Re: [zfs-discuss] Use of blocksize (-b) during zfs zvol create, poor performance
Hi Eff, There are a significant number of variables to work through with dedup and compression enabled. So the first suggestion I have is to disable those features for now so your not working with too many elements. With those features set aside an NTFS cluster operation does not = a 64k raw I/O block. As well the ZFS 64k blocksize does not = one I/O operation. We may also need to consider the overall network performance behavior and iSCSI protocol characteristics and the Windows network stack. iperf is a good tool to rule that out. What I primarily suspect the issue may be is that write I/O operations are not aligned and are waiting for a I/O completion over multiple vdevs. Alignment is important for write I/O optimization and how the I/O maps at the software raid mode will make a significant impact to the DMU and SPA operations on a specific vdev layout. You may also have an issue with write cache operations, by default large I/O calls such as 64K will not use a ZIL cache vdev, if you have one defined, but will be written directly to your array vdevs which will also include a transaction group write operation. To ensure ZIL log usage with 64k I/O's you can apply the following: edit the /etc/system file with set zfs:zfs_immediate_write_sz = 131071 a reboot is required to activate the system file You have also not indicated what your zpool configuration looks like, that would helpful in the discussion area. It appears that your applying the x4500 as a backup target which means you should (if not already) enable write caching on the COMSTAR LU properties for this type of application. e.g stmfadm modify-lu -p wcd=false 600144F02F2280004C1D62010001 To help triage the perf issue further you could post 2 'kstat zfs' + 2 'kstat stmf' outputs on a 5 min interval and a 'zpool iostat -v 30 5' which would help visualize the I/O behavior. Regards, Mike http://blog.laspina.ca/ -- This message posted from opensolaris.org ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] zfs send/receive as backup - reliability?
I use zfs send/recv in the enterprise and in smaller environments all time and it's is excellent. Have a look at how awesome the functionally is in this example. http://blog.laspina.ca/ubiquitous/provisioning_disaster_recovery_with_zfs Regards, Mike -- This message posted from opensolaris.org ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] HELP! SNV_97, 98, 99 zfs with iscsitadm and VMWare!
Ciao, Your GUID's must not be the same an NAA is already established on the targets and if you previously tried to initialize the LUN with VMware it would have assigned the value in the VMFS header wich is now stored on your raw ZFS backing store. This will confuse VMware and it will remember it now some where in its definitions. You need to remove the second datastore from VMware and delete the target definition and ZFS backing store. Once you recreate the backing and target you should have a new GUID and iqn which should cure the issue. Regards, Mike -- This message posted from opensolaris.org ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] HELP! SNV_97, 98, 99 zfs with iscsitadm and VMWare!
Hello Tano, The issue here is not the target or VMware but a missing GUID on the target as the issue. Observe the target smf properties using iscsitadm list target -v You have iSCSI Name: iqn.1986-03.com.sun:02:35ec26d8-f173-6dd5-b239-93a9690ffe46.vscsi Connections: 0 ACL list: TPGT list: TPGT: 1 LUN information: LUN: 0 GUID: 0 VID: SUN PID: SOLARIS Type: disk Size: 1.3T Backing store: /dev/zvol/rdsk/vdrive/LUNB Status: online Target: iscsi iSCSI Name: iqn.1986-03.com.sun:02:4d469663-2304-4796-87a5-dffa03cd14ea.iscsi Connections: 0 ACL list: TPGT list: TPGT: 1 LUN information: LUN: 0 GUID: 0 VID: SUN PID: SOLARIS Type: disk Size: 750G Backing store: /dev/zvol/rdsk/vdrive/LUNA Status: online Both targets have the same invalid GUID of zero and this will prevent NAA from working properly. To fix this you can create a two new temporary targets and export the smf props to an xml file. e.g. svccfg -export iscsitgt > /iscsibackup/myiscsitargetbu.xml then edit the xml file switching the newly generated guid's to your valid targets and zeroing the temp ones. Now you can import the file with scvadm import /iscsibackup/myiscsitargetbu.xml When you restart your iscsitgt server you should have the guids in place and it should work with vmware. The you can delete the temps targets. http://blog.laspina.ca -- This message posted from opensolaris.org ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss