Ubuntu
linux package

Bug #216878
Comment #6

Comment 6 for bug 216878

Revision history for this message

Hal (halbower) wrote on 2008-08-23: Re: Slow disk transfer rate on Hardy

The problem with 8.04 Hardy Heron's use of libata and improperly setting DMA
characteristics of systems is inhibiting effective use of solid-state media
in systems. On a number of systems I have confirmed that this does not
exist on Feisty (7.04) and Dapper (6.06) systems where full-speed is
attained on Flash-Memory-based systems. Here are some sample excerpts
from dmesg on different machines (All CF-IDE adapters verified as being DMA
capable, 4 different types):

1. Koolu (aka FIC A603). AMD Geode at 500 MHz, CF with 2 inches of cable
   between CF-44-pin adapter.
[ 24.433986] SCSI subsystem initialized
[ 24.491024] libata version 3.00 loaded.
[ 24.502688] scsi0 : pata_cs5536
[ 24.503175] scsi1 : pata_cs5536
[ 24.504264] ata1: PATA max UDMA/100 cmd 0x1f0 ctl 0x3f6 bmdma 0xff00 \
        irq 14
[ 24.504632] ata2: DUMMY
[ 24.668330] ata1.00: ATA-4: ELITE PRO CF CARD 4GB, 20071207, max UDMA/66
[ 24.668687] ata1.00: 7831152 sectors, multi 0: LBA
[ 24.668989] ata1.00: limited to UDMA/33 due to 40-wire cable
[ 24.684233] ata1.00: configured for UDMA/33
[ 24.684815] scsi 0:0:0:0: Direct-Access ATA ELITE PRO CF \
        CAR 2007 PQ: 0 ANSI: 5

2. Biostar Turiun64 3200 MicroATX Mobo, sda is IDE-CF Adapter with 80-wire
   cable, sdb is UDMA/133 Hard Drive.
[ 24.398426] SCSI subsystem initialized
[ 24.440126] libata version 3.00 loaded.
   ...
[ 24.500091] sata_via 0000:00:0f.0: version 2.3
[ 24.500109] ACPI: PCI Interrupt 0000:00:0f.0[B] -> Link [ALKA] -> GSI 20
        (level, low) -> IRQ 1
[ 24.500860] sata_via 0000:00:0f.0: routed to hard irq line 11
[ 24.508043] scsi0 : sata_via
[ 24.520038] USB Universal Host Controller Interface driver v3.0
[ 24.528029] scsi1 : sata_via
[ 24.529176] ata1: SATA max UDMA/133 cmd 0xde00 ctl 0xe400 bmdma 0xdd00
        irq 16
[ 24.529734] ata2: SATA max UDMA/133 cmd 0xe500 ctl 0xdc00 bmdma 0xdd08
        irq 16
   ...
[ 24.731771] ata1: SATA link down 1.5 Gbps (SStatus 0 SControl 300)
[ 24.943531] ata2: SATA link down 1.5 Gbps (SStatus 0 SControl 300)
   ...
[ 25.894752] pata_via 0000:00:0f.1: version 0.3.3
[ 25.894773] ACPI: PCI Interrupt 0000:00:0f.1[A] -> Link [ALKA] -> GSI 20
        (level, low) -> IRQ 1
[ 25.918239] scsi2 : pata_via
[ 25.940463] scsi3 : pata_via
[ 25.962812] ata3: PATA max UDMA/133 cmd 0x1f0 ctl 0x3f6 bmdma 0xdf00
        irq 14
[ 25.984729] ata4: PATA max UDMA/133 cmd 0x170 ctl 0x376 bmdma 0xdf08
        irq 15
[ 26.118214] usb 1-2: new full speed USB device using uhci_hcd and address 3
[ 26.170481] ata3.00: ATA-4: TRANSCEND, 20080128, max UDMA/66
[ 26.192508] ata3.00: 15662304 sectors, multi 0: LBA
[ 26.214508] ata3.00: limited to UDMA/33 due to 40-wire cable
[ 26.250259] ata3.00: configured for UDMA/33
[ 26.341366] usb 1-2: configuration #1 chosen from 1 choice
[ 26.434370] ata4.00: ATA-7: Maxtor 6Y120P0, YAR41BW0, max UDMA/133
[ 26.456746] ata4.00: 240121728 sectors, multi 16: LBA
[ 26.494165] ata4.00: configured for UDMA/133
[ 26.516437] scsi 2:0:0:0: Direct-Access ATA TRANSCEND \
        2008 PQ: 0 ANSI: 5
[ 26.539610] scsi 3:0:0:0: Direct-Access ATA Maxtor 6Y120P0 \
        YAR4 PQ: 0 ANSI: 5

3. Everex Cloudbook, 1.2 GHz Via with ZIF-ide to CF adapter for sda,
   original flex-cable.
[ 39.556831] libata version 3.00 loaded.
   ...
[ 39.793942] pata_via 0000:00:0f.0: version 0.3.3
[ 39.794265] PCI: Setting latency timer of device 0000:00:0f.0 to 64
[ 39.872724] scsi0 : pata_via
[ 39.926162] scsi1 : pata_via
[ 39.928990] ata1: PATA max UDMA/133 cmd 0x1f0 ctl 0x3f6 bmdma 0x4460 \
        irq 14
[ 39.929008] ata2: PATA max UDMA/133 cmd 0x170 ctl 0x376 bmdma 0x4468 \
        irq 15
[ 39.929085] ata1: port disabled. ignoring.
[ 40.093002] ata2.00: ATA-4: TRANSCEND, 20080128, max UDMA/66
[ 40.093021] ata2.00: 31326208 sectors, multi 0: LBA
[ 40.093068] ata2.00: limited to UDMA/33 due to 40-wire cable
[ 40.108920] ata2.00: configured for UDMA/33
[ 40.109266] scsi 1:0:0:0: Direct-Access ATA TRANSCEND \
        2008 PQ: 0 ANSI: 5

4. HP Mini-Note with Transcend 16 GB 300x CF in SATA I adapter. Via 1.2 GHz
   and support. Hardy Desktop installed in only 15 minutes from USB2 CDrom
   so prior to coming up it is definitely performing faster than UDMA/33.
[ 28.423721] SCSI subsystem initialized
   ...
[ 28.731099] libata version 3.00 loaded.
   ...
[ 28.783806] sata_via 0000:00:0f.0: version 2.3
[ 28.783865] ACPI: PCI Interrupt 0000:00:0f.0[B] -> GSI 21 (level, low) ->
        IRQ 19
[ 28.784289] sata_via 0000:00:0f.0: routed to hard irq line 5
[ 28.815058] scsi0 : sata_via
[ 28.851101] USB Universal Host Controller Interface driver v3.0
[ 28.886527] scsi1 : sata_via
[ 28.889807] ata1: SATA max UDMA/133 cmd 0xcc00 ctl 0xc880 bmdma 0xc400 \
        irq 19
[ 28.890135] ata2: SATA max UDMA/133 cmd 0xc800 ctl 0xc480 bmdma 0xc408 \
        irq 19
[ 29.090913] ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
[ 29.255041] ata1.00: ATA-4: TRANSCEND, 20080128, max UDMA/33
[ 29.255310] ata1.00: 31326208 sectors, multi 0: LBA
[ 29.255537] ata1.00: applying bridge limits
[ 29.271041] ata1.00: configured for UDMA/33
[ 29.474700] ata2: SATA link down 1.5 Gbps (SStatus 0 SControl 300)
[ 29.485976] scsi 0:0:0:0: Direct-Access ATA TRANSCEND
        2008 PQ: 0 ANSI: 5

5. Asus EeePC 701 4G. On-board 4 GB SSD. was ~43 MB/S under Feisty now
   ~23 MB/S under Hardy
[ 21.917001] SCSI subsystem initialized
   ...
[ 22.076497] libata version 3.00 loaded.
   ...
[ 22.296516] ata_piix 0000:00:1f.2: version 2.12
[ 22.296533] ata_piix 0000:00:1f.2: MAP [ P0 P2 IDE IDE ]
[ 22.296574] ACPI: PCI Interrupt 0000:00:1f.2[B] -> GSI 19 (level, low) \
        -> IRQ 20
[ 22.296650] PCI: Setting latency timer of device 0000:00:1f.2 to 64
[ 22.322692] scsi0 : ata_piix
[ 22.340914] scsi1 : ata_piix
[ 22.344297] ata1: SATA max UDMA/133 cmd 0x1f0 ctl 0x3f6 bmdma 0xffa0 \
        irq 14
[ 22.344306] ata2: PATA max UDMA/100 cmd 0x170 ctl 0x376 bmdma 0xffa8 \
        irq 15
[ 22.404377] usb 1-1: device not accepting address 2, error -71
[ 22.672794] ata2.00: ATA-4: SILICONMOTION SM223AC, , max UDMA/66
[ 22.672806] ata2.00: 7815024 sectors, multi 0: LBA
[ 22.672847] ata2.00: limited to UDMA/33 due to 40-wire cable
[ 22.688700] ata2.00: configured for UDMA/33
[ 22.689009] scsi 1:0:0:0: Direct-Access ATA SILICONMOTION SM \
        n/a PQ: 0 ANSI: 5
[ 22.956333] usb 5-1: new high speed USB device using ehci_hcd and \
        address 2

The problem with 8.04 Hardy Heron's use of libata and improperly setting DMA
characteristics of systems is inhibiting effective use of solid-state media
in systems.  On a number of systems I have confirmed that this does not
exist on Feisty (7.04) and Dapper (6.06) systems where full-speed is
attained on Flash-Memory-based systems.  Here are some sample excerpts
from dmesg on different machines (All CF-IDE adapters verified as being DMA
capable, 4 different types):

1. Koolu (aka FIC A603).  AMD Geode at 500 MHz, CF with 2 inches of cable
   between CF-44-pin adapter.
 [   24.433986] SCSI subsystem initialized
 [   24.491024] libata version 3.00 loaded.
 [   24.502688] scsi0 : pata_cs5536
 [   24.503175] scsi1 : pata_cs5536
 [   24.504264] ata1: PATA max UDMA/100 cmd 0x1f0 ctl 0x3f6 bmdma 0xff00 \
        irq 14
 [   24.504632] ata2: DUMMY
 [   24.668330] ata1.00: ATA-4: ELITE PRO CF CARD 4GB, 20071207, max UDMA/66
 [   24.668687] ata1.00: 7831152 sectors, multi 0: LBA
 [   24.668989] ata1.00: limited to UDMA/33 due to 40-wire cable
 [   24.684233] ata1.00: configured for UDMA/33
 [   24.684815] scsi 0:0:0:0: Direct-Access     ATA      ELITE PRO CF \
        CAR 2007 PQ: 0 ANSI: 5

2. Biostar Turiun64 3200 MicroATX Mobo, sda is IDE-CF Adapter with 80-wire
   cable, sdb is UDMA/133 Hard Drive.
 [   24.398426] SCSI subsystem initialized
 [   24.440126] libata version 3.00 loaded.
   ...
 [   24.500091] sata_via 0000:00:0f.0: version 2.3
 [   24.500109] ACPI: PCI Interrupt 0000:00:0f.0[B] -> Link [ALKA] -> GSI 20
        (level, low) -> IRQ 1
 [   24.500860] sata_via 0000:00:0f.0: routed to hard irq line 11
 [   24.508043] scsi0 : sata_via
 [   24.520038] USB Universal Host Controller Interface driver v3.0
 [   24.528029] scsi1 : sata_via
 [   24.529176] ata1: SATA max UDMA/133 cmd 0xde00 ctl 0xe400 bmdma 0xdd00
        irq 16
 [   24.529734] ata2: SATA max UDMA/133 cmd 0xe500 ctl 0xdc00 bmdma 0xdd08
        irq 16
   ...
 [   24.731771] ata1: SATA link down 1.5 Gbps (SStatus 0 SControl 300)
 [   24.943531] ata2: SATA link down 1.5 Gbps (SStatus 0 SControl 300)
   ...
 [   25.894752] pata_via 0000:00:0f.1: version 0.3.3
 [   25.894773] ACPI: PCI Interrupt 0000:00:0f.1[A] -> Link [ALKA] -> GSI 20
        (level, low) -> IRQ 1
 [   25.918239] scsi2 : pata_via
 [   25.940463] scsi3 : pata_via
 [   25.962812] ata3: PATA max UDMA/133 cmd 0x1f0 ctl 0x3f6 bmdma 0xdf00
        irq 14
 [   25.984729] ata4: PATA max UDMA/133 cmd 0x170 ctl 0x376 bmdma 0xdf08
        irq 15
 [   26.118214] usb 1-2: new full speed USB device using uhci_hcd and address 3
 [   26.170481] ata3.00: ATA-4: TRANSCEND, 20080128, max UDMA/66
 [   26.192508] ata3.00: 15662304 sectors, multi 0: LBA 
 [   26.214508] ata3.00: limited to UDMA/33 due to 40-wire cable
 [   26.250259] ata3.00: configured for UDMA/33
 [   26.341366] usb 1-2: configuration #1 chosen from 1 choice
 [   26.434370] ata4.00: ATA-7: Maxtor 6Y120P0, YAR41BW0, max UDMA/133
 [   26.456746] ata4.00: 240121728 sectors, multi 16: LBA 
 [   26.494165] ata4.00: configured for UDMA/133
 [   26.516437] scsi 2:0:0:0: Direct-Access     ATA      TRANSCEND \
        2008 PQ: 0 ANSI: 5
 [   26.539610] scsi 3:0:0:0: Direct-Access     ATA      Maxtor 6Y120P0 \
        YAR4 PQ: 0 ANSI: 5

3. Everex Cloudbook, 1.2 GHz Via with ZIF-ide to CF adapter for sda,
   original flex-cable.
 [   39.556831] libata version 3.00 loaded.
   ...
 [   39.793942] pata_via 0000:00:0f.0: version 0.3.3
 [   39.794265] PCI: Setting latency timer of device 0000:00:0f.0 to 64
 [   39.872724] scsi0 : pata_via
 [   39.926162] scsi1 : pata_via
 [   39.928990] ata1: PATA max UDMA/133 cmd 0x1f0 ctl 0x3f6 bmdma 0x4460 \
        irq 14
 [   39.929008] ata2: PATA max UDMA/133 cmd 0x170 ctl 0x376 bmdma 0x4468 \
        irq 15
 [   39.929085] ata1: port disabled. ignoring.
 [   40.093002] ata2.00: ATA-4: TRANSCEND, 20080128, max UDMA/66
 [   40.093021] ata2.00: 31326208 sectors, multi 0: LBA 
 [   40.093068] ata2.00: limited to UDMA/33 due to 40-wire cable
 [   40.108920] ata2.00: configured for UDMA/33
 [   40.109266] scsi 1:0:0:0: Direct-Access     ATA      TRANSCEND \
        2008 PQ: 0 ANSI: 5

4. HP Mini-Note with Transcend 16 GB 300x CF in SATA I adapter.  Via 1.2 GHz
   and support.  Hardy Desktop installed in only 15 minutes from USB2 CDrom 
   so prior to coming up it is definitely performing faster than UDMA/33.   
 [   28.423721] SCSI subsystem initialized
   ...
 [   28.731099] libata version 3.00 loaded.
   ...
 [   28.783806] sata_via 0000:00:0f.0: version 2.3
 [   28.783865] ACPI: PCI Interrupt 0000:00:0f.0[B] -> GSI 21 (level, low) ->
        IRQ 19
 [   28.784289] sata_via 0000:00:0f.0: routed to hard irq line 5
 [   28.815058] scsi0 : sata_via
 [   28.851101] USB Universal Host Controller Interface driver v3.0
 [   28.886527] scsi1 : sata_via
 [   28.889807] ata1: SATA max UDMA/133 cmd 0xcc00 ctl 0xc880 bmdma 0xc400 \
        irq 19
 [   28.890135] ata2: SATA max UDMA/133 cmd 0xc800 ctl 0xc480 bmdma 0xc408 \
        irq 19
 [   29.090913] ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
 [   29.255041] ata1.00: ATA-4: TRANSCEND, 20080128, max UDMA/33
 [   29.255310] ata1.00: 31326208 sectors, multi 0: LBA 
 [   29.255537] ata1.00: applying bridge limits
 [   29.271041] ata1.00: configured for UDMA/33
 [   29.474700] ata2: SATA link down 1.5 Gbps (SStatus 0 SControl 300)
 [   29.485976] scsi 0:0:0:0: Direct-Access     ATA      TRANSCEND
        2008 PQ: 0 ANSI: 5

5. Asus EeePC 701 4G. On-board 4 GB SSD.  was ~43 MB/S under Feisty now
   ~23 MB/S under Hardy
 [   21.917001] SCSI subsystem initialized
   ...
 [   22.076497] libata version 3.00 loaded.
   ...
 [   22.296516] ata_piix 0000:00:1f.2: version 2.12
 [   22.296533] ata_piix 0000:00:1f.2: MAP [ P0 P2 IDE IDE ]
 [   22.296574] ACPI: PCI Interrupt 0000:00:1f.2[B] -> GSI 19 (level, low) \
        -> IRQ 20
 [   22.296650] PCI: Setting latency timer of device 0000:00:1f.2 to 64
 [   22.322692] scsi0 : ata_piix
 [   22.340914] scsi1 : ata_piix
 [   22.344297] ata1: SATA max UDMA/133 cmd 0x1f0 ctl 0x3f6 bmdma 0xffa0 \
        irq 14
 [   22.344306] ata2: PATA max UDMA/100 cmd 0x170 ctl 0x376 bmdma 0xffa8 \
        irq 15
 [   22.404377] usb 1-1: device not accepting address 2, error -71
 [   22.672794] ata2.00: ATA-4: SILICONMOTION SM223AC, , max UDMA/66
 [   22.672806] ata2.00: 7815024 sectors, multi 0: LBA 
 [   22.672847] ata2.00: limited to UDMA/33 due to 40-wire cable
 [   22.688700] ata2.00: configured for UDMA/33
 [   22.689009] scsi 1:0:0:0: Direct-Access     ATA      SILICONMOTION SM \
        n/a  PQ: 0 ANSI: 5
 [   22.956333] usb 5-1: new high speed USB device using ehci_hcd and \
        address 2

Ubuntulinux package

Comment 6 for bug 216878

Ubuntu
linux package