Slow disk transfer rate
- by Nooklez
I have problem with slow disk transfer rate. It's static files server for our website. I was making backup of data and noticed that tar is very slow. So I did hdparm -t and...
hdparm -t /dev/sda3
/dev/sda3:
Timing buffered disk reads: 6 MB in 4.70 seconds = 1.28 MB/sec
It's low traffic hour now on our site, so huge I/O traffic is not a reason (iotop show less than 1 MB/s).
It's RAID10 setup (2x2 SATA drives).
Unit UnitType Status %RCmpl %V/I/M Stripe Size(GB) Cache AVrfy
------------------------------------------------------------------------------
u0 RAID-10 OK - - 64K 1396.96 W ON
VPort Status Unit Size Type Phy Encl-Slot Model
------------------------------------------------------------------------------
p0 OK u0 698.63 GB SATA 0 - WDC WD7500AADS-00M2
p1 OK u0 698.63 GB SATA 1 - WDC WD7500AADS-00M2
p2 OK u0 698.63 GB SATA 2 - WDC WD7500AADS-00M2
p3 OK u0 698.63 GB SATA 3 - WDC WD7500AADS-00M2
We have recently changed almost all components of server (excluding 3ware controller + disks). And I think problems started since then. Can it be configuration problem or hardware?
EDIT:
I found something like that in dmesg
[166843.625843] irq 16: nobody cared (try booting with the "irqpoll" option)
[166843.625846] Pid: 0, comm: swapper Not tainted 3.1.5-gentoo #3
[166843.625847] Call Trace:
[166843.625848] <IRQ> [<ffffffff810859d5>] __report_bad_irq+0x35/0xc1
[166843.625856] [<ffffffff81085cec>] note_interrupt+0x165/0x1e1
[166843.625859] [<ffffffff8108445f>] handle_irq_event_percpu+0x16f/0x187
[166843.625861] [<ffffffff810844a9>] handle_irq_event+0x32/0x51
[166843.625863] [<ffffffff8108640b>] handle_fasteoi_irq+0x75/0x99
[166843.625866] [<ffffffff810039d7>] handle_irq+0x83/0x8b
[166843.625868] [<ffffffff810036ad>] do_IRQ+0x48/0xa0
[166843.625871] [<ffffffff8155082b>] common_interrupt+0x6b/0x6b
[166843.625872] <EOI> [<ffffffff812981e8>] ? acpi_safe_halt+0x22/0x35
[166843.625877] [<ffffffff812981e2>] ? acpi_safe_halt+0x1c/0x35
[166843.625879] [<ffffffff81298216>] acpi_idle_do_entry+0x1b/0x2b
[166843.625881] [<ffffffff81298276>] acpi_idle_enter_c1+0x50/0x99
[166843.625884] [<ffffffff813b792a>] cpuidle_idle_call+0xed/0x171
[166843.625886] [<ffffffff81001257>] cpu_idle+0x55/0x81
[166843.625888] [<ffffffff81532a69>] rest_init+0x6d/0x6f
[166843.625891] [<ffffffff81aa1aca>] start_kernel+0x329/0x334
[166843.625893] [<ffffffff81aa12a6>] x86_64_start_reservations+0xb6/0xba
[166843.625894] [<ffffffff81aa139c>] x86_64_start_kernel+0xf2/0xf9
[166843.625896] handlers:
[166843.625898] [<ffffffff812dc8de>] twl_interrupt
[166843.625900] Disabling IRQ #16
It's related to problem?
EDIT #2:
Based on feedback in comments, here is more informations.
cat /proc/interrupts
16: 390813 0 0 0 IO-APIC-fasteoi 3w-sas
Controller model:
[ 1.095350] 3ware Storage Controller device driver for Linux v1.26.02.003.
[ 1.095467] 3ware 9000 Storage Controller device driver for Linux v2.26.02.014.
[ 1.095641] LSI 3ware SAS/SATA-RAID Controller device driver for Linux v3.26.02.000.
[ 1.095787] 3w-sas 0000:01:00.0: PCI INT A -> GSI 16 (level, low) -> IRQ 16
[ 1.095881] 3w-sas 0000:01:00.0: setting latency timer to 64
[ 1.910801] 3w-sas: scsi0: Found an LSI 3ware 9750-4i Controller at 0xfe560000, IRQ: 16.
[ 2.216537] 3w-sas: scsi0: Firmware FH9X 5.08.00.008, BIOS BE9X 5.07.00.011, Phys: 8.
[ 2.216836] scsi 0:0:0:0: Direct-Access LSI 9750-4i DISK 5.08 PQ: 0 ANSI: 5
And motherboard:
description: Motherboard
product: P8H67-M
vendor: ASUSTeK Computer INC.