[zfs-discuss] ZFS utility like Filefrag on linux to help analyzing the extents mapping

2011-02-16 Thread Jeff liu
Hello All, I'd like to know if there is an utility like `Filefrag' shipped with e2fsprogs on linux, which is used to fetch the extents mapping info of a file(especially a sparse file) located on ZFS? I am working on efficient sparse file detection and backup through lseek(SEEK_DATA/SEEK_HOLE)

[zfs-discuss] Best way/issues with large ZFS send?

2011-02-16 Thread Eff Norwood
I'm preparing to replicate about 200TB of data between two data centers using zfs send. We have ten 10TB zpools that are further broken down into zvols of various sizes in each data center. One DC is primary and the other will be the replication target and there is plenty of bandwidth between

Re: [zfs-discuss] ZFS utility like Filefrag on linux to help analyzing the extents mapping

2011-02-16 Thread Fajar A. Nugraha
On Wed, Feb 16, 2011 at 8:53 PM, Jeff liu jeff@oracle.com wrote: Hello All, I'd like to know if there is an utility like `Filefrag' shipped with e2fsprogs on linux, which is used to fetch the extents mapping info of a file(especially a sparse file) located on ZFS? Something like zdb

Re: [zfs-discuss] ZFS utility like Filefrag on linux to help analyzing the extents mapping

2011-02-16 Thread Jeff liu
Hi Fajar, Thanks for your quick response, just playing it around for a while, it is very useful to me. Have a nice day! -Jeff 在 2011-2-16,下午10:16, Fajar A. Nugraha 写道: On Wed, Feb 16, 2011 at 8:53 PM, Jeff liu jeff@oracle.com wrote: Hello All, I'd like to know if there is an

Re: [zfs-discuss] Very bad ZFS write performance. Ok Read.

2011-02-16 Thread Richard Elling
On Feb 15, 2011, at 11:26 PM, Khushil Dep wrote: Could you not also pin process' to cores, preventing switching should help too? I've done this for performance reasons before on a 24 core Linux box Yes. More importantly, you could send interrupts to a processor set. There are many ways to

Re: [zfs-discuss] Best way/issues with large ZFS send?

2011-02-16 Thread Richard Elling
On Feb 16, 2011, at 6:05 AM, Eff Norwood wrote: I'm preparing to replicate about 200TB of data between two data centers using zfs send. We have ten 10TB zpools that are further broken down into zvols of various sizes in each data center. One DC is primary and the other will be the

Re: [zfs-discuss] Best way/issues with large ZFS send?

2011-02-16 Thread Edward Ned Harvey
From: zfs-discuss-boun...@opensolaris.org [mailto:zfs-discuss- boun...@opensolaris.org] On Behalf Of Eff Norwood Are there any gotchas that I should be aware of? Also, at what level should I be taking the snapshot to do the zfs send? At the primary pool level or at the zvol level? Since the

Re: [zfs-discuss] Best way/issues with large ZFS send?

2011-02-16 Thread Tomas Ögren
On 16 February, 2011 - Richard Elling sent me these 1,3K bytes: On Feb 16, 2011, at 6:05 AM, Eff Norwood wrote: I'm preparing to replicate about 200TB of data between two data centers using zfs send. We have ten 10TB zpools that are further broken down into zvols of various sizes in

[zfs-discuss] ZFS send/recv initial data load

2011-02-16 Thread whitetr6
Hi, I have a very limited amount of bandwidth between main office and a colocated rack of servers in a managed datacenter. My hope is to be able to zfs send/recv small incremental changes on a nightly basis as a secondary offsite backup strategy. My question is about the initial seed of the

[zfs-discuss] ZFS space_map

2011-02-16 Thread Charlie Paper
Hello all, I am trying to understand how the allocation of space_map happens. What I am trying to figure out is how the recursive part is handled. From what I understand a new allocation (say appending to a file) will cause the space map to change by appending more allocs that will require extra

[zfs-discuss] Recover data from disk with zfs

2011-02-16 Thread Sergey
Hello everybody! Please, help me! I have Solaris 10x86_64 server with a 5x40gb hdd. 1 HDD with /root and /usr (and other partition) (ufs filesystem) were crashed. He's died. Other 4 HDD (zfs file system) were mounted by 4 pool (zfs create pool disk1 c0t1d0 and etc.). I install Solaris 10x86_64

Re: [zfs-discuss] ZFS send/recv initial data load

2011-02-16 Thread Richard Elling
On Feb 16, 2011, at 7:38 AM, white...@gmail.com wrote: Hi, I have a very limited amount of bandwidth between main office and a colocated rack of servers in a managed datacenter. My hope is to be able to zfs send/recv small incremental changes on a nightly basis as a secondary offsite

Re: [zfs-discuss] ZFS send/recv initial data load

2011-02-16 Thread a . smith
On Feb 16, 2011, at 7:38 AM, whitetr6 at gmail.com wrote: My question is about the initial seed of the data. Is it possible to use a portable drive to copy the initial zfs filesystem(s) to the remote location and then make the subsequent incrementals over the network? If so, what would I

Re: [zfs-discuss] ZFS send/recv initial data load

2011-02-16 Thread Karl Wagner
From what I have read, this is not the best way to do it. Your best bet is to create a ZFS pool using the external device (or even better, devices) then zfs send | zfs receive. You can then do the same at your remote location. If you just send to a file, you may find it was a wasted trip (or

Re: [zfs-discuss] Recover data from disk with zfs

2011-02-16 Thread Cindy Swearingen
Sergey, I think you are saying that you had 4 separate ZFS storage pools on 4 separate disks and one ZFS pool/fs didn't not import successfully. If you created a new storage pool on the disk for the pool that failed to import then the data on that disk is no longer available because it was

Re: [zfs-discuss] ZFS send/recv initial data load

2011-02-16 Thread Stephan Budach
Am 16.02.11 16:38, schrieb white...@gmail.com: Hi, I have a very limited amount of bandwidth between main office and a colocated rack of servers in a managed datacenter. My hope is to be able to zfs send/recv small incremental changes on a nightly basis as a secondary offsite backup strategy.

Re: [zfs-discuss] ZFS send/recv initial data load

2011-02-16 Thread Bill Sommerfeld
On 02/16/11 07:38, white...@gmail.com wrote: Is it possible to use a portable drive to copy the initial zfs filesystem(s) to the remote location and then make the subsequent incrementals over the network? Yes. If so, what would I need to do to make sure it is an exact copy? Thank you,

Re: [zfs-discuss] ZFS send/recv initial data load

2011-02-16 Thread whitetr6
All of these responses have been very helpful and are much appreciated. Thank you all. Mark On Feb 16, 2011 2:54pm, Erik ABLESON eable...@mac.com wrote: Check out : http://www.infrageeks.com/groups/infrageeks/wiki/8fb35/zfs_autoreplicate_script.html It also works to an external hard

Re: [zfs-discuss] ZFS send/recv initial data load

2011-02-16 Thread Erik Trimble
On 2/16/2011 8:08 AM, Richard Elling wrote: On Feb 16, 2011, at 7:38 AM, white...@gmail.com wrote: Hi, I have a very limited amount of bandwidth between main office and a colocated rack of servers in a managed datacenter. My hope is to be able to zfs send/recv small incremental changes on a

Re: [zfs-discuss] CPU Limited on Checksums?

2011-02-16 Thread Krunal Desai
On Wed, Feb 9, 2011 at 12:02 AM, Richard Elling richard.ell...@gmail.com wrote: The data below does not show heavy CPU usage. Do you have data that does show heavy CPU usage?  mpstat would be a good start. Here is mpstat output during a network copy; I think one of the CPUs disappeared due to a

Re: [zfs-discuss] fmadm faulty not showing faulty/offline disks?

2011-02-16 Thread Krunal Desai
On Wed, Feb 2, 2011 at 8:38 PM, Carson Gaspar car...@taltos.org wrote: Works For Me (TM). c7t0d0 is hanging off an LSI SAS3081E-R (SAS1068E chip) rev B3 MPT rev 105 Firmware rev 011d (1.29.00.00) (IT FW) This is a SATA disk - I don't have any SAS disks behind a LSI1068E to test. When I