While running the regression tests I hit the following panic while in the gnbd section of the tests. (3 node cluster, link-13 exporting, link-14 importing) [vs_gnbd] Exporting sdb1... [vs_gnbd] gnbd_export sdb1...pass [vs_gnbd] gnbd_import from link-13 to link-14...pass [vs_gnbd] [vs_gnbd] making the filesystems on link-14... [vs_gnbd] mount -t gfs /dev/gnbd/sdb1 /mnt/gnbd [vs_gnbd] [vs_gnbd] Starting I/O... [vs_gnbd] Getting /mnt/gnbd size from link-14 [vs_gnbd] Starting remote node IO... It was running the mmap1 tag, which completed without an error, so the <pass> section of the test case was run... ' rm -f mmap1' This was the last thing it ran before the panic. <test tag="mmap1"> <cmd> <![CDATA[ iogen -i 30s -m sequential -s mmread,mmwrite -t 1b -T 40000b 40000b:mmap1 | doio -av ]]> </cmd> <pass> <![CDATA[ rm -f mmap1 ]]> </pass> </test> [link-14] <start tag="mmap1" pid="26225" time="Thu Aug 18 09:17:55 2005" type=""/> [link-14] [mmap1] [link-14] [mmap1] iogen starting up with the following: [link-14] [mmap1] [link-14] [mmap1] Out-pipe: stdout [link-14] [mmap1] Iterations: 30 seconds [link-14] [mmap1] Seed: 26227 [link-14] [mmap1] Offset-Mode: sequential [link-14] [mmap1] Overlap Flag: off [link-14] [mmap1] Mintrans: 512 (1 blocks) [link-14] [mmap1] Maxtrans: 20480000 (40000 blocks) [link-14] [mmap1] O_RAW/O_SSD Multiple: (Determined by device) [link-14] [mmap1] Syscalls: mmread mmwrite [link-14] [mmap1] Aio completion types: none [link-14] [mmap1] Flags: buffered sync [link-14] [mmap1] [link-14] [mmap1] Test Files: [link-14] [mmap1] [link-14] [mmap1] Path Length iou raw iou file [link-14] [mmap1] (bytes) (bytes) (bytes) type [link-14] [mmap1] ----------------------------------------------------------------------------- [link-14] [mmap1] /mnt/gnbd/link-14/mmap1 20480000 1 512 regular [link-14] <pass tag="mmap1" pid="26225", time="Thu Aug 18 09:18:26 2005"/> [link-14] <start tag="mmap1" pid="26229" time="Thu Aug 18 09:18:26 2005" type="pass"/> [link-14] <ignore tag="mmap1" pid="26229" time="Thu Aug 18 09:18:39 2005"/> [link-14] Read from remote host link-14: Connection reset by peer^M <fail tag="link-14" pid="31399" time="Thu Aug 18 14:35:31 2005" ec="255"/> ALL STOP! ------------------------------------- Unable to handle kernel paging request at virtual address 0000000000200220 gfs_inoded[25844]: Oops 11012296146944 [1] Modules linked in: lock_dlm(U) gnbd(U) lock_nolock(U) gfs(U) lock_harness(U) dlm(U) cman(U) qla2xxx md5 ipv6 parport_pc lp parport autofs4 sunrpc vfat fat dm_mod button ohci_hcd ehci_hcd tg3 e100 mii ext3 jbd lpfc scsi_transport_fc mptscsih mptbase sd_mod scsi_mod Pid: 25844, CPU 0, comm: gfs_inoded psr : 0000121008026038 ifs : 800000000000060e ip : [<a0000002007b4ae1>] Not tainted ip is at gfs_depend_add+0x341/0x4e0 [gfs] unat: 0000000000000000 pfs : 000000000000060e rsc : 0000000000000003 rnat: 0000000000000000 bsps: 0000000000000000 pr : 0000000000002a41 ldrs: 0000000000000000 ccv : 0000000000000000 fpsr: 0009804c8a70033f csd : 0000000000000000 ssd : 0000000000000000 b0 : a0000002007b4ae0 b6 : a000000100015c40 b7 : a00000010000ed10 f6 : 1003e0000000000001400 f7 : 1003e8080808080808081 f8 : 1003e00000000000027d8 f9 : 1003e000000000ff00000 f10 : 1003e000000003b5f2d38 f11 : 1003e44b831eee7285baf r1 : a00000010099d0d0 r2 : 000000000000060e r3 : e00000003f925280 r8 : 0000000000000000 r9 : a0007fffffff4fa0 r10 : a0007fffffff4f78 r11 : 000000000006e9ef r12 : e00000002f097ce0 r13 : e00000002f090000 r14 : 0000000000000000 r15 : 0000000000000036 r16 : 0000000000000088 r17 : 0000000000000012 r18 : 0000000000200200 r19 : 000000010a328b74 r20 : 000000000007e6c8 r21 : 000000000000fcd9 r22 : e00000002f090dd4 r23 : a0000001007b0000 r24 : a0000001007b0000 r25 : e00000002f097c50 r26 : 000000000000000e r27 : 0000000000000000 r28 : a0000002003f44c4 r29 : 00000000000384c4 r30 : 0000000000000000 r31 : a0000002003bc258 Call Trace: [<a000000100016a60>] show_stack+0x80/0xa0 sp=e00000002f097870 bsp=e00000002f091150 [<a000000100017370>] show_regs+0x890/0x8c0 sp=e00000002f097a40 bsp=e00000002f091108 [<a00000010003d7f0>] die+0x150/0x240 sp=e00000002f097a60 bsp=e00000002f0910c8 [<a000000100060930>] ia64_do_page_fault+0x870/0xb80 sp=e00000002f097a60 bsp=e00000002f091060 [<a00000010000f480>] ia64_leave_kernel+0x0/0x260 sp=e00000002f097b10 bsp=e00000002f091060 [<a0000002007b4ae0>] gfs_depend_add+0x340/0x4e0 [gfs] sp=e00000002f097ce0 bsp=e00000002f090fe8 [<a00000020074b020>] gfs_wipe_buffers+0x5c0/0x920 [gfs] sp=e00000002f097cf0 bsp=e00000002f090f70 [<a0000002007b9f50>] gfs_difree+0x90/0xc0 [gfs] sp=e00000002f097d00 bsp=e00000002f090f40 [<a0000002007703a0>] gfs_inode_dealloc+0xb80/0xf60 [gfs] sp=e00000002f097d00 bsp=e00000002f090ed8 [<a0000002007c2650>] gfs_unlinked_dealloc+0x70/0x240 [gfs] sp=e00000002f097e30 bsp=e00000002f090e88 [<a0000002007433a0>] gfs_inoded+0x160/0x260 [gfs] sp=e00000002f097e30 bsp=e00000002f090e38 [<a000000100018930>] kernel_thread_helper+0x30/0x60 sp=e00000002f097e30 bsp=e00000002f090e10 [<a000000100008c60>] start_kernel_thread+0x20/0x40 sp=e00000002f097e30 bsp=e00000002f090e10 Kernel panic - not syncing: Fatal exception Looks like it may be a dup/related to: 164324 â gfs oops in gfs_wipe_buffers
*** This bug has been marked as a duplicate of 164324 ***