Skip site navigation (1)Skip section navigation (2)
Date:      Sat, 23 Jun 2001 12:05:31 -0500
From:      Jonathan Lemon <jlemon@flugsvamp.com>
To:        Matt Dillon <dillon@earth.backplane.com>
Cc:        Alfred Perlstein <bright@sneakerz.org>, Mike Silbersack <silby@FreeBSD.ORG>, cvs-committers@FreeBSD.ORG, cvs-all@FreeBSD.ORG, jlemon@FreeBSD.ORG, bmilekic@FreeBSD.ORG
Subject:   Re: cvs commit: src/sys/netinet tcp_input.c tcp_output.c tcp_subr.c tcp_timer.c tcp_usrreq.c tcp_var.h
Message-ID:  <20010623120531.V33375@prism.flugsvamp.com>
In-Reply-To: <200106231633.f5NGXqp72502@earth.backplane.com>
References:  <200106230321.f5N3Llv09510@freefall.freebsd.org> <20010623102801.F57058@sneakerz.org> <200106231633.f5NGXqp72502@earth.backplane.com>

next in thread | previous in thread | raw e-mail | index | archive | help
On Sat, Jun 23, 2001 at 09:33:52AM -0700, Matt Dillon wrote:
> 
> :* Mike Silbersack <silby@FreeBSD.org> [010622 22:21] wrote:
> :> silby       2001/06/22 20:21:47 PDT
> :> 
> :>   Modified files:
> :>     sys/netinet          tcp_input.c tcp_output.c tcp_subr.c 
> :>                          tcp_timer.c tcp_usrreq.c tcp_var.h 
> :>   Log:
> :>   Eliminate the allocation of a tcp template structure for each
> :>   connection.  The information contained in a tcptemp can be
> :>   reconstructed from a tcpcb when needed.
> :
> :I may have missed it, but did you guys happen to run a perf test
> :on this along the same lines as the excellent work done to benchmark
> :the new mbuf allocator?
> :
> :My main concern is that a simple bcopy is cheaper than digging into
> :the inpcb/tcpcb to fill in the packet info.
> :
> :There's patches avaiable to use a smaller zone-like allocation
> :strategy to conserve storage space that we may want to use instead
> :of eliminating it completely in case there is noticeable performance
> :penalties.
> :
> :Could someone generate those lovely numbers we saw earlier this
> :week with and without this patch?
> :
> :-Alfred
> 
>     I think the new way might even be faster.  If the in_pseudo() call could
>     be optimized, the new way would definitely be faster.  The problem with

The in_pseudo() call _is_ optimized, at least to some point; its
inline assembly in sys/i386/include/in_cksum.h.

-- 
Jonathan

To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe cvs-all" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20010623120531.V33375>