From mboxrd@z Thu Jan 1 00:00:00 1970 MIME-Version: 1.0 In-Reply-To: References: <2543e071cd8232fd7ea378f06cb4b3af@quintile.net> Date: Sat, 4 May 2013 11:09:25 -0700 Message-ID: From: Steven Stallion To: Fans of the OS Plan 9 from Bell Labs <9fans@9fans.net> Content-Type: multipart/alternative; boundary=047d7b2e48722cda7904dbe85ee8 Subject: Re: [9fans] anyone put their venti on an SSD? Topicbox-Message-UUID: 5752404e-ead8-11e9-9d60-3106f5b1d025 --047d7b2e48722cda7904dbe85ee8 Content-Type: text/plain; charset=ISO-8859-1 Makes sense. Moving to plan9port had more to do with making better use of the ReadyNAS in the rack than anything else. The performance was a nice if unexpected side-effect. On Friday, May 3, 2013, erik quanstrom wrote: > On Fri May 3 23:27:40 EDT 2013, sstallion@gmail.com wrote: > > > I had originally used a Crucial 32GB SSD years ago and swapped to a 55GB > > OCZ enterprise drive (using sdahci). More recently I've moved my venti > > arenas over to plan9port and have switched over to using the entire SSD > for > > fossil. So far this has been faster than running venti natively - though > I > > still take a replica each night out of paranoia. > > there are many components to the performance here, but i can think of at > least one simple issue. plan 9 loopback tcp can be pretty slow due to > scheduling > issues. (induced by the structure of tcp, not any issue with the > scheduler.) > my atom (which is slightly worse than a d525) gets > > ladd; nettest -l -n 10000 > tcp!192.168.0.136!39769 count 10000; 81920000 bytes in 2.649575 s > @ 29.5 MB/s (0ms) > > so i would imagine that working out how to post a fd to srv would really > help > a lot. not to mention, taking some funk out of configuring the network on > boot. :-) > > - erik > > --047d7b2e48722cda7904dbe85ee8 Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Makes sense. Moving to plan9port had more to do with making better use of t= he ReadyNAS in the rack than anything else. The performance was a nice if u= nexpected side-effect.=A0

On Friday, May 3, 2013, erik = quanstrom wrote:
On Fri May =A03 23:27:40 EDT 2013, sstallion@gmail.com wrote:

> I had originally used a Crucial 32GB SSD years ago and swapped to a 55= GB
> OCZ enterprise drive (using sdahci). More recently I've moved my v= enti
> arenas over to plan9port and have switched over to using the entire SS= D for
> fossil. So far this has been faster than running venti natively - thou= gh I
> still take a replica each night out of paranoia.

there are many components to the performance here, but i can think of at least one simple issue. =A0plan 9 loopback tcp can be pretty slow due to sc= heduling
issues. =A0(induced by the structure of tcp, not any issue with the schedul= er.)
my atom (which is slightly worse than a d525) gets

=A0 =A0 =A0 =A0 ladd; nettest -l -n 10000
=A0 =A0 =A0 =A0 tcp!192.168.0.136!39769 count 10000; 81920000 bytes in 2.64= 9575 s @ 29.5 MB/s (0ms)

so i would imagine that working out how to post a fd to srv would really he= lp
a lot. =A0not to mention, taking some funk out of configuring the network o= n
boot. =A0:-)

- erik

--047d7b2e48722cda7904dbe85ee8--