Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 18 Dec 2009 14:48:45 +0300
From:      "Alexander Zagrebin" <alexz@visp.ru>
To:        "'Andriy Gapon'" <avg@icyb.net.ua>
Cc:        freebsd-current@freebsd.org
Subject:   RE: 8.0-RELEASE: disk IO temporarily hangs up (ZFS or ATA related problem)
Message-ID:  <4F5E9203FBE0440780E31C376646F5B0@vosz.local>
In-Reply-To: <4B2B67FB.80705@icyb.net.ua>
References:  <39309F560B98453EBB9AEA0F29D9D80E@vosz.local><4C1C2598-4157-4B04-8DB8-C84F353AB8B8@nevada.net.nz><6FAA390A-1E40-4D7A-AAD5-DC72578CE974@nevada.net.nz>	<200912182027.11632.doconnor@gsoft.com.au><5C4BD0F81D1348B287B2ECD55EF283E1@vosz.local> <4B2B67FB.80705@icyb.net.ua>

next in thread | previous in thread | raw e-mail | index | archive | help
> >> I doubt this is the problem, I have WD10EADS disks in my ZFS 
> >> array and I 
> >> see the same issue.
> >>
> >> It strikes me as extremely unlikely that both of us would have dud 
> >> disks..
> >>
> >> In any case it seems to be a general problem not limited to 
> >> one area of 
> >> the disk so a dud sector is an unlikely reason.
> > 
> > Big thanks for confirmation!
> > Your confirmation is important for me.
> > There should be a way to define where the bug is: in the 
> ata (or filesystem)
> > driver or in the drive's firmware....
> 
> Just another 'me too'.
> >From the moment I started using zfs and till this day I saw 
> this pattern when
> writing lots data to zfs - first high throughput and then 
> idle pause, and so on.

May be it usual write caching? See gstat or iostat output.
At my case gstat shows abnormal value of %busy (usually approx. 180%)
and very long ms/r and ms/w.

-- 
Alexander Zagrebin




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4F5E9203FBE0440780E31C376646F5B0>