Date: Mon, 25 Oct 2010 10:22:01 +0100 From: Pete French <petefrench@ticketswitch.com> To: oberman@es.net, to.my.trociny@gmail.com Cc: pjd@freebsd.org, freebsd-stable@freebsd.org Subject: Re: hast vs ggate+gmirror sychrnoisation speed Message-ID: <E1PAJFh-000Bkx-0o@dilbert.ticketswitch.com> In-Reply-To: <20101022184551.B587D1CC3E@ptavv.es.net>
next in thread | previous in thread | raw e-mail | index | archive | help
> If you are 50ms RTT from the remote system, the default buffer size will > limit you to about 21 Mbps. Formula is Window-size(in bits/sec)/RTT(in > sec.) The result is the absolute maximum possible bandwidth in > bits/sec. Of course, you can replace window size with the bytes/sec and > the result will be in bytes. I've got a ping time of around 100us (ranges from 0.093ms to 0.109ms) So from your formula I should be able to saturate 1 gigabit ether. I was getting around 90 meg/sevond using ggate Am going to experiment now with the recompiled hastd using the buffesr sizes I was using with ggate and see what happens. thanks, -pete.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?E1PAJFh-000Bkx-0o>