* bad performance with SSD since kernel version 2.6.32
@ 2010-02-20 13:28 Benjamin S.
2010-02-20 18:35 ` Robert Hancock
0 siblings, 1 reply; 15+ messages in thread
From: Benjamin S. @ 2010-02-20 13:28 UTC (permalink / raw)
To: Jeff Garzik; +Cc: linux-ide
Hello list,
I have a Super Talent Ultradrive GX MLC 64GB SSD and an Intel
DH55HC board with H55 chipset. Processor is an Intel Core i5-661.
Since 2.6.32 the sequentiell read performance of the ssd is bad:
# dd if=/dev/sda of=/dev/zero bs=1M count=300
300+0 records in
300+0 records out
314572800 bytes (315 MB) copied, 4.61777 s, 68.1 MB/s
Same results with other blocksizes (e.g tested with 4K).
With 2.6.31.7 the same hardware is able to read with about
190MB/s.
The normal hard drive reads with both kernel versions with about 100MB/s.
Does somebody have an idea what I can test before I have to bisect
it?
dmesg:
[ 0.000000] Linux version 2.6.33-rc8 (root@pluto-lenny) (gcc version 4.4.3 20100108 (prerelease) (Debian 4.4.2-9) ) #4 SMP Sat Feb 20 13:39:26 CET 2010
[ 0.000000] Command line: BOOT_IMAGE=//vmlinuz-2.6.33-rc8 root=/dev/mapper/ST64GB-LENNYX64--ROOT ro selinux=0 acpi_sleep=s3_bios no_console_suspend rootfstype=ext4 enable_mtrr_cleanup resume=/dev/sdb1
[ 0.000000] BIOS-provided physical RAM map:
[ 0.000000] BIOS-e820: 0000000000000000 - 000000000009ac00 (usable)
[ 0.000000] BIOS-e820: 000000000009ac00 - 00000000000a0000 (reserved)
[ 0.000000] BIOS-e820: 00000000000e0000 - 0000000000100000 (reserved)
[ 0.000000] BIOS-e820: 0000000000100000 - 00000000cb43c000 (usable)
[ 0.000000] BIOS-e820: 00000000cb43c000 - 00000000cb47c000 (ACPI NVS)
[ 0.000000] BIOS-e820: 00000000cb47c000 - 00000000cb4fb000 (reserved)
[ 0.000000] BIOS-e820: 00000000cb4fb000 - 00000000cb50f000 (ACPI NVS)
[ 0.000000] BIOS-e820: 00000000cb50f000 - 00000000cb615000 (reserved)
[ 0.000000] BIOS-e820: 00000000cb615000 - 00000000cb618000 (ACPI NVS)
[ 0.000000] BIOS-e820: 00000000cb618000 - 00000000cb622000 (ACPI data)
[ 0.000000] BIOS-e820: 00000000cb622000 - 00000000cb62b000 (ACPI NVS)
[ 0.000000] BIOS-e820: 00000000cb62b000 - 00000000cb649000 (reserved)
[ 0.000000] BIOS-e820: 00000000cb649000 - 00000000cb68c000 (ACPI NVS)
[ 0.000000] BIOS-e820: 00000000cb68c000 - 00000000cb800000 (usable)
[ 0.000000] BIOS-e820: 00000000cde00000 - 00000000d0000000 (reserved)
[ 0.000000] BIOS-e820: 00000000fed1c000 - 00000000fed20000 (reserved)
[ 0.000000] BIOS-e820: 00000000ff000000 - 0000000100000000 (reserved)
[ 0.000000] BIOS-e820: 0000000100000000 - 0000000128000000 (usable)
[ 0.000000] NX (Execute Disable) protection: active
[ 0.000000] DMI 2.6 present.
[ 0.000000] No AGP bridge found
[ 0.000000] last_pfn = 0x128000 max_arch_pfn = 0x400000000
[ 0.000000] MTRR default type: uncachable
[ 0.000000] MTRR fixed ranges enabled:
[ 0.000000] 00000-9FFFF write-back
[ 0.000000] A0000-BFFFF uncachable
[ 0.000000] C0000-CFFFF write-protect
[ 0.000000] D0000-E7FFF uncachable
[ 0.000000] E8000-FFFFF write-protect
[ 0.000000] MTRR variable ranges enabled:
[ 0.000000] 0 base 000000000 mask F00000000 write-back
[ 0.000000] 1 base 100000000 mask FE0000000 write-back
[ 0.000000] 2 base 120000000 mask FF8000000 write-back
[ 0.000000] 3 base 0CC000000 mask FFC000000 uncachable
[ 0.000000] 4 base 0D0000000 mask FF0000000 uncachable
[ 0.000000] 5 base 0E0000000 mask FE0000000 uncachable
[ 0.000000] 6 disabled
[ 0.000000] 7 disabled
[ 0.000000] x86 PAT enabled: cpu 0, old 0x7040600070406, new 0x7010600070106
[ 0.000000] original variable MTRRs
[ 0.000000] reg 0, base: 0GB, range: 4GB, type WB
[ 0.000000] reg 1, base: 4GB, range: 512MB, type WB
[ 0.000000] reg 2, base: 4608MB, range: 128MB, type WB
[ 0.000000] reg 3, base: 3264MB, range: 64MB, type UC
[ 0.000000] reg 4, base: 3328MB, range: 256MB, type UC
[ 0.000000] reg 5, base: 3584MB, range: 512MB, type UC
[ 0.000000] total RAM covered: 3904M
[ 0.000000] Found optimal setting for mtrr clean up
[ 0.000000] gran_size: 64K chunk_size: 64K num_reg: 6 lose cover RAM: 0G
[ 0.000000] New variable MTRRs
[ 0.000000] reg 0, base: 0GB, range: 2GB, type WB
[ 0.000000] reg 1, base: 2GB, range: 1GB, type WB
[ 0.000000] reg 2, base: 3GB, range: 128MB, type WB
[ 0.000000] reg 3, base: 3200MB, range: 64MB, type WB
[ 0.000000] reg 4, base: 4GB, range: 512MB, type WB
[ 0.000000] reg 5, base: 4608MB, range: 128MB, type WB
[ 0.000000] e820 update range: 00000000cc000000 - 0000000100000000 (usable) ==> (reserved)
[ 0.000000] last_pfn = 0xcb800 max_arch_pfn = 0x400000000
[ 0.000000] e820 update range: 0000000000001000 - 0000000000010000 (usable) ==> (reserved)
[ 0.000000] Scanning 1 areas for low memory corruption
[ 0.000000] modified physical RAM map:
[ 0.000000] modified: 0000000000000000 - 0000000000001000 (usable)
[ 0.000000] modified: 0000000000001000 - 0000000000010000 (reserved)
[ 0.000000] modified: 0000000000010000 - 000000000009ac00 (usable)
[ 0.000000] modified: 000000000009ac00 - 00000000000a0000 (reserved)
[ 0.000000] modified: 00000000000e0000 - 0000000000100000 (reserved)
[ 0.000000] modified: 0000000000100000 - 00000000cb43c000 (usable)
[ 0.000000] modified: 00000000cb43c000 - 00000000cb47c000 (ACPI NVS)
[ 0.000000] modified: 00000000cb47c000 - 00000000cb4fb000 (reserved)
[ 0.000000] modified: 00000000cb4fb000 - 00000000cb50f000 (ACPI NVS)
[ 0.000000] modified: 00000000cb50f000 - 00000000cb615000 (reserved)
[ 0.000000] modified: 00000000cb615000 - 00000000cb618000 (ACPI NVS)
[ 0.000000] modified: 00000000cb618000 - 00000000cb622000 (ACPI data)
[ 0.000000] modified: 00000000cb622000 - 00000000cb62b000 (ACPI NVS)
[ 0.000000] modified: 00000000cb62b000 - 00000000cb649000 (reserved)
[ 0.000000] modified: 00000000cb649000 - 00000000cb68c000 (ACPI NVS)
[ 0.000000] modified: 00000000cb68c000 - 00000000cb800000 (usable)
[ 0.000000] modified: 00000000cde00000 - 00000000d0000000 (reserved)
[ 0.000000] modified: 00000000fed1c000 - 00000000fed20000 (reserved)
[ 0.000000] modified: 00000000ff000000 - 0000000100000000 (reserved)
[ 0.000000] modified: 0000000100000000 - 0000000128000000 (usable)
[ 0.000000] initial memory mapped : 0 - 20000000
[ 0.000000] init_memory_mapping: 0000000000000000-00000000cb800000
[ 0.000000] 0000000000 - 00cb800000 page 2M
[ 0.000000] kernel direct mapping tables up to cb800000 @ 16000-1b000
[ 0.000000] init_memory_mapping: 0000000100000000-0000000128000000
[ 0.000000] 0100000000 - 0128000000 page 2M
[ 0.000000] kernel direct mapping tables up to 128000000 @ 19000-1f000
[ 0.000000] RAMDISK: 37a45000 - 37fef35c
[ 0.000000] ACPI: RSDP 00000000000f0410 00024 (v02 INTEL)
[ 0.000000] ACPI: XSDT 00000000cb620e18 00054 (v01 INTEL DH55HC 01072009 MSFT 00010013)
[ 0.000000] ACPI: FACP 00000000cb61fd98 000F4 (v04 INTEL DH55HC 01072009 MSFT 00010013)
[ 0.000000] ACPI Warning: 32/64 FACS address mismatch in FADT - two FACS tables! (20091214/tbfadt-369)
[ 0.000000] ACPI Warning: 32/64X FACS address mismatch in FADT - CB628E40/00000000CB628D40, using 32 (20091214/tbfadt-486)
[ 0.000000] ACPI: DSDT 00000000cb618018 06148 (v01 INTEL DH55HC 00000000 INTL 20051117)
[ 0.000000] ACPI: FACS 00000000cb628e40 00040
[ 0.000000] ACPI: APIC 00000000cb61ff18 000CC (v02 INTEL DH55HC 01072009 MSFT 00010013)
[ 0.000000] ACPI: SSDT 00000000cb61fc18 0014E (v01 INTEL DH55HC 00000001 MSFT 03000001)
[ 0.000000] ACPI: MCFG 00000000cb621f18 0003C (v01 INTEL DH55HC 01072009 MSFT 00000097)
[ 0.000000] ACPI: HPET 00000000cb621e98 00038 (v01 INTEL DH55HC 01072009 AMI. 00000003)
[ 0.000000] ACPI: ASF! 00000000cb620c18 000A0 (v32 INTEL DH55HC 00000001 TFSM 000F4240)
[ 0.000000] ACPI: Local APIC address 0xfee00000
[ 0.000000] (9 early reservations) ==> bootmem [0000000000 - 0128000000]
[ 0.000000] #0 [0000000000 - 0000001000] BIOS data page ==> [0000000000 - 0000001000]
[ 0.000000] #1 [0001000000 - 0001421068] TEXT DATA BSS ==> [0001000000 - 0001421068]
[ 0.000000] #2 [0037a45000 - 0037fef35c] RAMDISK ==> [0037a45000 - 0037fef35c]
[ 0.000000] #3 [000009ac00 - 0000100000] BIOS reserved ==> [000009ac00 - 0000100000]
[ 0.000000] #4 [0001422000 - 000142221c] BRK ==> [0001422000 - 000142221c]
[ 0.000000] #5 [0000010000 - 0000012000] TRAMPOLINE ==> [0000010000 - 0000012000]
[ 0.000000] #6 [0000012000 - 0000016000] ACPI WAKEUP ==> [0000012000 - 0000016000]
[ 0.000000] #7 [0000016000 - 0000019000] PGTABLE ==> [0000016000 - 0000019000]
[ 0.000000] #8 [0000019000 - 000001a000] PGTABLE ==> [0000019000 - 000001a000]
[ 0.000000] [ffffea0000000000-ffffea00041fffff] PMD -> [ffff880028600000-ffff88002bdfffff] on node 0
[ 0.000000] Zone PFN ranges:
[ 0.000000] DMA 0x00000000 -> 0x00001000
[ 0.000000] DMA32 0x00001000 -> 0x00100000
[ 0.000000] Normal 0x00100000 -> 0x00128000
[ 0.000000] Movable zone start PFN for each node
[ 0.000000] early_node_map[5] active PFN ranges
[ 0.000000] 0: 0x00000000 -> 0x00000001
[ 0.000000] 0: 0x00000010 -> 0x0000009a
[ 0.000000] 0: 0x00000100 -> 0x000cb43c
[ 0.000000] 0: 0x000cb68c -> 0x000cb800
[ 0.000000] 0: 0x00100000 -> 0x00128000
[ 0.000000] On node 0 totalpages: 996667
[ 0.000000] DMA zone: 56 pages used for memmap
[ 0.000000] DMA zone: 112 pages reserved
[ 0.000000] DMA zone: 3811 pages, LIFO batch:0
[ 0.000000] DMA32 zone: 14280 pages used for memmap
[ 0.000000] DMA32 zone: 814568 pages, LIFO batch:31
[ 0.000000] Normal zone: 2240 pages used for memmap
[ 0.000000] Normal zone: 161600 pages, LIFO batch:31
[ 0.000000] ACPI: PM-Timer IO Port: 0x408
[ 0.000000] ACPI: Local APIC address 0xfee00000
[ 0.000000] ACPI: LAPIC (acpi_id[0x01] lapic_id[0x00] enabled)
[ 0.000000] ACPI: LAPIC (acpi_id[0x02] lapic_id[0x01] enabled)
[ 0.000000] ACPI: LAPIC (acpi_id[0x03] lapic_id[0x04] enabled)
[ 0.000000] ACPI: LAPIC (acpi_id[0x04] lapic_id[0x05] enabled)
[ 0.000000] ACPI: LAPIC (acpi_id[0x05] lapic_id[0x04] disabled)
[ 0.000000] ACPI: LAPIC (acpi_id[0x06] lapic_id[0x05] disabled)
[ 0.000000] ACPI: LAPIC (acpi_id[0x07] lapic_id[0x06] disabled)
[ 0.000000] ACPI: LAPIC (acpi_id[0x08] lapic_id[0x07] disabled)
[ 0.000000] ACPI: LAPIC (acpi_id[0x09] lapic_id[0x08] disabled)
[ 0.000000] ACPI: LAPIC (acpi_id[0x0a] lapic_id[0x09] disabled)
[ 0.000000] ACPI: LAPIC (acpi_id[0x0b] lapic_id[0x0a] disabled)
[ 0.000000] ACPI: LAPIC (acpi_id[0x0c] lapic_id[0x0b] disabled)
[ 0.000000] ACPI: LAPIC (acpi_id[0x0d] lapic_id[0x0c] disabled)
[ 0.000000] ACPI: LAPIC (acpi_id[0x0e] lapic_id[0x0d] disabled)
[ 0.000000] ACPI: LAPIC (acpi_id[0x0f] lapic_id[0x0e] disabled)
[ 0.000000] ACPI: LAPIC (acpi_id[0x10] lapic_id[0x0f] disabled)
[ 0.000000] ACPI: IOAPIC (id[0x00] address[0xfec00000] gsi_base[0])
[ 0.000000] IOAPIC[0]: apic_id 0, version 32, address 0xfec00000, GSI 0-23
[ 0.000000] ACPI: INT_SRC_OVR (bus 0 bus_irq 0 global_irq 2 dfl dfl)
[ 0.000000] ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 9 high level)
[ 0.000000] ACPI: IRQ0 used by override.
[ 0.000000] ACPI: IRQ2 used by override.
[ 0.000000] ACPI: IRQ9 used by override.
[ 0.000000] Using ACPI (MADT) for SMP configuration information
[ 0.000000] ACPI: HPET id: 0x8086a701 base: 0xfed00000
[ 0.000000] 16 Processors exceeds NR_CPUS limit of 4
[ 0.000000] SMP: Allowing 4 CPUs, 0 hotplug CPUs
[ 0.000000] nr_irqs_gsi: 24
[ 0.000000] PM: Registered nosave memory: 0000000000001000 - 0000000000010000
[ 0.000000] PM: Registered nosave memory: 000000000009a000 - 000000000009b000
[ 0.000000] PM: Registered nosave memory: 000000000009b000 - 00000000000a0000
[ 0.000000] PM: Registered nosave memory: 00000000000a0000 - 00000000000e0000
[ 0.000000] PM: Registered nosave memory: 00000000000e0000 - 0000000000100000
[ 0.000000] PM: Registered nosave memory: 00000000cb43c000 - 00000000cb47c000
[ 0.000000] PM: Registered nosave memory: 00000000cb47c000 - 00000000cb4fb000
[ 0.000000] PM: Registered nosave memory: 00000000cb4fb000 - 00000000cb50f000
[ 0.000000] PM: Registered nosave memory: 00000000cb50f000 - 00000000cb615000
[ 0.000000] PM: Registered nosave memory: 00000000cb615000 - 00000000cb618000
[ 0.000000] PM: Registered nosave memory: 00000000cb618000 - 00000000cb622000
[ 0.000000] PM: Registered nosave memory: 00000000cb622000 - 00000000cb62b000
[ 0.000000] PM: Registered nosave memory: 00000000cb62b000 - 00000000cb649000
[ 0.000000] PM: Registered nosave memory: 00000000cb649000 - 00000000cb68c000
[ 0.000000] PM: Registered nosave memory: 00000000cb800000 - 00000000cde00000
[ 0.000000] PM: Registered nosave memory: 00000000cde00000 - 00000000d0000000
[ 0.000000] PM: Registered nosave memory: 00000000d0000000 - 00000000fed1c000
[ 0.000000] PM: Registered nosave memory: 00000000fed1c000 - 00000000fed20000
[ 0.000000] PM: Registered nosave memory: 00000000fed20000 - 00000000ff000000
[ 0.000000] PM: Registered nosave memory: 00000000ff000000 - 0000000100000000
[ 0.000000] Allocating PCI resources starting at d0000000 (gap: d0000000:2ed1c000)
[ 0.000000] setup_percpu: NR_CPUS:4 nr_cpumask_bits:4 nr_cpu_ids:4 nr_node_ids:1
[ 0.000000] PERCPU: Embedded 25 pages/cpu @ffff880028200000 s73624 r8192 d20584 u524288
[ 0.000000] pcpu-alloc: s73624 r8192 d20584 u524288 alloc=1*2097152
[ 0.000000] pcpu-alloc: [0] 0 1 2 3
[ 0.000000] Built 1 zonelists in Zone order, mobility grouping on. Total pages: 979979
[ 0.000000] Kernel command line: BOOT_IMAGE=//vmlinuz-2.6.33-rc8 root=/dev/mapper/ST64GB-LENNYX64--ROOT ro selinux=0 acpi_sleep=s3_bios no_console_suspend rootfstype=ext4 enable_mtrr_cleanup resume=/dev/sdb1
[ 0.000000] PID hash table entries: 4096 (order: 3, 32768 bytes)
[ 0.000000] Dentry cache hash table entries: 524288 (order: 10, 4194304 bytes)
[ 0.000000] Inode-cache hash table entries: 262144 (order: 9, 2097152 bytes)
[ 0.000000] Checking aperture...
[ 0.000000] No AGP bridge found
[ 0.000000] Memory: 3845600k/4849664k available (2273k kernel code, 862996k absent, 140120k reserved, 1236k data, 380k init)
[ 0.000000] Hierarchical RCU implementation.
[ 0.000000] NR_IRQS:384
[ 0.000000] Extended CMOS year: 2000
[ 0.000000] Console: colour VGA+ 80x25
[ 0.000000] console [tty0] enabled
[ 0.000000] hpet clockevent registered
[ 0.000000] Fast TSC calibration using PIT
[ 0.004000] Detected 3325.507 MHz processor.
[ 0.000003] Calibrating delay loop (skipped), value calculated using timer frequency.. 6651.01 BogoMIPS (lpj=13302028)
[ 0.000132] Security Framework initialized
[ 0.000191] Mount-cache hash table entries: 256
[ 0.000310] CPU: Physical Processor ID: 0
[ 0.000356] CPU: Processor Core ID: 0
[ 0.000403] mce: CPU supports 9 MCE banks
[ 0.000457] CPU0: Thermal monitoring enabled (TM1)
[ 0.000507] CPU 0 MCA banks CMCI:2 CMCI:3 CMCI:5 CMCI:6
[ 0.000648] using mwait in idle threads.
[ 0.000695] Performance Events: Nehalem/Corei7 events, Intel PMU driver.
[ 0.000786] ... version: 3
[ 0.000833] ... bit width: 48
[ 0.000879] ... generic registers: 4
[ 0.000926] ... value mask: 0000ffffffffffff
[ 0.000974] ... max period: 000000007fffffff
[ 0.001022] ... fixed-purpose events: 3
[ 0.001069] ... event mask: 000000070000000f
[ 0.003075] ACPI: Core revision 20091214
[ 0.011046] Setting APIC routing to flat
[ 0.011431] ..TIMER: vector=0x30 apic1=0 pin1=2 apic2=-1 pin2=-1
[ 0.051044] CPU0: Intel(R) Core(TM) i5 CPU 661 @ 3.33GHz stepping 02
[ 0.155427] Booting Node 0, Processors #1
[ 0.243107] CPU 1 MCA banks SHD:2 SHD:3 SHD:5 SHD:6
[ 0.263231] #2
[ 0.350764] CPU 2 MCA banks CMCI:2 CMCI:3 CMCI:5 SHD:6
[ 0.370814] #3 Ok.
[ 0.458419] CPU 3 MCA banks SHD:2 SHD:3 SHD:5 SHD:6
[ 0.478458] Brought up 4 CPUs
[ 0.478550] Total of 4 processors activated (26600.53 BogoMIPS).
[ 0.479754] NET: Registered protocol family 16
[ 0.479963] ACPI: bus type pci registered
[ 0.480074] PCI: MMCONFIG for domain 0000 [bus 00-3f] at [mem 0xe0000000-0xe3ffffff] (base 0xe0000000)
[ 0.480150] PCI: not using MMCONFIG
[ 0.480196] PCI: Using configuration type 1 for base access
[ 0.481026] bio: create slab <bio-0> at 0
[ 0.481738] ACPI: EC: Look up EC in DSDT
[ 0.483273] ACPI: Executed 1 blocks of module-level executable AML code
[ 0.487600] ACPI: Interpreter enabled
[ 0.487648] ACPI: (supports S0 S1 S3 S4 S5)
[ 0.487798] ACPI: Using IOAPIC for interrupt routing
[ 0.487880] PCI: MMCONFIG for domain 0000 [bus 00-3f] at [mem 0xe0000000-0xe3ffffff] (base 0xe0000000)
[ 0.488030] PCI: MMCONFIG at [mem 0xe0000000-0xe3ffffff] reserved in ACPI motherboard resources
[ 0.489864] ACPI: BIOS _OSI(Linux) query ignored
[ 0.496079] ACPI: PCI Root Bridge [PCI0] (0000:00)
[ 0.496155] pci_root PNP0A08:00: ignoring host bridge windows from ACPI; boot with "pci=use_crs" to use them
[ 0.496330] pci_root PNP0A08:00: host bridge window [io 0x0000-0x0cf7] (ignored)
[ 0.496332] pci_root PNP0A08:00: host bridge window [io 0x0d00-0xffff] (ignored)
[ 0.496333] pci_root PNP0A08:00: host bridge window [mem 0x000a0000-0x000bffff] (ignored)
[ 0.496335] pci_root PNP0A08:00: host bridge window [mem 0xd0000000-0xffffffff] (ignored)
[ 0.496369] pci 0000:00:02.0: reg 10: [mem 0xfe000000-0xfe3fffff 64bit]
[ 0.496373] pci 0000:00:02.0: reg 18: [mem 0xd0000000-0xdfffffff 64bit pref]
[ 0.496375] pci 0000:00:02.0: reg 20: [io 0xf100-0xf107]
[ 0.496442] pci 0000:00:16.0: reg 10: [mem 0xfe42a000-0xfe42a00f 64bit]
[ 0.496494] pci 0000:00:16.0: PME# supported from D0 D3hot D3cold
[ 0.496498] pci 0000:00:16.0: PME# disabled
[ 0.496527] pci 0000:00:16.2: reg 10: [io 0xf0f0-0xf0f7]
[ 0.496532] pci 0000:00:16.2: reg 14: [io 0xf0e0-0xf0e3]
[ 0.496537] pci 0000:00:16.2: reg 18: [io 0xf0d0-0xf0d7]
[ 0.496542] pci 0000:00:16.2: reg 1c: [io 0xf0c0-0xf0c3]
[ 0.496547] pci 0000:00:16.2: reg 20: [io 0xf0b0-0xf0bf]
[ 0.496610] pci 0000:00:16.3: reg 10: [io 0xf0a0-0xf0a7]
[ 0.496617] pci 0000:00:16.3: reg 14: [mem 0xfe429000-0xfe429fff]
[ 0.496695] pci 0000:00:19.0: reg 10: [mem 0xfe400000-0xfe41ffff]
[ 0.496699] pci 0000:00:19.0: reg 14: [mem 0xfe428000-0xfe428fff]
[ 0.496704] pci 0000:00:19.0: reg 18: [io 0xf040-0xf05f]
[ 0.496736] pci 0000:00:19.0: PME# supported from D0 D3hot D3cold
[ 0.496739] pci 0000:00:19.0: PME# disabled
[ 0.496773] pci 0000:00:1a.0: reg 10: [mem 0xfe427000-0xfe4273ff]
[ 0.496821] pci 0000:00:1a.0: PME# supported from D0 D3hot D3cold
[ 0.496825] pci 0000:00:1a.0: PME# disabled
[ 0.496853] pci 0000:00:1b.0: reg 10: [mem 0xfe420000-0xfe423fff 64bit]
[ 0.496889] pci 0000:00:1b.0: PME# supported from D0 D3hot D3cold
[ 0.496892] pci 0000:00:1b.0: PME# disabled
[ 0.496947] pci 0000:00:1c.0: PME# supported from D0 D3hot D3cold
[ 0.496950] pci 0000:00:1c.0: PME# disabled
[ 0.497008] pci 0000:00:1c.4: PME# supported from D0 D3hot D3cold
[ 0.497011] pci 0000:00:1c.4: PME# disabled
[ 0.497049] pci 0000:00:1d.0: reg 10: [mem 0xfe426000-0xfe4263ff]
[ 0.497095] pci 0000:00:1d.0: PME# supported from D0 D3hot D3cold
[ 0.497099] pci 0000:00:1d.0: PME# disabled
[ 0.497239] pci 0000:00:1f.2: reg 10: [io 0xf090-0xf097]
[ 0.497243] pci 0000:00:1f.2: reg 14: [io 0xf080-0xf083]
[ 0.497247] pci 0000:00:1f.2: reg 18: [io 0xf070-0xf077]
[ 0.497251] pci 0000:00:1f.2: reg 1c: [io 0xf060-0xf063]
[ 0.497255] pci 0000:00:1f.2: reg 20: [io 0xf020-0xf03f]
[ 0.497260] pci 0000:00:1f.2: reg 24: [mem 0xfe425000-0xfe4257ff]
[ 0.497283] pci 0000:00:1f.2: PME# supported from D3hot
[ 0.497285] pci 0000:00:1f.2: PME# disabled
[ 0.497307] pci 0000:00:1f.3: reg 10: [mem 0xfe424000-0xfe4240ff 64bit]
[ 0.497319] pci 0000:00:1f.3: reg 20: [io 0xf000-0xf01f]
[ 0.497372] pci 0000:00:1c.0: PCI bridge to [bus 01-01]
[ 0.497461] pci 0000:00:1c.4: PCI bridge to [bus 02-02]
[ 0.497554] pci 0000:00:1e.0: PCI bridge to [bus 03-03] (subtractive decode)
[ 0.497625] pci_bus 0000:00: on NUMA node 0
[ 0.497628] ACPI: PCI Interrupt Routing Table [\_SB_.PCI0._PRT]
[ 0.497780] ACPI: PCI Interrupt Routing Table [\_SB_.PCI0.PEX4._PRT]
[ 0.497817] ACPI: PCI Interrupt Routing Table [\_SB_.PCI0.BR20._PRT]
[ 0.501652] ACPI: PCI Interrupt Link [LNKA] (IRQs 3 4 5 6 7 10 *11 12 14 15)
[ 0.501990] ACPI: PCI Interrupt Link [LNKB] (IRQs 3 4 *5 6 7 10 11 12 14 15)
[ 0.502330] ACPI: PCI Interrupt Link [LNKC] (IRQs 3 4 5 6 *10 11 12 14 15)
[ 0.502649] ACPI: PCI Interrupt Link [LNKD] (IRQs 3 4 5 6 10 *11 12 14 15)
[ 0.502967] ACPI: PCI Interrupt Link [LNKE] (IRQs *3 4 5 6 7 10 11 12 14 15)
[ 0.503304] ACPI: PCI Interrupt Link [LNKF] (IRQs 3 4 5 6 7 10 11 12 14 15) *0
[ 0.503678] ACPI: PCI Interrupt Link [LNKG] (IRQs 3 4 5 6 *7 10 11 12 14 15)
[ 0.504015] ACPI: PCI Interrupt Link [LNKH] (IRQs 3 *4 5 6 7 10 11 12 14 15)
[ 0.504380] vgaarb: device added: PCI:0000:00:02.0,decodes=io+mem,owns=io+mem,locks=none
[ 0.504456] vgaarb: loaded
[ 0.504545] usbcore: registered new interface driver usbfs
[ 0.504626] usbcore: registered new interface driver hub
[ 0.504694] usbcore: registered new device driver usb
[ 0.504825] PCI: Using ACPI for IRQ routing
[ 0.504873] PCI: pci_cache_line_size set to 64 bytes
[ 0.504982] hpet0: at MMIO 0xfed00000, IRQs 2, 8, 0, 0, 0, 0, 0, 0
[ 0.505198] hpet0: 8 comparators, 64-bit 14.318180 MHz counter
[ 0.507249] Switching to clocksource tsc
[ 0.507368] pnp: PnP ACPI init
[ 0.507416] ACPI: bus type pnp registered
[ 0.508961] pnp: PnP ACPI: found 11 devices
[ 0.509009] ACPI: ACPI bus type pnp unregistered
[ 0.509061] system 00:01: [mem 0xfed14000-0xfed19fff] has been reserved
[ 0.509115] system 00:01: [mem 0xe0000000-0xe3ffffff] has been reserved
[ 0.509165] system 00:01: [mem 0xfed90000-0xfed93fff] has been reserved
[ 0.509218] system 00:01: [mem 0xfed20000-0xfed3ffff] has been reserved
[ 0.509272] system 00:01: [mem 0xfee00000-0xfee0ffff] has been reserved
[ 0.509328] system 00:06: [io 0x04d0-0x04d1] has been reserved
[ 0.509381] system 00:09: [io 0x0400-0x047f] has been reserved
[ 0.509432] system 00:09: [io 0x1180-0x119f] has been reserved
[ 0.509484] system 00:09: [io 0x0500-0x057f] has been reserved
[ 0.509533] system 00:09: [mem 0xfed1c000-0xfed1ffff] has been reserved
[ 0.509590] system 00:09: [mem 0xfec00000-0xfecfffff] could not be reserved
[ 0.509644] system 00:09: [mem 0xfed08000-0xfed08fff] has been reserved
[ 0.509698] system 00:09: [mem 0xff000000-0xffffffff] has been reserved
[ 0.514472] pci 0000:00:1c.0: PCI bridge to [bus 01-01]
[ 0.514519] pci 0000:00:1c.0: bridge window [io disabled]
[ 0.514572] pci 0000:00:1c.0: bridge window [mem disabled]
[ 0.514624] pci 0000:00:1c.0: bridge window [mem pref disabled]
[ 0.514679] pci 0000:00:1c.4: PCI bridge to [bus 02-02]
[ 0.514728] pci 0000:00:1c.4: bridge window [io disabled]
[ 0.514778] pci 0000:00:1c.4: bridge window [mem disabled]
[ 0.514829] pci 0000:00:1c.4: bridge window [mem pref disabled]
[ 0.514883] pci 0000:00:1e.0: PCI bridge to [bus 03-03]
[ 0.514933] pci 0000:00:1e.0: bridge window [io disabled]
[ 0.514985] pci 0000:00:1e.0: bridge window [mem disabled]
[ 0.515036] pci 0000:00:1e.0: bridge window [mem pref disabled]
[ 0.515099] pci 0000:00:1c.0: PCI INT A -> GSI 17 (level, low) -> IRQ 17
[ 0.515152] pci 0000:00:1c.0: setting latency timer to 64
[ 0.515158] pci 0000:00:1c.4: PCI INT A -> GSI 17 (level, low) -> IRQ 17
[ 0.515212] pci 0000:00:1c.4: setting latency timer to 64
[ 0.515217] pci 0000:00:1e.0: setting latency timer to 64
[ 0.515219] pci_bus 0000:00: resource 0 [io 0x0000-0xffff]
[ 0.515221] pci_bus 0000:00: resource 1 [mem 0x00000000-0xffffffffffffffff]
[ 0.515222] pci_bus 0000:03: resource 3 [io 0x0000-0xffff]
[ 0.515224] pci_bus 0000:03: resource 4 [mem 0x00000000-0xffffffffffffffff]
[ 0.515250] NET: Registered protocol family 2
[ 0.515330] IP route cache hash table entries: 131072 (order: 8, 1048576 bytes)
[ 0.515605] TCP established hash table entries: 262144 (order: 10, 4194304 bytes)
[ 0.516597] TCP bind hash table entries: 65536 (order: 8, 1048576 bytes)
[ 0.516875] TCP: Hash tables configured (established 262144 bind 65536)
[ 0.516929] TCP reno registered
[ 0.516974] UDP hash table entries: 2048 (order: 4, 65536 bytes)
[ 0.517044] UDP-Lite hash table entries: 2048 (order: 4, 65536 bytes)
[ 0.517191] NET: Registered protocol family 1
[ 0.517249] pci 0000:00:02.0: Boot video device
[ 0.566159] PCI: CLS 64 bytes, default 64
[ 0.566187] Trying to unpack rootfs image as initramfs...
[ 0.648041] Freeing initrd memory: 5800k freed
[ 0.648967] PCI-DMA: Using software bounce buffering for IO (SWIOTLB)
[ 0.649024] Placing 64MB software IO TLB between ffff880020000000 - ffff880024000000
[ 0.649098] software IO TLB at phys 0x20000000 - 0x24000000
[ 0.649781] Scanning for low memory corruption every 60 seconds
[ 0.650126] HugeTLB registered 2 MB page size, pre-allocated 0 pages
[ 0.650311] VFS: Disk quotas dquot_6.5.2
[ 0.650369] Dquot-cache hash table entries: 512 (order 0, 4096 bytes)
[ 0.650456] msgmni has been set to 7524
[ 0.650590] alg: No test for stdrng (krng)
[ 0.650667] Block layer SCSI generic (bsg) driver version 0.4 loaded (major 253)
[ 0.650742] io scheduler noop registered (default)
[ 0.650790] io scheduler deadline registered
[ 0.650846] io scheduler cfq registered
[ 0.650948] pcieport 0000:00:1c.0: setting latency timer to 64
[ 0.650980] pcieport 0000:00:1c.0: irq 24 for MSI/MSI-X
[ 0.651038] pcieport 0000:00:1c.4: setting latency timer to 64
[ 0.651067] pcieport 0000:00:1c.4: irq 25 for MSI/MSI-X
[ 0.652686] Linux agpgart interface v0.103
[ 0.652741] agpgart-intel 0000:00:00.0: Intel Ironlake/D Chipset
[ 0.653424] agpgart-intel 0000:00:00.0: detected 32764K stolen memory
[ 0.704367] agpgart-intel 0000:00:00.0: AGP aperture is 256M @ 0xd0000000
[ 0.704448] Serial: 8250/16550 driver, 4 ports, IRQ sharing enabled
[ 0.704767] serial 0000:00:16.3: PCI INT B -> GSI 17 (level, low) -> IRQ 17
[ 0.704901] 0000:00:16.3: ttyS0 at I/O 0xf0a0 (irq = 17) is a 16550A
[ 0.705837] brd: module loaded
[ 0.705884] usbmon: debugfs is not available
[ 0.705973] PNP: PS/2 Controller [PNP0303:PS2K] at 0x60,0x64 irq 1
[ 0.706025] PNP: PS/2 appears to have AUX port disabled, if this is incorrect please boot with i8042.nopnp
[ 0.706583] serio: i8042 KBD port at 0x60,0x64 irq 1
[ 0.706700] mice: PS/2 mouse device common for all mice
[ 0.706783] rtc_cmos 00:04: RTC can wake from S4
[ 0.706863] rtc_cmos 00:04: rtc core: registered rtc_cmos as rtc0
[ 0.706939] rtc0: alarms up to one year, y3k, 114 bytes nvram, hpet irqs
[ 0.707010] cpuidle: using governor ladder
[ 0.707057] cpuidle: using governor menu
[ 0.707104] No iBFT detected.
[ 0.707272] TCP cubic registered
[ 0.707318] NET: Registered protocol family 17
[ 0.733095] input: AT Translated Set 2 keyboard as /devices/platform/i8042/serio0/input/input0
[ 0.733356] rtc_cmos 00:04: setting system clock to 2010-02-20 12:41:59 UTC (1266669719)
[ 0.733462] Freeing unused kernel memory: 380k freed
[ 0.760450] device-mapper: uevent: version 1.0.3
[ 0.760577] device-mapper: ioctl: 4.16.0-ioctl (2009-11-05) initialised: dm-devel@redhat.com
[ 0.780020] input: Power Button as /devices/LNXSYSTM:00/LNXSYBUS:00/PNP0C0C:00/input/input1
[ 0.780100] ACPI: Power Button [PWRB]
[ 0.780186] input: Power Button as /devices/LNXSYSTM:00/LNXPWRBN:00/input/input2
[ 0.780257] ACPI: Power Button [PWRF]
[ 0.782440] e1000e: Intel(R) PRO/1000 Network Driver - 1.0.2-k2
[ 0.782493] e1000e: Copyright (c) 1999 - 2009 Intel Corporation.
[ 0.782580] e1000e 0000:00:19.0: PCI INT A -> GSI 20 (level, low) -> IRQ 20
[ 0.782638] e1000e 0000:00:19.0: setting latency timer to 64
[ 0.782719] e1000e 0000:00:19.0: irq 26 for MSI/MSI-X
[ 0.784231] ehci_hcd: USB 2.0 'Enhanced' Host Controller (EHCI) Driver
[ 0.810504] SCSI subsystem initialized
[ 0.819456] libata version 3.00 loaded.
[ 1.209279] 0000:00:19.0: eth0: (PCI Express:2.5GB/s:Width x1) 00:27:0e:09:d5:df
[ 1.209355] 0000:00:19.0: eth0: Intel(R) PRO/1000 Network Connection
[ 1.209444] 0000:00:19.0: eth0: MAC: 9, PHY: 9, PBA No: ffffff-0ff
[ 1.209519] ehci_hcd 0000:00:1a.0: PCI INT A -> GSI 16 (level, low) -> IRQ 16
[ 1.209594] ehci_hcd 0000:00:1a.0: setting latency timer to 64
[ 1.209597] ehci_hcd 0000:00:1a.0: EHCI Host Controller
[ 1.209663] ehci_hcd 0000:00:1a.0: new USB bus registered, assigned bus number 1
[ 1.209761] ehci_hcd 0000:00:1a.0: debug port 2
[ 1.213716] ehci_hcd 0000:00:1a.0: cache line size of 64 is not supported
[ 1.213730] ehci_hcd 0000:00:1a.0: irq 16, io mem 0xfe427000
[ 1.229667] ehci_hcd 0000:00:1a.0: USB 2.0 started, EHCI 1.00
[ 1.229750] usb usb1: New USB device found, idVendor=1d6b, idProduct=0002
[ 1.229804] usb usb1: New USB device strings: Mfr=3, Product=2, SerialNumber=1
[ 1.229877] usb usb1: Product: EHCI Host Controller
[ 1.229926] usb usb1: Manufacturer: Linux 2.6.33-rc8 ehci_hcd
[ 1.229977] usb usb1: SerialNumber: 0000:00:1a.0
[ 1.230080] hub 1-0:1.0: USB hub found
[ 1.230128] hub 1-0:1.0: 3 ports detected
[ 1.230215] ahci 0000:00:1f.2: version 3.0
[ 1.230225] ahci 0000:00:1f.2: PCI INT B -> GSI 19 (level, low) -> IRQ 19
[ 1.230305] ahci 0000:00:1f.2: irq 27 for MSI/MSI-X
[ 1.246141] ahci 0000:00:1f.2: AHCI 0001.0300 32 slots 6 ports 3 Gbps 0x3f impl SATA mode
[ 1.246223] ahci 0000:00:1f.2: flags: 64bit ncq sntf ilck pm led clo pio slum part ems sxs apst
[ 1.248282] ahci 0000:00:1f.2: setting latency timer to 64
[ 1.286038] scsi0 : ahci
[ 1.286146] scsi1 : ahci
[ 1.286222] scsi2 : ahci
[ 1.286301] scsi3 : ahci
[ 1.286378] scsi4 : ahci
[ 1.286455] scsi5 : ahci
[ 1.286607] ata1: SATA max UDMA/133 abar m2048@0xfe425000 port 0xfe425100 irq 27
[ 1.286682] ata2: SATA max UDMA/133 abar m2048@0xfe425000 port 0xfe425180 irq 27
[ 1.286756] ata3: SATA max UDMA/133 abar m2048@0xfe425000 port 0xfe425200 irq 27
[ 1.286830] ata4: SATA max UDMA/133 abar m2048@0xfe425000 port 0xfe425280 irq 27
[ 1.286905] ata5: SATA max UDMA/133 abar m2048@0xfe425000 port 0xfe425300 irq 27
[ 1.286979] ata6: SATA max UDMA/133 abar m2048@0xfe425000 port 0xfe425380 irq 27
[ 1.287071] ehci_hcd 0000:00:1d.0: PCI INT A -> GSI 23 (level, low) -> IRQ 23
[ 1.287136] ehci_hcd 0000:00:1d.0: setting latency timer to 64
[ 1.287139] ehci_hcd 0000:00:1d.0: EHCI Host Controller
[ 1.287192] ehci_hcd 0000:00:1d.0: new USB bus registered, assigned bus number 2
[ 1.287284] ehci_hcd 0000:00:1d.0: debug port 2
[ 1.291270] ehci_hcd 0000:00:1d.0: cache line size of 64 is not supported
[ 1.291278] ehci_hcd 0000:00:1d.0: irq 23, io mem 0xfe426000
[ 1.304943] ehci_hcd 0000:00:1d.0: USB 2.0 started, EHCI 1.00
[ 1.305024] usb usb2: New USB device found, idVendor=1d6b, idProduct=0002
[ 1.305077] usb usb2: New USB device strings: Mfr=3, Product=2, SerialNumber=1
[ 1.305151] usb usb2: Product: EHCI Host Controller
[ 1.305199] usb usb2: Manufacturer: Linux 2.6.33-rc8 ehci_hcd
[ 1.305250] usb usb2: SerialNumber: 0000:00:1d.0
[ 1.305338] hub 2-0:1.0: USB hub found
[ 1.305386] hub 2-0:1.0: 3 ports detected
[ 1.540234] usb 1-1: new high speed USB device using ehci_hcd and address 2
[ 1.608041] ata3: SATA link down (SStatus 0 SControl 300)
[ 1.608113] ata2: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
[ 1.608180] ata1: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
[ 1.608396] ata5: SATA link down (SStatus 0 SControl 300)
[ 1.608400] ata6: SATA link down (SStatus 0 SControl 300)
[ 1.608416] ata1.00: ATA-8: STT_FTM64GX25H, 1819, max UDMA/133
[ 1.608421] ata1.00: 125045424 sectors, multi 1: LBA48 NCQ (depth 31/32), AA
[ 1.608429] ata4: SATA link down (SStatus 0 SControl 300)
[ 1.608932] ata2.00: HPA detected: current 1250261615, native 1250263728
[ 1.609058] ata2.00: ATA-8: WDC WD6400AAKS-00A7B0, 01.03B01, max UDMA/133
[ 1.609117] ata2.00: 1250261615 sectors, multi 16: LBA48 NCQ (depth 31/32), AA
[ 1.610116] ata2.00: configured for UDMA/133
[ 1.610342] ata1.00: configured for UDMA/133
[ 1.624077] scsi 0:0:0:0: Direct-Access ATA STT_FTM64GX25H 1819 PQ: 0 ANSI: 5
[ 1.624246] scsi 1:0:0:0: Direct-Access ATA WDC WD6400AAKS-0 01.0 PQ: 0 ANSI: 5
[ 1.626840] sd 0:0:0:0: [sda] 125045424 512-byte logical blocks: (64.0 GB/59.6 GiB)
[ 1.626905] sd 1:0:0:0: [sdb] 1250261615 512-byte logical blocks: (640 GB/596 GiB)
[ 1.626929] sd 1:0:0:0: [sdb] Write Protect is off
[ 1.626931] sd 1:0:0:0: [sdb] Mode Sense: 00 3a 00 00
[ 1.626941] sd 1:0:0:0: [sdb] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
[ 1.627009] sdb:
[ 1.627143] sd 0:0:0:0: [sda] Write Protect is off
[ 1.627229] sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00
[ 1.627238] sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
[ 1.627364] sda: sda1 sda2 < sda5 >
[ 1.627978] sd 0:0:0:0: [sda] Attached SCSI disk
[ 1.642051] sdb1 sdb2 sdb3 < sdb5 sdb6 sdb7 sdb8
[ 1.673676] usb 1-1: New USB device found, idVendor=8087, idProduct=0020
[ 1.673771] usb 1-1: New USB device strings: Mfr=0, Product=0, SerialNumber=0
[ 1.673965] hub 1-1:1.0: USB hub found
[ 1.674172] hub 1-1:1.0: 6 ports detected
[ 1.674239] sdb9 sdb10 sdb11 >
[ 1.694390] sd 1:0:0:0: [sdb] Attached SCSI disk
[ 1.783512] usb 2-1: new high speed USB device using ehci_hcd and address 2
[ 1.916412] usb 2-1: New USB device found, idVendor=8087, idProduct=0020
[ 1.916472] usb 2-1: New USB device strings: Mfr=0, Product=0, SerialNumber=0
[ 1.916675] hub 2-1:1.0: USB hub found
[ 1.916777] hub 2-1:1.0: 8 ports detected
[ 1.987936] usb 1-1.3: new full speed USB device using ehci_hcd and address 3
[ 2.083631] usb 1-1.3: New USB device found, idVendor=04a9, idProduct=220e
[ 2.083707] usb 1-1.3: New USB device strings: Mfr=1, Product=2, SerialNumber=0
[ 2.083771] usb 1-1.3: Product: CanoScan
[ 2.083812] usb 1-1.3: Manufacturer: Canon
[ 2.158518] usb 1-1.4: new full speed USB device using ehci_hcd and address 4
[ 2.177245] PM: Starting manual resume from disk
[ 2.186451] EXT4-fs (dm-0): mounted filesystem with ordered data mode
[ 2.254718] usb 1-1.4: New USB device found, idVendor=1532, idProduct=00fb
[ 2.254777] usb 1-1.4: New USB device strings: Mfr=1, Product=2, SerialNumber=0
[ 2.254839] usb 1-1.4: Product: Habu Mouse
[ 2.254880] usb 1-1.4: Manufacturer: Tempest
[ 2.330987] usb 1-1.5: new high speed USB device using ehci_hcd and address 5
[ 2.365344] udev: starting version 150
[ 2.422956] ACPI: SSDT 00000000cb617c18 0038C (v01 AMI IST 00000001 MSFT 03000001)
[ 2.436079] Monitor-Mwait will be used to enter C-2 state
[ 2.437886] usb 1-1.5: New USB device found, idVendor=0424, idProduct=2512
[ 2.437937] usb 1-1.5: New USB device strings: Mfr=0, Product=0, SerialNumber=0
[ 2.438153] hub 1-1.5:1.0: USB hub found
[ 2.438258] hub 1-1.5:1.0: 2 ports detected
[ 2.445559] Monitor-Mwait will be used to enter C-3 state
[ 2.480207] usbcore: registered new interface driver hiddev
[ 2.482442] input: Tempest Habu Mouse as /devices/pci0000:00/0000:00:1a.0/usb1/1-1/1-1.4/1-1.4:1.0/input/input3
[ 2.482570] generic-usb 0003:1532:00FB.0001: input,hidraw0: USB HID v1.00 Mouse [Tempest Habu Mouse] on usb-0000:00:1a.0-1.4/input0
[ 2.482664] usbcore: registered new interface driver usbhid
[ 2.482711] usbhid: USB HID core driver
[ 2.522607] HDA Intel 0000:00:1b.0: PCI INT A -> GSI 22 (level, low) -> IRQ 22
[ 2.522723] HDA Intel 0000:00:1b.0: irq 28 for MSI/MSI-X
[ 2.522742] HDA Intel 0000:00:1b.0: setting latency timer to 64
[ 2.604837] hda_codec: ALC888: BIOS auto-probing.
[ 2.713762] usb 1-1.5.1: new high speed USB device using ehci_hcd and address 6
[ 2.753771] Slow work thread pool: Starting up
[ 2.753848] Slow work thread pool: Ready
[ 2.756280] w83627ehf: Found W83627DHG-P chip at 0xa10
[ 2.761163] loop: module loaded
[ 2.804734] usb 1-1.5.1: New USB device found, idVendor=0424, idProduct=2602
[ 2.804812] usb 1-1.5.1: New USB device strings: Mfr=0, Product=0, SerialNumber=0
[ 2.804995] hub 1-1.5.1:1.0: USB hub found
[ 2.805093] hub 1-1.5.1:1.0: 4 ports detected
[ 2.911635] EXT4-fs (dm-5): warning: maximal mount count reached, running e2fsck is recommended
[ 2.911856] EXT4-fs (dm-5): mounted filesystem with ordered data mode
[ 2.917788] EXT4-fs (dm-7): warning: maximal mount count reached, running e2fsck is recommended
[ 2.917998] EXT4-fs (dm-7): mounted filesystem with ordered data mode
[ 2.926803] EXT2-fs (sda1): warning: mounting unchecked fs, running e2fsck is recommended
[ 2.930408] EXT4-fs (dm-6): warning: maximal mount count reached, running e2fsck is recommended
[ 2.930603] EXT4-fs (dm-6): mounted filesystem with ordered data mode
[ 2.949253] REISERFS (device sdb11): found reiserfs format "3.6" with standard journal
[ 2.949338] REISERFS (device sdb11): using ordered data mode
[ 2.962467] REISERFS (device sdb11): journal params: device sdb11, size 8192, journal first block 18, max trans len 1024, max batch 900, max commit age 30, max trans age 30
[ 2.962766] REISERFS (device sdb11): checking transaction log (sdb11)
[ 3.030320] REISERFS (device sdb11): Using r5 hash to sort names
[ 3.075800] usb 1-1.5.1.1: new high speed USB device using ehci_hcd and address 7
[ 3.257251] usb 1-1.5.1.1: New USB device found, idVendor=0424, idProduct=2228
[ 3.257325] usb 1-1.5.1.1: New USB device strings: Mfr=1, Product=2, SerialNumber=3
[ 3.257399] usb 1-1.5.1.1: Product: Flash Card Reader
[ 3.257443] usb 1-1.5.1.1: Manufacturer: Generic
[ 3.257486] usb 1-1.5.1.1: SerialNumber: 26020128B005
[ 3.265601] Initializing USB Mass Storage driver...
[ 3.265739] scsi6 : usb-storage 1-1.5.1.1:1.0
[ 3.265852] usbcore: registered new interface driver usb-storage
[ 3.265899] USB Mass Storage support registered.
[ 8.258353] scsi 6:0:0:0: Direct-Access Generic Flash HS-CF 5.39 PQ: 0 ANSI: 0
[ 8.261613] scsi 6:0:0:1: Direct-Access Generic Flash HS-COMBO 5.39 PQ: 0 ANSI: 0
[ 8.306857] sd 6:0:0:0: [sdc] Attached SCSI removable disk
[ 8.311016] sd 6:0:0:1: [sdd] Attached SCSI removable disk
[ 848.231244] Bridge firewalling registered
[ 848.232209] device eth0 entered promiscuous mode
[ 848.252255] e1000e 0000:00:19.0: irq 26 for MSI/MSI-X
[ 848.302916] e1000e 0000:00:19.0: irq 26 for MSI/MSI-X
[ 851.768292] e1000e: eth0 NIC Link is Up 1000 Mbps Full Duplex, Flow Control: RX
[ 851.770095] br0: port 1(eth0) entering learning state
[ 866.723462] br0: port 1(eth0) entering forwarding state
[ 867.519929] NET: Registered protocol family 10
[ 867.520201] lo: Disabled Privacy Extensions
[ 867.949030] fuse init (API version 7.13)
[ 877.761384] eth0: no IPv6 routers present
[ 877.874660] br0: no IPv6 routers present
[ 882.669218] [drm] Initialized drm 1.1.0 20060810
[ 882.691484] i915 0000:00:02.0: PCI INT A -> GSI 16 (level, low) -> IRQ 16
[ 882.691494] i915 0000:00:02.0: setting latency timer to 64
[ 882.716978] i915 0000:00:02.0: irq 29 for MSI/MSI-X
[ 882.716988] [drm] set up 31M of stolen space
[ 882.997828] Console: switching to colour frame buffer device 240x75
[ 882.997837] fb0: inteldrmfb frame buffer device
[ 882.997840] registered panic notifier
[ 882.997981] ACPI Exception: AE_NOT_FOUND, Evaluating _DOD (20091214/video-1891)
[ 882.998054] input: Video Bus as /devices/LNXSYSTM:00/LNXSYBUS:00/PNP0A08:00/LNXVIDEO:00/input/input4
[ 882.998091] ACPI: Video Device [GFX0] (multi-head: no rom: yes post: no)
[ 882.998113] [drm] Initialized i915 1.6.0 20080730 for
0000:00:02.0 on minor 0
regards
Benjamin
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: bad performance with SSD since kernel version 2.6.32
2010-02-20 13:28 bad performance with SSD since kernel version 2.6.32 Benjamin S.
@ 2010-02-20 18:35 ` Robert Hancock
2010-02-21 1:26 ` Benjamin S.
0 siblings, 1 reply; 15+ messages in thread
From: Robert Hancock @ 2010-02-20 18:35 UTC (permalink / raw)
To: Benjamin S.; +Cc: Jeff Garzik, linux-ide
On 02/20/2010 07:28 AM, Benjamin S. wrote:
>
> Hello list,
>
> I have a Super Talent Ultradrive GX MLC 64GB SSD and an Intel
> DH55HC board with H55 chipset. Processor is an Intel Core i5-661.
>
> Since 2.6.32 the sequentiell read performance of the ssd is bad:
>
> # dd if=/dev/sda of=/dev/zero bs=1M count=300
> 300+0 records in
> 300+0 records out
> 314572800 bytes (315 MB) copied, 4.61777 s, 68.1 MB/s
>
> Same results with other blocksizes (e.g tested with 4K).
>
>
> With 2.6.31.7 the same hardware is able to read with about
> 190MB/s.
>
>
> The normal hard drive reads with both kernel versions with about 100MB/s.
>
>
> Does somebody have an idea what I can test before I have to bisect
> it?
Could be some kind of block layer or IO scheduler behavior change.. you
could try testing after doing:
echo noop > /sys/block/sda/queue/scheduler
or
echo deadline > /sys/block/sda/queue/scheduler
and see if that affects the speed..
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: bad performance with SSD since kernel version 2.6.32
2010-02-20 18:35 ` Robert Hancock
@ 2010-02-21 1:26 ` Benjamin S.
[not found] ` <51f3faa71002210922i542c37f0j9e0e4a84d0977f90@mail.gmail.com>
0 siblings, 1 reply; 15+ messages in thread
From: Benjamin S. @ 2010-02-21 1:26 UTC (permalink / raw)
To: Robert Hancock; +Cc: Jeff Garzik, linux-ide
> > Does somebody have an idea what I can test before I have to bisect
> > it?
>
> Could be some kind of block layer or IO scheduler behavior change.. you
> could try testing after doing:
>
> echo noop > /sys/block/sda/queue/scheduler
>
> or
>
> echo deadline > /sys/block/sda/queue/scheduler
Thanks for your reply. I have already tested both schedulers.
Unfortunately it does not make any difference which of them is
used.
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: bad performance with SSD since kernel version 2.6.32
[not found] ` <51f3faa71002211400u2177660ei1c0dc3d9306b146e@mail.gmail.com>
@ 2010-02-22 13:18 ` Benjamin S.
2010-02-22 14:41 ` Robert Hancock
2010-02-22 19:05 ` Jens Axboe
0 siblings, 2 replies; 15+ messages in thread
From: Benjamin S. @ 2010-02-22 13:18 UTC (permalink / raw)
To: Robert Hancock; +Cc: Jeff Garzik, linux-ide, Jens Axboe
On Sun, 21 Feb 2010 16:00:35 -0600
Robert Hancock <hancockrwd@gmail.com> wrote:
> Hmm.. Well, that's not it then.. I suspect a bisection is likely the
> easiest route at this point..
fb1e75389bd06fd5987e9cda1b4e0305c782f854 is the first bad commit
commit fb1e75389bd06fd5987e9cda1b4e0305c782f854
Author: Jens Axboe <jens.axboe@oracle.com>
Date: Thu Jul 30 08:18:24 2009 +0200
block: improve queue_should_plug() by looking at IO depths
Instead of just checking whether this device uses block layer
tagging, we can improve the detection by looking at the maximum
queue depth it has reached. If that crosses 4, then deem it a
queuing device.
This is important on high IOPS devices, since plugging hurts
the performance there (it can be as much as 10-15% of the sys
time).
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commitdiff;h=fb1e75389bd06fd5987e9cda1b4e0305c782f854
Without that patch my SSD (Super Talent Ultradrive GX MLC 64GB)
reaches about 200MB/s sequentiell read. After applying the patch it
reaches only 70MB/s.
Note: Added Jens to CC.
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: bad performance with SSD since kernel version 2.6.32
2010-02-22 13:18 ` Benjamin S.
@ 2010-02-22 14:41 ` Robert Hancock
2010-02-22 19:05 ` Jens Axboe
1 sibling, 0 replies; 15+ messages in thread
From: Robert Hancock @ 2010-02-22 14:41 UTC (permalink / raw)
To: Benjamin S.; +Cc: Jeff Garzik, linux-ide, Jens Axboe, Rafael J. Wysocki
CCing Rafael, this should be added to the list of known regressions.
On Mon, Feb 22, 2010 at 7:18 AM, Benjamin S. <sbenni@gmx.de> wrote:
>
> On Sun, 21 Feb 2010 16:00:35 -0600
> Robert Hancock <hancockrwd@gmail.com> wrote:
>
>> Hmm.. Well, that's not it then.. I suspect a bisection is likely the
>> easiest route at this point..
>
> fb1e75389bd06fd5987e9cda1b4e0305c782f854 is the first bad commit
> commit fb1e75389bd06fd5987e9cda1b4e0305c782f854
> Author: Jens Axboe <jens.axboe@oracle.com>
> Date: Thu Jul 30 08:18:24 2009 +0200
>
> block: improve queue_should_plug() by looking at IO depths
>
> Instead of just checking whether this device uses block layer
> tagging, we can improve the detection by looking at the maximum
> queue depth it has reached. If that crosses 4, then deem it a
> queuing device.
>
> This is important on high IOPS devices, since plugging hurts
> the performance there (it can be as much as 10-15% of the sys
> time).
>
> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
>
>
>
>
> http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commitdiff;h=fb1e75389bd06fd5987e9cda1b4e0305c782f854
>
>
> Without that patch my SSD (Super Talent Ultradrive GX MLC 64GB)
> reaches about 200MB/s sequentiell read. After applying the patch it
> reaches only 70MB/s.
>
>
>
> Note: Added Jens to CC.
>
>
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: bad performance with SSD since kernel version 2.6.32
2010-02-22 13:18 ` Benjamin S.
2010-02-22 14:41 ` Robert Hancock
@ 2010-02-22 19:05 ` Jens Axboe
2010-02-22 20:25 ` Benjamin S.
2010-02-22 21:49 ` Mark Lord
1 sibling, 2 replies; 15+ messages in thread
From: Jens Axboe @ 2010-02-22 19:05 UTC (permalink / raw)
To: Benjamin S.; +Cc: Robert Hancock, Jeff Garzik, linux-ide
On Mon, Feb 22 2010, Benjamin S. wrote:
>
> On Sun, 21 Feb 2010 16:00:35 -0600
> Robert Hancock <hancockrwd@gmail.com> wrote:
>
> > Hmm.. Well, that's not it then.. I suspect a bisection is likely the
> > easiest route at this point..
>
> fb1e75389bd06fd5987e9cda1b4e0305c782f854 is the first bad commit
> commit fb1e75389bd06fd5987e9cda1b4e0305c782f854
> Author: Jens Axboe <jens.axboe@oracle.com>
> Date: Thu Jul 30 08:18:24 2009 +0200
>
> block: improve queue_should_plug() by looking at IO depths
>
> Instead of just checking whether this device uses block layer
> tagging, we can improve the detection by looking at the maximum
> queue depth it has reached. If that crosses 4, then deem it a
> queuing device.
>
> This is important on high IOPS devices, since plugging hurts
> the performance there (it can be as much as 10-15% of the sys
> time).
>
> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
>
>
>
>
> http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commitdiff;h=fb1e75389bd06fd5987e9cda1b4e0305c782f854
>
>
> Without that patch my SSD (Super Talent Ultradrive GX MLC 64GB)
> reaches about 200MB/s sequentiell read. After applying the patch it
> reaches only 70MB/s.
That's not good. Can you send me the dmesg snippet that includes the
drive detection?
--
Jens Axboe
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: bad performance with SSD since kernel version 2.6.32
2010-02-22 19:05 ` Jens Axboe
@ 2010-02-22 20:25 ` Benjamin S.
2010-02-23 6:22 ` Jens Axboe
2010-02-22 21:49 ` Mark Lord
1 sibling, 1 reply; 15+ messages in thread
From: Benjamin S. @ 2010-02-22 20:25 UTC (permalink / raw)
To: Jens Axboe; +Cc: Robert Hancock, Jeff Garzik, linux-ide, Rafael J. Wysocki
On Mon, 22 Feb 2010 20:05:22 +0100
Jens Axboe <jens.axboe@oracle.com> wrote:
> On Mon, Feb 22 2010, Benjamin S. wrote:
> >
> > Without that patch my SSD (Super Talent Ultradrive GX MLC 64GB)
> > reaches about 200MB/s sequentiell read. After applying the patch it
> > reaches only 70MB/s.
>
> That's not good. Can you send me the dmesg snippet that includes the
> drive detection?
[ 0.819456] libata version 3.00 loaded.
[ 1.230215] ahci 0000:00:1f.2: version 3.0
[ 1.230225] ahci 0000:00:1f.2: PCI INT B -> GSI 19 (level, low) -> IRQ 19
[ 1.230305] ahci 0000:00:1f.2: irq 27 for MSI/MSI-X
[ 1.246141] ahci 0000:00:1f.2: AHCI 0001.0300 32 slots 6 ports 3 Gbps 0x3f impl SATA mode
[ 1.246223] ahci 0000:00:1f.2: flags: 64bit ncq sntf ilck pm led clo pio slum part ems sxs apst
[ 1.248282] ahci 0000:00:1f.2: setting latency timer to 64
[ 1.286038] scsi0 : ahci
[ 1.286146] scsi1 : ahci
[ 1.286222] scsi2 : ahci
[ 1.286301] scsi3 : ahci
[ 1.286378] scsi4 : ahci
[ 1.286455] scsi5 : ahci
[ 1.286607] ata1: SATA max UDMA/133 abar m2048@0xfe425000 port 0xfe425100 irq 27
[ 1.286682] ata2: SATA max UDMA/133 abar m2048@0xfe425000 port 0xfe425180 irq 27
[ 1.286756] ata3: SATA max UDMA/133 abar m2048@0xfe425000 port 0xfe425200 irq 27
[ 1.286830] ata4: SATA max UDMA/133 abar m2048@0xfe425000 port 0xfe425280 irq 27
[ 1.286905] ata5: SATA max UDMA/133 abar m2048@0xfe425000 port 0xfe425300 irq 27
[ 1.286979] ata6: SATA max UDMA/133 abar m2048@0xfe425000 port 0xfe425380 irq 27
[ 1.608041] ata3: SATA link down (SStatus 0 SControl 300)
[ 1.608113] ata2: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
[ 1.608180] ata1: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
[ 1.608396] ata5: SATA link down (SStatus 0 SControl 300)
[ 1.608400] ata6: SATA link down (SStatus 0 SControl 300)
[ 1.608416] ata1.00: ATA-8: STT_FTM64GX25H, 1819, max UDMA/133
[ 1.608421] ata1.00: 125045424 sectors, multi 1: LBA48 NCQ (depth 31/32), AA
[ 1.608429] ata4: SATA link down (SStatus 0 SControl 300)
[ 1.608932] ata2.00: HPA detected: current 1250261615, native 1250263728
[ 1.609058] ata2.00: ATA-8: WDC WD6400AAKS-00A7B0, 01.03B01, max UDMA/133
[ 1.609117] ata2.00: 1250261615 sectors, multi 16: LBA48 NCQ (depth 31/32), AA
[ 1.610116] ata2.00: configured for UDMA/133
[ 1.610342] ata1.00: configured for UDMA/133
[ 1.624077] scsi 0:0:0:0: Direct-Access ATA STT_FTM64GX25H 1819 PQ: 0 ANSI: 5
[ 1.624246] scsi 1:0:0:0: Direct-Access ATA WDC WD6400AAKS-0 01.0 PQ: 0 ANSI: 5
[ 1.626840] sd 0:0:0:0: [sda] 125045424 512-byte logical blocks: (64.0 GB/59.6 GiB)
[ 1.626905] sd 1:0:0:0: [sdb] 1250261615 512-byte logical blocks: (640 GB/596 GiB)
[ 1.626929] sd 1:0:0:0: [sdb] Write Protect is off
[ 1.626931] sd 1:0:0:0: [sdb] Mode Sense: 00 3a 00 00
[ 1.626941] sd 1:0:0:0: [sdb] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
[ 1.627009] sdb:
[ 1.627143] sd 0:0:0:0: [sda] Write Protect is off
[ 1.627229] sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00
[ 1.627238] sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
[ 1.627364] sda: sda1 sda2 < sda5 >
[ 1.627978] sd 0:0:0:0: [sda] Attached SCSI disk
[ 1.642051] sdb1 sdb2 sdb3 < sdb5 sdb6 sdb7 sdb8
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: bad performance with SSD since kernel version 2.6.32
2010-02-22 19:05 ` Jens Axboe
2010-02-22 20:25 ` Benjamin S.
@ 2010-02-22 21:49 ` Mark Lord
2010-02-22 23:22 ` Robert Hancock
1 sibling, 1 reply; 15+ messages in thread
From: Mark Lord @ 2010-02-22 21:49 UTC (permalink / raw)
To: Jens Axboe; +Cc: Benjamin S., Robert Hancock, Jeff Garzik, linux-ide
On 02/22/10 14:05, Jens Axboe wrote:
--- a/block/blk-core.c
+++ b/block/blk-core.c
...
@@ -1857,8 +1857,15 @@ void blk_dequeue_request(struct request *rq)
* and to it is freed is accounted as io that is in progress at
* the driver side.
*/
- if (blk_account_rq(rq))
+ if (blk_account_rq(rq)) {
q->in_flight[rq_is_sync(rq)]++;
+ /*
+ * Mark this device as supporting hardware queuing, if
+ * we have more IOs in flight than 4.
+ */
+ if (!blk_queue_queuing(q) && queue_in_flight(q) > 4)
+ set_bit(QUEUE_FLAG_CQ, &q->queue_flags);
+ }
}
...
Mmm.. So is this code actually trying to rely upon the software being quick
enough to queue five or more commands before the drive completes one of them?
Wouldn't a better way be to just look at the queue_depth, for SCSI/SATA at least?
-ml
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: bad performance with SSD since kernel version 2.6.32
2010-02-22 21:49 ` Mark Lord
@ 2010-02-22 23:22 ` Robert Hancock
2010-02-23 6:21 ` Jens Axboe
0 siblings, 1 reply; 15+ messages in thread
From: Robert Hancock @ 2010-02-22 23:22 UTC (permalink / raw)
To: Mark Lord; +Cc: Jens Axboe, Benjamin S., Jeff Garzik, linux-ide
On Mon, Feb 22, 2010 at 3:49 PM, Mark Lord <kernel@teksavvy.com> wrote:
> On 02/22/10 14:05, Jens Axboe wrote:
>
> --- a/block/blk-core.c
> +++ b/block/blk-core.c
> ...
> @@ -1857,8 +1857,15 @@ void blk_dequeue_request(struct request *rq)
> * and to it is freed is accounted as io that is in progress at
> * the driver side.
> */
> - if (blk_account_rq(rq))
> + if (blk_account_rq(rq)) {
> q->in_flight[rq_is_sync(rq)]++;
> + /*
> + * Mark this device as supporting hardware queuing, if
> + * we have more IOs in flight than 4.
> + */
> + if (!blk_queue_queuing(q) && queue_in_flight(q) > 4)
> + set_bit(QUEUE_FLAG_CQ, &q->queue_flags);
> + }
> }
> ...
>
> Mmm.. So is this code actually trying to rely upon the software being quick
> enough to queue five or more commands before the drive completes one of
> them?
>
> Wouldn't a better way be to just look at the queue_depth, for SCSI/SATA at
> least?
Yeah, that seems like a rather fragile heuristic to me..
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: bad performance with SSD since kernel version 2.6.32
2010-02-22 23:22 ` Robert Hancock
@ 2010-02-23 6:21 ` Jens Axboe
2010-02-24 15:09 ` Mark Lord
0 siblings, 1 reply; 15+ messages in thread
From: Jens Axboe @ 2010-02-23 6:21 UTC (permalink / raw)
To: Robert Hancock; +Cc: Mark Lord, Benjamin S., Jeff Garzik, linux-ide
On Mon, Feb 22 2010, Robert Hancock wrote:
> On Mon, Feb 22, 2010 at 3:49 PM, Mark Lord <kernel@teksavvy.com> wrote:
> > On 02/22/10 14:05, Jens Axboe wrote:
> >
> > --- a/block/blk-core.c
> > +++ b/block/blk-core.c
> > ...
> > @@ -1857,8 +1857,15 @@ void blk_dequeue_request(struct request *rq)
> > * and to it is freed is accounted as io that is in progress at
> > * the driver side.
> > */
> > - if (blk_account_rq(rq))
> > + if (blk_account_rq(rq)) {
> > q->in_flight[rq_is_sync(rq)]++;
> > + /*
> > + * Mark this device as supporting hardware queuing, if
> > + * we have more IOs in flight than 4.
> > + */
> > + if (!blk_queue_queuing(q) && queue_in_flight(q) > 4)
> > + set_bit(QUEUE_FLAG_CQ, &q->queue_flags);
> > + }
> > }
> > ...
> >
> > Mmm.. So is this code actually trying to rely upon the software being quick
> > enough to queue five or more commands before the drive completes one of
> > them?
Yes, it'll trigger easily. If it's the boot drive, it'll be on before
booting has completed.
> > Wouldn't a better way be to just look at the queue_depth, for SCSI/SATA at
> > least?
>
> Yeah, that seems like a rather fragile heuristic to me..
It may seem fragile, but it's not. Queue depth is device information
that isn't available at the block level.
--
Jens Axboe
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: bad performance with SSD since kernel version 2.6.32
2010-02-22 20:25 ` Benjamin S.
@ 2010-02-23 6:22 ` Jens Axboe
0 siblings, 0 replies; 15+ messages in thread
From: Jens Axboe @ 2010-02-23 6:22 UTC (permalink / raw)
To: Benjamin S.; +Cc: Robert Hancock, Jeff Garzik, linux-ide, Rafael J. Wysocki
On Mon, Feb 22 2010, Benjamin S. wrote:
> On Mon, 22 Feb 2010 20:05:22 +0100
> Jens Axboe <jens.axboe@oracle.com> wrote:
>
> > On Mon, Feb 22 2010, Benjamin S. wrote:
> > >
> > > Without that patch my SSD (Super Talent Ultradrive GX MLC 64GB)
> > > reaches about 200MB/s sequentiell read. After applying the patch it
> > > reaches only 70MB/s.
> >
> > That's not good. Can you send me the dmesg snippet that includes the
> > drive detection?
>
> [ 0.819456] libata version 3.00 loaded.
[snip]
OK, thanks. I'll revert the commit for 2.6.33.
--
Jens Axboe
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: bad performance with SSD since kernel version 2.6.32
2010-02-23 6:21 ` Jens Axboe
@ 2010-02-24 15:09 ` Mark Lord
2010-02-24 15:34 ` Jens Axboe
0 siblings, 1 reply; 15+ messages in thread
From: Mark Lord @ 2010-02-24 15:09 UTC (permalink / raw)
To: Jens Axboe; +Cc: Robert Hancock, Benjamin S., Jeff Garzik, linux-ide
On 02/23/10 01:21, Jens Axboe wrote:
> On Mon, Feb 22 2010, Robert Hancock wrote:
>> On Mon, Feb 22, 2010 at 3:49 PM, Mark Lord<kernel@teksavvy.com> wrote:
>>> On 02/22/10 14:05, Jens Axboe wrote:
>>>
>>> --- a/block/blk-core.c
>>> +++ b/block/blk-core.c
>>> ...
>>> @@ -1857,8 +1857,15 @@ void blk_dequeue_request(struct request *rq)
>>> * and to it is freed is accounted as io that is in progress at
>>> * the driver side.
>>> */
>>> - if (blk_account_rq(rq))
>>> + if (blk_account_rq(rq)) {
>>> q->in_flight[rq_is_sync(rq)]++;
>>> + /*
>>> + * Mark this device as supporting hardware queuing, if
>>> + * we have more IOs in flight than 4.
>>> + */
>>> + if (!blk_queue_queuing(q)&& queue_in_flight(q)> 4)
>>> + set_bit(QUEUE_FLAG_CQ,&q->queue_flags);
>>> + }
>>> }
>>> ...
>>>
>>> Mmm.. So is this code actually trying to rely upon the software being quick
>>> enough to queue five or more commands before the drive completes one of
>>> them?
>
> Yes, it'll trigger easily. If it's the boot drive, it'll be on before
> booting has completed.
...
Mmm.. but that all assumes (1) a fast CPU and (2) a slow mechanical drive.
Neither of which are true in many modern systems.
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: bad performance with SSD since kernel version 2.6.32
2010-02-24 15:09 ` Mark Lord
@ 2010-02-24 15:34 ` Jens Axboe
2010-02-24 15:48 ` Mark Lord
0 siblings, 1 reply; 15+ messages in thread
From: Jens Axboe @ 2010-02-24 15:34 UTC (permalink / raw)
To: Mark Lord; +Cc: Robert Hancock, Benjamin S., Jeff Garzik, linux-ide
On Wed, Feb 24 2010, Mark Lord wrote:
> On 02/23/10 01:21, Jens Axboe wrote:
>> On Mon, Feb 22 2010, Robert Hancock wrote:
>>> On Mon, Feb 22, 2010 at 3:49 PM, Mark Lord<kernel@teksavvy.com> wrote:
>>>> On 02/22/10 14:05, Jens Axboe wrote:
>>>>
>>>> --- a/block/blk-core.c
>>>> +++ b/block/blk-core.c
>>>> ...
>>>> @@ -1857,8 +1857,15 @@ void blk_dequeue_request(struct request *rq)
>>>> * and to it is freed is accounted as io that is in progress at
>>>> * the driver side.
>>>> */
>>>> - if (blk_account_rq(rq))
>>>> + if (blk_account_rq(rq)) {
>>>> q->in_flight[rq_is_sync(rq)]++;
>>>> + /*
>>>> + * Mark this device as supporting hardware queuing, if
>>>> + * we have more IOs in flight than 4.
>>>> + */
>>>> + if (!blk_queue_queuing(q)&& queue_in_flight(q)> 4)
>>>> + set_bit(QUEUE_FLAG_CQ,&q->queue_flags);
>>>> + }
>>>> }
>>>> ...
>>>>
>>>> Mmm.. So is this code actually trying to rely upon the software being quick
>>>> enough to queue five or more commands before the drive completes one of
>>>> them?
>>
>> Yes, it'll trigger easily. If it's the boot drive, it'll be on before
>> booting has completed.
> ...
>
> Mmm.. but that all assumes (1) a fast CPU and (2) a slow mechanical drive.
> Neither of which are true in many modern systems.
No, that's simply not true. I didn't base the above comment on
speculation, it's observed behaviour. Granted it's a heuristic and as
such not infallible, but it works much better than you seem to assume.
FWIW, on both my desktop and laptop with SSD drives it's on before on
before you log in. Besides, the code wont have any effect on a
mechanical drive (slow or not), since it's specifically only on for
non-rotation drives.
--
Jens Axboe
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: bad performance with SSD since kernel version 2.6.32
2010-02-24 15:34 ` Jens Axboe
@ 2010-02-24 15:48 ` Mark Lord
2010-02-24 19:05 ` Jens Axboe
0 siblings, 1 reply; 15+ messages in thread
From: Mark Lord @ 2010-02-24 15:48 UTC (permalink / raw)
To: Jens Axboe; +Cc: Robert Hancock, Benjamin S., Jeff Garzik, linux-ide
On 02/24/10 10:34, Jens Axboe wrote:
> On Wed, Feb 24 2010, Mark Lord wrote:
>> On 02/23/10 01:21, Jens Axboe wrote:
>>> On Mon, Feb 22 2010, Robert Hancock wrote:
>>>> On Mon, Feb 22, 2010 at 3:49 PM, Mark Lord<kernel@teksavvy.com> wrote:
>>>>> On 02/22/10 14:05, Jens Axboe wrote:
>>>>>
>>>>> --- a/block/blk-core.c
>>>>> +++ b/block/blk-core.c
>>>>> ...
>>>>> @@ -1857,8 +1857,15 @@ void blk_dequeue_request(struct request *rq)
>>>>> * and to it is freed is accounted as io that is in progress at
>>>>> * the driver side.
>>>>> */
>>>>> - if (blk_account_rq(rq))
>>>>> + if (blk_account_rq(rq)) {
>>>>> q->in_flight[rq_is_sync(rq)]++;
>>>>> + /*
>>>>> + * Mark this device as supporting hardware queuing, if
>>>>> + * we have more IOs in flight than 4.
>>>>> + */
>>>>> + if (!blk_queue_queuing(q)&& queue_in_flight(q)> 4)
>>>>> + set_bit(QUEUE_FLAG_CQ,&q->queue_flags);
>>>>> + }
>>>>> }
>>>>> ...
>>>>>
>>>>> Mmm.. So is this code actually trying to rely upon the software being quick
>>>>> enough to queue five or more commands before the drive completes one of
>>>>> them?
>>>
>>> Yes, it'll trigger easily. If it's the boot drive, it'll be on before
>>> booting has completed.
>> ...
>>
>> Mmm.. but that all assumes (1) a fast CPU and (2) a slow mechanical drive.
>> Neither of which are true in many modern systems.
>
> No, that's simply not true. I didn't base the above comment on
> speculation, it's observed behaviour. Granted it's a heuristic and as
> such not infallible, but it works much better than you seem to assume.
>
> FWIW, on both my desktop and laptop with SSD drives it's on before on
> before you log in. Besides, the code wont have any effect on a
> mechanical drive (slow or not), since it's specifically only on for
> non-rotation drives.
..
Okay, so it works for you, and fails for others.
Good to see it reverted for now in 2.6.33, but what about 2.6.32 as well ?
Thanks
^ permalink raw reply [flat|nested] 15+ messages in thread
* Re: bad performance with SSD since kernel version 2.6.32
2010-02-24 15:48 ` Mark Lord
@ 2010-02-24 19:05 ` Jens Axboe
0 siblings, 0 replies; 15+ messages in thread
From: Jens Axboe @ 2010-02-24 19:05 UTC (permalink / raw)
To: Mark Lord; +Cc: Robert Hancock, Benjamin S., Jeff Garzik, linux-ide
On Wed, Feb 24 2010, Mark Lord wrote:
> On 02/24/10 10:34, Jens Axboe wrote:
>> On Wed, Feb 24 2010, Mark Lord wrote:
>>> On 02/23/10 01:21, Jens Axboe wrote:
>>>> On Mon, Feb 22 2010, Robert Hancock wrote:
>>>>> On Mon, Feb 22, 2010 at 3:49 PM, Mark Lord<kernel@teksavvy.com> wrote:
>>>>>> On 02/22/10 14:05, Jens Axboe wrote:
>>>>>>
>>>>>> --- a/block/blk-core.c
>>>>>> +++ b/block/blk-core.c
>>>>>> ...
>>>>>> @@ -1857,8 +1857,15 @@ void blk_dequeue_request(struct request *rq)
>>>>>> * and to it is freed is accounted as io that is in progress at
>>>>>> * the driver side.
>>>>>> */
>>>>>> - if (blk_account_rq(rq))
>>>>>> + if (blk_account_rq(rq)) {
>>>>>> q->in_flight[rq_is_sync(rq)]++;
>>>>>> + /*
>>>>>> + * Mark this device as supporting hardware queuing, if
>>>>>> + * we have more IOs in flight than 4.
>>>>>> + */
>>>>>> + if (!blk_queue_queuing(q)&& queue_in_flight(q)> 4)
>>>>>> + set_bit(QUEUE_FLAG_CQ,&q->queue_flags);
>>>>>> + }
>>>>>> }
>>>>>> ...
>>>>>>
>>>>>> Mmm.. So is this code actually trying to rely upon the software being quick
>>>>>> enough to queue five or more commands before the drive completes one of
>>>>>> them?
>>>>
>>>> Yes, it'll trigger easily. If it's the boot drive, it'll be on before
>>>> booting has completed.
>>> ...
>>>
>>> Mmm.. but that all assumes (1) a fast CPU and (2) a slow mechanical drive.
>>> Neither of which are true in many modern systems.
>>
>> No, that's simply not true. I didn't base the above comment on
>> speculation, it's observed behaviour. Granted it's a heuristic and as
>> such not infallible, but it works much better than you seem to assume.
>>
>> FWIW, on both my desktop and laptop with SSD drives it's on before on
>> before you log in. Besides, the code wont have any effect on a
>> mechanical drive (slow or not), since it's specifically only on for
>> non-rotation drives.
> ..
>
> Okay, so it works for you, and fails for others.
You are misunderstanding the issue completely, it's not about that
particular piece of logic working of failing. As a matter of fact, it's
most definitely working for the reporter of the issue as well, or he
would not see the performance regression he's seeing. The issue (and the
reason for the revert) is the plugging itself, which is altered by the
logic having triggered.
> Good to see it reverted for now in 2.6.33, but what about 2.6.32 as well ?
I'll make sure it gets to stable as well, of course.
--
Jens Axboe
^ permalink raw reply [flat|nested] 15+ messages in thread
end of thread, other threads:[~2010-02-24 19:05 UTC | newest]
Thread overview: 15+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2010-02-20 13:28 bad performance with SSD since kernel version 2.6.32 Benjamin S.
2010-02-20 18:35 ` Robert Hancock
2010-02-21 1:26 ` Benjamin S.
[not found] ` <51f3faa71002210922i542c37f0j9e0e4a84d0977f90@mail.gmail.com>
[not found] ` <20100221225544.5a9ded51@pluto-lenny.milky.way>
[not found] ` <51f3faa71002211400u2177660ei1c0dc3d9306b146e@mail.gmail.com>
2010-02-22 13:18 ` Benjamin S.
2010-02-22 14:41 ` Robert Hancock
2010-02-22 19:05 ` Jens Axboe
2010-02-22 20:25 ` Benjamin S.
2010-02-23 6:22 ` Jens Axboe
2010-02-22 21:49 ` Mark Lord
2010-02-22 23:22 ` Robert Hancock
2010-02-23 6:21 ` Jens Axboe
2010-02-24 15:09 ` Mark Lord
2010-02-24 15:34 ` Jens Axboe
2010-02-24 15:48 ` Mark Lord
2010-02-24 19:05 ` Jens Axboe
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).