From: <4n...@re...> - 2008-01-17 11:08:12
|
On mercoled=EC 16 gennaio 2008, Vladislav Bolkhovitin wrote: > cheng xu wrote: > > im seeing irregular crashes with scst and LSI card (amd64bit) > > the only output i can get is > What kind of activity did you do before crash? I all , tonoght at 4 oclock I've also a scst crash.... last operation is cron backup , using an lto tape on a lsi card.... so I think it can be same problem, I've update scst yesterday , from @239 t= o=20 @245 svn , at cron backup time I see that: Jan 17 04:28:02 storage kernel: ------------[ cut here ]------------ Jan 17 04:28:02 storage kernel: kernel BUG at lib/radix-tree.c:319! Jan 17 04:28:02 storage kernel: invalid opcode: 0000 [1] SMP Jan 17 04:28:02 storage kernel: CPU 1 Jan 17 04:28:02 storage kernel: Modules linked in: nfsd exportfs lockd nfs_= acl=20 auth_rpcgss ipv6 iscsi_scst qla2x00tgt scst_cdrom scst_changer scst_tape scst_vdisk scst sunrpc bonding dm_multipath sbs battery backlight ac osst= =20 qla2xxx i2c_i801 e1000 floppy sg i2c_core st scsi_transport_fc ide_cd button cdrom dm_snapshot dm_zero dm_mirror dm_mod ide_disk ata_piix libata 3w_9xx= x=20 mptspi mptscsih scsi_transport_spi mptbase sd_mod scsi_mod ext3 jbd Jan 17 04:28:02 storage kernel: Pid: 9414, comm: tar Not tainted=20 2.6.23.9-SAN21 #2 Jan 17 04:28:02 storage kernel: RIP: 0010:[<ffffffff802dfe28>] =20 [<ffffffff802dfe28>] radix_tree_insert+0x152/0x18c Jan 17 04:28:02 storage kernel: RSP: 0018:ffff8101010199c8 EFLAGS: 00010086 Jan 17 04:28:02 storage kernel: RAX: 00000000ffffffff RBX: ffff810118f84de8= =20 RCX: 000000000004c900 Jan 17 04:28:02 storage kernel: RDX: 0000000000000000 RSI: 000000000004c9e2= =20 RDI: ffff810118f84de8 Jan 17 04:28:02 storage kernel: RBP: ffff8100ce697d40 R08: ffff81010271b408= =20 R09: ffff81010271b470 Jan 17 04:28:02 storage kernel: R10: ffff81011fd85ac0 R11: ffff81010271b408= =20 R12: 0000000000000022 Jan 17 04:28:02 storage kernel: R13: 0000000000000000 R14: 00000000fffffffa= =20 R15: ffff8100043f2dc0 Jan 17 04:28:02 storage kernel: FS: 00002ab3c30a7e10(0000)=20 GS:ffff81011fca9e40(0000) knlGS:0000000000000000 Jan 17 04:28:02 storage kernel: CS: 0010 DS: 0000 ES: 0000 CR0:=20 0000000080050033 Jan 17 04:28:02 storage kernel: CR2: 00002b0ebd81d0a8 CR3: 0000000107996000= =20 CR4: 00000000000006e0 Jan 17 04:28:02 storage kernel: DR0: 0000000000000000 DR1: 0000000000000000= =20 DR2: 0000000000000000 Jan 17 04:28:02 storage kernel: DR3: 0000000000000000 DR6: 00000000ffff0ff0= =20 DR7: 0000000000000400 Jan 17 04:28:02 storage kernel: Process tar (pid: 9414, threadinfo=20 ffff810101018000, task ffff81011259d080) Jan 17 04:28:02 storage kernel: Stack: 000000000004c9e2 ffff8100043f2dc0=20 0000000000000000 ffff810118f84de0 Jan 17 04:28:02 storage kernel: 000000000004c9e2 ffffffff8801dabf=20 ffff810118f84de0 ffffffff802576b4 Jan 17 04:28:02 storage kernel: 000000000000134d ffff8100043f2dc0=20 000000000000134c ffff810101019c28 Jan 17 04:28:02 storage kernel: Call Trace: Jan 17 04:28:02 storage kernel: =20 [<ffffffff8801dabf>] :ext3:ext3_get_block+0x0/0xe4 Jan 17 04:28:02 storage kernel: [<ffffffff802576b4>]=20 add_to_page_cache+0x3d/0x93 Jan 17 04:28:02 storage kernel: [<ffffffff8029b32a>]=20 mpage_readpages+0x95/0x13b Jan 17 04:28:02 storage kernel: =20 [<ffffffff8801dabf>] :ext3:ext3_get_block+0x0/0xe4 Jan 17 04:28:02 storage kernel: [<ffffffff8025b30d>] __alloc_pages+0xdf/0x= 2a0 Jan 17 04:28:02 storage kernel: [<ffffffff8025cc7d>]=20 __do_page_cache_readahead+0x16b/0x25b Jan 17 04:28:02 storage kernel: [<ffffffff8025cfc9>]=20 ondemand_readahead+0xf1/0xf8 Jan 17 04:28:02 storage kernel: [<ffffffff802579ce>]=20 do_generic_mapping_read+0x123/0x3fd Jan 17 04:28:02 storage kernel: [<ffffffff80257219>] file_read_actor+0x0/0= xf8 Jan 17 04:28:02 storage kernel: [<ffffffff80258fea>]=20 generic_file_aio_read+0x11d/0x160 Jan 17 04:28:02 storage kernel: [<ffffffff80276b18>] do_sync_read+0xc9/0x1= 0c Jan 17 04:28:02 storage kernel: [<ffffffff80243e2d>]=20 autoremove_wake_function+0x0/0x2e Jan 17 04:28:02 storage kernel: [<ffffffff80277280>] vfs_read+0xaa/0x132 Jan 17 04:28:02 storage kernel: [<ffffffff8027761c>] sys_read+0x45/0x6e Jan 17 04:28:02 storage kernel: [<ffffffff8020b6be>] system_call+0x7e/0x83 Jan 17 04:28:02 storage kernel: Jan 17 04:28:02 storage kernel: Jan 17 04:28:02 storage kernel: Code: 0f 0b eb fe 8b 43 04 49 83 cf 01 4c 8= 9=20 7b 08 a9 00 00 10 00 Jan 17 04:28:02 storage kernel: RIP [<ffffffff802dfe28>]=20 radix_tree_insert+0x152/0x18c Jan 17 04:28:02 storage kernel: RSP <ffff8101010199c8> Tonight I will back to @239 because it run 4 me for almost 2weeks without a= ny=20 kind of problem having same load. My system is a qcore intel with centos5.1 x86-64 and scst patched vanilla=20 kernel. this is the lsi adapter: 02:01.0 SCSI storage controller: LSI Logic / Symbios Logic 53c1030 PCI-X=20 =46usion-MPT Dual Ultra320 SCSI (rev 07) 02:01.1 SCSI storage controller: LSI Logic / Symbios Logic 53c1030 PCI-X=20 =46usion-MPT Dual Ultra320 SCSI (rev 07) Vlad , if you need more info please tell me . bye, marco. |