Promise TX4 performance problems

All of lore.kernel.org
 help / color / mirror / Atom feed

* Promise TX4 performance problems
@ 2008-04-12 12:56 Marko Koivusalo
  2008-04-12 15:26 ` Alan Cox
  2008-04-12 17:47 ` Mikael Pettersson
  0 siblings, 2 replies; 6+ messages in thread
From: Marko Koivusalo @ 2008-04-12 12:56 UTC (permalink / raw)
  To: jgarzik; +Cc: linux-ide

Hello,

I'm unfortunate owner of Promise TX4 SATA300 (rev2). In Feb 2007 my
raid started to drop drives under heavy load. Back then it was not
known to hapend because of TX4 asic bug or at least I was unable to
find such information at the time. And the card had worked fine for a
year or so. Well eventually I ended up replacing whole home server
piece by piece and finally deemed that the TX4 was propably broken.

Now a year later and after finding out that asic bug was found & fixed
I thought to utilize TX4 once more. I'm currently running driver from
kernel 2.6.24.4 which I had to backport into 2.6.23.1 due my TX4
replacement card (HPT rr174x) that has binary-wrapper drivers only
(sigh) and I'm unable to compile them in 2.6.24.4.

However the problem with Promise TX4 is now extremely poor
performance, it writes around 5.2MB/s  with average CPU utilization of
3.2 on my 2.4GHz p4 (measured over 12 hours).

First thought was that DMA is not enabled, but according to hdparm it
is. My plan to use this for RAID once again is doomed unless solution
is found.

I think iostat revealed something out of ordinary:

avg-cpu:  %user   %nice %system %iowait  %steal   %idle
           0.00    0.00    0.00  100.00    0.00    0.00

Device:         rrqm/s   wrqm/s     r/s     w/s    rMB/s    wMB/s
avgrq-sz avgqu-sz   await  svctm  %util
sdh               0.00  4640.00    0.00    8.00     0.00     3.94
1008.00   134.82 4807.00 125.50 100.40

For non TX4 devices these numbers are quite different. Full details
and other possibly related info can be found at
http://pastebin.com/f40f5ae27

Perhaps the asic patch made things this slow? If so, no wonder that it
hides problem that occurs only under heavy load?

I'm building unmodified 2.6.24.4 kernel to test this, but I doubt my
few lines of backporting are cause of this slowness.

Since I somewhat need to get this working, I'm ready to test patches
and so on. Any ideas or comments ?

--
Marko Koivusalo

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: Promise TX4 performance problems
  2008-04-12 12:56 Promise TX4 performance problems Marko Koivusalo
@ 2008-04-12 15:26 ` Alan Cox
  2008-04-12 20:50   ` Marko Koivusalo
  2008-04-12 17:47 ` Mikael Pettersson
  1 sibling, 1 reply; 6+ messages in thread
From: Alan Cox @ 2008-04-12 15:26 UTC (permalink / raw)
  To: Marko Koivusalo; +Cc: jgarzik, linux-ide

> replacement card (HPT rr174x) that has binary-wrapper drivers only
> (sigh) and I'm unable to compile them in 2.6.24.4.

Isn't the 174x just a marvell with different PCI identifiers ?

The dmesg output and hdparm -t values for that controller/device would be
useful just as a guide to low level behaviour

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: Promise TX4 performance problems
  2008-04-12 15:26 ` Alan Cox
@ 2008-04-12 20:50   ` Marko Koivusalo
  2008-04-12 21:56     ` Mikael Pettersson
  0 siblings, 1 reply; 6+ messages in thread
From: Marko Koivusalo @ 2008-04-12 20:50 UTC (permalink / raw)
  To: Alan Cox, mikpe; +Cc: linux-ide

On Sat, Apr 12, 2008 at 6:26 PM, Alan Cox <alan@lxorguk.ukuu.org.uk> wrote:
>  Isn't the 174x just a marvell with different PCI identifiers ?

Yes it's some marvell chip, apparently you've updated sata_mv some
time ago to include identifiers for rr174x. Last time I checked for
Open Source alternative there were nothing available. Currently
Marvell SATA support is labeled HIGHLY EXPERIMENTAL. How stable they
actually are, or am I better off with binary drivers for now?

Anyway here's my identifiers for that device, if any use ..

02:00.0 SCSI storage controller: HighPoint Technologies, Inc.
RocketRAID 1740 (rev 02)
        Subsystem: Marvell Technology Group Ltd. Unknown device 11ab
        Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop-
ParErr- Stepping- SERR- FastB2B- DisINTx-
        Status: Cap+ 66MHz+ UDF- FastB2B+ ParErr- DEVSEL=medium
>TAbort- <TAbort- <MAbort- >SERR- <PERR- INTx-
        Latency: 32, Cache Line Size: 32 bytes
        Interrupt: pin A routed to IRQ 11
        Region 0: Memory at e5000000 (64-bit, non-prefetchable) [size=1M]
        Region 2: I/O ports at 8000 [size=256]
        Capabilities: [40] Power Management version 2
                Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA
PME(D0-,D1-,D2-,D3hot-,D3cold-)
                Status: D0 PME-Enable- DSel=0 DScale=0 PME-
        Capabilities: [50] Message Signalled Interrupts: Mask- 64bit+
Queue=0/0 Enable-
                Address: 0000000000000000  Data: 0000
        Capabilities: [60] PCI-X non-bridge device
                Command: DPERE- ERO- RBC=512 OST=4
                Status: Dev=ff:1f.0 64bit+ 133MHz+ SCD- USC- DC=simple
DMMRBC=512 DMOST=4 DMCRS=8 RSCEM- 266MHz- 533MHz-

>  The dmesg output and hdparm -t values for that controller/device would be
>  useful just as a guide to low level behaviour

I compiled 2.6.25-rc9 and ran some more tests.

hdparm -t /dev/sdd

/dev/sdd:
 Timing buffered disk reads:  228 MB in  3.01 seconds =  75.66 MB/sec

So aparantly read speeds are just fine. However write speeds are still
very slow.

dd if=/dev/zero of=1gb bs=1M count=1024
1073741824 bytes (1.1 GB) copied, 107.068 s, 10.0 MB/s

All ideas how to proceed are appreciated, power supply is high quality
and adequate for sure (4 different power rails, over 20A in reserve).
Only thing I can think of is to yank all other controllers off and try
if it helps ...

lspci and dmesg outputs below.

lspci:

00:00.0 Host bridge: Intel Corporation 82845 845 [Brookdale] Chipset
Host Bridge (rev 11)
00:01.0 PCI bridge: Intel Corporation 82845 845 [Brookdale] Chipset
AGP Bridge (rev 11)
00:1d.0 USB Controller: Intel Corporation 82801DB/DBL/DBM
(ICH4/ICH4-L/ICH4-M) USB UHCI Controller #1 (rev 01)
00:1d.1 USB Controller: Intel Corporation 82801DB/DBL/DBM
(ICH4/ICH4-L/ICH4-M) USB UHCI Controller #2 (rev 01)
00:1d.2 USB Controller: Intel Corporation 82801DB/DBL/DBM
(ICH4/ICH4-L/ICH4-M) USB UHCI Controller #3 (rev 01)
00:1d.7 USB Controller: Intel Corporation 82801DB/DBM (ICH4/ICH4-M)
USB2 EHCI Controller (rev 01)
00:1e.0 PCI bridge: Intel Corporation 82801 PCI Bridge (rev 81)
00:1f.0 ISA bridge: Intel Corporation 82801DB/DBL (ICH4/ICH4-L) LPC
Interface Bridge (rev 01)
00:1f.1 IDE interface: Intel Corporation 82801DB (ICH4) IDE Controller (rev 01)
00:1f.3 SMBus: Intel Corporation 82801DB/DBL/DBM (ICH4/ICH4-L/ICH4-M)
SMBus Controller (rev 01)
01:00.0 VGA compatible controller: nVidia Corporation NV5M64 [RIVA
TNT2 Model 64/Model 64 Pro] (rev 15)
02:00.0 SCSI storage controller: HighPoint Technologies, Inc.
RocketRAID 1740 (rev 02)
02:01.0 Ethernet controller: 3Com Corporation 3c905B 100BaseTX
[Cyclone] (rev 24)
02:02.0 RAID bus controller: Promise Technology, Inc. PDC20371
(FastTrak S150 TX2plus) (rev 02)
02:03.0 Mass storage controller: Promise Technology, Inc. PDC40718
(SATA 300 TX4) (rev 02)
02:04.0 RAID bus controller: HighPoint Technologies, Inc. HPT374 (rev 07)
02:04.1 RAID bus controller: HighPoint Technologies, Inc. HPT374 (rev 07)
02:05.0 USB Controller: VIA Technologies, Inc. VT82xxxxx UHCI USB 1.1
Controller (rev 50)
02:05.1 USB Controller: VIA Technologies, Inc. VT82xxxxx UHCI USB 1.1
Controller (rev 50)
02:05.2 USB Controller: VIA Technologies, Inc. USB 2.0 (rev 51)
02:06.0 Ethernet controller: Realtek Semiconductor Co., Ltd.
RTL-8139/8139C/8139C+ (rev 10)

full dmesg:

Linux version 2.6.25-rc9-120408 (root@xxx) (gcc version 4.2.3 20071123
(prerelease) (Debian 4.2.2-4)) #1 Sat Apr 12 21:29:30 EEST 2008
BIOS-provided physical RAM map:
 BIOS-e820: 0000000000000000 - 00000000000a0000 (usable)
 BIOS-e820: 00000000000f0000 - 0000000000100000 (reserved)
 BIOS-e820: 0000000000100000 - 000000003fff0000 (usable)
 BIOS-e820: 000000003fff0000 - 000000003fff3000 (ACPI NVS)
 BIOS-e820: 000000003fff3000 - 0000000040000000 (ACPI data)
 BIOS-e820: 00000000fec00000 - 00000000fec01000 (reserved)
 BIOS-e820: 00000000fee00000 - 00000000fee01000 (reserved)
 BIOS-e820: 00000000ffb00000 - 0000000100000000 (reserved)
Warning only 896MB will be used.
Use a HIGHMEM enabled kernel.
896MB LOWMEM available.
Entering add_active_range(0, 0, 229376) 0 entries of 256 used
Zone PFN ranges:
  DMA             0 ->     4096
  Normal       4096 ->   229376
Movable zone start PFN for each node
early_node_map[1] active PFN ranges
    0:        0 ->   229376
On node 0 totalpages: 229376
  DMA zone: 32 pages used for memmap
  DMA zone: 0 pages reserved
  DMA zone: 4064 pages, LIFO batch:0
  Normal zone: 1760 pages used for memmap
  Normal zone: 223520 pages, LIFO batch:31
  Movable zone: 0 pages used for memmap
DMI 2.2 present.
ACPI: RSDP 000F7330, 0014 (r0 IntelR)
ACPI: RSDT 3FFF3000, 002C (r1 IntelR AWRDACPI 42302E31 AWRD        0)
ACPI: FACP 3FFF3040, 0074 (r1 IntelR AWRDACPI 42302E31 AWRD        0)
ACPI: DSDT 3FFF30C0, 4346 (r1 INTELR AWRDACPI     1000 MSFT  100000C)
ACPI: FACS 3FFF0000, 0040
ACPI: APIC 3FFF7440, 005A (r1 IntelR AWRDACPI 42302E31 AWRD        0)
ACPI: PM-Timer IO Port: 0x408
Allocating PCI resources starting at 50000000 (gap: 40000000:bec00000)
Built 1 zonelists in Zone order, mobility grouping on.  Total pages: 227584
Kernel command line: root=/dev/hda2 ro
Enabling fast FPU save and restore... done.
Enabling unmasked SIMD FPU exception support... done.
Initializing CPU#0
PID hash table entries: 4096 (order: 12, 16384 bytes)
Detected 2403.126 MHz processor.
Console: colour VGA+ 80x25
console [tty0] enabled
Dentry cache hash table entries: 131072 (order: 7, 524288 bytes)
Inode-cache hash table entries: 65536 (order: 6, 262144 bytes)
Memory: 902796k/917504k available (2428k kernel code, 14076k reserved,
1051k data, 204k init, 0k highmem)
virtual kernel memory layout:
    fixmap  : 0xffff6000 - 0xfffff000   (  36 kB)
    vmalloc : 0xf8800000 - 0xffff4000   ( 119 MB)
    lowmem  : 0xc0000000 - 0xf8000000   ( 896 MB)
      .init : 0xc046a000 - 0xc049d000   ( 204 kB)
      .data : 0xc035f2f8 - 0xc0466260   (1051 kB)
      .text : 0xc0100000 - 0xc035f2f8   (2428 kB)
Checking if this processor honours the WP bit even in supervisor mode...Ok.
CPA: page pool initialized 1 of 1 pages preallocated
Calibrating delay using timer specific routine.. 4809.64 BogoMIPS (lpj=9619296)
Mount-cache hash table entries: 512
CPU: Trace cache: 12K uops, L1 D cache: 8K
CPU: L2 cache: 512K
Intel machine check architecture supported.
Intel machine check reporting enabled on CPU#0.
CPU0: Intel P4/Xeon Extended MCE MSRs (12) available
Compat vDSO mapped to ffffe000.
CPU: Intel(R) Pentium(R) 4 CPU 2.40GHz stepping 04
Checking 'hlt' instruction... OK.
Freeing SMP alternatives: 0k freed
ACPI: Core revision 20070126
ACPI: setting ELCR to 0200 (from 1eb8)
net_namespace: 440 bytes
xor: automatically using best checksumming function: pIII_sse
   pIII_sse  :  3165.000 MB/sec
xor: using function: pIII_sse (3165.000 MB/sec)
NET: Registered protocol family 16
No dock devices found.
ACPI: bus type pci registered
PCI: PCI BIOS revision 2.10 entry at 0xfb230, last bus=2
PCI: Using configuration type 1
Setting up standard PCI resources
ACPI: EC: Look up EC in DSDT
ACPI: Interpreter enabled
ACPI: (supports S0 S1 S5)
ACPI: Using PIC for interrupt routing
ACPI: PCI Root Bridge [PCI0] (0000:00)
* The chipset may have PM-Timer Bug. Due to workarounds for a bug,
* this clock source is slow. If you are sure your timer does not have
* this bug, please use "acpi_pm_good" to disable the workaround
pci 0000:00:1f.0: quirk: region 0400-047f claimed by ICH4 ACPI/GPIO/TCO
pci 0000:00:1f.0: quirk: region 0480-04bf claimed by ICH4 GPIO
PCI: Transparent bridge - 0000:00:1e.0
ACPI: PCI Interrupt Routing Table [\_SB_.PCI0._PRT]
ACPI: PCI Interrupt Routing Table [\_SB_.PCI0.HUB0._PRT]
ACPI: PCI Interrupt Link [LNKA] (IRQs 3 4 5 6 7 9 10 *11 12 14 15)
ACPI: PCI Interrupt Link [LNKB] (IRQs *3 4 5 6 7 9 10 11 12 14 15)
ACPI: PCI Interrupt Link [LNKC] (IRQs 3 4 5 6 7 9 10 11 *12 14 15)
ACPI: PCI Interrupt Link [LNKD] (IRQs 3 4 *5 6 7 9 10 11 12 14 15)
ACPI: PCI Interrupt Link [LNKE] (IRQs 3 4 5 6 7 9 *10 11 12 14 15)
ACPI: PCI Interrupt Link [LNKF] (IRQs 3 *4 5 6 7 9 10 11 12 14 15)
ACPI: PCI Interrupt Link [LNK0] (IRQs 3 4 5 6 *7 9 10 11 12 14 15)
ACPI: PCI Interrupt Link [LNK1] (IRQs 3 4 5 6 7 *9 10 11 12 14 15)
Linux Plug and Play Support v0.97 (c) Adam Belay
pnp: PnP ACPI init
ACPI: bus type pnp registered
pnp: PnP ACPI: found 9 devices
ACPI: ACPI bus type pnp unregistered
SCSI subsystem initialized
libata version 3.00 loaded.
usbcore: registered new interface driver usbfs
usbcore: registered new interface driver hub
usbcore: registered new device driver usb
PCI: Using ACPI for IRQ routing
PCI: If a device doesn't work, try "pci=routeirq".  If it helps, post a report
system 00:02: ioport range 0x400-0x4bf could not be reserved
system 00:03: ioport range 0xb78-0xb7b has been reserved
system 00:03: ioport range 0xf78-0xf7b has been reserved
system 00:03: ioport range 0xa78-0xa7b has been reserved
system 00:03: ioport range 0xe78-0xe7b has been reserved
system 00:03: ioport range 0xbbc-0xbbf has been reserved
system 00:03: ioport range 0xfbc-0xfbf has been reserved
system 00:03: ioport range 0x4d0-0x4d1 has been reserved
system 00:03: ioport range 0x290-0x29f has been reserved
PCI: Bridge: 0000:00:01.0
  IO window: disabled.
  MEM window: 0xe2000000-0xe3ffffff
  PREFETCH window: 0x00000000e0000000-0x00000000e1ffffff
PCI: Bridge: 0000:00:1e.0
  IO window: 8000-cfff
  MEM window: 0xe4000000-0xe5ffffff
  PREFETCH window: disabled.
PCI: Setting latency timer of device 0000:00:1e.0 to 64
NET: Registered protocol family 2
IP route cache hash table entries: 32768 (order: 5, 131072 bytes)
TCP established hash table entries: 131072 (order: 8, 1048576 bytes)
TCP bind hash table entries: 65536 (order: 6, 262144 bytes)
TCP: Hash tables configured (established 131072 bind 65536)
TCP reno registered
Unpacking initramfs... done
Freeing initrd memory: 2152k freed
apm: BIOS version 1.2 Flags 0x07 (Driver version 1.16ac)
apm: overridden by ACPI.
Installing knfsd (copyright (C) 1996 okir@monad.swb.de).
fuse init (API version 7.9)
async_tx: api initialized (sync-only)
io scheduler noop registered
io scheduler anticipatory registered
io scheduler deadline registered
io scheduler cfq registered (default)
pci 0000:01:00.0: Boot video device
input: Power Button (FF) as /class/input/input0
ACPI: Power Button (FF) [PWRF]
input: Power Button (CM) as /class/input/input1
ACPI: Power Button (CM) [PWRB]
ACPI: PNP0C0B:00 is registered as cooling_device0
ACPI: Fan [FAN] (on)
ACPI: ACPI0007:00 is registered as cooling_device1
ACPI: Processor [CPU0] (supports 2 throttling states)
ACPI: LNXTHERM:01 is registered as thermal_zone0
ACPI: Thermal Zone [THRM] (46 C)
isapnp: Scanning for PnP cards...
isapnp: No Plug & Play device found
Linux agpgart interface v0.103
agpgart: Detected an Intel 845G Chipset.
agpgart: AGP aperture is 4M @ 0xe6000000
floppy0: no floppy controllers found
8139cp: 10/100 PCI Ethernet driver v1.3 (Mar 22, 2004)
8139cp 0000:02:06.0: This (id 10ec:8139 rev 10) is not an 8139C+ compatible chip
8139cp 0000:02:06.0: Try the "8139too" driver instead.
8139too Fast Ethernet driver 0.9.28
ACPI: PCI Interrupt Link [LNK0] enabled at IRQ 7
PCI: setting IRQ 7 as level-triggered
ACPI: PCI Interrupt 0000:02:06.0[A] -> Link [LNK0] -> GSI 7 (level,
low) -> IRQ 7
eth0: RealTek RTL8139 at 0xcc00, 00:50:8d:fd:04:01, IRQ 7
eth0:  Identified 8139 chip type 'RTL-8100B/8139D'
Uniform Multi-Platform E-IDE driver
ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx
ICH4: IDE controller (0x8086:0x24cb rev 0x01) at  PCI slot 0000:00:1f.1
ACPI: PCI Interrupt Link [LNKC] enabled at IRQ 12
PCI: setting IRQ 12 as level-triggered
ACPI: PCI Interrupt 0000:00:1f.1[A] -> Link [LNKC] -> GSI 12 (level,
low) -> IRQ 12
ICH4: not 100% native mode: will probe irqs later
    ide0: BM-DMA at 0xf000-0xf007, BIOS settings: hda:DMA, hdb:PIO
    ide1: BM-DMA at 0xf008-0xf00f, BIOS settings: hdc:PIO, hdd:PIO
Probing IDE interface ide0...
hda: HDS728080PLAT20, ATA DISK drive
hda: host max PIO4 wanted PIO255(auto-tune) selected PIO4
hda: UDMA/100 mode selected
Probing IDE interface ide1...
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
HPT374: IDE controller (0x1103:0x0008 rev 0x07) at  PCI slot 0000:02:04.0
ACPI: PCI Interrupt Link [LNKE] enabled at IRQ 10
PCI: setting IRQ 10 as level-triggered
ACPI: PCI Interrupt 0000:02:04.0[A] -> Link [LNKE] -> GSI 10 (level,
low) -> IRQ 10
HPT374: DPLL base: 48 MHz, f_CNT: 150, assuming 33 MHz PCI
HPT374: using 50 MHz DPLL clock
HPT374: 100% native mode on irq 10
ACPI: PCI Interrupt 0000:02:04.1[A] -> Link [LNKE] -> GSI 10 (level,
low) -> IRQ 10
HPT374: DPLL base: 48 MHz, f_CNT: 150, assuming 33 MHz PCI
HPT374: using 50 MHz DPLL clock
    ide2: BM-DMA at 0xac00-0xac07, BIOS settings: hde:DMA, hdf:DMA
    ide3: BM-DMA at 0xac08-0xac0f, BIOS settings: hdg:DMA, hdh:DMA
    ide4: BM-DMA at 0xc000-0xc007, BIOS settings: hdi:PIO, hdj:PIO
    ide5: BM-DMA at 0xc008-0xc00f, BIOS settings: hdk:PIO, hdl:PIO
Probing IDE interface ide2...
hde: Maxtor 6B200P0, ATA DISK drive
hdf: IC35L180AVV207-1, ATA DISK drive
hde: host max PIO4 wanted PIO255(auto-tune) selected PIO4
hde: UDMA/100 mode selected
hdf: host max PIO4 wanted PIO255(auto-tune) selected PIO4
hdf: UDMA/100 mode selected
Probing IDE interface ide3...
hdg: ST3160021A, ATA DISK drive
hdh: ST3200822A, ATA DISK drive
hdg: host max PIO4 wanted PIO255(auto-tune) selected PIO4
hdg: UDMA/100 mode selected
hdh: host max PIO4 wanted PIO255(auto-tune) selected PIO4
hdh: UDMA/100 mode selected
Probing IDE interface ide4...
Probing IDE interface ide5...
ide2 at 0x9c00-0x9c07,0xa002 on irq 10
ide3 at 0xa400-0xa407,0xa802 on irq 10
Probing IDE interface ide1...
Probing IDE interface ide4...
Probing IDE interface ide5...
hda: max request size: 512KiB
hda: 160836480 sectors (82348 MB) w/1719KiB Cache, CHS=16383/255/63
hda: cache flushes supported
 hda: hda1 < hda5 > hda2 hda3
hde: max request size: 512KiB
hde: 398297088 sectors (203928 MB) w/8192KiB Cache, CHS=24792/255/63
hde: cache flushes supported
 hde: unknown partition table
hdf: max request size: 512KiB
hdf: 361882080 sectors (185283 MB) w/7965KiB Cache, CHS=22526/255/63
hdf: cache flushes supported
 hdf: unknown partition table
hdg: max request size: 512KiB
hdg: 312581808 sectors (160041 MB) w/2048KiB Cache, CHS=19457/255/63
hdg: cache flushes supported
 hdg: unknown partition table
hdh: max request size: 512KiB
hdh: 390721968 sectors (200049 MB) w/8192KiB Cache, CHS=24321/255/63
hdh: cache flushes supported
 hdh: unknown partition table
Driver 'sd' needs updating - please use bus_type methods
sata_promise 0000:02:02.0: version 2.12
ACPI: PCI Interrupt 0000:02:02.0[A] -> Link [LNKC] -> GSI 12 (level,
low) -> IRQ 12
scsi0 : sata_promise
scsi1 : sata_promise
scsi2 : sata_promise
ata1: SATA max UDMA/133 mmio m4096@0xe51c5000 port 0xe51c5200 irq 12
ata2: SATA max UDMA/133 mmio m4096@0xe51c5000 port 0xe51c5280 irq 12
ata3: PATA max UDMA/133 mmio m4096@0xe51c5000 port 0xe51c5300 irq 12
ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
ata1.00: ATA-6: ST3200822AS, 3.01, max UDMA/133
ata1.00: 390721968 sectors, multi 0: LBA48
ata1.00: configured for UDMA/133
ata2: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
ata2.00: ATA-7: ST3300831AS, 3.01, max UDMA/133
ata2.00: 586072368 sectors, multi 0: LBA48 NCQ (depth 0/32)
ata2.00: configured for UDMA/133
ata3.00: ATA-7: SAMSUNG SP1604N, TM100-24, max UDMA/100
ata3.00: 312581808 sectors, multi 0: LBA48
ata3.00: limited to UDMA/33 due to 40-wire cable
ata3.00: configured for UDMA/33
scsi 0:0:0:0: Direct-Access     ATA      ST3200822AS      3.01 PQ: 0 ANSI: 5
sd 0:0:0:0: [sda] 390721968 512-byte hardware sectors (200050 MB)
sd 0:0:0:0: [sda] Write Protect is off
sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00
sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't
support DPO or FUA
sd 0:0:0:0: [sda] 390721968 512-byte hardware sectors (200050 MB)
sd 0:0:0:0: [sda] Write Protect is off
sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00
sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't
support DPO or FUA
 sda: sda1
sd 0:0:0:0: [sda] Attached SCSI disk
scsi 1:0:0:0: Direct-Access     ATA      ST3300831AS      3.01 PQ: 0 ANSI: 5
sd 1:0:0:0: [sdb] 586072368 512-byte hardware sectors (300069 MB)
sd 1:0:0:0: [sdb] Write Protect is off
sd 1:0:0:0: [sdb] Mode Sense: 00 3a 00 00
sd 1:0:0:0: [sdb] Write cache: enabled, read cache: enabled, doesn't
support DPO or FUA
sd 1:0:0:0: [sdb] 586072368 512-byte hardware sectors (300069 MB)
sd 1:0:0:0: [sdb] Write Protect is off
sd 1:0:0:0: [sdb] Mode Sense: 00 3a 00 00
sd 1:0:0:0: [sdb] Write cache: enabled, read cache: enabled, doesn't
support DPO or FUA
 sdb: sdb1
sd 1:0:0:0: [sdb] Attached SCSI disk
scsi 2:0:0:0: Direct-Access     ATA      SAMSUNG SP1604N  TM10 PQ: 0 ANSI: 5
sd 2:0:0:0: [sdc] 312581808 512-byte hardware sectors (160042 MB)
sd 2:0:0:0: [sdc] Write Protect is off
sd 2:0:0:0: [sdc] Mode Sense: 00 3a 00 00
sd 2:0:0:0: [sdc] Write cache: enabled, read cache: enabled, doesn't
support DPO or FUA
sd 2:0:0:0: [sdc] 312581808 512-byte hardware sectors (160042 MB)
sd 2:0:0:0: [sdc] Write Protect is off
sd 2:0:0:0: [sdc] Mode Sense: 00 3a 00 00
sd 2:0:0:0: [sdc] Write cache: enabled, read cache: enabled, doesn't
support DPO or FUA
 sdc: sdc1
sd 2:0:0:0: [sdc] Attached SCSI disk
ACPI: PCI Interrupt Link [LNKD] enabled at IRQ 5
PCI: setting IRQ 5 as level-triggered
ACPI: PCI Interrupt 0000:02:03.0[A] -> Link [LNKD] -> GSI 5 (level,
low) -> IRQ 5
scsi3 : sata_promise
scsi4 : sata_promise
scsi5 : sata_promise
scsi6 : sata_promise
ata4: SATA max UDMA/133 mmio m4096@0xe51c4000 port 0xe51c4380 irq 5
ata5: SATA max UDMA/133 mmio m4096@0xe51c4000 port 0xe51c4280 irq 5
ata6: SATA max UDMA/133 mmio m4096@0xe51c4000 port 0xe51c4200 irq 5
ata7: SATA max UDMA/133 mmio m4096@0xe51c4000 port 0xe51c4300 irq 5
ata4: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
ata4.00: ATA-8: WDC WD1000FYPS-01ZKB0, 02.01B01, max UDMA/133
ata4.00: 1953525168 sectors, multi 0: LBA48 NCQ (depth 0/32)
ata4.00: configured for UDMA/133
ata5: SATA link down (SStatus 0 SControl 300)
ata6: SATA link down (SStatus 0 SControl 300)
ata7: SATA link down (SStatus 0 SControl 300)
scsi 3:0:0:0: Direct-Access     ATA      WDC WD1000FYPS-0 02.0 PQ: 0 ANSI: 5
sd 3:0:0:0: [sdd] 1953525168 512-byte hardware sectors (1000205 MB)
sd 3:0:0:0: [sdd] Write Protect is off
sd 3:0:0:0: [sdd] Mode Sense: 00 3a 00 00
sd 3:0:0:0: [sdd] Write cache: enabled, read cache: enabled, doesn't
support DPO or FUA
sd 3:0:0:0: [sdd] 1953525168 512-byte hardware sectors (1000205 MB)
sd 3:0:0:0: [sdd] Write Protect is off
sd 3:0:0:0: [sdd] Mode Sense: 00 3a 00 00
sd 3:0:0:0: [sdd] Write cache: enabled, read cache: enabled, doesn't
support DPO or FUA
 sdd: sdd1
sd 3:0:0:0: [sdd] Attached SCSI disk
ACPI: PCI Interrupt Link [LNK1] enabled at IRQ 9
PCI: setting IRQ 9 as level-triggered
ACPI: PCI Interrupt 0000:00:1d.7[D] -> Link [LNK1] -> GSI 9 (level,
low) -> IRQ 9
PCI: Setting latency timer of device 0000:00:1d.7 to 64
ehci_hcd 0000:00:1d.7: EHCI Host Controller
ehci_hcd 0000:00:1d.7: new USB bus registered, assigned bus number 1
PCI: cache line size of 128 is not supported by device 0000:00:1d.7
ehci_hcd 0000:00:1d.7: irq 9, io mem 0xe6400000
ehci_hcd 0000:00:1d.7: USB 2.0 started, EHCI 1.00, driver 10 Dec 2004
usb usb1: configuration #1 chosen from 1 choice
hub 1-0:1.0: USB hub found
hub 1-0:1.0: 6 ports detected
ACPI: PCI Interrupt Link [LNKF] enabled at IRQ 4
PCI: setting IRQ 4 as level-triggered
ACPI: PCI Interrupt 0000:02:05.2[C] -> Link [LNKF] -> GSI 4 (level,
low) -> IRQ 4
ehci_hcd 0000:02:05.2: EHCI Host Controller
ehci_hcd 0000:02:05.2: new USB bus registered, assigned bus number 2
ehci_hcd 0000:02:05.2: irq 4, io mem 0xe51c6000
ehci_hcd 0000:02:05.2: USB 2.0 started, EHCI 0.95, driver 10 Dec 2004
usb usb2: configuration #1 chosen from 1 choice
hub 2-0:1.0: USB hub found
hub 2-0:1.0: 4 ports detected
Initializing USB Mass Storage driver...
usbcore: registered new interface driver usb-storage
USB Mass Storage support registered.
PNP: PS/2 Controller [PNP0303:PS2K] at 0x60,0x64 irq 1
PNP: PS/2 appears to have AUX port disabled, if this is incorrect
please boot with i8042.nopnp
serio: i8042 KBD port at 0x60,0x64 irq 1
mice: PS/2 mouse device common for all mice
input: AT Translated Set 2 keyboard as /class/input/input2
md: linear personality registered for level -1
md: raid0 personality registered for level 0
md: raid1 personality registered for level 1
raid6: int32x1    622 MB/s
raid6: int32x2    577 MB/s
raid6: int32x4    710 MB/s
raid6: int32x8    516 MB/s
raid6: mmxx1     1997 MB/s
raid6: mmxx2     2071 MB/s
raid6: sse1x1    1013 MB/s
raid6: sse1x2    1900 MB/s
raid6: sse2x1    2070 MB/s
raid6: sse2x2    2496 MB/s
raid6: using algorithm sse2x2 (2496 MB/s)
md: raid6 personality registered for level 6
md: raid5 personality registered for level 5
md: raid4 personality registered for level 4
device-mapper: ioctl: 4.13.0-ioctl (2007-10-18) initialised: dm-devel@redhat.com
cpuidle: using governor ladder
Netfilter messages via NETLINK v0.30.
nf_conntrack version 0.5.0 (14336 buckets, 57344 max)
ip_tables: (C) 2000-2006 Netfilter Core Team
arp_tables: (C) 2002 David S. Miller
TCP cubic registered
NET: Registered protocol family 1
NET: Registered protocol family 17
RPC: Registered udp transport module.
RPC: Registered tcp transport module.
Using IPI Shortcut mode
Freeing unused kernel memory: 204k freed
ACPI: PCI Interrupt Link [LNKB] enabled at IRQ 3
PCI: setting IRQ 3 as level-triggered
ACPI: PCI Interrupt 0000:02:01.0[A] -> Link [LNKB] -> GSI 3 (level,
low) -> IRQ 3
3c59x: Donald Becker and others.
0000:02:01.0: 3Com PCI 3c905B Cyclone 100baseTx at f881a000.
md: md0 stopped.
md: bind<sdb1>
raid5: device sdb1 operational as raid disk 2
raid5: not enough operational devices for md0 (3/4 failed)
RAID5 conf printout:
 --- rd:4 wd:1
 disk 2, o:1, dev:sdb1
raid5: failed to run raid set md0
md: pers->run() failed ...
kjournald starting.  Commit interval 5 seconds
EXT3-fs: mounted filesystem with ordered data mode.
Adding 1951824k swap on /dev/hda5.  Priority:-1 extents:1 across:1951824k
EXT3 FS on hda2, internal journal
ReiserFS: dm-0: found reiserfs format "3.6" with standard journal
ReiserFS: dm-0: using ordered data mode
ReiserFS: dm-0: journal params: device dm-0, size 8192, journal first
block 18, max trans len 1024, max batch 900, max commit age 30, max
trans age 30
ReiserFS: dm-0: checking transaction log (dm-0)
ReiserFS: dm-0: Using r5 hash to sort names
kjournald starting.  Commit interval 5 seconds
EXT3 FS on hda3, internal journal
EXT3-fs: mounted filesystem with ordered data mode.
ReiserFS: sda1: found reiserfs format "3.6" with standard journal
ReiserFS: sda1: using ordered data mode
ReiserFS: sda1: journal params: device sda1, size 8192, journal first
block 18, max trans len 1024, max batch 900, max commit age 30, max
trans age 30
ReiserFS: sda1: checking transaction log (sda1)
ReiserFS: sda1: Using r5 hash to sort names
eth0: link up, 100Mbps, full-duplex, lpa 0x45E1
eth1:  setting full-duplex.
warning: `dnsmasq' uses 32-bit capabilities (legacy support in use)
svc: 127.0.0.1, port=54195: unknown version (3 for prog 100003, nfsd)

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: Promise TX4 performance problems
  2008-04-12 20:50   ` Marko Koivusalo
@ 2008-04-12 21:56     ` Mikael Pettersson
  2008-04-12 23:20       ` Marko Koivusalo
  0 siblings, 1 reply; 6+ messages in thread
From: Mikael Pettersson @ 2008-04-12 21:56 UTC (permalink / raw)
  To: Marko Koivusalo; +Cc: Alan Cox, mikpe, linux-ide

Marko Koivusalo writes:
 > I compiled 2.6.25-rc9 and ran some more tests.
 > 
 > hdparm -t /dev/sdd
 > 
 > /dev/sdd:
 >  Timing buffered disk reads:  228 MB in  3.01 seconds =  75.66 MB/sec
 > 
 > So aparantly read speeds are just fine. However write speeds are still
 > very slow.
 > 
 > dd if=/dev/zero of=1gb bs=1M count=1024
 > 1073741824 bytes (1.1 GB) copied, 107.068 s, 10.0 MB/s

That includes overheads from whatever file system / raid layers
you have on top of the device. Please do the dd straight to
/dev/sdd or /dev/sdd1.

Also, I note that while you have an Intel 845 chipset, your kernel
doesn't mention either the local APIC or the I/O APIC. I would have
expected both to be present; using them typically results in less
IRQ sharing and lower IRQ handling overheads. Might be worthwhile
to try to enable them.

/Mikael

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: Promise TX4 performance problems
  2008-04-12 21:56     ` Mikael Pettersson
@ 2008-04-12 23:20       ` Marko Koivusalo
  0 siblings, 0 replies; 6+ messages in thread
From: Marko Koivusalo @ 2008-04-12 23:20 UTC (permalink / raw)
  To: Mikael Pettersson; +Cc: Alan Cox, linux-ide

>  That includes overheads from whatever file system / raid layers
>  you have on top of the device. Please do the dd straight to
>  /dev/sdd or /dev/sdd1.
>
>  Also, I note that while you have an Intel 845 chipset, your kernel
>  doesn't mention either the local APIC or the I/O APIC. I would have
>  expected both to be present; using them typically results in less
>  IRQ sharing and lower IRQ handling overheads. Might be worthwhile
>  to try to enable them.
>
>  /Mikael

I think I've figured out what's the problem.

Measuring directly from device performance increased up to 13MB/s.
After enabling APIC & I/O APIC it was up to 18MB/s. I tried to yank
all other controllers but it didn't have any effect. This ruled out
pretty much everything except the Promise TX4 .. and the HDD itself. I
tried to plug disk into motherboard controller (HPT374) and it gives
me exactly same write performance ... 18MB/s.

Apparently this brand new 1 Tt Western Digital is either amazingly
slow on write or I have faulty unit.

Model number: WDC WD1000FYPS-01ZKB0
Model name: Western Digital RE2-GP (Green Power)

Western Digitals Specification for the drive state:
Transfer Rate (Buffer To Disk)	84 MB/s (Sustained)

Uh, I'm a little puzzled .. what to do next .. I don't think I want to
have drive with real world 5-10MB/s write performance .. replacing it
trough warranty may be troublesome since it works fine otherwise.
Perhaps I'll contact WD directly ...

It would seem to be as always, problems is where you least expect it to be.

--
Marko Koivusalo

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: Promise TX4 performance problems
  2008-04-12 12:56 Promise TX4 performance problems Marko Koivusalo
  2008-04-12 15:26 ` Alan Cox
@ 2008-04-12 17:47 ` Mikael Pettersson
  1 sibling, 0 replies; 6+ messages in thread
From: Mikael Pettersson @ 2008-04-12 17:47 UTC (permalink / raw)
  To: Marko Koivusalo; +Cc: jgarzik, linux-ide

Marko Koivusalo writes:
 > Hello,
 > 
 > I'm unfortunate owner of Promise TX4 SATA300 (rev2). In Feb 2007 my
 > raid started to drop drives under heavy load. Back then it was not
 > known to hapend because of TX4 asic bug or at least I was unable to
 > find such information at the time. And the card had worked fine for a
 > year or so. Well eventually I ended up replacing whole home server
 > piece by piece and finally deemed that the TX4 was propably broken.
 > 
 > Now a year later and after finding out that asic bug was found & fixed
 > I thought to utilize TX4 once more. I'm currently running driver from
 > kernel 2.6.24.4 which I had to backport into 2.6.23.1 due my TX4
 > replacement card (HPT rr174x) that has binary-wrapper drivers only
 > (sigh) and I'm unable to compile them in 2.6.24.4.
 > 
 > However the problem with Promise TX4 is now extremely poor
 > performance, it writes around 5.2MB/s  with average CPU utilization of
 > 3.2 on my 2.4GHz p4 (measured over 12 hours).
 > 
 > First thought was that DMA is not enabled, but according to hdparm it
 > is. My plan to use this for RAID once again is doomed unless solution
 > is found.
 > 
 > I think iostat revealed something out of ordinary:
 > 
 > avg-cpu:  %user   %nice %system %iowait  %steal   %idle
 >            0.00    0.00    0.00  100.00    0.00    0.00
 > 
 > Device:         rrqm/s   wrqm/s     r/s     w/s    rMB/s    wMB/s
 > avgrq-sz avgqu-sz   await  svctm  %util
 > sdh               0.00  4640.00    0.00    8.00     0.00     3.94
 > 1008.00   134.82 4807.00 125.50 100.40
 > 
 > For non TX4 devices these numbers are quite different. Full details
 > and other possibly related info can be found at
 > http://pastebin.com/f40f5ae27
 > 
 > Perhaps the asic patch made things this slow? If so, no wonder that it
 > hides problem that occurs only under heavy load?

My News server (PDC20378, VIA KT800 chipset, 2GHz Athlon64) gets
69MB/s reads and 56MB/s writes on a non-raid ext3 fs. My Promise
test box (550MHz Athlon, AMD751/756 chipset) gets 55MB/s reads and
and 42MB/s writes on one disk, and 69MB/s reads and 49MB/s writes
on another disk, with non-raid ext3.

So I don't think the ASIC bug workaround is related to your poor
write performance. Your performance problem could be due to:
- that HPT rr174x driver
- a dodgy mainboard or ACPI
- disk errors and I/O retries caused by an underdimensioned PSU
But we'd need a lot more detailed information about your system
to make any sort of educated guess.

It would be interesting to see raw read and write performance on
your TX4 with a vanilla 2.6.25-rc9 kernel. You can for instance
use dd or hdparm on /dev/sdh to do the measurements. (And please
include lspci output and the complete kernel log as well.)

/Mikael

^ permalink raw reply	[flat|nested] 6+ messages in thread

end of thread, other threads:[~2008-04-12 23:20 UTC | newest]

Thread overview: 6+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2008-04-12 12:56 Promise TX4 performance problems Marko Koivusalo
2008-04-12 15:26 ` Alan Cox
2008-04-12 20:50   ` Marko Koivusalo
2008-04-12 21:56     ` Mikael Pettersson
2008-04-12 23:20       ` Marko Koivusalo
2008-04-12 17:47 ` Mikael Pettersson

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.