Date: Mon, 25 Oct 2010 15:12:42 +0300 From: Mikolaj Golub <to.my.trociny@gmail.com> To: Pete French <petefrench@ticketswitch.com> Cc: freebsd-stable@freebsd.org Subject: Re: hast vs ggate+gmirror sychrnoisation speed Message-ID: <86wrp6jwsl.fsf@zhuzha.ua1> In-Reply-To: <E1PAKiE-000CdG-C2@dilbert.ticketswitch.com> (Pete French's message of "Mon, 25 Oct 2010 11:55:34 %2B0100") References: <E1PAKiE-000CdG-C2@dilbert.ticketswitch.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, 25 Oct 2010 11:55:34 +0100 Pete French wrote: >> You could change the values and recompile hastd :-). It would be interesting >> to know about the results of your experiment (if you do). PF> I changed the buffer sizes to the same as I was using for ggate, but the speed PF> is still the same - 44meg/second (about half of what the link can do) You can check if the queue size is an issue monitoring with netstat Recv-Q and Send-Q for hastd connections during the test. Running something like below: while sleep 1; do netstat -na |grep '\.8457.*ESTAB'; done Also tcpdump may help :-) -- Mikolaj Golub
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?86wrp6jwsl.fsf>