Date: Thu, 30 Sep 2010 21:23:58 +0300 From: Andriy Gapon <avg@icyb.net.ua> To: "R.P. Aditya" <aditya@grot.org> Cc: freebsd-performance@FreeBSD.org Subject: Re: monitoring per-process disk io Message-ID: <4CA4D5BE.5030502@icyb.net.ua> In-Reply-To: <slrnia9k5s.2psp.aditya@tiny.grot.org> References: <slrnia9k5s.2psp.aditya@tiny.grot.org>
next in thread | previous in thread | raw e-mail | index | archive | help
on 30/09/2010 21:02 R.P. Aditya said the following: > I'm trying to monitor, over the long-term, per-process disk IO (a > counter of bytes read and written per pid would be ideal). > > I currently monitor per pid cpu and memory usage using the SNMP > Host-Resources MIB, however I don't see any oids for io (disk or > otherwise) per oid. > > The closest I've come to finding what I want -- per-process disk IO > stats -- is the Linux tool dstat -- something like "screenshot 3" at: > > http://dag.wieers.com/home-made/dstat/ > > which is the output of: > > dstat -c --top-cpu -d --top-bio --top-latency > > would be good...iostat, vmstat don't give that sort of info... > > any suggestions or hints? 1) top -m io 2) rolling your own customized monitoring using dtrace -- Andriy Gapon
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4CA4D5BE.5030502>