardy
2015-01-16 19:18 ` Thomas Graf
2015-01-16 19:35 ` Patrick McHardy
2015-01-16 20:46 ` Pablo Neira Ayuso
2015-01-16 20:53 ` Patrick McHardy
2015-01-19 9:01 ` Paul E. McKenney
2015-01-21 5:23 ` Herbert Xu
2015-01-21 5:29 ` Paul E. McKenney
2015-01-21 5:30 ` Herbert Xu
2015-01-21 5:36 ` Paul E. McKenney
2015-01-16 20:49 ` Herbert Xu
2015-01-16 21:31 ` Patrick McHardy [this message]
2015-01-17 0:33 ` Herbert Xu
2015-01-17 8:06 ` Patrick McHardy
2015-01-17 9:32 ` Herbert Xu
2015-01-17 9:51 ` Patrick McHardy
2015-01-17 10:13 ` Herbert Xu
2015-01-17 11:56 ` Patrick McHardy
2015-01-16 21:36 ` Thomas Graf
2015-01-16 22:07 ` Patrick McHardy
2015-01-16 23:34 ` Thomas Graf
2015-01-17 8:02 ` Patrick McHardy
2015-01-19 12:58 ` Thomas Graf
2015-01-19 9:45 ` David Laight
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=20150116213156.GA7109@acer.localdomain \
--to=kaber@trash.net \
--cc=David.Laight@ACULAB.COM \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=herbert@gondor.apana.org.au \
--cc=john.r.fastabend@intel.com \
--cc=josh@joshtriplett.org \
--cc=netdev@vger.kernel.org \
--cc=netfilter-devel@vger.kernel.org \
--cc=paulmck@linux.vnet.ibm.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 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).