Zsolt K?ti wrote:>My system produces these messages that I already know well from this >list (as well ;): >ad4: TIMEOUT - WRITE_DMA retrying (2 retries left) LBA=213249674 > >Like many people I was confronted with "TIMEOUT - READ_DMA" and "TIMEOUT - WRITE_DMA" errors on my drives. I was frustrated. But I found a workaround: Turning off ACPI. I just received a Highpoint RocketRaid 1640 controller, 2 Maxtor 300GB drives, and a Supermicro 5-drive SATA cage. I am testing this configuration for a storage server. I am using an old motherboard, DTK brand, Slot 1. 300A Celeron. Under a fresh install of 5.3-RELEASE I am unable to read or write both drives heavily at the same time. One drive alone seems to work OK. When I run dd blasting both drives with seqential IO, I get TIMEOUT - WRITE(READ)_DMA. Repeatably, within 15 seconds. However I got a good test before I installed 5.3-R, the box was running with 5.3-BETA. Only difference was I booted without ACPI. So I rebooted the freshly installed 5.3-R without ACPI, and It works! I can read at 50MB/s per drive concurrently (hitting PCI bus speed limit?), and write at 30MB/s per drive concurrently. No errors so far, and its been dd'ing for a half hour. I hope this report helps someone! Joe Koberg joe at osoft dot us dmesg: FreeBSD 5.3-RELEASE #0: Fri Nov 5 04:19:18 UTC 2004 root@harlow.cse.buffalo.edu:/usr/obj/usr/src/sys/GENERIC Timecounter "i8254" frequency 1193182 Hz quality 0 CPU: Pentium II/Pentium II Xeon/Celeron (307.84-MHz 686-class CPU) Origin = "GenuineIntel" Id = 0x660 Stepping = 0 Features=0x183f9ff<FPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,MMX,FXSR> real memory = 402587648 (383 MB) avail memory = 384270336 (366 MB) npx0: [FAST] npx0: <math processor> on motherboard npx0: INT 16 interface pcib0: <Intel 82443LX (440 LX) host to PCI bridge> pcibus 0 on motherboard pir0: <PCI Interrupt Routing Table: 7 Entries> on motherboard pci0: <PCI bus> on pcib0 agp0: <Intel 82443LX (440 LX) host to PCI bridge> mem 0xe0000000-0xe3ffffff at device 0.0 on pci0 pcib1: <PCI-PCI bridge> at device 1.0 on pci0 pci1: <PCI bus> on pcib1 pci1: <display, VGA> at device 0.0 (no driver attached) isab0: <PCI-ISA bridge> at device 7.0 on pci0 isa0: <ISA bus> on isab0 atapci0: <Intel PIIX4 UDMA33 controller> port 0xf000-0xf00f,0x376,0x170-0x177,0x3f6,0x1f0-0x1f7 at device 7.1 on pci0 ata0: channel #0 on atapci0 ata1: channel #1 on atapci0 uhci0: <Intel 82371AB/EB (PIIX4) USB controller> port 0xb000-0xb01f irq 10 at device 7.2 on pci0 uhci0: [GIANT-LOCKED] usb0: <Intel 82371AB/EB (PIIX4) USB controller> on uhci0 usb0: USB revision 1.0 uhub0: Intel UHCI root hub, class 9/0, rev 1.00/1.00, addr 1 uhub0: 2 ports with 2 removable, self powered ums0: Microsoft Microsoft 5-Button Mouse with IntelliEye(TM), rev 1.10/3.00, addr 2, iclass 3/1 ums0: 5 buttons and Z dir. pci0: <bridge, PCI-unknown> at device 7.3 (no driver attached) atapci1: <HighPoint HPT374 (channel 0+1) UDMA133 controller> port 0xc400-0xc4ff,0xc000-0xc003,0xbc00-0xbc07,0xb800-0xb803,0xb400-0xb407 irq 11 at device 17.0 on pci0 ata2: channel #0 on atapci1 ata3: channel #1 on atapci1 atapci2: <HighPoint HPT374 (channel 2+3) UDMA133 controller> port 0xd800-0xd8ff,0xd400-0xd403,0xd000-0xd007,0xcc00-0xcc03,0xc800-0xc807 irq 11 at device 17.1 on pci0 ata4: channel #0 on atapci2 ata5: channel #1 on atapci2 dc0: <ADMtek AN985 10/100BaseTX> port 0xdc00-0xdcff mem 0xec000000-0xec0003ff irq 12 at device 18.0 on pci0 miibus0: <MII bus> on dc0 ukphy0: <Generic IEEE 802.3u media interface> on miibus0 ukphy0: 10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, auto dc0: Ethernet address: 00:04:5a:56:80:76 dc0: if_start running deferred for Giant dc0: [GIANT-LOCKED] pci0: <multimedia, audio> at device 19.0 (no driver attached) cpu0 on motherboard orm0: <ISA Option ROMs> at iomem 0xcc000-0xcdfff,0xc0000-0xc8fff on isa0 pmtimer0 on isa0 atkbdc0: <Keyboard controller (i8042)> at port 0x64,0x60 on isa0 atkbd0: <AT Keyboard> irq 1 on atkbdc0 kbd0 at atkbd0 atkbd0: [GIANT-LOCKED] fdc0: <Enhanced floppy controller> at port 0x3f0-0x3f5 irq 6 drq 2 on isa0 fdc0: [FAST] fd0: <1440-KB 3.5" drive> on fdc0 drive 0 ppc0: <Parallel port> at port 0x378-0x37f irq 7 on isa0 ppc0: SMC-like chipset (ECP/EPP/PS2/NIBBLE) in COMPATIBLE mode ppc0: FIFO with 16/16/8 bytes threshold ppbus0: <Parallel port bus> on ppc0 plip0: <PLIP network interface> on ppbus0 lpt0: <Printer> on ppbus0 lpt0: Interrupt-driven port ppi0: <Parallel I/O> on ppbus0 sc0: <System console> at flags 0x100 on isa0 sc0: VGA <16 virtual consoles, flags=0x300> sio0 at port 0x3f8-0x3ff irq 4 flags 0x10 on isa0 sio0: type 16550A sio1 at port 0x2f8-0x2ff irq 3 on isa0 sio1: type 16550A vga0: <Generic ISA VGA> at port 0x3c0-0x3df iomem 0xa0000-0xbffff on isa0 unknown: <PNP0303> can't assign resources (port) unknown: <PNP0c02> can't assign resources (memory) unknown: <PNP0a03> can't assign resources (port) unknown: <PNP0501> can't assign resources (port) unknown: <PNP0501> can't assign resources (port) unknown: <PNP0700> can't assign resources (port) unknown: <PNP0401> can't assign resources (port) Timecounter "TSC" frequency 307842170 Hz quality 800 Timecounters tick every 10.000 msec ad0: 43979MB <IBM-DTLA-307045/TX6OA60A> [89355/16/63] at ata0-master UDMA33 ad4: 286188MB <Maxtor 6B300S0/BANC1B10> [581463/16/63] at ata2-master UDMA133 ad6: 286188MB <Maxtor 6B300S0/BANC1B10> [581463/16/63] at ata3-master UDMA133 Mounting root from ufs:/dev/ad0s1a>After these messages the two former cases result in FAILURE and finally >in panic. Even background fsck cannot run without another panic, only >single user mode can help. All these prevent using them on my HW. >However B7, although displays the messages as well, works seemingly >fine. For the time being this version is sufficent, but I'd like to >know - if possible at all - what the difference could be between the >versions and if one can expect to bring the actual 5.3 version's >state to B7's in this respect? > >Further to this, the different versions display the behavior of >relatively frequently (many time in an hour?) stalling their >responsivity for some seconds. Most of the times no message can be seen >on the consol after this. It is also more rare on B7. > >I also found that pendrive's sensing by 5.3 RELEASE/STABLE more >frequently results in panic than B7's. (As a matter of fact I have not >seen it with B7 for weeks since I installed it.) > >I use the following either with GENERIC or custom kernel: >Abit NF7-S (nVidia chipsets, SiI3112 on board), Athlon 2600+, >Samsung 120G SATA, LEXAR MEDIA JUMPDRIVE, rev 1.10/0.01 > > >Please cc it to me as well, since I'am not on the list for the time >being. >Many thanks! > >Zsolt > >-------------------- >Zsolt Kuti >_______________________________________________ >freebsd-current@freebsd.org mailing list >http://lists.freebsd.org/mailman/listinfo/freebsd-current >To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebsd.org" > >
----- Original Message ----- From: "Joe Koberg" <joe@osoft.us> To: "Zsolt K?ti" <kutizs@axelero.hu> Cc: <freebsd-current@freebsd.org>; <freebsd-stable@freebsd.org> Sent: Monday, December 27, 2004 6:29 PM Subject: Re: TIMEOUT - WRITE_DMA - A possible FIX! turn off ACPI> Zsolt K?ti wrote: > > >My system produces these messages that I already know well from this > >list (as well ;): > >ad4: TIMEOUT - WRITE_DMA retrying (2 retries left) LBA=213249674 > > > > > Like many people I was confronted with "TIMEOUT - READ_DMA" > and "TIMEOUT - WRITE_DMA" errors on my drives. I was frustrated. > But I found a workaround: Turning off ACPI. > > I just received a Highpoint RocketRaid 1640 controller, > 2 Maxtor 300GB drives, and a Supermicro 5-drive SATA cage. > I am testing this configuration for a storage server. > > I am using an old motherboard, DTK brand, Slot 1. 300A Celeron. > > Under a fresh install of 5.3-RELEASE I am unable to read or write > both drives heavily at the same time. One drive alone seems to work > OK. When I run dd blasting both drives with seqential IO, I get > TIMEOUT - WRITE(READ)_DMA. Repeatably, within 15 seconds. > > However I got a good test before I installed 5.3-R, the box was running > with 5.3-BETA. Only difference was I booted without ACPI. > > So I rebooted the freshly installed 5.3-R without ACPI, and It works! > I can read at 50MB/s per drive concurrently (hitting PCI bus speed > limit?), and write at 30MB/s per drive concurrently. No errors so > far, and its been dd'ing for a half hour. > > I hope this report helps someone! > > > > Joe Koberg > joe at osoft dot usI 2 have been seeing this error sence 4.9 with my westeren digital 80gig hd the error message has changed a little between the two vers .. but i do have this in device.hints , hint.acpi.0.disabled="1" , and i still see the error messages . any way i just whanted to post in and let every one know that turning off ACPI , might not work for you. ohh and off subject here , i had acpi turned off becouse my net cards wouldnt work with it on ..> dmesg: > > FreeBSD 5.3-RELEASE #0: Fri Nov 5 04:19:18 UTC 2004 > root@harlow.cse.buffalo.edu:/usr/obj/usr/src/sys/GENERIC > Timecounter "i8254" frequency 1193182 Hz quality 0 > CPU: Pentium II/Pentium II Xeon/Celeron (307.84-MHz 686-class CPU) > Origin = "GenuineIntel" Id = 0x660 Stepping = 0 > >Features=0x183f9ff<FPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,SEP,MTRR,PGE,MCA,CMOV, PAT,PSE36,MMX,FXSR>> real memory = 402587648 (383 MB) > avail memory = 384270336 (366 MB) > npx0: [FAST] > npx0: <math processor> on motherboard > npx0: INT 16 interface > pcib0: <Intel 82443LX (440 LX) host to PCI bridge> pcibus 0 on motherboard > pir0: <PCI Interrupt Routing Table: 7 Entries> on motherboard > pci0: <PCI bus> on pcib0 > agp0: <Intel 82443LX (440 LX) host to PCI bridge> mem > 0xe0000000-0xe3ffffff at device 0.0 on pci0 > pcib1: <PCI-PCI bridge> at device 1.0 on pci0 > pci1: <PCI bus> on pcib1 > pci1: <display, VGA> at device 0.0 (no driver attached) > isab0: <PCI-ISA bridge> at device 7.0 on pci0 > isa0: <ISA bus> on isab0 > atapci0: <Intel PIIX4 UDMA33 controller> port > 0xf000-0xf00f,0x376,0x170-0x177,0x3f6,0x1f0-0x1f7 at device 7.1 on pci0 > ata0: channel #0 on atapci0 > ata1: channel #1 on atapci0 > uhci0: <Intel 82371AB/EB (PIIX4) USB controller> port 0xb000-0xb01f irq > 10 at device 7.2 on pci0 > uhci0: [GIANT-LOCKED] > usb0: <Intel 82371AB/EB (PIIX4) USB controller> on uhci0 > usb0: USB revision 1.0 > uhub0: Intel UHCI root hub, class 9/0, rev 1.00/1.00, addr 1 > uhub0: 2 ports with 2 removable, self powered > ums0: Microsoft Microsoft 5-Button Mouse with IntelliEye(TM), rev > 1.10/3.00, addr 2, iclass 3/1 > ums0: 5 buttons and Z dir. > pci0: <bridge, PCI-unknown> at device 7.3 (no driver attached) > atapci1: <HighPoint HPT374 (channel 0+1) UDMA133 controller> port > 0xc400-0xc4ff,0xc000-0xc003,0xbc00-0xbc07,0xb800-0xb803,0xb400-0xb407 > irq 11 at device 17.0 on pci0 > ata2: channel #0 on atapci1 > ata3: channel #1 on atapci1 > atapci2: <HighPoint HPT374 (channel 2+3) UDMA133 controller> port > 0xd800-0xd8ff,0xd400-0xd403,0xd000-0xd007,0xcc00-0xcc03,0xc800-0xc807 > irq 11 at device 17.1 on pci0 > ata4: channel #0 on atapci2 > ata5: channel #1 on atapci2 > dc0: <ADMtek AN985 10/100BaseTX> port 0xdc00-0xdcff mem > 0xec000000-0xec0003ff irq 12 at device 18.0 on pci0 > miibus0: <MII bus> on dc0 > ukphy0: <Generic IEEE 802.3u media interface> on miibus0 > ukphy0: 10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, auto > dc0: Ethernet address: 00:04:5a:56:80:76 > dc0: if_start running deferred for Giant > dc0: [GIANT-LOCKED] > pci0: <multimedia, audio> at device 19.0 (no driver attached) > cpu0 on motherboard > orm0: <ISA Option ROMs> at iomem 0xcc000-0xcdfff,0xc0000-0xc8fff on isa0 > pmtimer0 on isa0 > atkbdc0: <Keyboard controller (i8042)> at port 0x64,0x60 on isa0 > atkbd0: <AT Keyboard> irq 1 on atkbdc0 > kbd0 at atkbd0 > atkbd0: [GIANT-LOCKED] > fdc0: <Enhanced floppy controller> at port 0x3f0-0x3f5 irq 6 drq 2 on isa0 > fdc0: [FAST] > fd0: <1440-KB 3.5" drive> on fdc0 drive 0 > ppc0: <Parallel port> at port 0x378-0x37f irq 7 on isa0 > ppc0: SMC-like chipset (ECP/EPP/PS2/NIBBLE) in COMPATIBLE mode > ppc0: FIFO with 16/16/8 bytes threshold > ppbus0: <Parallel port bus> on ppc0 > plip0: <PLIP network interface> on ppbus0 > lpt0: <Printer> on ppbus0 > lpt0: Interrupt-driven port > ppi0: <Parallel I/O> on ppbus0 > sc0: <System console> at flags 0x100 on isa0 > sc0: VGA <16 virtual consoles, flags=0x300> > sio0 at port 0x3f8-0x3ff irq 4 flags 0x10 on isa0 > sio0: type 16550A > sio1 at port 0x2f8-0x2ff irq 3 on isa0 > sio1: type 16550A > vga0: <Generic ISA VGA> at port 0x3c0-0x3df iomem 0xa0000-0xbffff on isa0 > unknown: <PNP0303> can't assign resources (port) > unknown: <PNP0c02> can't assign resources (memory) > unknown: <PNP0a03> can't assign resources (port) > unknown: <PNP0501> can't assign resources (port) > unknown: <PNP0501> can't assign resources (port) > unknown: <PNP0700> can't assign resources (port) > unknown: <PNP0401> can't assign resources (port) > Timecounter "TSC" frequency 307842170 Hz quality 800 > Timecounters tick every 10.000 msec > ad0: 43979MB <IBM-DTLA-307045/TX6OA60A> [89355/16/63] at ata0-masterUDMA33> ad4: 286188MB <Maxtor 6B300S0/BANC1B10> [581463/16/63] at ata2-master > UDMA133 > ad6: 286188MB <Maxtor 6B300S0/BANC1B10> [581463/16/63] at ata3-master > UDMA133 > Mounting root from ufs:/dev/ad0s1a > > > > > > > > > > > >After these messages the two former cases result in FAILURE and finally > >in panic. Even background fsck cannot run without another panic, only > >single user mode can help. All these prevent using them on my HW. > >However B7, although displays the messages as well, works seemingly > >fine. For the time being this version is sufficent, but I'd like to > >know - if possible at all - what the difference could be between the > >versions and if one can expect to bring the actual 5.3 version's > >state to B7's in this respect? > > > >Further to this, the different versions display the behavior of > >relatively frequently (many time in an hour?) stalling their > >responsivity for some seconds. Most of the times no message can be seen > >on the consol after this. It is also more rare on B7. > > > >I also found that pendrive's sensing by 5.3 RELEASE/STABLE more > >frequently results in panic than B7's. (As a matter of fact I have not > >seen it with B7 for weeks since I installed it.) > > > >I use the following either with GENERIC or custom kernel: > >Abit NF7-S (nVidia chipsets, SiI3112 on board), Athlon 2600+, > >Samsung 120G SATA, LEXAR MEDIA JUMPDRIVE, rev 1.10/0.01 > > > > > >Please cc it to me as well, since I'am not on the list for the time > >being. > >Many thanks! > > > >Zsolt > > > >-------------------- > >Zsolt Kuti > >_______________________________________________ > >freebsd-current@freebsd.org mailing list > >http://lists.freebsd.org/mailman/listinfo/freebsd-current > >To unsubscribe, send any mail to"freebsd-current-unsubscribe@freebsd.org"> > > > > > _______________________________________________ > freebsd-stable@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-stable > To unsubscribe, send any mail to "freebsd-stable-unsubscribe@freebsd.org" >
Arno J. Klaassen
2004-Dec-28 17:47 UTC
TIMEOUT - WRITE_DMA - A possible FIX! turn off ACPI
Joe Koberg <joe@osoft.us> writes:> Zsolt K?ti wrote: > > >My system produces these messages that I already know well from this > >list (as well ;): > >ad4: TIMEOUT - WRITE_DMA retrying (2 retries left) LBA=213249674 > > > > > Like many people I was confronted with "TIMEOUT - READ_DMA" > and "TIMEOUT - WRITE_DMA" errors on my drives. I was frustrated. > But I found a workaround: Turning off ACPI.dunno, I'd more suspect ACPI<->APIC issues : untill now I only had problems on nForce based systems, but today I installed a brand new VIA based A7VT mini-server and re-voila les "XXX_DMA" errors (and accompanying severe system slow-down). (Disk swapped from the old PII-233 minimalist-server; worked OK there; disabling APIC (in BOIS and/or config and/or hints) made disappear the XXX_DMA messages (and gave me my network connexion back ;) ) whilst ACPI still enabled). FYI, Arno
On Mon, 27 Dec 2004, Joe Koberg wrote:> Zsolt K?ti wrote: > >> My system produces these messages that I already know well from this >> list (as well ;): >> ad4: TIMEOUT - WRITE_DMA retrying (2 retries left) LBA=213249674 >> >> > So I rebooted the freshly installed 5.3-R without ACPI, and It works! > I can read at 50MB/s per drive concurrently (hitting PCI bus speed > limit?), and write at 30MB/s per drive concurrently. No errors so > far, and its been dd'ing for a half hour.Regular PCI and PCI-X (eXtended) is: 33hmz/32bits 132 Megabyte 66mhz/32bits 264 Megabyte 66mhz/64bits 520 Megabyte 100mhz/64bits 784 Megabyte 133mhz/64bits 1040 Megabyte etc. With overhead included I'd say 100 Megabyte is pretty reasonable for a normal pci bus. Keep in mind that this is for the whole bus, which is why most server motherboard have multiple seperate busses. PCI-X is an extension to regular pci, with more mhz/bits. PCI-E ( Express ) is a redesign with higher speeds and fewer traces needed. The big problem with 64bits pci is not the slot but the fact that you have to run all those extra (fast) lines to the slots which means that you'll need extra space (mainly layers) to store them, ergo an expensive motherboard. HTH, HAND. -- Sten Spans "There is a crack in everything, that's how the light gets in." Leonard Cohen - Anthem -------------- next part -------------- _______________________________________________ freebsd-current@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebsd.org"