[zfs-discuss] Is my 3-way mirror completely lost?
Hello list, My ZFS pool has found it's way into a bad state after a period of neglect and now I'm having trouble recovering. The pool is a three-way mirror of which 2 disks started showing errors and thus the pool was degraded. I shut down the system and started at the lowest level by using ES Tool (Samsung) to do a diagnostic. Sure enough the 2 disks were showing bad sectors. After a low level format I attempted to reintroduce these disks back into the mirror. However, when resilvering the system would hang/freeze at about 50% and I needed to reset the system. My next attempt was to just leave the single good disk in the system (detach mirrors) and attempt a scrub. Again the system hangs at 50%. Final attempt was to just try and copy the data to a new pool using a 'cp -R'. Ran great for some time but the copy did not complete. It hung just like resilver and scrub. The good disk still comes through the Samsung (full) diagnostic with no issues found. I'm not sure what to do next. Is my final pool completely lost? I'll try other hardware (power supply, memory) next... FYI: I'm using OpenSolaris Nevada (76 I believe) but have also tried the OpenSolaris 2008.05 Live CD. Regards, - Emiel ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] The best motherboard for a home ZFS fileserver
Actually, my ideal setup would be: Shuttle XPC w/ 2x PCI-e x8 or x16 lanes 2x PCI-e eSATA cards (each with 4 eSATA port multiplier ports) Mike, may I ask which eSATA controllers you used? I searched the Solaris HCL and found very few listed there Thanks justin smime.p7s Description: S/MIME cryptographic signature ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] The best motherboard for a home ZFS fileserver
I didn't use any. That would be my -ideal- setup :) I waited and waited, and still no eSATA/Port Multiplier support out there, or isn't stable enough. So I scrapped it. 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] The best motherboard for a home ZFS fileserver
I agree with mike503. If you create the awareness (of the instability of recorded information) there is a large potential market waiting for a ZFS/NAS little server! Very nice the thin client idea. It will be good to also use the NAS server as a full server and use remotely with a very thin client! (in this sense it can be larger ;-) This message posted from opensolaris.org ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
[zfs-discuss] Errors in ZFS/NFSv4 ACL Documentation
I noticed some errors in ls(1), acl(5) and the ZFS Admin Guide about ZFS/NFSv4 ACLs: ls(1): read_acl (r) Permission to read the ACL of a file. The compact representation of read_acl is c, not r. ls(1): -c | -vThe same as -l, and in addition displays the [...] The options are in fact -/ c or -/ v. ls(1): The display in verbose mode (/ v) uses full attribute [...]. This should read (-/ v). acl(5): execute (X). The x should be lowercase: (x) acl(5) does not document 3 ACEs: success access (S), failed access (F), inherited (I). The ZFS Admin Guide does not document the same 3 ACEs. The ZFS Admin Guide gives examples listing a compact representation of ACLs containing only 6 inheritance flags instead of 7. For example in the section Setting and Displaying ACLs on ZFS Files in Compact Format: # ls -V file.1 -rw-r--r-- 1 root root 206663 Feb 16 11:00 file.1 owner@:--x---:--:deny ^^ 7th position for flag 'I' missing By the way, where can I find the latest version of the ls(1) manpage online ? I cannot find it, neither on src.opensolaris.org, nor in the manpage consolidation download center [1]. I'd like to check whether the errors I found in ls(1) are fixed before submitting a bug report. [1] http://opensolaris.org/os/downloads/manpages/ -marc ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] Adding slices from same drive to a pool
Ian Collins wrote: I'd like to extend my ZFS root pool by adding the old swap and root slice left over from the previous LU BE. Are there any known issues with concatenating slices from the same drive? Having done this in the past (many builds ago) I found the performance wasn't good. It is really bad if you tried to mirror between different slices of the same drive (use copies=2 instead). If the old swap and root slices are after the ZFS root pool then you should be able to use format to delete them and add them onto the end of the slice the pool is in. If they are before it then I think you are out of luck. If they are before the ZFS root pool one possible thing you might be able to do would be to boot failsafe (which runs compeltely from RAM) then making sure the pool as NOT imported use some dd to shift the stuff (overlaping slices might help with this). But I'd make sure you have a full and verified backup before trying that. Note that I've not tried this myself but I might be tempted to give it a go on my OpenSolaris 2008.05 (upgrade to snv_93) system since it has swap as a separate slice at the start of the disk. -- Darren J Moffat ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] Supermicro AOC-SAT2-MV8 hang when drive removed
A little more information today. I had a feeling that ZFS would continue quite some time before giving an error, and today I've shown that you can carry on working with the filesystem for at least half an hour with the disk removed. I suspect on a system with little load you could carry on working for several hours without any indication that there is a problem. It looks to me like ZFS is caching reads writes, and that provided requests can be fulfilled from the cache, it doesn't care whether the disk is present or not. I would guess that ZFS is attempting to write to the disk in the background, and that this is silently failing. Here's the log of the tests I did today. After removing the drive, over a period of 30 minutes I copied folders to the filesystem, created an archive, set permissions, and checked properties. I did this both in the command line and with the graphical file manager tool in Solaris. Neither reported any errors, and all the data could be read written fine. Until the reboot, at which point all the data was lost, again without error. If you're not interested in the detail, please skip to the end where I've got some thoughts on just how many problems there are here. # zpool status test pool: test state: ONLINE scrub: none requestedconfig: NAMESTATE READ WRITE CKSUMtestONLINE 0 0 0 c2t7d0ONLINE 0 0 0 errors: No known data errors# zfs list testNAME USED AVAIL REFER MOUNTPOINTtest 243M 228G 242M /test# zpool list testNAME SIZE USED AVAILCAP HEALTH ALTROOTtest 232G 243M 232G 0% ONLINE - -- drive removed -- # cfgadm |grep sata1/7sata1/7sata-portempty unconfigured ok -- cfgadmin knows the drive is removed. How come ZFS does not? -- # cp -r /rc-pool/copytest /test/copytest# zpool list testNAME SIZE USED AVAILCAP HEALTH ALTROOTtest 232G 73.4M 232G 0% ONLINE -# zfs list testNAME USED AVAIL REFER MOUNTPOINTtest 142K 228G18K /test -- Yup, still up. Let's start the clock -- # dateTue Jul 29 09:31:33 BST 2008# du -hs /test/copytest 667K /test/copytest -- 5 minutes later, still going strong -- # dateTue Jul 29 09:36:30 BST 2008# zpool list testNAME SIZE USED AVAIL CAP HEALTH ALTROOTtest 232G 73.4M 232G 0% ONLINE -# cp -r /rc-pool/copytest /test/copytest2# ls /testcopytest copytest2# du -h -s /test 1.3M /test# zpool list testNAME SIZE USED AVAILCAP HEALTH ALTROOTtest 232G 73.4M 232G 0% ONLINE -# find /test | wc -l 2669# find //test/copytest | wc -l1334# find /rc-pool/copytest | wc -l1334# du -h -s /rc-pool/copytest 5.3M /rc-pool/copytest -- Not sure why the original pool has 5.3MB of data when I use du. -- -- File Manager reports that they both have the same size -- -- 15 minutes later it's still working. I can read data fine -- # dateTue Jul 29 09:43:04 BST 2008# chmod 777 /test/*# mkdir /rc-pool/test2# cp -r /test/copytest2 /rc-pool/test2/copytest2# find /rc-pool/test2/copytest2 | wc -l1334# zpool list testNAME SIZE USED AVAILCAP HEALTH ALTROOTtest 232G 73.4M 232G 0% ONLINE - -- and yup, the drive is still offline -- # cfgadm | grep sata1/7sata1/7sata-portempty unconfigured ok -- And finally, after 30 minutes the pool is still going strong -- # dateTue Jul 29 09:59:56 BST 2008 # tar -cf /test/copytest.tar /test/copytest/*# ls -ltotal 3drwxrwxrwx 3 root root 3 Jul 29 09:30 copytest-rwxrwxrwx 1 root root 4626432 Jul 29 09:59 copytest.tardrwxrwxrwx 3 root root 3 Jul 29 09:39 copytest2# zpool list testNAME SIZE USED AVAILCAP HEALTH ALTROOTtest 232G 73.4M 232G 0% ONLINE - After a full 30 minutes there's no indication whatsoever of any problem. Checking properties of the folder in File Browser reports 2665 items, totalling 9.0MB. At this point I tried # zfs set sharesmb=on test. I didn't really expect it to work, and sure enough, that command hung. zpool status also hung, so I had to reboot the server. -- Rebooted server -- Now I found that not only are all the files I've written in the last 30 minutes missing, but in fact files that I had deleted several minutes prior to removing the drive have re-appeared. -- /test mount point is still present, I'll probably have to remove that manually -- # cd /# lsbin export media procsystemboot homemnt rc-pool testdev kernel net rc-usb tmpdevices lib opt rootusretc lost+found platformsbinvar -- ZFS still has the pool mounted, but at least now it realises it's not working -- # zpool listNAME SIZE
Re: [zfs-discuss] Is my 3-way mirror completely lost?
On Tue, 29 Jul 2008, Emiel van de Laar wrote: I'm not sure what to do next. Is my final pool completely lost? It sounds like your good disk has some serious problems and that formatting the two disks with bad sectors was the wrong thing to do. You might have been able to recover using the two failing disks by removing the good disk which was causing the hang. Since diagnostics on the good disk succeeded, there may still be some hope by using a low-level tool like 'dd' to transfer the underlying data to more reliable storage. If there is a successful transfer, then you have something to work with. Bob == Bob Friesenhahn [EMAIL PROTECTED], http://www.simplesystems.org/users/bfriesen/ GraphicsMagick Maintainer,http://www.GraphicsMagick.org/ ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] The best motherboard for a home ZFS fileserver
On Tue, 29 Jul 2008, Steve wrote: I agree with mike503. If you create the awareness (of the instability of recorded information) there is a large potential market waiting for a ZFS/NAS little server! The big mistake in the posting was to assume that Sun should be in this market. Sun has no experience in the consumer market and as far as I know, it has never tried to field a consumer product. Anyone here is free to go into business selling ready-made NAS servers based on OpenSolaris. Except for Adaptec SnapServer (which is pricey), almost all of the competition for small NAS servers is based on a special version of Microsoft Windows targeted for NAS service and which only offers CIFS. Bob == Bob Friesenhahn [EMAIL PROTECTED], http://www.simplesystems.org/users/bfriesen/ GraphicsMagick Maintainer,http://www.GraphicsMagick.org/ ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] ? SX:CE snv_91 - ZFS - raid and mirror - drive sizes don't add correctl
There may be some work being done to fix this: zpool should support raidz of mirrors http://bugs.opensolaris.org/bugdatabase/view_bug.do?bug_id=6485689 Discussed in this thread: Mirrored Raidz ( Posted: Oct 19, 2006 9:02 PM ) http://opensolaris.org/jive/thread.jspa?threadID=15854tstart=0 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] Errors in ZFS/NFSv4 ACL Documentation
Mark, Thanks for your detailed review comments. I will check where the latest man pages are online and get back to you. In the meantime, I can file the bugs to get these issues fixed on your behalf. Thanks again, Cindy Marc Bevand wrote: I noticed some errors in ls(1), acl(5) and the ZFS Admin Guide about ZFS/NFSv4 ACLs: ls(1): read_acl (r) Permission to read the ACL of a file. The compact representation of read_acl is c, not r. ls(1): -c | -vThe same as -l, and in addition displays the [...] The options are in fact -/ c or -/ v. ls(1): The display in verbose mode (/ v) uses full attribute [...]. This should read (-/ v). acl(5): execute (X). The x should be lowercase: (x) acl(5) does not document 3 ACEs: success access (S), failed access (F), inherited (I). The ZFS Admin Guide does not document the same 3 ACEs. The ZFS Admin Guide gives examples listing a compact representation of ACLs containing only 6 inheritance flags instead of 7. For example in the section Setting and Displaying ACLs on ZFS Files in Compact Format: # ls -V file.1 -rw-r--r-- 1 root root 206663 Feb 16 11:00 file.1 owner@:--x---:--:deny ^^ 7th position for flag 'I' missing By the way, where can I find the latest version of the ls(1) manpage online ? I cannot find it, neither on src.opensolaris.org, nor in the manpage consolidation download center [1]. I'd like to check whether the errors I found in ls(1) are fixed before submitting a bug report. [1] http://opensolaris.org/os/downloads/manpages/ -marc ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] The best motherboard for a home ZFS fileserver
waynel wrote: We have a couple of machines similar to your just spec'ed. They have worked great. The only problem is, the power management routine only works for K10 and later. We will move to Intel core 2 duo for future machines (mainly b/c power management considerations). So is Intel better? Which motherboard could be a good choice? (microatx?) 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] Is my 3-way mirror completely lost?
Bob Friesenhahn wrote: On Tue, 29 Jul 2008, Emiel van de Laar wrote: I'm not sure what to do next. Is my final pool completely lost? It sounds like your good disk has some serious problems and that formatting the two disks with bad sectors was the wrong thing to do. You might have been able to recover using the two failing disks by removing the good disk which was causing the hang. Since diagnostics on the good disk succeeded, there may still be some hope by using a low-level tool like 'dd' to transfer the underlying data to more reliable storage. If there is a successful transfer, then you have something to work with. Good idea. This eliminates ZFS from the equation and should verify that the data is readable. Also check for errors or faults discovered by FMA using fmdump. If these are consumer grade disks, they may not return failure when an unrecoverable read is attempted, but the request should timeout eventually. You may be seeing serial timeouts which should show up in the FMA records. -- richard ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
[zfs-discuss] Datto ZFS OpenSolaris NAS Product
I just read about this new NAS product based on OpenSolaris and ZFS. There are lots of questions on this forum about good hardware for a home NAS box so the hardware/software this company is using might be interesting. From their site, they are using a 1.5 Ghz Low Voltage VIA C7 processor with 1 GB of RAM to serve up a ZFS mirror. http://www.dattobackup.com/zseries-tech.php Haik 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] Supermicro AOC-SAT2-MV8 hang when drive removed
I think the important point here is that this makes the case for ZFS handling at least one layer of redundancy. If the disk you pulled was part of a mirror or raidz, there wouldn't be data loss when your system was rebooted. In fact, the zpool status commands would likely keep working, and a reboot wouldn't be necessary at all. I think it's unreasonable to expect a system with any file system to recover from a single drive being pulled. Of course, loosing extra work because of the delayed notification is bad, but none the less, this is not a reasonable test. Basically, always provide redundancy in your zpool config. Jon Ross Smith wrote: A little more information today. I had a feeling that ZFS would continue quite some time before giving an error, and today I've shown that you can carry on working with the filesystem for at least half an hour with the disk removed. I suspect on a system with little load you could carry on working for several hours without any indication that there is a problem. It looks to me like ZFS is caching reads writes, and that provided requests can be fulfilled from the cache, it doesn't care whether the disk is present or not. I would guess that ZFS is attempting to write to the disk in the background, and that this is silently failing. Here's the log of the tests I did today. After removing the drive, over a period of 30 minutes I copied folders to the filesystem, created an archive, set permissions, and checked properties. I did this both in the command line and with the graphical file manager tool in Solaris. Neither reported any errors, and all the data could be read written fine. Until the reboot, at which point all the data was lost, again without error. If you're not interested in the detail, please skip to the end where I've got some thoughts on just how many problems there are here. # zpool status test pool: test state: ONLINE scrub: none requested config: NAMESTATE READ WRITE CKSUM testONLINE 0 0 0 c2t7d0ONLINE 0 0 0 errors: No known data errors # zfs list test NAME USED AVAIL REFER MOUNTPOINT test 243M 228G 242M /test # zpool list test NAME SIZE USED AVAILCAP HEALTH ALTROOT test 232G 243M 232G 0% ONLINE - -- drive removed -- # cfgadm |grep sata1/7 sata1/7sata-portemptyunconfigured ok -- cfgadmin knows the drive is removed. How come ZFS does not? -- # cp -r /rc-pool/copytest /test/copytest # zpool list test NAME SIZE USED AVAILCAP HEALTH ALTROOT test 232G 73.4M 232G 0% ONLINE - # zfs list test NAME USED AVAIL REFER MOUNTPOINT test 142K 228G18K /test -- Yup, still up. Let's start the clock -- # date Tue Jul 29 09:31:33 BST 2008 # du -hs /test/copytest 667K /test/copytest -- 5 minutes later, still going strong -- # date Tue Jul 29 09:36:30 BST 2008 # zpool list test NAME SIZE USED AVAILCAP HEALTH ALTROOT test 232G 73.4M 232G 0% ONLINE - # cp -r /rc-pool/copytest /test/copytest2 # ls /test copytest copytest2 # du -h -s /test 1.3M /test # zpool list test NAME SIZE USED AVAILCAP HEALTH ALTROOT test 232G 73.4M 232G 0% ONLINE - # find /test | wc -l 2669 # find //test/copytest | wc -l 1334 # find /rc-pool/copytest | wc -l 1334 # du -h -s /rc-pool/copytest 5.3M /rc-pool/copytest -- Not sure why the original pool has 5.3MB of data when I use du. -- -- File Manager reports that they both have the same size -- -- 15 minutes later it's still working. I can read data fine -- # date Tue Jul 29 09:43:04 BST 2008 # chmod 777 /test/* # mkdir /rc-pool/test2 # cp -r /test/copytest2 /rc-pool/test2/copytest2 # find /rc-pool/test2/copytest2 | wc -l 1334 # zpool list test NAME SIZE USED AVAILCAP HEALTH ALTROOT test 232G 73.4M 232G 0% ONLINE - -- and yup, the drive is still offline -- # cfgadm | grep sata1/7 sata1/7sata-portemptyunconfigured ok -- And finally, after 30 minutes the pool is still going strong -- # date Tue Jul 29 09:59:56 BST 2008 # tar -cf /test/copytest.tar /test/copytest/* # ls -l total 3 drwxrwxrwx 3 root root 3 Jul 29 09:30 copytest -rwxrwxrwx 1 root root 4626432 Jul 29 09:59 copytest.tar drwxrwxrwx 3 root root 3 Jul 29 09:39 copytest2 # zpool list test NAME SIZE USED AVAILCAP HEALTH ALTROOT test 232G 73.4M 232G 0% ONLINE - After a full 30 minutes there's no indication whatsoever of any problem. Checking properties of the folder in File Browser reports 2665 items, totalling 9.0MB. At this point I tried # zfs set sharesmb=on
Re: [zfs-discuss] Supermicro AOC-SAT2-MV8 hang when drive removed
Just a side comment: this discussion shows all the classic symptoms of two groups of people with different basic assumptions, each wondering why the other said what they did. Getting these out in the open would be A Good Thing (;-)) --dave Jonathan Loran wrote: I think the important point here is that this makes the case for ZFS handling at least one layer of redundancy. If the disk you pulled was part of a mirror or raidz, there wouldn't be data loss when your system was rebooted. In fact, the zpool status commands would likely keep working, and a reboot wouldn't be necessary at all. I think it's unreasonable to expect a system with any file system to recover from a single drive being pulled. Of course, loosing extra work because of the delayed notification is bad, but none the less, this is not a reasonable test. Basically, always provide redundancy in your zpool config. Jon Ross Smith wrote: A little more information today. I had a feeling that ZFS would continue quite some time before giving an error, and today I've shown that you can carry on working with the filesystem for at least half an hour with the disk removed. I suspect on a system with little load you could carry on working for several hours without any indication that there is a problem. It looks to me like ZFS is caching reads writes, and that provided requests can be fulfilled from the cache, it doesn't care whether the disk is present or not. I would guess that ZFS is attempting to write to the disk in the background, and that this is silently failing. Here's the log of the tests I did today. After removing the drive, over a period of 30 minutes I copied folders to the filesystem, created an archive, set permissions, and checked properties. I did this both in the command line and with the graphical file manager tool in Solaris. Neither reported any errors, and all the data could be read written fine. Until the reboot, at which point all the data was lost, again without error. If you're not interested in the detail, please skip to the end where I've got some thoughts on just how many problems there are here. # zpool status test pool: test state: ONLINE scrub: none requested config: NAMESTATE READ WRITE CKSUM testONLINE 0 0 0 c2t7d0ONLINE 0 0 0 errors: No known data errors # zfs list test NAME USED AVAIL REFER MOUNTPOINT test 243M 228G 242M /test # zpool list test NAME SIZE USED AVAILCAP HEALTH ALTROOT test 232G 243M 232G 0% ONLINE - -- drive removed -- # cfgadm |grep sata1/7 sata1/7sata-portemptyunconfigured ok -- cfgadmin knows the drive is removed. How come ZFS does not? -- # cp -r /rc-pool/copytest /test/copytest # zpool list test NAME SIZE USED AVAILCAP HEALTH ALTROOT test 232G 73.4M 232G 0% ONLINE - # zfs list test NAME USED AVAIL REFER MOUNTPOINT test 142K 228G18K /test -- Yup, still up. Let's start the clock -- # date Tue Jul 29 09:31:33 BST 2008 # du -hs /test/copytest 667K /test/copytest -- 5 minutes later, still going strong -- # date Tue Jul 29 09:36:30 BST 2008 # zpool list test NAME SIZE USED AVAILCAP HEALTH ALTROOT test 232G 73.4M 232G 0% ONLINE - # cp -r /rc-pool/copytest /test/copytest2 # ls /test copytest copytest2 # du -h -s /test 1.3M /test # zpool list test NAME SIZE USED AVAILCAP HEALTH ALTROOT test 232G 73.4M 232G 0% ONLINE - # find /test | wc -l 2669 # find //test/copytest | wc -l 1334 # find /rc-pool/copytest | wc -l 1334 # du -h -s /rc-pool/copytest 5.3M /rc-pool/copytest -- Not sure why the original pool has 5.3MB of data when I use du. -- -- File Manager reports that they both have the same size -- -- 15 minutes later it's still working. I can read data fine -- # date Tue Jul 29 09:43:04 BST 2008 # chmod 777 /test/* # mkdir /rc-pool/test2 # cp -r /test/copytest2 /rc-pool/test2/copytest2 # find /rc-pool/test2/copytest2 | wc -l 1334 # zpool list test NAME SIZE USED AVAILCAP HEALTH ALTROOT test 232G 73.4M 232G 0% ONLINE - -- and yup, the drive is still offline -- # cfgadm | grep sata1/7 sata1/7sata-portemptyunconfigured ok -- And finally, after 30 minutes the pool is still going strong -- # date Tue Jul 29 09:59:56 BST 2008 # tar -cf /test/copytest.tar /test/copytest/* # ls -l total 3 drwxrwxrwx 3 root root 3 Jul 29 09:30 copytest -rwxrwxrwx 1 root root 4626432 Jul 29 09:59 copytest.tar drwxrwxrwx 3 root root 3 Jul 29 09:39 copytest2 # zpool list test NAME SIZE USED AVAILCAP HEALTH ALTROOT test 232G 73.4M 232G 0% ONLINE - After a full 30 minutes there's no indication whatsoever of
Re: [zfs-discuss] The best motherboard for a home ZFS fileserver
On Tue, Jul 29, 2008 at 9:20 AM, Steve [EMAIL PROTECTED] wrote: So is Intel better? Which motherboard could be a good choice? (microatx?) Inexpensive Intel motherboards do not support ECC memory while all current AMD cpus do. If ECC is important to you, Intel is not a good choice. I'm disappointed that there is no support for power management on the K8, which is a bit of a shock since Sun's been selling K8 based systems for a few years now. The cost of an X3 ($125) and AM2+ mobo ($80) is about the same as an Intel chip ($80) and motherboard ($150) that supports ECC. -B -- Brandon High [EMAIL PROTECTED] The good is the enemy of the best. - Nietzsche ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
[zfs-discuss] questions about ZFS Send/Receive
Hi guys, we are proposing a customer a couple of X4500 (24 Tb) used as NAS (i.e. NFS server). Both server will contain the same files and should be accessed by different clients at the same time (i.e. they should be both active) So we need to guarantee that both x4500 contain the same files: We could simply copy the contents on both x4500 , which is an option because the new files are in a limited number and rate , but we would really like to use ZFS send receive commands: AFAIK the commands works fine but generally speaking are there any known limitations ? And, in detail , it is not clear if the receiving ZFS file system could be used regularly while it is in receiving mode: in poor words is it possible to read and export in nfs, files from a ZFS file system while it is receiving update from another ZFS send ? Clearly until the new updates are received and applied the old copy would be used TIA Stefano Sun Microsystems Spa Viale Fulvio testi 327 20162 Milano ITALY me *STEFANO PINI* Senior Technical Specialist at Sun Microsystems Italy http://www.sun.com/italy contact | [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] | +39 02 64152150 ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] questions about ZFS Send/Receive
On Tue, Jul 29, 2008 at 5:13 PM, Stefano Pini [EMAIL PROTECTED] wrote: Hi guys, we are proposing a customer a couple of X4500 (24 Tb) used as NAS (i.e. NFS server). Both server will contain the same files and should be accessed by different clients at the same time (i.e. they should be both active) So we need to guarantee that both x4500 contain the same files: We could simply copy the contents on both x4500 , which is an option because the new files are in a limited number and rate , but we would really like to use ZFS send receive commands: If they are truly limited, something like an rsync or similar. There was a script being thrown around a while back that was touted as the Best Backup Script That Doesn't Do Backups, but I can't find it. In essence, it just created a list of what changed since the last backup and allowed you to use tar/cpio/cp - whatever to do the backup. AFAIK the commands works fine but generally speaking are there any known limitations ? And, in detail , it is not clear if the receiving ZFS file system could be used regularly while it is in receiving mode: in poor words is it possible to read and export in nfs, files from a ZFS file system while it is receiving update from another ZFS send ? First, the zfs send works only on a snapshot. -i sends incremental snapshots, so you would think that would work. From the zfs man page, you'll see that during a receive, the destination file system is unmounted and cannot be accessed during the receive. If an incremental stream is received, then the destina- tion file system must already exist, and its most recent snapshot must match the incremental stream's source. The destination file system and all of its child file sys- tems are unmounted and cannot be accessed during the receive operation. Clearly until the new updates are received and applied the old copy would be used TIA Stefano Sun Microsystems Spa Viale Fulvio testi 327 20162 Milano ITALY me *STEFANO PINI* Senior Technical Specialist at Sun Microsystems Italy http://www.sun.com/italy contact | [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] | +39 02 64152150 ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss -- chris -at- microcozm -dot- net === Si Hoc Legere Scis Nimium Eruditionis Habes ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] The best motherboard for a home ZFS fileserver
I'd say some good places to look are silentpcreview.com and mini-itx.com. I found this tasty morsel on an ad at mini-itx... http://www.american-portwell.com/product.php?productid=16133 6x onboard SATA. 4 gig support. core2duo support. which means 64 bit = yes, 4 gig = yes, 6x sata is nice. now if only I could find a chassis for this. AFAIK the Chenbro is the only 2 drive mini-itx chassis so far. I wish I knew metal working and carve up my own :P 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] questions about ZFS Send/Receive
Stefano Pini wrote: Hi guys, we are proposing a customer a couple of X4500 (24 Tb) used as NAS (i.e. NFS server). Both server will contain the same files and should be accessed by different clients at the same time (i.e. they should be both active) What exactly are they trying to do? AVS can be used to keep two systems in sync, but for a simple design, there should be two NFS file systems, one active for each X4500. There has recently been some discussions on [EMAIL PROTECTED] about using AVS to keep the unshared storage in sync. -- richard So we need to guarantee that both x4500 contain the same files: We could simply copy the contents on both x4500 , which is an option because the new files are in a limited number and rate , but we would really like to use ZFS send receive commands: AFAIK the commands works fine but generally speaking are there any known limitations ? And, in detail , it is not clear if the receiving ZFS file system could be used regularly while it is in receiving mode: in poor words is it possible to read and export in nfs, files from a ZFS file system while it is receiving update from another ZFS send ? Clearly until the new updates are received and applied the old copy would be used TIA Stefano Sun Microsystems Spa Viale Fulvio testi 327 20162 Milano ITALY me *STEFANO PINI* Senior Technical Specialist at Sun Microsystems Italy http://www.sun.com/italy contact | [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] | +39 02 64152150 ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] questions about ZFS Send/Receive
On Jul 29, 2008, at 2:24 PM, Chris Cosby wrote: On Tue, Jul 29, 2008 at 5:13 PM, Stefano Pini [EMAIL PROTECTED] wrote: Hi guys, we are proposing a customer a couple of X4500 (24 Tb) used as NAS (i.e. NFS server). Both server will contain the same files and should be accessed by different clients at the same time (i.e. they should be both active) So we need to guarantee that both x4500 contain the same files: We could simply copy the contents on both x4500 , which is an option because the new files are in a limited number and rate , but we would really like to use ZFS send receive commands: If they are truly limited, something like an rsync or similar. There was a script being thrown around a while back that was touted as the Best Backup Script That Doesn't Do Backups, but I can't find it. In essence, it just created a list of what changed since the last backup and allowed you to use tar/cpio/cp - whatever to do the backup. I think zfs send/recv would be a great way to go here - see below. AFAIK the commands works fine but generally speaking are there any known limitations ? And, in detail , it is not clear if the receiving ZFS file system could be used regularly while it is in receiving mode: in poor words is it possible to read and export in nfs, files from a ZFS file system while it is receiving update from another ZFS send ? First, the zfs send works only on a snapshot. -i sends incremental snapshots, so you would think that would work. From the zfs man page, you'll see that during a receive, the destination file system is unmounted and cannot be accessed during the receive. If an incremental stream is received, then the destina- tion file system must already exist, and its most recent snapshot must match the incremental stream's source. The destination file system and all of its child file sys- tems are unmounted and cannot be accessed during the receive operation. Actually we don't unmount the file systems anymore for incremental send/recv, see: 6425096 want online 'zfs recv' (read only and read/write) Available since November 2007 in OpenSolaris/Nevada. Coming to a s10u6 near you. eric ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] questions about ZFS Send/Receive
Obviously, I should stop answering, as all I deal with and all that I will deal with is GA Solaris. OpenSolaris might as well not exist as far as I'm concerned. With that in mind, I'll just keep reading and appreciating all of the good zfs info that comes along. Peace out. On Tue, Jul 29, 2008 at 5:54 PM, eric kustarz [EMAIL PROTECTED] wrote: On Jul 29, 2008, at 2:24 PM, Chris Cosby wrote: On Tue, Jul 29, 2008 at 5:13 PM, Stefano Pini [EMAIL PROTECTED] wrote: Hi guys, we are proposing a customer a couple of X4500 (24 Tb) used as NAS (i.e. NFS server). Both server will contain the same files and should be accessed by different clients at the same time (i.e. they should be both active) So we need to guarantee that both x4500 contain the same files: We could simply copy the contents on both x4500 , which is an option because the new files are in a limited number and rate , but we would really like to use ZFS send receive commands: If they are truly limited, something like an rsync or similar. There was a script being thrown around a while back that was touted as the Best Backup Script That Doesn't Do Backups, but I can't find it. In essence, it just created a list of what changed since the last backup and allowed you to use tar/cpio/cp - whatever to do the backup. I think zfs send/recv would be a great way to go here - see below. AFAIK the commands works fine but generally speaking are there any known limitations ? And, in detail , it is not clear if the receiving ZFS file system could be used regularly while it is in receiving mode: in poor words is it possible to read and export in nfs, files from a ZFS file system while it is receiving update from another ZFS send ? First, the zfs send works only on a snapshot. -i sends incremental snapshots, so you would think that would work. From the zfs man page, you'll see that during a receive, the destination file system is unmounted and cannot be accessed during the receive. If an incremental stream is received, then the destina- tion file system must already exist, and its most recent snapshot must match the incremental stream's source. The destination file system and all of its child file sys- tems are unmounted and cannot be accessed during the receive operation. Actually we don't unmount the file systems anymore for incremental send/recv, see: 6425096 want online 'zfs recv' (read only and read/write) Available since November 2007 in OpenSolaris/Nevada. Coming to a s10u6 near you. eric -- chris -at- microcozm -dot- net === Si Hoc Legere Scis Nimium Eruditionis Habes ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] Ideal Setup: RAID-5, Areca, etc!
Hello Bob, Friday, July 25, 2008, 9:00:41 PM, you wrote: BF On Fri, 25 Jul 2008, Brandon High wrote: I am not sure if ZFS really has to wait for both sides of a mirror to finish, but even if it does, if there are enough VDEVs then ZFS can still proceed with writing. It would have to wait on an fsync() call, since that won't return until both halves of the mirror have completed. If the cards you're using have NVRAM, then they could return faster. BF While it is possible that the ZFS implementation does actually wait BF for both drives to report that the data is written, it only has to BF know that the data is committed to one drive in order to satisfy the BF synchronous write expectation. This is not the case for legacy BF mirrored pairs where the disks are absolutely required to contain the BF same content at the same logical locations. ZFS does not require that BF disks in a mirrored pair contain identical content at all times. AFAIK zfs does require that all writes are committed to all devices to satisfy configured redundancy unless some of devices were marked as failed. Otherwise, especially in sync case, you could loose data because of a disk failure in a redundant configuration. Not to mention other possible issues. -- Best regards, Robert Milkowskimailto:[EMAIL PROTECTED] http://milek.blogspot.com ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] The best motherboard for a home ZFS fileserver
A little case modding maybe not so difficult...there are examples (and instructions) like: http://www.mashie.org/casemods/udat2.html But for sure there are more advanced like: http://forums.bit-tech.net/showthread.php?t=76374pp=20 And here you can have a full example of the human ingenious!! http://www.darkroastedblend.com/2007/06/cool-computer-case-mods.html 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] The best motherboard for a home ZFS fileserver
that mashie link might be exactly what i wanted... that mini-itx board w/ 6 SATA. use CF maybe for boot (might need IDE to CF converter) - 5 drive holder (hotswap as a bonus) - you get 4 gig ram, core2-based chip (64-bit), onboard graphics, 5 SATA2 drives... that is cool. however. would need to hack it up (and I don't have any metal cutting stuff) and who knows how loud it is without any front on those drives. i'd want a small cover on top to help with noise. looks like i might have to hang out over on the mashie site now too ;) 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-code] Peak every 4-5 second
Hello Bob, Friday, July 25, 2008, 4:58:54 PM, you wrote: BF On Fri, 25 Jul 2008, Robert Milkowski wrote: Both on 2540 and 6540 if you do not disable it your performance will be very bad especially for synchronous IOs as ZIL will force your array to flush its cache every time. If you are not using ZFS on any other storage than 2540 on your servers then put set zfs:zfs_nocacheflush=1 in /etc/system and do a reboot. If you haven't done so it should help you considerably. BF This does not seem wise since then data (records of trades) may be BF lost if the system crashes or loses power. It is much better to apply BF the firmware tweaks so that the 2540 reports that the data is written BF as soon as it is safely in its NVRAM rather than waiting for it to be BF on disk. ZFS should then perform rather well with low latency. Both cases are basically the same. Please notice I'm not talking about disabling ZIL, I'm talking about disabling cache flushes in ZFS. ZFS will still wait for the array to confirm that it did receive data (nvram). If you loose power the behavior will be the same - no difference here. -- Best regards, Robert Milkowskimailto:[EMAIL PROTECTED] http://milek.blogspot.com ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] The best motherboard for a home ZFS fileserver
If I understood properly there is just one piece that has to be modified: a flat alluminium board with a squared hole in the center, that any fine mechanic around your city should do very easily... The problem more than the noise in this tight case might be the temperature! 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-code] Peak every 4-5 second
On Wed, 30 Jul 2008, Robert Milkowski wrote: Both cases are basically the same. Please notice I'm not talking about disabling ZIL, I'm talking about disabling cache flushes in ZFS. ZFS will still wait for the array to confirm that it did receive data (nvram). So it seems that in your opinion, the periodic burp in system call completion time is due to ZFS's periodic cache flush. That is certainly quite possible. Testing will prove it, but the testing can be on someone else's system rather than my own. :) Bob == Bob Friesenhahn [EMAIL PROTECTED], http://www.simplesystems.org/users/bfriesen/ GraphicsMagick Maintainer,http://www.GraphicsMagick.org/ ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
[zfs-discuss] My first 'unrecoverable error', what to do?
I've had my 10x500 ZFS+ running for probably 6 months now and had thought it was scrubbing occasionally (wrong) so I started a scrub this morning, its almost done now and I got this: errors: No known data errors # zpool status pool: pile state: ONLINE status: One or more devices has experienced an unrecoverable error. An attempt was made to correct the error. Applications are unaffected. action: Determine if the device needs to be replaced, and clear the errors using 'zpool clear' or replace the device with 'zpool replace'. see: http://www.sun.com/msg/ZFS-8000-9P scrub: scrub in progress, 97.93% done, 0h5m to go config: NAMESTATE READ WRITE CKSUM pileONLINE 0 0 0 raidz2ONLINE 0 0 0 c5t0d0 ONLINE 0 0 0 c5t1d0 ONLINE 0 0 0 c5t2d0 ONLINE 0 0 0 c5t3d0 ONLINE 0 0 0 c5t4d0 ONLINE 0 0 1 c5t5d0 ONLINE 0 0 0 c5t6d0 ONLINE 0 0 1 c5t7d0 ONLINE 0 0 0 c3d0ONLINE 0 0 1 c4d0ONLINE 0 0 0 So it says its a minor error but still one to be concerned about, I thought resilvering takes care of checksum errors, does it not? Should I be running to buy 3 new 500GB drives? Thanks, Sam 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] My first 'unrecoverable error', what to do?
Could this someway be related to this rather large (100GB) difference that 'zfs list' and 'zpool list' report: NAME SIZE USED AVAILCAP HEALTH ALTROOT pile 4.53T 4.31T 223G95% ONLINE - # zfs list NAME USED AVAIL REFER MOUNTPOINT pile 3.44T 120G 3.44T /pile I know there should be a 1TB difference in SIZE but the difference in AVAIL makes no sense. 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] My first 'unrecoverable error', what to do?
Sam schrieb: I've had my 10x500 ZFS+ running for probably 6 months now and had thought it was scrubbing occasionally (wrong) so I started a scrub this morning, its almost done now and I got this: errors: No known data errors # zpool status pool: pile state: ONLINE status: One or more devices has experienced an unrecoverable error. An attempt was made to correct the error. Applications are unaffected. action: Determine if the device needs to be replaced, and clear the errors using 'zpool clear' or replace the device with 'zpool replace'. see: http://www.sun.com/msg/ZFS-8000-9P scrub: scrub in progress, 97.93% done, 0h5m to go config: NAMESTATE READ WRITE CKSUM pileONLINE 0 0 0 raidz2ONLINE 0 0 0 c5t0d0 ONLINE 0 0 0 c5t1d0 ONLINE 0 0 0 c5t2d0 ONLINE 0 0 0 c5t3d0 ONLINE 0 0 0 c5t4d0 ONLINE 0 0 1 c5t5d0 ONLINE 0 0 0 c5t6d0 ONLINE 0 0 1 c5t7d0 ONLINE 0 0 0 c3d0ONLINE 0 0 1 c4d0ONLINE 0 0 0 So it says its a minor error but still one to be concerned about, I thought resilvering takes care of checksum errors, does it not? Should I be running to buy 3 new 500GB drives? Failures can have different cause. Maybe a cable is defect. Also occosinal defect sectors are normal and are managed quite good by the defect managment of the drive. You can use zpool clear to reset the counters to 0. Arne ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] The best motherboard for a home ZFS fileserver
exactly. that's why i'm trying to get an account on that site (looks like open registration for the forums is disabled) so i can shoot the breeze and talk about all this stuff too. zfs would be perfect for this as most these guys are trying to find hardware raid cards that will fit, etc... with mini-itx boards coming with 4 and now 6 ports, that isn't an issue, as long as onboard SATA2+ZFS is fast enough everyone wins. 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] My first 'unrecoverable error', what to do?
On Tue, 29 Jul 2008, Sam wrote: So it says its a minor error but still one to be concerned about, I thought resilvering takes care of checksum errors, does it not? Should I be running to buy 3 new 500GB drives? Presumably these are SATA drives. Studies show that typical SATA drives tend to produce recurring data errors during their lifetime so a few data errors are likely nothing to be alarmed about. If you see many tens or hundreds then there would be cause for concern. Enterprise SCSI drives produce very few such errors and evidence suggests that data errors may portend doom. I have yet to see an error here. Knock on wood! Bob == Bob Friesenhahn [EMAIL PROTECTED], http://www.simplesystems.org/users/bfriesen/ GraphicsMagick Maintainer,http://www.GraphicsMagick.org/ ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss