Re: [zfs-discuss] does log device (ZIL) require a mirror setup?

> From: zfs-discuss-boun...@opensolaris.org [mailto:zfs-discuss- > boun...@opensolaris.org] On Behalf Of Thomas Nau > > We use a STEC ZeusRAM as a log device for a 200TB RAID-Z2 pool. > As they are supposed to be read only after a crash or when booting and > those nice things are pretty expensive

Re: [zfs-discuss] Improving L1ARC cache efficiency with dedup

On Sun, Dec 11, 2011 at 04:04:37PM +0400, Jim Klimov wrote: > I would not be surprised to see that there is some disk IO > adding delays for the second case (read of a deduped file > "clone"), because you still have to determine references > to this second file's blocks, and another path of on-disk

Re: [zfs-discuss] Improving L1ARC cache efficiency with dedup

Not exactly. What is dedup'ed is the stream only, which is infect not very efficient. Real dedup aware replication is taking the necessary steps to avoid sending a block that exists on the other storage system. Mertol Özyöney | Storage Sales Mobile: +90 533 931 0752 Em

Re: [zfs-discuss] Improving L1ARC cache efficiency with dedup

I am almost sure that in cache things are still hydrated. There is an outstanding RFE for this, while I am not sure, I think this feature will be implemented sooner or later. And in theory there will be little benefits as most dedup'ed shares are used for archive purposes... PS: NetApp's do have s

Re: [zfs-discuss] Improving L1ARC cache efficiency with dedup

Thanks everyone for your input on this thread.  It sounds like there is sufficient weightbehind the affirmative that I will include this methodology into my performance analysistest plan.  If the performance goes well, I will share some of the results when we concludein January/February timeframe.R

Re: [zfs-discuss] Improving L1ARC cache efficiency with dedup

2011-12-12 19:03, Pawel Jakub Dawidek пишет: On Sun, Dec 11, 2011 at 04:04:37PM +0400, Jim Klimov wrote: I would not be surprised to see that there is some disk IO adding delays for the second case (read of a deduped file "clone"), because you still have to determine references to this second fi

[zfs-discuss] Sun X4540 disk replacement

Sorry for the off-topic question. I'm needing to replace a disk in a x4540 zfs file system. I have replacement ST31000NSSUN disks, but it's not obvious to me how to separate the original disk from its drive sled, it seems to be attached by more than the usual 4 screws. Is it meant to be separate

Re: [zfs-discuss] Sun X4540 disk replacement

You need to pry the drive sled off of the disk once the screws are removed. There are two or four notches that hold onto the disk. You'll end up spreading the carrier frame slightly. -- Edmund White ewwh...@mac.com On 12/12/11 5:25 PM, "Tony Schreiner" wrote: >Sorry for the off-topic questi

Re: [zfs-discuss] Sun X4540 disk replacement

Thanks for that. Success. I was apprehensive about prying too hard. Tony On Dec 12, 2011, at 11:53 AM, Edmund White wrote: > You need to pry the drive sled off of the disk once the screws are > removed. There are two or four notches that hold onto the disk. You'll end > up spreading the carrier f

[zfs-discuss] CPU sizing for ZFS/iSCSI/NFS server

We're preparing to purchase an X4170M2 as an upgrade for our existing X4100M2 server for ZFS, NFS, and iSCSI. We have a choice for CPU, some more expensive than others. Our current system has a dual-core 1.8Ghz Opteron 2210 CPU with 8GB. Seems like either a 6-core Intel E5649 2.53Ghz CPU or 4-core

Re: [zfs-discuss] CPU sizing for ZFS/iSCSI/NFS server

please check out the ZFS appliance 7120 spec 2.4Ghz /24GB memory and ZIL(SSD) may be try the ZFS simulator SW regards On 12/12/2011 2:28 PM, Albert Chin wrote: We're preparing to purchase an X4170M2 as an upgrade for our existing X4100M2 server for ZFS, NFS, and iSCSI. We have a choice for C

Re: [zfs-discuss] CPU sizing for ZFS/iSCSI/NFS server

On Mon, Dec 12, 2011 at 02:40:52PM -0500, "Hung-Sheng Tsao (Lao Tsao 老曹) Ph.D." wrote: > please check out the ZFS appliance 7120 spec 2.4Ghz /24GB memory and > ZIL(SSD) > may be try the ZFS simulator SW Good point. Thanks. > regards > > On 12/12/2011 2:28 PM, Albert Chin wrote: > >We're prepari

Re: [zfs-discuss] CPU sizing for ZFS/iSCSI/NFS server

4c@2.4ghz On 12/12/2011 2:44 PM, Albert Chin wrote: On Mon, Dec 12, 2011 at 02:40:52PM -0500, "Hung-Sheng Tsao (Lao Tsao 老曹) Ph.D." wrote: please check out the ZFS appliance 7120 spec 2.4Ghz /24GB memory and ZIL(SSD) may be try the ZFS simulator SW Good point. Thanks. regards On 12/12/2011

Re: [zfs-discuss] CPU sizing for ZFS/iSCSI/NFS server

On Mon, Dec 12, 2011 at 03:01:08PM -0500, "Hung-Sheng Tsao (Lao Tsao 老曹) Ph.D." wrote: > 4c@2.4ghz Yep, that's the plan. Thanks. > On 12/12/2011 2:44 PM, Albert Chin wrote: > >On Mon, Dec 12, 2011 at 02:40:52PM -0500, "Hung-Sheng Tsao (Lao Tsao 老曹) > >Ph.D." wrote: > >>please check out the ZFS

Re: [zfs-discuss] CPU sizing for ZFS/iSCSI/NFS server

On Dec 12, 2011, at 11:42 AM, "\"Hung-Sheng Tsao (Lao Tsao 老曹) Ph.D.\"" wrote: > please check out the ZFS appliance 7120 spec 2.4Ghz /24GB memory and ZIL(SSD) Do those appliances also use the F20 PCIe flash cards? I know the Exadata storage cells use them but they aren't utilizing ZFS in the Linu

Re: [zfs-discuss] Improving L1ARC cache efficiency with dedup

On Dec 11, 2011, at 2:59 PM, Mertol Ozyoney wrote: > Not exactly. What is dedup'ed is the stream only, which is infect not very > efficient. Real dedup aware replication is taking the necessary steps to > avoid sending a block that exists on the other storage system. These exist outside of ZFS (e

Re: [zfs-discuss] CPU sizing for ZFS/iSCSI/NFS server

On 12/12/2011 3:02 PM, Gary Driggs wrote: On Dec 12, 2011, at 11:42 AM, "\"Hung-Sheng Tsao (Lao Tsao 老曹) Ph.D.\"" wrote: please check out the ZFS appliance 7120 spec 2.4Ghz /24GB memory and ZIL(SSD) Do those appliances also use the F20 PCIe flash cards? no, these controller need the slots f

Re: [zfs-discuss] Improving L1ARC cache efficiency with dedup

On 12/12/2011 12:23 PM, Richard Elling wrote: On Dec 11, 2011, at 2:59 PM, Mertol Ozyoney wrote: Not exactly. What is dedup'ed is the stream only, which is infect not very efficient. Real dedup aware replication is taking the necessary steps to avoid sending a block that exists on the other sto