Re: [zfs-discuss] zpool import panics
Am 11.11.10 11:51, schrieb Ville Ojamo: Some generic ideas: Looks like the zdb output is cut, is it cut because of mail reader or because zdb died for some reason? If died pstack core.. What does panic stack trace say? Does zpool import work any better with option -f or -F? Some have in the past suggested giving -o ro to it as well, but don't think that would do much (?). Well, I had cut the zdb output, since it was going on listing all sorts of other information from the datasets and I figured that this output wouldn't be of any use to anyone, as long as nobody requests it. I tried to import the pool when having booted from the OSol snv_134 live CD, with the following options: echo aok/W 1 | mdb -kw echo zfs_recover/W 1 | mdb -kw zpool import -f -F pool zfs then read from the devices and after a couple of seconds the host rebooted again with a kernel panic. I guess, since I booted off the live CD I don't have any core dumps at hand. Maybe on the other host, which also has the same issue with another pool, where a core dump should have been written somewhere, although I seem unable to find it anywhere. -- Stephan Budach Jung von Matt/it-services GmbH Glashüttenstraße 79 20357 Hamburg Tel: +49 40-4321-1353 Fax: +49 40-4321-1114 E-Mail: stephan.bud...@jvm.de Internet: http://www.jvm.com Geschäftsführer: Ulrich Pallas, Frank Wilhelm AG HH HRB 98380 ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] zpool import panics
Am 11.11.10 14:26, schrieb Steve Gonczi: Dumpadm should tell you how your Dumps are set up Also you could load mdb before importing I have located the dump, it's called vmdump.0. I also loaded mdb before I imported the pool, but that didn't help. Actually I tried it this way: mdb -K -F :c zpool import -f -o readonly pool Afterwards I tried to get back to mdb by hitting F1-a, but that didn't work - it was only printing 'a' on the console. Otherwise I would have tried systemdump, but that didn't came to pass. Is there anything I can do with the vmdump.0 file. Unfortuanetly I am not a Kernel hacker… Thanks -- Stephan Budach Jung von Matt/it-services GmbH Glashüttenstraße 79 20357 Hamburg Tel: +49 40-4321-1353 Fax: +49 40-4321-1114 E-Mail: stephan.bud...@jvm.de Internet: http://www.jvm.com Geschäftsführer: Ulrich Pallas, Frank Wilhelm AG HH HRB 98380 ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] zpool import panics
Hi, # savecore -vf vmdump.0 This should produce two files: unix.0 and vmcore.0 Now we use mdb on these as follows: # mdb unix.0 vmcore.0 Now when presented with the '' prompt, type ::status and send us all the output please? --- W. A. Khushil Dep - khushil@gmail.com - 07905374843 Visit my blog at http://www.khushil.com/ On 11 November 2010 14:51, Stephan Budach stephan.bud...@jvm.de wrote: vmdump.0 ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] zpool import panics
The vmdump.0 is a compressed crash dump. You will need to convert it to a format that can be read. # savecore -f ./vmdump.0 ./ This will create a couple of files, but the ones you will need next is unix.0 vmcore.0. Use mdb to print out the stack. # mdb unix.0 vmcore.0 run the following to print the stack. This would at least tell you what function the system is having a panic in. You could then do a sunsolve search or google search. $C and gather zio_state data ::zio_state And check the msgbuf to see if there are any hardware problems. ::msgbuf Then quit mdb. More drill down would be dependent on what you see. ::quit Dave On 11/11/10 08:51, Stephan Budach wrote: Am 11.11.10 14:26, schrieb Steve Gonczi: Dumpadm should tell you how your Dumps are set up Also you could load mdb before importing I have located the dump, it's called vmdump.0. I also loaded mdb before I imported the pool, but that didn't help. Actually I tried it this way: mdb -K -F :c zpool import -f -o readonly pool Afterwards I tried to get back to mdb by hitting F1-a, but that didn't work - it was only printing 'a' on the console. Otherwise I would have tried systemdump, but that didn't came to pass. Is there anything I can do with the vmdump.0 file. Unfortuanetly I am not a Kernel hacker… Thanks - ___ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Re: [zfs-discuss] zpool import panics
David, thanks so much (and of course to all other helpful souls here as well) for providing such great guidance! Here we go: Am 11.11.10 16:17, schrieb David Blasingame Oracle: The vmdump.0 is a compressed crash dump. You will need to convert it to a format that can be read. # savecore -f ./vmdump.0 ./ This will create a couple of files, but the ones you will need next is unix.0 vmcore.0. Use mdb to print out the stack. # mdb unix.0 vmcore.0 run the following to print the stack. This would at least tell you what function the system is having a panic in. You could then do a sunsolve search or google search. $C $C ff0023b7d450 zap_leaf_lookup_closest+0x40(ff0588c61750, 0, 0, ff0023b7d470) ff0023b7d4e0 fzap_cursor_retrieve+0xc9(ff0588c61750, ff0023b7d5c0, ff0023b7d600) ff0023b7d5a0 zap_cursor_retrieve+0x19a(ff0023b7d5c0, ff0023b7d600) ff0023b7d780 zfs_purgedir+0x4c(ff0581079260) ff0023b7d7d0 zfs_rmnode+0x52(ff0581079260) ff0023b7d810 zfs_zinactive+0xb5(ff0581079260) ff0023b7d860 zfs_inactive+0xee(ff058118ae00, ff056ac3c108, 0) ff0023b7d8b0 fop_inactive+0xaf(ff058118ae00, ff056ac3c108, 0) ff0023b7d8d0 vn_rele+0x5f(ff058118ae00) ff0023b7dac0 zfs_unlinked_drain+0xaf(ff05874c8b00) ff0023b7daf0 zfsvfs_setup+0xfb(ff05874c8b00, 1) ff0023b7db50 zfs_domount+0x17c(ff0588aaf698, ff0580cb3d80) ff0023b7dc70 zfs_mount+0x1e4(ff0588aaf698, ff0588a9f100, ff0023b7de20, ff056ac3c108) ff0023b7dca0 fsop_mount+0x21(ff0588aaf698, ff0588a9f100, ff0023b7de20, ff056ac3c108) ff0023b7de00 domount+0xae3(0, ff0023b7de20, ff0588a9f100, ff056ac3c108, ff0023b7de18) ff0023b7de80 mount+0x121(ff0580c7e548, ff0023b7de98) ff0023b7dec0 syscall_ap+0x8c() ff0023b7df10 _sys_sysenter_post_swapgs+0x149() and gather zio_state data ::zio_state ::zio_state ADDRESS TYPE STAGEWAITER ff0584be2348 NULL OPEN - ff0570ebcc88 NULL OPEN - And check the msgbuf to see if there are any hardware problems. ::msgbuf ::msgbuf MESSAGE QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50925h, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 26h 0h 0h 0h 0h 0h QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50aefh, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 26h 0h 0h 0h 0h 0h WARNING: pool 'obelixData' could not be loaded as it was last accessed by another system (host : opensolaris hostid: 0x75b3c). See: http://www.sun.com/msg/ZFS-8000-EY QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50925h, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 26h 0h 0h 0h 0h 0h QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50aefh, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 26h 0h 0h 0h 0h 0h WARNING: pool 'obelixData' could not be loaded as it was last accessed by another system (host : opensolaris hostid: 0x75b3c). See: http://www.sun.com/msg/ZFS-8000-EY QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50aefh, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 26h 0h 0h 0h 0h 0h QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50925h, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 26h 0h 0h 0h 0h 0h WARNING: pool 'obelixData' could not be loaded as it was last accessed by another system (host : opensolaris hostid: 0x75b3c). See: http://www.sun.com/msg/ZFS-8000-EY pseudo-device: devinfo0 devinfo0 is /pseudo/devi...@0 pcplusmp: asy (asy) instance 0 irq 0x4 vector 0xb0 ioapic 0x0 intin 0x4 is bound to cpu 2 ISA-device: asy0 asy0 is /p...@0,0/i...@1f/a...@1,3f8 pcplusmp: asy (asy) instance 1 irq 0x3 vector 0xb1 ioapic 0x0 intin 0x3 is bound to cpu 3 ISA-device: asy1 asy1 is /p...@0,0/i...@1f/a...@1,2f8 pseudo-device: ucode0 ucode0 is /pseudo/uc...@0 sgen0 at ata0: target 0 lun 0 sgen0 is /p...@0,0/pci-...@1f,2/i...@0/s...@0,0 sgen2 at mega_sas0: target 0 lun 1 sgen2 is /p...@0,0/pci8086,2...@1c/pci1028,1...@0/s...@0,1 QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50925h, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 26h 0h 0h 0h 0h 0h QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50925h, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 20h 0h 0h 0h 0h 0h sd4 at fp0: unit-address w21d02305ff42,0: 50925 sd4 is /p...@0,0/pci8086,3...@7/pci1077,1...@0/f...@0,0/d...@w21d02305ff42,0 pseudo-device: llc10 llc10 is /pseudo/l...@0 pseudo-device: lofi0 lofi0 is /pseudo/l...@0 pseudo-device: ramdisk1024 ramdisk1024 is /pseudo/ramd...@1024 pseudo-device: dcpc0 dcpc0 is /pseudo/d...@0 pseudo-device: fasttrap0 fasttrap0 is /pseudo/fastt...@0 pseudo-device: fbt0 fbt0 is
Re: [zfs-discuss] zpool import panics
In this function, the second argument is a pointer to the osname (mount). You can dump out the string of what it is. ff0023b7db50 zfs_domount+0x17c(ff0588aaf698, ff0580cb3d80) mdb unix.0 vmcore.0 ff0580cb3d80/S Should print out the offending FS. You could try to then import the pool read only (-o ro) and set the parameter to the file system to readonly (zfs set readonly=on fs). Dave On 11/11/10 09:37, Stephan Budach wrote: David, thanks so much (and of course to all other helpful souls here as well) for providing such great guidance! Here we go: Am 11.11.10 16:17, schrieb David Blasingame Oracle: The vmdump.0 is a compressed crash dump. You will need to convert it to a format that can be read. # savecore -f ./vmdump.0 ./ This will create a couple of files, but the ones you will need next is unix.0 vmcore.0. Use mdb to print out the stack. # mdb unix.0 vmcore.0 run the following to print the stack. This would at least tell you what function the system is having a panic in. You could then do a sunsolve search or google search. $C $C ff0023b7d450 zap_leaf_lookup_closest+0x40(ff0588c61750, 0, 0, ff0023b7d470) ff0023b7d4e0 fzap_cursor_retrieve+0xc9(ff0588c61750, ff0023b7d5c0, ff0023b7d600) ff0023b7d5a0 zap_cursor_retrieve+0x19a(ff0023b7d5c0, ff0023b7d600) ff0023b7d780 zfs_purgedir+0x4c(ff0581079260) ff0023b7d7d0 zfs_rmnode+0x52(ff0581079260) ff0023b7d810 zfs_zinactive+0xb5(ff0581079260) ff0023b7d860 zfs_inactive+0xee(ff058118ae00, ff056ac3c108, 0) ff0023b7d8b0 fop_inactive+0xaf(ff058118ae00, ff056ac3c108, 0) ff0023b7d8d0 vn_rele+0x5f(ff058118ae00) ff0023b7dac0 zfs_unlinked_drain+0xaf(ff05874c8b00) ff0023b7daf0 zfsvfs_setup+0xfb(ff05874c8b00, 1) ff0023b7db50 zfs_domount+0x17c(ff0588aaf698, ff0580cb3d80) ff0023b7dc70 zfs_mount+0x1e4(ff0588aaf698, ff0588a9f100, ff0023b7de20, ff056ac3c108) ff0023b7dca0 fsop_mount+0x21(ff0588aaf698, ff0588a9f100, ff0023b7de20, ff056ac3c108) ff0023b7de00 domount+0xae3(0, ff0023b7de20, ff0588a9f100, ff056ac3c108, ff0023b7de18) ff0023b7de80 mount+0x121(ff0580c7e548, ff0023b7de98) ff0023b7dec0 syscall_ap+0x8c() ff0023b7df10 _sys_sysenter_post_swapgs+0x149() and gather zio_state data ::zio_state ::zio_state ADDRESS TYPE STAGEWAITER ff0584be2348 NULL OPEN - ff0570ebcc88 NULL OPEN - And check the msgbuf to see if there are any hardware problems. ::msgbuf ::msgbuf MESSAGE QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50925h, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 26h 0h 0h 0h 0h 0h QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50aefh, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 26h 0h 0h 0h 0h 0h WARNING: pool 'obelixData' could not be loaded as it was last accessed by another system (host : opensolaris hostid: 0x75b3c). See: http://www.sun.com/msg/ZFS-8000-EY QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50925h, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 26h 0h 0h 0h 0h 0h QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50aefh, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 26h 0h 0h 0h 0h 0h WARNING: pool 'obelixData' could not be loaded as it was last accessed by another system (host : opensolaris hostid: 0x75b3c). See: http://www.sun.com/msg/ZFS-8000-EY QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50aefh, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 26h 0h 0h 0h 0h 0h QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50925h, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 26h 0h 0h 0h 0h 0h WARNING: pool 'obelixData' could not be loaded as it was last accessed by another system (host : opensolaris hostid: 0x75b3c). See: http://www.sun.com/msg/ZFS-8000-EY pseudo-device: devinfo0 devinfo0 is /pseudo/devi...@0 pcplusmp: asy (asy) instance 0 irq 0x4 vector 0xb0 ioapic 0x0 intin 0x4 is bound to cpu 2 ISA-device: asy0 asy0 is /p...@0,0/i...@1f/a...@1,3f8 pcplusmp: asy (asy) instance 1 irq 0x3 vector 0xb1 ioapic 0x0 intin 0x3 is bound to cpu 3 ISA-device: asy1 asy1 is /p...@0,0/i...@1f/a...@1,2f8 pseudo-device: ucode0 ucode0 is /pseudo/uc...@0 sgen0 at ata0: target 0 lun 0 sgen0 is /p...@0,0/pci-...@1f,2/i...@0/s...@0,0 sgen2 at mega_sas0: target 0 lun 1 sgen2 is /p...@0,0/pci8086,2...@1c/pci1028,1...@0/s...@0,1 QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50925h, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 26h 0h 0h 0h 0h 0h QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50925h, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h
Re: [zfs-discuss] zpool import panics
David, thanks a lot for your support. I have been able to get both of my zpools up again by checking which zfs fs caused these problems. And... today I also learned at least a bit about zpool troubleshooting. Thanks Stephan -- Von meinem iPhone iOS4 gesendet. In this function, the second argument is a pointer to the osname (mount). You can dump out the string of what it is. ff0023b7db50 zfs_domount+0x17c(ff0588aaf698, ff0580cb3d80) mdb unix.0 vmcore.0 ff0580cb3d80/S Should print out the offending FS. You could try to then import the pool read only (-o ro) and set the parameter to the file system to readonly (zfs set readonly=on fs). Dave On 11/11/10 09:37, Stephan Budach wrote: David, thanks so much (and of course to all other helpful souls here as well) for providing such great guidance! Here we go: Am 11.11.10 16:17, schrieb David Blasingame Oracle: The vmdump.0 is a compressed crash dump. You will need to convert it to a format that can be read. # savecore -f ./vmdump.0 ./ This will create a couple of files, but the ones you will need next is unix.0 vmcore.0. Use mdb to print out the stack. # mdb unix.0 vmcore.0 run the following to print the stack. This would at least tell you what function the system is having a panic in. You could then do a sunsolve search or google search. $C $C ff0023b7d450 zap_leaf_lookup_closest+0x40(ff0588c61750, 0, 0, ff0023b7d470) ff0023b7d4e0 fzap_cursor_retrieve+0xc9(ff0588c61750, ff0023b7d5c0, ff0023b7d600) ff0023b7d5a0 zap_cursor_retrieve+0x19a(ff0023b7d5c0, ff0023b7d600) ff0023b7d780 zfs_purgedir+0x4c(ff0581079260) ff0023b7d7d0 zfs_rmnode+0x52(ff0581079260) ff0023b7d810 zfs_zinactive+0xb5(ff0581079260) ff0023b7d860 zfs_inactive+0xee(ff058118ae00, ff056ac3c108, 0) ff0023b7d8b0 fop_inactive+0xaf(ff058118ae00, ff056ac3c108, 0) ff0023b7d8d0 vn_rele+0x5f(ff058118ae00) ff0023b7dac0 zfs_unlinked_drain+0xaf(ff05874c8b00) ff0023b7daf0 zfsvfs_setup+0xfb(ff05874c8b00, 1) ff0023b7db50 zfs_domount+0x17c(ff0588aaf698, ff0580cb3d80) ff0023b7dc70 zfs_mount+0x1e4(ff0588aaf698, ff0588a9f100, ff0023b7de20, ff056ac3c108) ff0023b7dca0 fsop_mount+0x21(ff0588aaf698, ff0588a9f100, ff0023b7de20, ff056ac3c108) ff0023b7de00 domount+0xae3(0, ff0023b7de20, ff0588a9f100, ff056ac3c108, ff0023b7de18) ff0023b7de80 mount+0x121(ff0580c7e548, ff0023b7de98) ff0023b7dec0 syscall_ap+0x8c() ff0023b7df10 _sys_sysenter_post_swapgs+0x149() and gather zio_state data ::zio_state ::zio_state ADDRESS TYPE STAGEWAITER ff0584be2348 NULL OPEN - ff0570ebcc88 NULL OPEN - And check the msgbuf to see if there are any hardware problems. ::msgbuf ::msgbuf MESSAGE QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50925h, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 26h 0h 0h 0h 0h 0h QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50aefh, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 26h 0h 0h 0h 0h 0h WARNING: pool 'obelixData' could not be loaded as it was last accessed by another system (host : opensolaris hostid: 0x75b3c). See: http://www.sun.com/msg/ZFS-8000-EY QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50925h, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 26h 0h 0h 0h 0h 0h QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50aefh, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 26h 0h 0h 0h 0h 0h WARNING: pool 'obelixData' could not be loaded as it was last accessed by another system (host : opensolaris hostid: 0x75b3c). See: http://www.sun.com/msg/ZFS-8000-EY QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50aefh, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 26h 0h 0h 0h 0h 0h QEL qlc(0,0): ql_status_error, check condition sense data, d_id=50925h, lun=0h 70h 0h 5h 0h 0h 0h 0h ah 0h 0h 0h 0h 26h 0h 0h 0h 0h 0h WARNING: pool 'obelixData' could not be loaded as it was last accessed by another system (host : opensolaris hostid: 0x75b3c). See: http://www.sun.com/msg/ZFS-8000-EY pseudo-device: devinfo0 devinfo0 is /pseudo/devi...@0 pcplusmp: asy (asy) instance 0 irq 0x4 vector 0xb0 ioapic 0x0 intin 0x4 is bound to cpu 2 ISA-device: asy0 asy0 is /p...@0,0/i...@1f/a...@1,3f8 pcplusmp: asy (asy) instance 1 irq 0x3 vector 0xb1 ioapic 0x0 intin 0x3 is bound to cpu 3 ISA-device: asy1 asy1 is /p...@0,0/i...@1f/a...@1,2f8 pseudo-device: ucode0 ucode0 is /pseudo/uc...@0 sgen0 at ata0: target 0 lun 0 sgen0 is