[DRBD-user] drbd-0.8pre6 (svn rev 2590) - kernel fails

Vitaly Kuznetsov vitty at ruir.com
Tue Nov 7 12:23:26 CET 2006

Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.


I tried to use it with Xen-3.0
It works well on 2 servers, and on third after some time of usage (about
2 hours) it fails.  I tried Primary/Primary and Primary/Secondary. Only
Primary host fails.
Here is logmessages:

First fail:
Nov  7 11:05:39 cluster02 kernel: Unable to handle kernel paging request
at virtual address ea66e000
Nov  7 11:05:39 cluster02 kernel:  printing eip:
Nov  7 11:05:39 cluster02 kernel: c0171175
Nov  7 11:05:39 cluster02 kernel: 00b60000 -> *pde = 00000000:3eb18001
Nov  7 11:05:39 cluster02 kernel: 00b18000 -> *pme = 00000000:3ec3c067
Nov  7 11:05:39 cluster02 kernel: 00c3c000 -> *pte = 00000000:00000000
Nov  7 11:05:39 cluster02 kernel: Oops: 0000 [#1]
Nov  7 11:05:39 cluster02 kernel: SMP
Nov  7 11:05:39 cluster02 kernel: last sysfs file:
/devices/pci0000:00/0000:00:06.0/0000:06:00.0/subsystem_device
Nov  7 11:05:39 cluster02 kernel: Modules linked in: xt_physdev
iptable_filter ip_tables x_tables af_packet bridge ipv6 drbd blkbk netbk
netloop raw button battery ac apparmor aamatch_pcre loop hw_random
i8xx_tco tg3 shpchp pci_hotplug i2c_i801 i2c_core ehci_hcd uhci_hcd
usbcore reiserfs dm_snapshot dm_mod fan thermal processor mptspi
mptscsih mptbase scsi_transport_spi sg sr_mod cdrom ata_piix libata
sd_mod scsi_mod
Nov  7 11:05:39 cluster02 kernel: CPU:    0
Nov  7 11:05:39 cluster02 kernel: EIP:    0061:[<c0171175>]    Tainted:
G     U VLI
Nov  7 11:05:39 cluster02 kernel: EFLAGS: 00010206
(2.6.16.21-0.25-xenpae #1)
Nov  7 11:05:39 cluster02 kernel: EIP is at __bio_clone+0x35/0xc0
Nov  7 11:05:39 cluster02 kernel: eax: 000000c0   ebx: ea41e380   ecx:
00000002   edx: ea66dec0
Nov  7 11:05:39 cluster02 kernel: esi: ea66e000   edi: eac87a38   ebp:
ea41e380   esp: c7443b88
Nov  7 11:05:39 cluster02 kernel: ds: 007b   es: 007b   ss: 0069
Nov  7 11:05:39 cluster02 kernel: Process xvd 2 93:02 (pid: 5602,
threadinfo=c7442000 task=c0b05630)
Nov  7 11:05:39 cluster02 kernel: Stack: <0>ead32b60 ea41e380 ea66dec0
ea41b288 ea41b000 c0171230 00000800 00111bba
Nov  7 11:05:39 cluster02 kernel:        ee4cbe81 c154cda0 c154cda0
00000001 ea66d000 c0166c96 00000c00 00000001
Nov  7 11:05:39 cluster02 kernel:        c0bed264 ffffffff c81cfcc8
c0bef680 0000002d 00000000 00000000 00000000
Nov  7 11:05:39 cluster02 kernel: Call Trace:
Nov  7 11:05:39 cluster02 kernel:  [<c0171230>] bio_clone+0x30/0x40
Nov  7 11:05:39 cluster02 kernel:  [<ee4cbe81>]
drbd_make_request_common+0x221/0xdc0 [drbd]
Nov  7 11:05:39 cluster02 kernel:  [<c0166c96>]
cache_alloc_refill+0x86/0x5a0
Nov  7 11:05:39 cluster02 kernel:  [<c01350b0>]
autoremove_wake_function+0x0/0x50
Nov  7 11:05:39 cluster02 kernel:  [<ee4ccc5f>]
drbd_make_request_26+0x23f/0x3a7 [drbd]
Nov  7 11:05:39 cluster02 kernel:  [<ee4ccdad>]
drbd_make_request_26+0x38d/0x3a7 [drbd]
Nov  7 11:05:39 cluster02 kernel:  [<c01d0d80>]
generic_make_request+0x150/0x200
Nov  7 11:05:39 cluster02 kernel:  [<c0166c96>]
cache_alloc_refill+0x86/0x5a0
Nov  7 11:05:39 cluster02 kernel:  [<ee4ca22a>]
drbd_merge_bvec+0xca/0x130 [drbd]
Nov  7 11:05:39 cluster02 kernel:  [<ee4ca160>]
drbd_merge_bvec+0x0/0x130 [drbd]
Nov  7 11:05:39 cluster02 kernel:  [<c0170954>] __bio_add_page+0x104/0x3c0
Nov  7 11:05:39 cluster02 kernel:  [<c01d339f>] submit_bio+0x4f/0xf0
Nov  7 11:05:39 cluster02 kernel:  [<c0170c47>] bio_add_page+0x37/0x50
Nov  7 11:05:39 cluster02 kernel:  [<ee399799>]
dispatch_rw_block_io+0x3b9/0x460 [blkbk]
Nov  7 11:05:39 cluster02 kernel:  [<ee4d7bbf>]
drbd_unplug_fn+0xef/0x290 [drbd]
Nov  7 11:05:39 cluster02 kernel:  [<ee399a4b>]
blkif_schedule+0x20b/0x420 [blkbk]
Nov  7 11:05:39 cluster02 kernel:  [<c01350b0>]
autoremove_wake_function+0x0/0x50
Nov  7 11:05:39 cluster02 kernel:  [<ee399840>] blkif_schedule+0x0/0x420
[blkbk]
Nov  7 11:05:39 cluster02 kernel:  [<c0134e2b>] kthread+0xab/0xe0
Nov  7 11:05:39 cluster02 kernel:  [<c0134d80>] kthread+0x0/0xe0
Nov  7 11:05:39 cluster02 kernel:  [<c0102b55>]
kernel_thread_helper+0x5/0x10
Nov  7 11:05:39 cluster02 kernel: Code: 5c 24 04 89 74 24 08 89 7c 24 0c
8b 42 0c 8b 40 58 8b 40 38 89 04 24 8b 42 2c 8b 7d 30 8b 72 30 8d 04 40
c1 e0 02 89 c1 c1 e9 02 <f3> a5 89 c1 83 e1 03 74 02 f3 a4 8b 42 0c 8b
0a 8b 5a 04 83 4d

Second fail:
Nov  7 13:25:17 cluster02 kernel: Unable to handle kernel paging request
at virtual address eb4e9000
Nov  7 13:25:17 cluster02 kernel:  printing eip:
Nov  7 13:25:17 cluster02 kernel: c0171175
Nov  7 13:25:17 cluster02 kernel: 2c1b6000 -> *pde = 00000000:12ba8001
Nov  7 13:25:17 cluster02 kernel: 2bda8000 -> *pme = 00000000:3ec43067
Nov  7 13:25:17 cluster02 kernel: 00c43000 -> *pte = 00000000:00000000
Nov  7 13:25:17 cluster02 kernel: Oops: 0000 [#1]
Nov  7 13:25:17 cluster02 kernel: SMP
Nov  7 13:25:17 cluster02 kernel: last sysfs file:
/devices/pci0000:00/0000:00:06.0/0000:06:00.0/subsystem_device
Nov  7 13:25:17 cluster02 kernel: Modules linked in: xt_physdev
iptable_filter ip_tables x_tables af_packet bridge ipv6 drbd blkbk netbk
netloop raw button battery ac apparmor aamatch_pcre loop hw_random
i8xx_tco uhci_hcd ehci_hcd i2c_i801 i2c_core shpchp usbcore pci_hotplug
tg3 reiserfs dm_snapshot dm_mod fan thermal processor mptspi mptscsih
mptbase scsi_transport_spi sg sr_mod cdrom ata_piix libata sd_mod scsi_mod
Nov  7 13:25:17 cluster02 kernel: CPU:    1
Nov  7 13:25:17 cluster02 kernel: EIP:    0061:[<c0171175>]    Tainted:
G     U VLI
Nov  7 13:25:17 cluster02 kernel: EFLAGS: 00010206
(2.6.16.21-0.25-xenpae #1)
Nov  7 13:25:17 cluster02 kernel: EIP is at __bio_clone+0x35/0xc0
Nov  7 13:25:17 cluster02 kernel: eax: 000000c0   ebx: c8c6bf80   ecx:
00000002   edx: eb4e8ec0
Nov  7 13:25:17 cluster02 kernel: esi: eb4e9000   edi: c822d338   ebp:
c8c6bf80   esp: c9229b88
Nov  7 13:25:17 cluster02 kernel: ds: 007b   es: 007b   ss: 0069
Nov  7 13:25:17 cluster02 kernel: Process xvd 1 93:02 (pid: 5262,
threadinfo=c9228000 task=ec151050)
Nov  7 13:25:17 cluster02 kernel: Stack: <0>c092d7a4 c8c6bf80 eb4e8ec0
c0546288 c0546000 c0171230 00000800 0018a7ba
Nov  7 13:25:17 cluster02 kernel:        ee4cde81 00000000 c09d1240
00000000 c8319780 c01711d5 00000c00 00000000
Nov  7 13:25:17 cluster02 kernel:        00000000 c0546000 c7c87b08
0018a78a 00000000 00000000 00000000 00000000
Nov  7 13:25:17 cluster02 kernel: Call Trace:
Nov  7 13:25:17 cluster02 kernel:  [<c0171230>] bio_clone+0x30/0x40
Nov  7 13:25:17 cluster02 kernel:  [<ee4cde81>]
drbd_make_request_common+0x221/0xdc0 [drbd]
Nov  7 13:25:17 cluster02 kernel:  [<c01711d5>] __bio_clone+0x95/0xc0
Nov  7 13:25:17 cluster02 kernel:  [<ee0ab740>]
mptscsih_io_done+0x0/0x5b0 [mptscsih]
Nov  7 13:25:17 cluster02 kernel:  [<c01350b0>]
autoremove_wake_function+0x0/0x50
Nov  7 13:25:17 cluster02 kernel:  [<ee4cec5f>]
drbd_make_request_26+0x23f/0x3a7 [drbd]
Nov  7 13:25:17 cluster02 kernel:  [<ee4cedad>]
drbd_make_request_26+0x38d/0x3a7 [drbd]
Nov  7 13:25:17 cluster02 kernel:  [<c010691c>] do_IRQ+0x3c/0x70
Nov  7 13:25:17 cluster02 kernel:  [<c01d0d80>]
generic_make_request+0x150/0x200
Nov  7 13:25:17 cluster02 kernel:  [<c0166c96>]
cache_alloc_refill+0x86/0x5a0
Nov  7 13:25:17 cluster02 kernel:  [<ee4cc160>]
drbd_merge_bvec+0x0/0x130 [drbd]
Nov  7 13:25:17 cluster02 kernel:  [<c0170954>] __bio_add_page+0x104/0x3c0
Nov  7 13:25:17 cluster02 kernel:  [<c01d339f>] submit_bio+0x4f/0xf0
Nov  7 13:25:17 cluster02 kernel:  [<c0170c47>] bio_add_page+0x37/0x50
Nov  7 13:25:17 cluster02 kernel:  [<ee33b799>]
dispatch_rw_block_io+0x3b9/0x460 [blkbk]
Nov  7 13:25:17 cluster02 kernel:  [<ee4d9bbf>]
drbd_unplug_fn+0xef/0x290 [drbd]
Nov  7 13:25:17 cluster02 kernel:  [<ee33b991>]
blkif_schedule+0x151/0x420 [blkbk]
Nov  7 13:25:17 cluster02 kernel:  [<c01350b0>]
autoremove_wake_function+0x0/0x50
Nov  7 13:25:17 cluster02 kernel:  [<ee33b840>] blkif_schedule+0x0/0x420
[blkbk]
Nov  7 13:25:17 cluster02 kernel:  [<c0134e2b>] kthread+0xab/0xe0
Nov  7 13:25:17 cluster02 kernel:  [<c0134d80>] kthread+0x0/0xe0
Nov  7 13:25:17 cluster02 kernel:  [<c0102b55>]
kernel_thread_helper+0x5/0x10
Nov  7 13:25:17 cluster02 kernel: Code: 5c 24 04 89 74 24 08 89 7c 24 0c
8b 42 0c 8b 40 58 8b 40 38 89 04 24 8b 42 2c 8b 7d 30 8b 72 30 8d 04 40
c1 e0 02 89 c1 c1 e9 02 <f3> a5 89 c1 83 e1 03 74 02 f3 a4 8b 42 0c 8b
0a 8b 5a 04 83 4d

Any suggestions?



More information about the drbd-user mailing list