Date: Wed, 9 Nov 2005 14:27:32 +0000 From: Joao Barros <joao.barros@gmail.com> To: Jeremie Le Hen <jeremie@le-hen.org> Cc: freebsd-performance@freebsd.org Subject: Re: Poor Samba throughput on 6.0 Message-ID: <70e8236f0511090627p24c90400ke39bdb0da222a323@mail.gmail.com> In-Reply-To: <70e8236f0511090517g29b3f887x1b97ef5dec04548@mail.gmail.com> References: <70e8236f0511050457s5ce6d8batf805fbc9edd91360@mail.gmail.com> <20051109060931.GD5188@obiwan.tataz.chchile.org> <70e8236f0511090517g29b3f887x1b97ef5dec04548@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On 11/9/05, Joao Barros <joao.barros@gmail.com> wrote: > On 11/9/05, Jeremie Le Hen <jeremie@le-hen.org> wrote: > > Hi, Joao, > > > > > Last month I started a thread[1] on current@ about this, but I guess = I > > > should have done it here, my apologies for that. > > > > > > After my initial post I did some more testing and I'm going to start > > > clean here with all my findings :) > > > > > > I started with Samba 3 installed on a PIII 733MHz with fxp (82559) an= d > > > a RAID5 consisting of 4 drives connected to an amr. > > > Performance reading or writing was poor, around 5.5MB/s measured on > > > two Windows clients and iostat never topped that by much. > > > cpu was mbufs were available and there were no IRQs shared. > > > To dismiss the amr out of the question I tried with a local IDE > > > attached yielding the same results. > > > I then tested the same on a machine I have at work, an HP Proliant > > > server, Pentium 4 3.06GHz, used SMP instead of GENERIC to use HTT. > > > I could get 8MB/s with 2 read or write simultaneous operations. With = 1 > > > operation I still can only get 6MB/s > > > This machine has 1GB ram and after copying a 700MB file to it it was > > > all cached. > > > A copy to dev/null took 1 second. > > > A copy via samba took the same time as if there was no cache for it. > > > iostat always showed 0.0 during the operation so that pretty much > > > takes disks, controllers, IO out of the picture. > > > > > > Both machines have cpu, IO and mbufs to spare and they still can't us= e > > > them. Why? > > > > I won't be able to help you much, but as almost nobody answered you, > > I take it for the moment in order to ask you some more informations. > > > > Which scheduler are you using, 4BSD or ULE ? It might be worth testing > > the other one and sending us the new benchmark results. > > The testings were all with either GENERIC or SMP thus using 4BSD, I > can try ULE and see if I get any different results. > On a P4 3.06GHz with HTT enabled and ULE I get the same results. I get a flat line at 58% looking at the bandwith in task manager on a Windows 2003 Server while doing a cached read. I can get up to 70% bandwith during writes. Percentages are relative to 100Mbits bandwith. > > > > Also, if you are able to remove a drive from your RAID5, you can try > > R/W performances from/to it, without using amr(4), both with 4BSD and > > ULE. > > I tried using a single drive, an IDE and a SCSI-2 and on 2 machines at > work both with a RAID1. > Even better, there is a part in my initial email where I mention that > having a 700MB file cached (iostat reported no reads) the results were > the same. With this in mind I don't think the problem is at the > storage level. -- Joao Barros
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?70e8236f0511090627p24c90400ke39bdb0da222a323>