[zfs-discuss] Re: Re: Help understanding some benchmark results

2007-01-13 Thread Chris Smith
Unfortunately I've started restoring data onto my array (2.5TB @ the 20ish MB/sec my LTO2 drive maxes out at will take a while ;) ) so I can't do any more testing that involves destroying the zpool and/or individual devices... So all the numbers below are to a 16-disk raidz2 zpool (unless otherw

[zfs-discuss] zfs umount -a in a global zone

2007-01-13 Thread Robert Milkowski
Hello zfs-discuss, I did 'zfs umount -a' in a global zone and all (non busy) datasets also in local zone were unmounted (one dataset was delegated to the local zone and other datasets were created inside). Well, I belive it shouldn't be that way at least not by default. What do you thi

Re: [zfs-discuss] ZFS and HDLM 5.8 ... does that coexist well ?

2007-01-13 Thread Torrey McMahon
Richard Elling wrote: Gael wrote: jumps8002:/etc/apache2 #cat /etc/release Solaris 10 11/06 s10s_u3wos_10 SPARC Copyright 2006 Sun Microsystems, Inc. All Rights Reserved. Use is subject to license terms. Assemb

Re: [zfs-discuss] ZFS and HDLM 5.8 ... does that coexist well ?

2007-01-13 Thread Richard Elling
Gael wrote: jumps8002:/etc/apache2 #cat /etc/release Solaris 10 11/06 s10s_u3wos_10 SPARC Copyright 2006 Sun Microsystems, Inc. All Rights Reserved. Use is subject to license terms. Assembled 14 November 2006

Re: Re[2]: [zfs-discuss] Replacing a drive in a raidz2 group

2007-01-13 Thread Jason J. W. Williams
Hi Robert, Will build 54 offline the drive? Best Regards, Jason On 1/13/07, Robert Milkowski <[EMAIL PROTECTED]> wrote: Hello Jason, Saturday, January 13, 2007, 12:06:57 AM, you wrote: JJWW> Hi Robert, JJWW> We've experienced luck with flaky SATA drives in our STK array by JJWW> unseating a

Re: [zfs-discuss] ZFS and HDLM 5.8 ... does that coexist well ?

2007-01-13 Thread Joerg Schilling
Eric Schrock <[EMAIL PROTECTED]> wrote: > On Sat, Jan 13, 2007 at 12:11:26PM -0800, Richard Elling wrote: > > > > So, what is in your format.dat? I haven't seen an MD21 in over 15 years. > > I would have thought that we removed it from format.dat long ago... > > -- richard > > This sounds like:

Re: [zfs-discuss] ZFS and HDLM 5.8 ... does that coexist well ?

2007-01-13 Thread Gael
On 1/13/07, Eric Schrock <[EMAIL PROTECTED]> wrote: On Sat, Jan 13, 2007 at 01:30:19PM -0600, Gael wrote: > Hello, > > jumps8002 #zpool create sanpool c7t50060E8004758654d0 c7t50060E8004758654d1 > c7t50060E8004758654d2 > cannot open '/dev/dsk/c7t50060E8004758654d0s0': This is a strange error, c

Re: [zfs-discuss] ZFS and HDLM 5.8 ... does that coexist well ?

2007-01-13 Thread Eric Schrock
On Sat, Jan 13, 2007 at 01:30:19PM -0600, Gael wrote: > Hello, > > jumps8002 #zpool create sanpool c7t50060E8004758654d0 c7t50060E8004758654d1 > c7t50060E8004758654d2 > cannot open '/dev/dsk/c7t50060E8004758654d0s0': This is a strange error, can you do a 'truss -topen' of this process? Does the a

Re: [zfs-discuss] ZFS and HDLM 5.8 ... does that coexist well ?

2007-01-13 Thread Gael
On 1/13/07, Eric Schrock <[EMAIL PROTECTED]> wrote: On Sat, Jan 13, 2007 at 12:11:26PM -0800, Richard Elling wrote: > > So, what is in your format.dat? I haven't seen an MD21 in over 15 years. > I would have thought that we removed it from format.dat long ago... > -- richard This sounds like:

Re: [zfs-discuss] ZFS and HDLM 5.8 ... does that coexist well ?

2007-01-13 Thread Gael
On 1/13/07, Richard Elling <[EMAIL PROTECTED]> wrote: Gael wrote: > Hello, > > I'm currently trying to convert a system from Solaris 10 U1 with Veritas > VM to Solaris 10 U3 with ZFS... the san portion of the server is managed > by Hitachi HDLM 5.8. > > I'm seeing two distinct errors... let me k

Re: [zfs-discuss] ZFS and HDLM 5.8 ... does that coexist well ?

2007-01-13 Thread Eric Schrock
On Sat, Jan 13, 2007 at 12:11:26PM -0800, Richard Elling wrote: > > So, what is in your format.dat? I haven't seen an MD21 in over 15 years. > I would have thought that we removed it from format.dat long ago... > -- richard This sounds like: 5020503 *format* Unknown controller 'MD21' warnings

Re: [zfs-discuss] ZFS and HDLM 5.8 ... does that coexist well ?

2007-01-13 Thread Richard Elling
Gael wrote: Hello, I'm currently trying to convert a system from Solaris 10 U1 with Veritas VM to Solaris 10 U3 with ZFS... the san portion of the server is managed by Hitachi HDLM 5.8. I'm seeing two distinct errors... let me know if they are classical or if I should open a ticket (bug re

[zfs-discuss] ZFS and HDLM 5.8 ... does that coexist well ?

2007-01-13 Thread Gael
Hello, I'm currently trying to convert a system from Solaris 10 U1 with Veritas VM to Solaris 10 U3 with ZFS... the san portion of the server is managed by Hitachi HDLM 5.8. I'm seeing two distinct errors... let me know if they are classical or if I should open a ticket (bug report)... Thanks i

Re: [zfs-discuss] question about self healing

2007-01-13 Thread Richard Elling
roland wrote: i have come across an interesting article at : http://www.anandtech.com/IT/showdoc.aspx?i=2859&p=5 it`s about sata vs. sas/scsi realiability , telling that typical desktop sata drives ".on average experience an Unrecoverable Error every 12.5 terabytes written or read (EUR of

Re: [zfs-discuss] question about self healing

2007-01-13 Thread Toby Thain
On 13-Jan-07, at 11:52 AM, roland wrote: i have come across an interesting article at : http://www.anandtech.com/IT/showdoc.aspx?i=2859&p=5 it`s about sata vs. sas/scsi realiability , telling that typical desktop sata drives ".on average experience an Unrecoverable Error every 12.5 te

Re: [zfs-discuss] Re: question about self healing

2007-01-13 Thread James Dickens
On 1/13/07, roland <[EMAIL PROTECTED]> wrote: thanks for your infos! > > can zfs protect my data from such single-bit-errors with a single drive ? > > >nope.. but it can tell you that it has occurred. can it also tell (or can i use a tool to determine), which data/file is affected by this erro

[zfs-discuss] Re: question about self healing

2007-01-13 Thread roland
thanks for your infos! > > can zfs protect my data from such single-bit-errors with a single drive ? > > >nope.. but it can tell you that it has occurred. can it also tell (or can i use a tool to determine), which data/file is affected by this error (and needs repair/restore from backup) ? T

Re: [zfs-discuss] question about self healing

2007-01-13 Thread James Dickens
On 1/13/07, roland <[EMAIL PROTECTED]> wrote: i have come across an interesting article at : http://www.anandtech.com/IT/showdoc.aspx?i=2859&p=5 it`s about sata vs. sas/scsi realiability , telling that typical desktop sata drives ".on average experience an Unrecoverable Error every 12.5 te

[zfs-discuss] question about self healing

2007-01-13 Thread roland
i have come across an interesting article at : http://www.anandtech.com/IT/showdoc.aspx?i=2859&p=5 it`s about sata vs. sas/scsi realiability , telling that typical desktop sata drives ".on average experience an Unrecoverable Error every 12.5 terabytes written or read (EUR of 1 in 1014 bit

[zfs-discuss] Extremely poor ZFS perf and other observations

2007-01-13 Thread Anantha N. Srirama
I'm observing the following behavior in our environment (Sol10U2, E2900, 24x96, 2x2Gbps, ...) - I've a compressed ZFS filesystem where I'm creating a large tar file. I notice that the tar process is running fine (accumulating CPU, truss shows writes, ...) but for whatever reason the timestamp o

Re: [zfs-discuss] Question: ZFS + Block level SHA256 ~= almost free CAS Squishing?

2007-01-13 Thread Pawel Jakub Dawidek
On Mon, Jan 08, 2007 at 11:00:36AM -0600, [EMAIL PROTECTED] wrote: > I have been looking at zfs source trying to get up to speed on the > internals. One thing that interests me about the fs is what appears to be > a low hanging fruit for block squishing CAS (Content Addressable Storage). > I think

Re[2]: [zfs-discuss] Replacing a drive in a raidz2 group

2007-01-13 Thread Robert Milkowski
Hello Jason, Saturday, January 13, 2007, 12:06:57 AM, you wrote: JJWW> Hi Robert, JJWW> We've experienced luck with flaky SATA drives in our STK array by JJWW> unseating and reseating the drive to cause a reset of the firmware. It JJWW> may be a bad drive, or the firmware may just have hit a bug