... >=20 > My yardstick is currently "when a month goes by without ... meets that criteria... > >It seems stable enough > > for a number of ... is fixed, but ZFS seems much more stable than it was ... into the future - if ZFS will become stable > relatively shortly, it ...

freebsd-current - Brooks Davis - Jan 4 2008 - 14:12

... safe to assume ZFS will never become > stable during 7.x ... least that was my impression when I made last integration, I ... I'm going to ask re@ for approval for this patch ... 3D1073741824 vm.kmem_size_max=3D1073741824 vfs.zfs.prefetch_disable=3D1 My laptop is ...

freebsd-current - Pawel Jakub Dawidek - Jan 7 2008 - 05:59

... My yardstick is currently "when a month goes by without anyone ... crashed on him" :) >It seems stable enough > for a number of ... into the future - if ZFS will become stable relatively shortly, it ... crashes, but if not, there will be no near-future deployments ...

freebsd-current - Ivan Voras - Jan 4 2008 - 13:58

... ? So when CPU and drive speed increase, the >> new amount will always ... the box" that is what you're most likely to end up ... values known >> to work)? > > OK. > >>> ZFS already tells you up front ... it's ever going to be stable for 7.x. > > This was ...

freebsd-current - Gary Corcoran - Jan 6 2008 - 14:48

... enough > > This looks like we're constantly chasing the "right amount" ... So when CPU and drive speed increase, the new > amount will ... values known to work)? OK. >> ZFS already tells you up front ... s > ever going to be stable for 7.x. This was ...

freebsd-current - Kris Kennaway - Jan 6 2008 - 13:12

... I heard, rsync didn't crash Solaris on ZFS :) > > > > [Citation needed] > > I can't provide citation about a ... conclude that solaris is more stable in my situation is premature. -- regards Claus When lenity and cruelty play for a kingdom, the ...

freebsd-current - Claus Guttesen - Jan 6 2008 - 16:00

... it safe to assume ZFS will never become > stable during 7.x lifetime ... "), but it's what you're doing here: asking a question which ... is based on the premise that ZFS in FreeBSD 7 is unstable. ... to loader.conf: vm.kmem_size="1G" vfs.zfs.arc_min="64M" vfs. ...

freebsd-current - Dag-Erling Smørgrav - Jan 7 2008 - 10:04

... what would it > take to fix the problems, is it safe to assume ZFS will never become > stable during 7.x lifetime? I suppose that depends what you mean by stable. It seems stable enough for a number of applications today. It ...

freebsd-current - Brooks Davis - Jan 4 2008 - 12:33

... it take > to fix the problems, is it safe to assume ZFS will never become stable > during 7.x lifetime? I'm not sure if anyone has ... worth taking into account in considering the stability of ZFS is whether or not Sun considers it a ...

freebsd-current - Robert Watson - Jan 6 2008 - 11:36

... (with many files / >>>> large files) on ZFS without any stability issues. Problems for me ... you >> experience. > > I agree that ZFS is pretty stable itself. I use 32bit ... way of tuning to stop it crashing. When I do some > rsyncing, especially beetwen ...

freebsd-current - Kris Kennaway - Jan 6 2008 - 11:46

... (with many files / >>>>>> large files) on ZFS without any stability issues. Problems for me ... panics you experience. >>> I agree that ZFS is pretty stable itself. I use 32bit ... of tuning to stop it crashing. When I >>> do some rsyncing, especially beetwen ...

freebsd-current - Kris Kennaway - Jan 6 2008 - 12:22

... (with many > >>>>>> files / large files) on ZFS without any stability issues. > >>>>>> Problems for ... you experience. > >>> I agree that ZFS is pretty stable itself. I use 32bit ... of tuning to stop it crashing. When I > >>> do some rsyncing, especially ...

freebsd-current - Maciej Suszko - Jan 6 2008 - 15:56

... many files / > >> large files) on ZFS without any stability issues. Problems ... Mostly. I did have a ZFS crash with rsync that wasn ... experience. I agree that ZFS is pretty stable itself. I use ... tuning to stop it crashing. When I do some rsyncing, especially ...

freebsd-current - Maciej Suszko - Jan 6 2008 - 09:46

... Mostly. I did have a ZFS crash with rsync that wasn ... experience. > > > > I agree that ZFS is pretty stable itself. I use ... tuning to stop it crashing. When I > > do some rsyncing, especially ... be studied and understood. You're right - I turned debugging off ...

freebsd-current - Maciej Suszko - Jan 6 2008 - 12:05

... , rsync didn't crash Solaris on ZFS :) >> >> My admittedly second-hand understanding is that ... still missing is that ZFS also causes memory exhaustion panics when run on 32- ... have since fixed it), the opensolaris ZFS code makes *absolutely no attempt* ...

freebsd-current - Kris Kennaway - Jan 6 2008 - 13:43

... enough=20 This looks like we're constantly chasing the "right amount". ... ? So when CPU and drive speed increase, the new = amount will ... the values known to work)? > ZFS already tells you up front ... in if it's = ever going to be stable for 7.x. ...

freebsd-current - Ivan Voras - Jan 6 2008 - 12:45

... rsync didn't crash Solaris on ZFS :) >=20 > My admittedly second-hand ... on FreeBSD is that people run ZFS = > on sytems with 32-bit ... memory. It could be that ZFS= =20 > should be enforcing higher ... of=20 tuning like "it will run slowly if you don't ...

freebsd-current - Ivan Voras - Jan 6 2008 - 13:28

... didn't crash Solaris on ZFS :) >=20 > [Citation needed] I can't ... rsync on my Solaris with ZFS=20 and *it didn't ... searching for "rsync crash solaris zfs": 790 results, most of them= ... that the number of Solaris+ZFS installations worldwide is larger=20 ...

freebsd-current - Ivan Voras - Jan 6 2008 - 13:36

... , rsync didn't crash Solaris on ZFS :) >> >> [Citation needed] > > I can't provide citation ... > * searching for "rsync crash solaris zfs": 790 results, most of them > ... feel that the number of Solaris+ZFS installations worldwide is larger > than that ...

freebsd-current - Kris Kennaway - Jan 6 2008 - 14:10

... a "properly tuned" FreeBSD system with ZFS will not > result in a slowdown - ... tuning" is > counterproductive and bad engineering. ZFS is clearly marked as experimental so its ... crashes. If its still the case when the experimental status is lifted then ...

freebsd-current - Andrew Thompson - Jan 7 2008 - 16:46