Sorry...irgendwie hat mich der Crash härter getroffen also ich zuerst befürchtete..;-) Also hier: Apr 29 04:32:57 serv1 kernel: [18446743979.483274] ------------[ cut here ]------------ Apr 29 04:32:57 serv1 kernel: [18446743979.483290] WARNING: at /usr/src/packages/BUILD/kernel-default-2.6.32.45/linux-2.6.32/kernel/sched.c:3859 find_busiest_group+0xc7f/0xc90() Apr 29 04:32:57 serv1 kernel: [18446743979.483294] Hardware name: X8DTN Apr 29 04:32:57 serv1 kernel: [18446743979.483296] Modules linked in: lp parport_pc ppdev parport af_packet st ide_cd_mod nfsd lockd nfs_acl auth_rpcgss sunrpc exportfs autofs4 ipv 6 cpufreq_conservative cpufreq_userspace cpufreq_powersave acpi_cpufreq microcode fuse loop dm_mod igb shpchp sr_mod iTCO_wdt rtc_cmos ioatdma mptctl i2c_i801 rtc_core dca tpm_tis iTCO_vendor_support pci_hotplug tpm rtc_lib pcspkr tpm_bios floppy i2c_core sg cdrom joydev button usbhid hid uhci_hcd ehci_hcd usbcore sd_mod crc_t10dif edd ext3 mbcache jbd fan p rocessor 3w_9xxx ide_pci_generic ide_core pata_jmicron ata_generic ata_piix libata mptsas mptscsih mptbase scsi_transport_sas scsi_mod thermal thermal_sys hwmon [last unloaded: par port_pc] Apr 29 04:32:57 serv1 kernel: [18446743979.483347] Supported: Yes Apr 29 04:32:57 serv1 kernel: [18446743979.483351] Pid: 19949, comm: nfsd Tainted: G W 2.6.32.45-0.3-default #1 Apr 29 04:32:57 serv1 kernel: [18446743979.483354] Call Trace: Apr 29 04:32:57 serv1 kernel: [18446743979.483371] [<ffffffff810061dc>] dump_trace+0x6c/0x2d0 Apr 29 04:32:57 serv1 kernel: [18446743979.483380] [<ffffffff81398846>] dump_stack+0x69/0x73 Apr 29 04:32:57 serv1 kernel: [18446743979.483389] [<ffffffff8104d554>] warn_slowpath_common+0x74/0xd0 Apr 29 04:32:57 serv1 kernel: [18446743979.483395] [<ffffffff8103daaf>] find_busiest_group+0xc7f/0xc90 Apr 29 04:32:57 serv1 kernel: [18446743979.483401] [<ffffffff8104640d>] load_balance_newidle+0xcd/0x380 Apr 29 04:32:57 serv1 kernel: [18446743979.483407] [<ffffffff8139963b>] thread_return+0x2a7/0x34c Apr 29 04:32:57 serv1 kernel: [18446743979.483412] [<ffffffff813999c3>] schedule_timeout+0x143/0x240 Apr 29 04:32:57 serv1 kernel: [18446743979.483431] [<ffffffffa03cbf69>] svc_recv+0x699/0x7a0 [sunrpc] Apr 29 04:32:57 serv1 kernel: [18446743979.483481] [<ffffffffa0428a55>] nfsd+0x95/0x150 [nfsd] Apr 29 04:32:57 serv1 kernel: [18446743979.483490] [<ffffffff81064436>] kthread+0x96/0xa0 Apr 29 04:32:57 serv1 kernel: [18446743979.483496] [<ffffffff81003fba>] child_rip+0xa/0x20 Apr 29 04:32:57 serv1 kernel: [18446743979.483501] ---[ end trace 8c9afce26963385c ]--- Apr 29 04:32:57 serv1 kernel: [18446743979.483503] update_group_power: cpu_power = 2347317421 Apr 29 04:32:57 serv1 kernel: klogd 1.4.1, ---------- state change ---------- Apr 29 04:32:57 serv1 kernel: [18446743979.483642] update_group_power: cpu_power = 2348216549 Apr 29 04:32:57 serv1 kernel: [18446743979.484906] update_group_power: cpu_power = 2522351442 Apr 29 04:32:57 serv1 kernel: [18446743979.485396] update_group_power: cpu_power = 2522843300 Apr 29 04:32:57 serv1 kernel: [18446743979.485976] update_group_power: cpu_power = 2523423088 Apr 29 04:32:57 serv1 kernel: [18446743979.487109] update_group_power: cpu_power = 2524556158 Apr 29 04:32:57 serv1 kernel: [18446743979.487497] update_group_power: cpu_power = 2524945089 Apr 29 04:32:57 serv1 kernel: [18446743979.488509] update_group_power: cpu_power = 2525957565 Apr 29 04:32:57 serv1 kernel: [18446743979.491346] update_group_power: cpu_power = 2360365295 Apr 29 04:32:57 serv1 kernel: [18446743979.491888] update_group_power: cpu_power = 2374918347 Apr 29 04:32:57 serv1 kernel: [18446743979.491902] update_group_power: cpu_power = 2375473915 Apr 29 04:32:57 serv1 kernel: [18446743979.492615] update_group_power: cpu_power = 2377169686 Apr 29 04:32:57 serv1 kernel: [18446743979.493120] update_group_power: cpu_power = 2378710656 Apr 29 04:32:57 serv1 kernel: [18446743979.493749] update_group_power: cpu_power = 2381020730 Apr 29 04:32:57 serv1 kernel: [18446743979.494852] update_group_power: cpu_power = 2383193660 Apr 29 04:32:57 serv1 kernel: [18446743979.495349] update_group_power: cpu_power = 2384289916 Apr 29 04:32:57 serv1 kernel: [18446743979.495361] update_group_power: cpu_power = 2384303756 Apr 29 04:32:57 serv1 kernel: [18446743979.495852] update_group_power: cpu_power = 2387025068 Apr 29 04:32:57 serv1 kernel: [18446743979.497076] update_group_power: cpu_power = 3184962682 Apr 29 04:32:57 serv1 kernel: [18446743979.497124] update_group_power: cpu_power = 3185323808 Apr 29 04:32:57 serv1 kernel: [18446743979.497450] update_group_power: cpu_power = 3185952191 -- Freundliche Grüsse Anton Renner Systemadministrator RASEA RUAG Schweiz AG RUAG Aviation -- Um die Liste abzubestellen, schicken Sie eine Mail an: opensuse-de+unsubscribe@opensuse.org Um den Listen Administrator zu erreichen, schicken Sie eine Mail an: opensuse-de+owner@opensuse.org

...

Apr 29 04:32:57 serv1 kernel: [18446743979.483412] [<ffffffff813999c3>] schedule_timeout+0x143/0x240 Apr 29 04:32:57 serv1 kernel: [18446743979.483431] [<ffffffffa03cbf69>] svc_recv+0x699/0x7a0 [sunrpc] Apr 29 04:32:57 serv1 kernel: [18446743979.483481] [<ffffffffa0428a55>] nfsd+0x95/0x150 [nfsd]

Das schaut danach aus, als ob da was via NFS in ein timeout gelaufen ist. Aber Crash war _das_ keiner, nur ein "WARNING". Könnte natürlich anschließend, wo cpu_power wohl durcheinander kommt noch ein nicht mehr geloggter Fehler aufgetreten sein. Wie sind denn die Kerneloptionen (cat /proc/cmdline)? Wie die Einstellungen bzgl. CPU "power"?

Also war eigentlich kein Crash. Ich konnte nichts mehr machen, kein Access zur Maschine. Blieb nur ein reboot am Reset-Knopf :-( Das mit dem NFS könnte schon was dran sein. Hab von Zeit zu Zeit das Problem mit lockd not responding auf dem Server. Dies vermehrt mit 12.1 Clients: Apr 19 10:00:50 serv1 kernel: [17171615.493179] lockd: server mcp22 not responding, timed out Apr 19 10:01:38 serv1 kernel: [17171663.396051] lockd: server mcp22 not responding, timed out Apr 19 10:02:38 serv1 kernel: [17171723.279592] lockd: server mcp22 not responding, timed out ... Und seit/ab 11.3 hab ich auch auf teils Clients mount.nfs Crashes: Dec 16 10:19:59 bserv1 kernel: [3380946.147748] __alloc_pages_slowpath: 3 callbacks suppressed Dec 16 10:19:59 bserv1 kernel: [3380946.147752] mount.nfs: page allocation failure. order:4, mode:0xd0, alloc_flags:0x40 pflags:0x400100 Dec 16 10:19:59 bserv1 kernel: [3380946.147756] Pid: 12550, comm: mount.nfs Not tainted 2.6.34.10-0.2-default #1 Dec 16 10:19:59 bserv1 kernel: [3380946.147758] Call Trace: Dec 16 10:19:59 bserv1 kernel: [3380946.147770] [<c0206303>] try_stack_unwind+0x173/0x190 Dec 16 10:19:59 bserv1 kernel: [3380946.147776] [<c020509f>] dump_trace+0x3f/0xe0 Dec 16 10:19:59 bserv1 kernel: [3380946.147780] [<c020636b>] show_trace_log_lvl+0x4b/0x60 Dec 16 10:19:59 bserv1 kernel: [3380946.147784] [<c0206398>] show_trace+0x18/0x20 Dec 16 10:19:59 bserv1 kernel: [3380946.147789] [<c05bb5a1>] dump_stack+0x6d/0x72 ... ... Betreffend /proc/cmdline nichts besonderes auf dem Server: # cat /proc/cmdline root=/dev/disk/by-id/scsi-3600050e0e7e43f00d626000007120000-part3 resume=/dev/disk/by-id/scsi-3600050e0e7e43f00d626000007120000-part1 splash=silent crashkernel=256M-:128M vga=0x317 Mit mit CPU "power"hab nich nix gemacht, d.h. Standard-Werte genommen -- Freundliche Grüsse Anton Renner Systemadministrator RASEA RUAG Schweiz AG RUAG Aviation -- Um die Liste abzubestellen, schicken Sie eine Mail an: opensuse-de+unsubscribe@opensuse.org Um den Listen Administrator zu erreichen, schicken Sie eine Mail an: opensuse-de+owner@opensuse.org