Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 14 Jun 2011 18:07:28 +0300
From:      Daniel Kalchev <daniel@digsys.bg>
To:        Mikolaj Golub <trociny@freebsd.org>
Cc:        pjd@freebsd.org, freebsd-stable@freebsd.org
Subject:   Re: HAST instability
Message-ID:  <4DF77930.3060203@digsys.bg>
In-Reply-To: <86ei2wmpg4.fsf@in138.ua3>
References:  <4DE21C64.8060107@digsys.bg> <4DE3ACF8.4070809@digsys.bg>	<86d3j02fox.fsf@kopusha.home.net> <4DE4E43B.7030302@digsys.bg>	<86zkm3t11g.fsf@in138.ua3> <4DE5048B.3080206@digsys.bg>	<4DE5D535.20804@digsys.bg> <4DE8FE78.6070401@digsys.bg>	<4DE90955.9020505@digsys.bg> <86zklp8vmg.fsf@kopusha.home.net>	<86vcwd8vj8.fsf@kopusha.home.net> <4DF7647F.7020901@digsys.bg> <86ei2wmpg4.fsf@in138.ua3>

next in thread | previous in thread | raw e-mail | index | archive | help


On 14.06.11 17:56, Mikolaj Golub wrote:
> It has turned out that automatic receive buffer sizing works only for
> connections in ESTABLISHED state. And with small receive buffer the connection
> might stuck sending data only via TCP window probes -- one byte every few
> seconds (see "Scenario to make recv(MSG_WAITALL) stuck" in net@ for details).
>
I have tried some TCP/IP tuning to help utilize the faster network, but 
for the moment it is likely local disks limit the throughput to about 
230 MB/sec peak. The peaks now are the same as before, but now the total 
performance is better.

However, it may turn out that single TCP/IP session across 10Gbit 
network would not be able to achieve very high throughput. It may be 
beneficial to support multiple parallel TCP/IP connections between 
primary/slave in order to utilize faster networks.

Daniel



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4DF77930.3060203>