netfilter-devel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Thomas Graf <tgraf@suug.ch>
To: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: alexei.starovoitov@gmail.com, herbert@gondor.apana.org.au,
	kaber@trash.net, davem@davemloft.net, ying.xue@windriver.com,
	netdev@vger.kernel.org, netfilter-devel@vger.kernel.org,
	josh@joshtriplett.org
Subject: Re: Ottawa and slow hash-table resize
Date: Mon, 23 Feb 2015 21:00:37 +0000	[thread overview]
Message-ID: <20150223210037.GA806@casper.infradead.org> (raw)
In-Reply-To: <20150223184904.GA24955@linux.vnet.ibm.com>

On 02/23/15 at 10:49am, Paul E. McKenney wrote:
> Hello!
> 
> Alexei mentioned that there was some excitement a couple of weeks ago in
> Ottawa, something about the resizing taking forever when there were large
> numbers of concurrent additions.  One approach comes to mind:
> 
> o	Currently, the hash table does not allow additions concurrently
> 	with resize operations.  One way to allow this would be to
> 	have the addition operations add to the new hash table at the
> 	head of the lists.  This would clearly require also updating the
> 	pointers used to control the unzip operation.

I've already added this. Additions and removals can occur in
parallel to the resize and will go to the head of the new chain.

> o	Count the number of entries added during the resize operation.
> 	Then, at the end of the resize operation, if enough entries have
> 	been added, do a resize, but by multiple factors of two if
> 	need be.
> 
> This should allow the table to take arbitrarily large numbers of updates
> during a resize operation.  There are some other possibilities if this
> approach does not work out.

The main problem is rapid growth of the table on small tables,
e.g. shift 4-6. Going through multiple grow cycles while
thousands of entries are being added will lead to long chains
which will require multiple RCU grace periods per growth and
thus slowing things down.

The bucket locking is designed to ignore the highest order bit
of the hash to make sure that a single bucket lock in the new
double sized table protectes both buckets which map to the 
same bucket in the old table. This simplifies locking a lot and
does not require nested locking. Growing by more than a factor
of two would require to manually lock all buckets to which
entries in the old bucket may map to.

However, we do not want to grow the bucket lock mask
indefinitely so we could for example growth quicker if the
lock mask allows. Needs some more thought but it's definitely
doable and we need to provide users of the hash table with
ways to find a balance according to their needs.

  parent reply	other threads:[~2015-02-23 21:00 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-02-23 18:49 Ottawa and slow hash-table resize Paul E. McKenney
2015-02-23 19:12 ` josh
2015-02-23 21:03   ` Thomas Graf
2015-02-23 21:52     ` Paul E. McKenney
2015-02-23 22:32       ` David Miller
2015-02-23 23:06         ` Paul E. McKenney
2015-02-24  8:37           ` Thomas Graf
2015-02-24 10:39             ` Patrick McHardy
2015-02-24 10:46               ` David Laight
2015-02-24 10:48                 ` Patrick McHardy
2015-02-24 17:09               ` David Miller
2015-02-24 17:50                 ` Thomas Graf
2015-02-24 18:26                   ` David Miller
2015-02-24 18:45                     ` josh
2015-02-24 22:34                       ` Thomas Graf
2015-02-25  8:56                         ` Herbert Xu
2015-02-25 17:38                           ` Thomas Graf
2015-02-24 18:33                   ` josh
2015-02-25  8:55                 ` Herbert Xu
2015-02-25 17:38                   ` Thomas Graf
2015-02-23 21:00 ` Thomas Graf [this message]
2015-02-23 22:35   ` Paul E. McKenney
2015-02-24  8:59 ` Thomas Graf
2015-02-24  9:38   ` Daniel Borkmann
2015-02-24 10:42     ` Patrick McHardy
2015-02-24 16:14       ` Josh Hunt
2015-02-24 16:25         ` Patrick McHardy
2015-02-24 16:57           ` David Miller
  -- strict thread matches above, loose matches on Subject: below --
2015-02-23 22:17 Alexei Starovoitov
2015-02-23 22:34 ` David Miller
2015-02-23 22:37 ` Paul E. McKenney
2015-02-23 23:07 Alexei Starovoitov
2015-02-23 23:15 ` David Miller

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=20150223210037.GA806@casper.infradead.org \
    --to=tgraf@suug.ch \
    --cc=alexei.starovoitov@gmail.com \
    --cc=davem@davemloft.net \
    --cc=herbert@gondor.apana.org.au \
    --cc=josh@joshtriplett.org \
    --cc=kaber@trash.net \
    --cc=netdev@vger.kernel.org \
    --cc=netfilter-devel@vger.kernel.org \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=ying.xue@windriver.com \
    /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).