Date: Wed, 03 Feb 2010 13:48:30 +0100 From: Attila Nagy <bra@fsn.hu> To: =?UTF-8?B?VG9tbWkgTMOkdHRp?= <sty@iki.fi> Cc: freebsd-fs@freebsd.org Subject: Re: Machine stops for some seconds with ZFS Message-ID: <4B69709E.1090601@fsn.hu> In-Reply-To: <f43ef3191002030440j4fa9738fsf360f84771ebb986@mail.gmail.com> References: <4B694689.2030704@fsn.hu> <f43ef3191002030409t16fe0056m9d6c83041d8051@mail.gmail.com> <4B696CB7.7070607@fsn.hu> <f43ef3191002030440j4fa9738fsf360f84771ebb986@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Tommi Lätti wrote: >> I'm not sure about these are being the same. When I see these "stops", >> nothing happens. gstat shows no IO, and everything goes very quiet for some >> painful (10s of) seconds. Also, buildworld doesn't do too heavy IO, at least >> for these drives. >> > > Well that's what I experienced. iostat says 0, machine is kind of > responsive, unless you try to read or write from the zfs pool.. > Oh, that wasn't clear to me, so you are also experiencing a total blackout in disk IO. I'm not sure how this could be traced. > >> BTW, we are doing tests in a completely different environment with ZFS and >> NFS (15k drives, with BBWC), and it seems something similar happens there >> too, resulting in a freeze in the end. >> >>> Combine with 5400 rpm consumer drives... well... >>> >>> >> Doesn't really count, but these drives are 7k2. >> > > If it's a zfs arc problem it would definitely manifest on 15k drives > too, what I meant that the impact might be unnoticeable. But since I > don't have a nice SAN to test with right now I can't try it out with > 100+ disks. > I'm still not getting the point. If you see zero IO during the problem, how would a faster storage make impact on its visibility?
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4B69709E.1090601>