Bug#723761: irq 16: nobody cared errors for the mptsas driver

2014-01-21 Thread Dániel L .
Hello,

I have Debian 7 on IBM X3250 with LSI SAS1064e HW RAID1.
We experience very poor read speeds, 2-3Mb/sec.

The suggested solution didnt help.

Any Ideas?

Thank You.


Bug#723761: irq 16: nobody cared errors for the mptsas driver

2013-09-19 Thread Marco d'Itri
Package: src:linux
Version: 3.2.46-1+deb7u1
Severity: normal

This is an IBM x3250 server.

At boot time I get:

[7.160384] scsi2 : ioc0: LSISAS1064E B1, FwRev=0110h, Ports=1, 
MaxQ=511, IRQ=16
[7.184758] mptsas: ioc0: attaching sata device: fw_channel 0, fw_id 5, phy 
0, sas_addr 0xdd61424dbd929f78
[7.187410] scsi 2:0:0:0: Direct-Access ATA  WDC WD2500YS-23S 6C04 
PQ: 0 ANSI: 5
[7.189626] scsi 2:0:0:0: Attached scsi generic sg1 type 0
[7.191026] mptsas: ioc0: attaching sata device: fw_channel 0, fw_id 1, phy 
1, sas_addr 0xdd61424dbe8a9e78
[7.193670] scsi 2:0:1:0: Direct-Access ATA  WDC WD2500YS-23S 6C04 
PQ: 0 ANSI: 5
[7.195860] scsi 2:0:1:0: Attached scsi generic sg2 type 0
[7.197245] mptsas: ioc0: attaching raid volume, channel 1, id 0
[7.198152] scsi 2:1:0:0: Direct-Access LSILOGIC Logical Volume   3000 
PQ: 0 ANSI: 2
[7.205961] scsi 2:1:0:0: Attached scsi generic sg3 type 0

[   10.683522] irq 16: nobody cared (try booting with the irqpoll option)
[   10.683636] Pid: 635, comm: ls Not tainted 3.2.0-4-amd64 #1 Debian 
3.2.46-1+deb7u1
[   10.683756] Call Trace:
[   10.683799]  IRQ  [810926f9] ? __report_bad_irq+0x2c/0xb5
[   10.683922]  [81092ab6] ? note_interrupt+0x170/0x1f2
[   10.684007]  [81090e6c] ? handle_irq_event_percpu+0x15f/0x17d
[   10.684007]  [8104c231] ? __do_softirq+0x13e/0x177
[   10.684007]  [81090ebe] ? handle_irq_event+0x34/0x52
[   10.684007]  [8109322d] ? handle_fasteoi_irq+0x7c/0xaf
[   10.684007]  [8100f88d] ? handle_irq+0x1d/0x21
[   10.684007]  [8100f5bd] ? do_IRQ+0x42/0x98
[   10.684007]  [8134ee6e] ? common_interrupt+0x6e/0x6e
[   10.684007]  EOI 
[   10.684007] handlers:
[   10.684007] [a003e069] usb_hcd_irq
[   10.684007] [a0171d67] mpt_interrupt
[   10.684007] Disabling IRQ #16

And then disk performance sucks and I get a lot of messages like:

INFO: task apt-cacher:14260 blocked for more than 120 seconds.
echo 0  /proc/sys/kernel/hung_task_timeout_secs disables this message.
apt-cacher  D 88012fd13780 0 14260   8418 0x
 880128bb0f20 0082 0082 88012aeaa0c0
 00013780 8800c91f5fd8 8800c91f5fd8 880128bb0f20
 8800c92ae288 8800c91f5e68 8800c91f5d68 88011f45cd48
Call Trace:
 [8134e11c] ? __mutex_lock_common.isra.5+0xff/0x164
 [8134e00a] ? mutex_lock+0x1a/0x2d
 [81104c9b] ? do_last+0x1b1/0x58d
 [8110566f] ? path_openat+0xce/0x33a
 [811b01a8] ? timerqueue_add+0x80/0xa0
 [8110599d] ? do_filp_open+0x2a/0x6e
 [8134d81c] ? _cond_resched+0x7/0x1c
 [811b3d99] ? __strncpy_from_user+0x18/0x48
 [8110e723] ? alloc_fd+0x64/0x109
 [810f9971] ? do_sys_open+0x5e/0xe5
 [81353b52] ? system_call_fastpath+0x16/0x1b

   CPU0   CPU1   
  0: 45  0   IO-APIC-edge  timer
  1:  3  0   IO-APIC-edge  i8042
  4: 10  0   IO-APIC-edge  serial
  8:  1  0   IO-APIC-edge  rtc0
  9:  0  0   IO-APIC-fasteoi   acpi
 12:  5  0   IO-APIC-edge  i8042
 14: 81  0   IO-APIC-edge  ata_piix
 15:  0  0   IO-APIC-edge  ata_piix
 16: 21  0   IO-APIC-fasteoi   uhci_hcd:usb5, ioc0
 18:  0  0   IO-APIC-fasteoi   uhci_hcd:usb4, radeon
 19:  0  0   IO-APIC-fasteoi   uhci_hcd:usb3
 23:  0  0   IO-APIC-fasteoi   ehci_hcd:usb1, uhci_hcd:usb2
 40:  28367  0   PCI-MSI-edge  eth0
 41:   8746  0   PCI-MSI-edge  eth1
NMI: 16 12   Non-maskable interrupts
LOC:  39406  29110   Local timer interrupts
SPU:  0  0   Spurious interrupts
PMI: 16 12   Performance monitoring interrupts
IWI:  0  0   IRQ work interrupts
RES:  10410  11558   Rescheduling interrupts
CAL:256406   Function call interrupts
TLB:760641   TLB shootdowns
TRM:  0  0   Thermal event interrupts
THR:  0  0   Threshold APIC interrupts
MCE:  0  0   Machine check exceptions
MCP:  4  4   Machine check polls
ERR:  0
MIS:  0

-- 
ciao,
Marco


signature.asc
Description: Digital signature


Bug#723761: irq 16: nobody cared errors for the mptsas driver

2013-09-19 Thread Bjørn Mork
Marco d'Itri m...@linux.it writes:

 Package: src:linux
 Version: 3.2.46-1+deb7u1
 Severity: normal

 This is an IBM x3250 server.

 At boot time I get:

 [7.160384] scsi2 : ioc0: LSISAS1064E B1, FwRev=0110h, Ports=1, 
 MaxQ=511, IRQ=16
 [7.184758] mptsas: ioc0: attaching sata device: fw_channel 0, fw_id 5, 
 phy 0, sas_addr 0xdd61424dbd929f78
 [7.187410] scsi 2:0:0:0: Direct-Access ATA  WDC WD2500YS-23S 6C04 
 PQ: 0 ANSI: 5
 [7.189626] scsi 2:0:0:0: Attached scsi generic sg1 type 0
 [7.191026] mptsas: ioc0: attaching sata device: fw_channel 0, fw_id 1, 
 phy 1, sas_addr 0xdd61424dbe8a9e78
 [7.193670] scsi 2:0:1:0: Direct-Access ATA  WDC WD2500YS-23S 6C04 
 PQ: 0 ANSI: 5
 [7.195860] scsi 2:0:1:0: Attached scsi generic sg2 type 0
 [7.197245] mptsas: ioc0: attaching raid volume, channel 1, id 0
 [7.198152] scsi 2:1:0:0: Direct-Access LSILOGIC Logical Volume   3000 
 PQ: 0 ANSI: 2
 [7.205961] scsi 2:1:0:0: Attached scsi generic sg3 type 0

 [   10.683522] irq 16: nobody cared (try booting with the irqpoll option)


Don't know how to solve the bug, but wanted to tip about a workaround
I've been happy with (on a LSISAS1068E B3):  Adding

  options mptbase mpt_msi_enable_sas=1

to /etc/modprobe.d/somefile.conf makes the controller use MSI instead.

I haven't got the faintest idea why that's not the default setting for
these devices...



Bjørn


--
To UNSUBSCRIBE, email to debian-kernel-requ...@lists.debian.org
with a subject of unsubscribe. Trouble? Contact listmas...@lists.debian.org
Archive: http://lists.debian.org/87vc1w22ag@nemi.mork.no