[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20150313114018.GA3439@gondor.apana.org.au>
Date: Fri, 13 Mar 2015 22:40:18 +1100
From: Herbert Xu <herbert@...dor.apana.org.au>
To: David Laight <David.Laight@...LAB.COM>
Cc: Thomas Graf <tgraf@...g.ch>,
"netdev@...r.kernel.org" <netdev@...r.kernel.org>
Subject: Re: [PATCH 3/6] rhashtable: Move seed init into bucket_table_alloc
On Fri, Mar 13, 2015 at 11:33:39AM +0000, David Laight wrote:
>
> If the decision to resize a hash table is based on the length
> of the hash chains, then changing the hash function might either
> make that unnecessary or make an immediate resize be needed.
My plan is to trigger a delayed resize (as we do now) if we're
over 75%.
If we get a chain length above 4 then we do an immediate resize
if we're already over 75% and the delayed resize hasn't started
yet, otherwise we do an immediate rehash with no change in the
hash table size.
Note that in my new scheme the rehash will contain two distinct
parts. The first part that is executed immediately will only
involve allocating the hash table.
The hard work of movings across is always performed in the kernel
thread.
Cheers,
--
Email: Herbert Xu <herbert@...dor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists