After the e2fsck I was able to mount the OST cleanly and the CPU locks went away.<div>Thanks!</div><div>Erik<br><br><div class="gmail_quote">On Fri, Jan 1, 2010 at 7:27 PM, Erik Froese <span dir="ltr"><<a href="mailto:erik.froese@gmail.com">erik.froese@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">I think you're right. I'm re fsking it right now.<div>Erik<div><div></div><div class="h5"><br><br><div class="gmail_quote">
On Thu, Dec 31, 2009 at 1:29 PM, Aaron Knister <span dir="ltr"><<a href="mailto:aaron.knister@gmail.com" target="_blank">aaron.knister@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">My best guess is that there's something still not right on-disk. This is my $.02, but I'd suggest running another fsck on that ost if you haven't already.<br>
<div><div></div><div><br>
On Dec 31, 2009, at 12:20 PM, Erik Froese wrote:<br>
<br>
> Yesterday we had an OST fail. I had to e2fsck it to fix it (although there was some corruption).<br>
><br>
> All servers are:<br>
> RH 5.3 with Lustre 1.8.1.1<br>
> Mellanox QDR IB<br>
> Fiber connected storage.<br>
><br>
> I left the OST mounted yesterday but it was deactivated on the mds.<br>
> [root@mds-0-0 osc]# cat /proc/fs/lustre/osc/scratch-OST000e-osc/active<br>
> 0<br>
><br>
> At some point this morning the OSS locked up and had to be rebooted. I couldn't even access it on the console.<br>
><br>
> I see I/O errors when trying to copy files that exist on that OST (lfs find -O scratch-OST000e_UUID /scratch)<br>
><br>
> Now we're seeing CPU lockups on the OSS<br>
><br>
> Soft lockup - CPU#4 stuck for 10s! [ll_ost_26:10467]<br>
> Dec 31 12:12:12 oss-0-0 kernel: BUG: soft lockup - CPU#2 stuck for 10s! [ll_ost_500:12066]<br>
> Dec 31 12:12:22 oss-0-0 kernel: BUG: soft lockup - CPU#4 stuck for 10s! [ll_ost_26:10467]<br>
> Dec 31 12:12:22 oss-0-0 kernel: BUG: soft lockup - CPU#2 stuck for 10s! [ll_ost_500:12066]<br>
> Dec 31 12:12:32 oss-0-0 kernel: BUG: soft lockup - CPU#4 stuck for 10s! [ll_ost_26:10467]<br>
> Dec 31 12:12:32 oss-0-0 kernel: BUG: soft lockup - CPU#2 stuck for 10s! [ll_ost_500:12066]<br>
> Dec 31 12:12:42 oss-0-0 kernel: BUG: soft lockup - CPU#4 stuck for 10s! [ll_ost_26:10467]<br>
> Dec 31 12:12:42 oss-0-0 kernel: BUG: soft lockup - CPU#2 stuck for 10s! [ll_ost_500:12066]<br>
><br>
> dmesg:<br>
><br>
> BUG: soft lockup - CPU#2 stuck for 10s! [ll_ost_500:12066]<br>
> CPU 2:<br>
> Modules linked in: obdfilter(U) fsfilt_ldiskfs(U) mgc(U) ldiskfs(U) crc16(U) ost(U) lustre(U) lov(U) mdc(U) lquota(U) osc(U) ptlrpc(U) obdclass(U) lvfs(U) ksocklnd(U) ko2iblnd(<br>
> U) lnet(U) libcfs(U) autofs4(U) ipmi_devintf(U) ipmi_si(U) ipmi_msghandler(U) sunrpc(U) ip_conntrack_netbios_ns(U) ipt_REJECT(U) xt_state(U) ip_conntrack(U) nfnetlink(U) iptabl<br>
> e_filter(U) ip_tables(U) ip6t_REJECT(U) xt_tcpudp(U) ip6table_filter(U) ip6_tables(U) x_tables(U) rdma_ucm(U) ib_sdp(U) rdma_cm(U) iw_cm(U) ib_addr(U) ib_ipoib(U) ipoib_helper(<br>
> U) ib_cm(U) ib_sa(U) ipv6(U) xfrm_nalgo(U) crypto_api(U) ib_uverbs(U) ib_umad(U) mlx4_ib(U) ib_mthca(U) ib_mad(U) ib_core(U) dm_mirror(U) dm_multipath(U) scsi_dh(U) video(U) hw<br>
> mon(U) backlight(U) sbs(U) i2c_ec(U) button(U) battery(U) asus_acpi(U) acpi_memhotplug(U) ac(U) parport_pc(U) lp(U) parport(U) joydev(U) sr_mod(U) cdrom(U) mlx4_core(U) pcspkr(<br>
> U) igb(U) i2c_i801(U) i2c_core(U) dm_raid45(U) dm_message(U) dm_region_hash(U) dm_log(U) dm_mod(U) dm_mem_cache(U) mppVhba(U) usb_storage(U) qla2xxx(U) scsi_transport_fc(U) ahc<br>
> i(U) libata(U) shpchp(U) aacraid(U) mppUpper(U) sg(U) sd_mod(U) scsi_mod(U) ext3(U) jbd(U) uhci_hcd(U) ohci_hcd(U) ehci_hcd(U)<br>
> Pid: 12066, comm: ll_ost_500 Tainted: G 2.6.18-128.7.1.el5_lustre.1.8.1.1 #1<br>
> RIP: 0010:[<ffffffff88b3bb64>] [<ffffffff88b3bb64>] :ldiskfs:ldiskfs_find_entry+0x244/0x5c0<br>
> RSP: 0018:ffff8106656e9610 EFLAGS: 00000202<br>
> RAX: 0000000000000000 RBX: 0000000000000007 RCX: 0000000000000004<br>
> RDX: ffff81031a0f3000 RSI: ffff81033a504b4f RDI: ffff8103551591fb<br>
> RBP: 0000000000000002 R08: ffff810355159ff8 R09: ffff810355159000<br>
> R10: ffff810001014f00 R11: 000000004b3cd2fd R12: ffff81033a5d7550<br>
> R13: ffffffff80063b4c R14: ffff8106656e96c8 R15: ffffffff80014fae<br>
> FS: 00002aeb511bd220(0000) GS:ffff81010c499240(0000) knlGS:0000000000000000<br>
> CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b<br>
> CR2: 00000039f5499a50 CR3: 0000000000201000 CR4: 00000000000006e0<br>
><br>
> Call Trace:<br>
> [<ffffffff80089bdd>] dequeue_task+0x18/0x37<br>
> [<ffffffff80063098>] thread_return+0x62/0xfe<br>
> [<ffffffff88b3df63>] :ldiskfs:ldiskfs_lookup+0x53/0x290<br>
> [<ffffffff800366e8>] __lookup_hash+0x10b/0x130<br>
> [<ffffffff80063d2a>] .text.lock.mutex+0x5/0x14<br>
> [<ffffffff800e2c9b>] lookup_one_len+0x53/0x61<br>
> [<ffffffff88ba61ed>] :obdfilter:filter_fid2dentry+0x42d/0x730<br>
> [<ffffffff8026f08b>] __down_trylock+0x44/0x4e<br>
> [<ffffffff800647c0>] __down_failed_trylock+0x35/0x3a<br>
> [<ffffffff88bbff9b>] :obdfilter:filter_lvbo_init+0x3bb/0x68b<br>
> [<ffffffff888da2e6>] :ptlrpc:ldlm_resource_get+0x8f6/0xa50<br>
> [<ffffffff88b084a0>] :ost:ost_blocking_ast+0x0/0xaa0<br>
> [<ffffffff888f9470>] :ptlrpc:ldlm_server_completion_ast+0x0/0x5d0<br>
> [<ffffffff888d0eba>] :ptlrpc:ldlm_lock_create+0xba/0x9f0<br>
> [<ffffffff889158d1>] :ptlrpc:lustre_swab_buf+0x81/0x170<br>
> [<ffffffff888e1adb>] :ptlrpc:target_queue_recovery_request+0x9b/0x1690<br>
> [<ffffffff888f3f30>] :ptlrpc:ldlm_server_glimpse_ast+0x0/0x3b0<br>
> [<ffffffff888f3f30>] :ptlrpc:ldlm_server_glimpse_ast+0x0/0x3b0<br>
> [<ffffffff888f9470>] :ptlrpc:ldlm_server_completion_ast+0x0/0x5d0<br>
> [<ffffffff88b084a0>] :ost:ost_blocking_ast+0x0/0xaa0<br>
> [<ffffffff888f75a0>] :ptlrpc:ldlm_handle_enqueue+0x670/0x1210<br>
> [<ffffffff889145d8>] :ptlrpc:lustre_msg_check_version_v2+0x8/0x20<br>
> [<ffffffff88b107b3>] :ost:ost_handle+0x54b3/0x5a70<br>
> [<ffffffff800d73cd>] free_block+0x126/0x143<br>
> [<ffffffff88758305>] :lnet:lnet_match_blocked_msg+0x375/0x390<br>
> [<ffffffff88919f05>] :ptlrpc:lustre_msg_get_conn_cnt+0x35/0xf0<br>
> [<ffffffff80089d8d>] enqueue_task+0x41/0x56<br>
> [<ffffffff8891ec1d>] :ptlrpc:ptlrpc_check_req+0x1d/0x110<br>
> [<ffffffff88921357>] :ptlrpc:ptlrpc_server_handle_request+0xa97/0x1170<br>
> [<ffffffff80063098>] thread_return+0x62/0xfe<br>
> [<ffffffff8003d382>] lock_timer_base+0x1b/0x3c<br>
> [<ffffffff8001c6fa>] __mod_timer+0xb0/0xbe<br>
> [<ffffffff88924e08>] :ptlrpc:ptlrpc_main+0x1218/0x13e0<br>
> [<ffffffff8008a3f3>] default_wake_function+0x0/0xe<br>
> [<ffffffff800b48f2>] audit_syscall_exit+0x33c/0x357<br>
> [<ffffffff8005dfb1>] child_rip+0xa/0x11<br>
> [<ffffffff88923bf0>] :ptlrpc:ptlrpc_main+0x0/0x13e0<br>
> [<ffffffff8005dfa7>] child_rip+0x0/0x11<br>
><br>
> On the MDS I se this in dmesg:<br>
> BUG: soft lockup - CPU#1 stuck for 10s! [ll_evictor:11659]<br>
> CPU 1:<br>
> Modules linked in: mds(U) fsfilt_ldiskfs(U) mgs(U) mgc(U) ldiskfs(U) lustre(U) lov(U) mdc(U) lquota(U) osc(U) ptlrpc(U) obdclass(U) lvfs(U) nfs(U) lockd(U) fscache(U) nfs_acl(U<br>
> ) ksocklnd(U) ko2iblnd(U) lnet(U) libcfs(U) raid10(U) crc16(U) raid1(U) autofs4(U) ipmi_devintf(U) ipmi_si(U) ipmi_msghandler(U) sunrpc(U) ip_conntrack_netbios_ns(U) ipt_REJECT<br>
> (U) xt_state(U) ip_conntrack(U) nfnetlink(U) iptable_filter(U) ip_tables(U) ip6t_REJECT(U) xt_tcpudp(U) ip6table_filter(U) ip6_tables(U) x_tables(U) cpufreq_ondemand(U) acpi_cp<br>
> ufreq(U) freq_table(U) rdma_ucm(U) ib_sdp(U) rdma_cm(U) iw_cm(U) ib_addr(U) ib_ipoib(U) ipoib_helper(U) ib_cm(U) ib_sa(U) ipv6(U) xfrm_nalgo(U) crypto_api(U) ib_uverbs(U) ib_um<br>
> ad(U) mlx4_ib(U) ib_mthca(U) ib_mad(U) ib_core(U) dm_mirror(U) dm_multipath(U) scsi_dh(U) video(U) hwmon(U) backlight(U) sbs(U) i2c_ec(U) button(U) battery(U) asus_acpi(U) acpi<br>
> _memhotplug(U) ac(U) parport_pc(U) lp(U) parport(U) joydev(U) sr_mod(U) cdrom(U) mlx4_core(U) igb(U) i2c_i801(U) i2c_core(U) pcspkr(U) dm_raid45(U) dm_message(U) dm_region_hash<br>
> (U) dm_log(U) dm_mod(U) dm_mem_cache(U) mppVhba(U) usb_storage(U) ahci(U) libata(U) mptsas(U) mptscsih(U) scsi_transport_sas(U) mptbase(U) shpchp(U) aacraid(U) mppUpper(U) sg(U<br>
> ) sd_mod(U) scsi_mod(U) ext3(U) jbd(U) uhci_hcd(U) ohci_hcd(U) ehci_hcd(U)<br>
> Pid: 11659, comm: ll_evictor Tainted: G 2.6.18-128.7.1.el5_lustre.1.8.1.1 #1<br>
> RIP: 0010:[<ffffffff80064aee>] [<ffffffff80064aee>] _write_lock+0x7/0xf<br>
> RSP: 0018:ffff81034fcefc78 EFLAGS: 00000246<br>
> RAX: 000000000000ffff RBX: 000000000000a09f RCX: 00000000000d0117<br>
> RDX: 0000000000000195 RSI: ffffffff802fae80 RDI: ffffc20011f029fc<br>
> RBP: 0000000000000286 R08: ffff81000100e8e0 R09: 0000000000000000<br>
> R10: ffff8106070f5200 R11: 0000000000000150 R12: 0000000000000286<br>
> R13: ffff81034fcefc20 R14: ffff8106070f5258 R15: ffff8106070f5200<br>
> FS: 00002af849256220(0000) GS:ffff81010c4994c0(0000) knlGS:0000000000000000<br>
> CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b<br>
> CR2: 000000386ba41900 CR3: 0000000000201000 CR4: 00000000000006e0<br>
><br>
> Call Trace:<br>
> [<ffffffff88830ba7>] :obdclass:lustre_hash_for_each_empty+0x237/0x2b0<br>
> [<ffffffff88837ae8>] :obdclass:class_disconnect+0x398/0x420<br>
> [<ffffffff88bc75e1>] :mds:mds_disconnect+0x121/0xe40<br>
> [<ffffffff8014b87a>] snprintf+0x44/0x4c<br>
> [<ffffffff88833994>] :obdclass:class_fail_export+0x384/0x4c0<br>
> [<ffffffff88904238>] :ptlrpc:ping_evictor_main+0x4f8/0x7e0<br>
> [<ffffffff8008a3f3>] default_wake_function+0x0/0xe<br>
> [<ffffffff800b48f2>] audit_syscall_exit+0x33c/0x357<br>
> [<ffffffff8005dfb1>] child_rip+0xa/0x11<br>
> [<ffffffff88903d40>] :ptlrpc:ping_evictor_main+0x0/0x7e0<br>
> [<ffffffff8005dfa7>] child_rip+0x0/0x11<br>
><br>
> Can anyone shed some light on this?<br>
><br>
> Thanks<br>
> Erik<br>
><br>
><br>
</div></div><div><div></div><div>> _______________________________________________<br>
> Lustre-discuss mailing list<br>
> <a href="mailto:Lustre-discuss@lists.lustre.org" target="_blank">Lustre-discuss@lists.lustre.org</a><br>
> <a href="http://lists.lustre.org/mailman/listinfo/lustre-discuss" target="_blank">http://lists.lustre.org/mailman/listinfo/lustre-discuss</a><br>
<br>
_______________________________________________<br>
Lustre-discuss mailing list<br>
<a href="mailto:Lustre-discuss@lists.lustre.org" target="_blank">Lustre-discuss@lists.lustre.org</a><br>
<a href="http://lists.lustre.org/mailman/listinfo/lustre-discuss" target="_blank">http://lists.lustre.org/mailman/listinfo/lustre-discuss</a><br>
</div></div></blockquote></div><br></div></div></div>
</blockquote></div><br></div>