Re: Slow SATA write speeds with SMB
On 2009-04-22, Whyzzi wrote: > I was happy /w the re driver too until 4.4 (I think my previous > firewall/samba share server was 4.2) > > I did mention in my original post I was watching systat vmstat, during > the post I mentioned I was watching hard drive kbyte writes. When I > decided to run out and buy the em I noticed my re was doing 4 to 6k+ > interrupt requests a second. and I was "tweaked" samba it rose even > higher via systat vmstat. I didn't mention the interrupt storm because that sounds like normal operation if you're pushing packets out, not a storm. > I no longer want to fuss the system or argue /w tico or mess with > duplex settings as it was all pointless - as I saw it already had the > solution to my problem in hand for 36+cdn $: the new em card. it looked like you already messed with duplex settings.. well, glad you found a way to fix things. the em is faster anyway. >> re -> bge > > Is that loopback or between two boxes with a switch in the middle? two boxes, with two switches between.
Re: Slow SATA write speeds with SMB
I was happy /w the re driver too until 4.4 (I think my previous firewall/samba share server was 4.2) I did mention in my original post I was watching systat vmstat, during the post I mentioned I was watching hard drive kbyte writes. When I decided to run out and buy the em I noticed my re was doing 4 to 6k+ interrupt requests a second. and I was "tweaked" samba it rose even higher via systat vmstat. I didn't mention the interrupt storm because I no longer want to fuss the system or argue /w tico or mess with duplex settings as it was all pointless - as I saw it already had the solution to my problem in hand for 36+cdn $: the new em card. Am I happy about the change? hell ya, my doorstop compaq pentium 866 writes to the 1GB WD hard drive between 18000+k every systat vmstat blip. I ain't complaining now. I only mention it here because the original poster of the thread didn't mention how his network was configured. If his nvidia+8169s phy is his samba interface I'm left to wonder if he is seeing something similar to what I was experiencing. And like a typical end user I was after results, thus instead of further testing & further listerv followup i threw money at it to make it work to a point where I was satisfied.. > rl is pretty different to re. I'm fairly happy with re(4) considering > how cheap they are. > > re -> bge Is that loopback or between two boxes with a switch in the middle? > re-box$ tcpbench bge-box > pid elapsed_ms bytes Mbps > 15569 1030 69931144 543.155 > 15569 2024 67539536 544.125 > 15569 3027 68251072 544.375 > 15569 4020 67548992 544.201 > 15569 5024 68086608 543.064 > 15569 6027 67858352 541.243 > 15569 7018 67436728 544.943 > 15569 8022 68277960 544.590 > 15569 9025 68331152 545.014 > > of course the more expensive NICs are better. bge -> re > > bge-box$ tcpbench re-box > pid elapsed_ms bytes Mbps > 31564 1007 110421616 877.232 > 31564 2009 104687432 836.663 > 31564 3007 104840696 840.406 > 31564 4007 109819488 879.435 > 31564 5007 116304656 931.369 > 31564 6007 115594504 925.682 > 31564 7007 116234288 930.805 > 31564 8007 116101120 929.739 > 31564 9006 116120392 929.893 > 3156410006 116213104 930.635 > 3156411006 115465648 924.650 > 3156412006 116225744 929.806 > 3156413006 116123152 929.915 > > (single tcp stream, opteron 146 on a supermicro aplus board > running i386 - for anyone interested, CWM on the bge was peaking > at 46). > > re0 at pci1 dev 0 function 0 "Realtek 8168" rev 0x01: RTL8168 2 (0x3800), apic 2 int 16 (irq 11), address 00:30:18:a0:6a:f6 > rgephy0 at re0 phy 7: RTL8169S/8110S PHY, rev. 2 > > bge0 at pci2 dev 3 function 0 "Broadcom BCM5704C" rev 0x10, BCM5704 B0 (0x2100): apic 2 int 8 (irq 5), address 00:30:48:58:86:40 > brgphy0 at bge0 phy 1: BCM5704 10/100/1000baseT PHY, rev. 0 > >> My ports/misc thread: >> http://marc.info/?l=openbsd-ports&m=122703016321404&w=2 >> http://marc.info/?l=openbsd-misc&m=122719611210846&w=2 Cheers & good day.
Re: Slow SATA write speeds with SMB
On 2009-04-20, Kristian Rooke wrote: > Hi Alexander, > > I was more than happy to dump the whole dmesg, but I just didn't want to put > too much into my first message. quite the reverse actually. put all the information you can think of right there in the first message. On 2009-04-21, why...@gmail.com wrote: >> rl0 at pci1 dev 5 function 0 "Realtek 8139" rev 0x10: irq 10, address >> 00:40:f4:1d:22:8c >> rlphy0 at rl0 phy 0: RTL internal PHY > >> em0 at pci1 dev 6 function 0 "Intel PRO/1000GT (82541GI)" rev 0x05: irq >> 11, >> address 00:0e:0c:81:65:5a >> nfe0 at pci0 dev 15 function 0 "NVIDIA MCP73 LAN" rev 0xa2: irq 15, >> address >> 00:1f:c6:dd:d3:64 >> rgephy0 at nfe0 phy 1: RTL8169S/8110S PHY, rev. 2 >> vga1 at pci0 dev 16 function 0 vendor "NVIDIA", unknown product 0x07e1 rev > > I have no idea how you configured your network. Which interface is pointing > to LAN where you're copying from? > > I had a 4.4 samba issue as well until I completely dropped the realtek > network cards and bought an intel GigE card. Do yourself a favor and do the > same, even if you have to disable the onboard LAN (realtek PHY - same > problem as mine) to do it. rl is pretty different to re. I'm fairly happy with re(4) considering how cheap they are. re -> bge re-box$ tcpbench bge-box pid elapsed_ms bytes Mbps 15569 1030 69931144 543.155 15569 2024 67539536 544.125 15569 3027 68251072 544.375 15569 4020 67548992 544.201 15569 5024 68086608 543.064 15569 6027 67858352 541.243 15569 7018 67436728 544.943 15569 8022 68277960 544.590 15569 9025 68331152 545.014 of course the more expensive NICs are better. bge -> re bge-box$ tcpbench re-box pid elapsed_ms bytes Mbps 31564 1007 110421616 877.232 31564 2009 104687432 836.663 31564 3007 104840696 840.406 31564 4007 109819488 879.435 31564 5007 116304656 931.369 31564 6007 115594504 925.682 31564 7007 116234288 930.805 31564 8007 116101120 929.739 31564 9006 116120392 929.893 3156410006 116213104 930.635 3156411006 115465648 924.650 3156412006 116225744 929.806 3156413006 116123152 929.915 (single tcp stream, opteron 146 on a supermicro aplus board running i386 - for anyone interested, CWM on the bge was peaking at 46). re0 at pci1 dev 0 function 0 "Realtek 8168" rev 0x01: RTL8168 2 (0x3800), apic 2 int 16 (irq 11), address 00:30:18:a0:6a:f6 rgephy0 at re0 phy 7: RTL8169S/8110S PHY, rev. 2 bge0 at pci2 dev 3 function 0 "Broadcom BCM5704C" rev 0x10, BCM5704 B0 (0x2100): apic 2 int 8 (irq 5), address 00:30:48:58:86:40 brgphy0 at bge0 phy 1: BCM5704 10/100/1000baseT PHY, rev. 0 > My ports/misc thread: > http://marc.info/?l=openbsd-ports&m=122703016321404&w=2 > http://marc.info/?l=openbsd-misc&m=122719611210846&w=2 > best I can think of is something changed between 4.3 or 4.2 (I can't > remember which version I was running before 4.4) in the realtek driver that > made the card interupt crazy. I don't see anything about "interrupt crazy" in your posts.. it looks like you were forcing settings there, most likely resulting in a duplex mismatch.
Re: Slow SATA write speeds with SMB
My 2cents worth: On Apr 20, 2009 12:58am, Kristian Rooke wrote: > OpenBSD 4.4 (GENERIC) #1021: Tue Aug 12 17:16:55 MDT 2008 ok you're running 4.4 > rl0 at pci1 dev 5 function 0 "Realtek 8139" rev 0x10: irq 10, address > 00:40:f4:1d:22:8c > rlphy0 at rl0 phy 0: RTL internal PHY > em0 at pci1 dev 6 function 0 "Intel PRO/1000GT (82541GI)" rev 0x05: irq > 11, > address 00:0e:0c:81:65:5a > nfe0 at pci0 dev 15 function 0 "NVIDIA MCP73 LAN" rev 0xa2: irq 15, > address > 00:1f:c6:dd:d3:64 > rgephy0 at nfe0 phy 1: RTL8169S/8110S PHY, rev. 2 > vga1 at pci0 dev 16 function 0 vendor "NVIDIA", unknown product 0x07e1 rev I have no idea how you configured your network. Which interface is pointing to LAN where you're copying from? I had a 4.4 samba issue as well until I completely dropped the realtek network cards and bought an intel GigE card. Do yourself a favor and do the same, even if you have to disable the onboard LAN (realtek PHY - same problem as mine) to do it. My ports/misc thread: http://marc.info/?l=openbsd-ports&m=122703016321404&w=2 http://marc.info/?l=openbsd-misc&m=122719611210846&w=2 best I can think of is something changed between 4.3 or 4.2 (I can't remember which version I was running before 4.4) in the realtek driver that made the card interupt crazy. I ran out bought the intel/em card and haven't had a problem since. agian though this is the ramblings of some lurker trying to offer his 2 cents worth of experience, thus "your milage may vary". Cheers & good luck.
Re: Slow SATA write speeds with SMB
Thank you! On 20/04/2009, frantisek holop wrote: > hmm, on Mon, Apr 20, 2009 at 05:19:05PM -0500, Tony Abernethy said that >> frantisek holop wrote: >> > all hw is unrealible to some degree, >> ... and all degrees of unreliability are equivalent? >> Methinks some people like stuff that is LESS unreliable. >> Even going so far as to make an OS that is LESS unreliable. > > not that i disagree, but sometimes, it is enough to be unreliable once. > > and reliable hw tends to make one sloppy and not think of > worst case scenarios :] > > -f > -- > want to forget all your troubles? wear tight shoes.
Re: Slow SATA write speeds with SMB
If i had the skills required, I would try.. but at this stage I have enough trouble configuring OpenBSD to perform basic tasks. So I think it may be a little out of my reach. On Tue, Apr 21, 2009 at 8:55 AM, Tyler Mace wrote: > Or write the support yourself... > > -Original Message- > From: owner-m...@openbsd.org [mailto:owner-m...@openbsd.org] On Behalf Of > Syntic > Sent: Monday, April 20, 2009 4:50 PM > To: misc@openbsd.org > Subject: Re: Slow SATA write speeds with SMB > > So from what I can tell... my chipset is crap and nobody wants to > develop/fix > AHCI support for it, so I either buy a new motherboard, or give up and use > IDE rather than AHCI? :) > > > Marco Peereboom wrote: > > > > On Tue, Apr 21, 2009 at 12:06:18AM +0200, frantisek holop wrote: > >> hmm, on Mon, Apr 20, 2009 at 02:48:15PM -0500, Marco Peereboom said that > >> > > some of the devs really need to give up their thinkpads and start > >> > > buying cheap msi or other stuff with amd and nvidia monstrosities :] > >> > > >> > Right, dealing with hardware that is unreliable on a daily basis is > >> > exactly what I need. I mean I am totally not busy at all so what is a > >> > random reboot here and there anyway. > >> > >> all hw is unrealible to some degree, that's why we make backups. > >> i am sure there are lenovo models that pack some shitty components.. > >> my thinkpad had it's own peculiarities (apm not working was one of > them). > > > > I don't use stinkpads either ;-) > > > >> and once again, for the record. that was a joke. there is a smiley. > >> geez. i know it's monday but loosen up a bit > > > > You need to go write some acpi code and tell me again to loosen up. > > Once you have taken a few bites of that shittaco tell me again how funny > > this is. > > > >> > >> -f > >> -- > >> windows error: 004 erroneous error. nothing wrong. > > > > > > > > -- > View this message in context: > http://www.nabble.com/Slow-SATA-write-speeds-with-SMB-tp23130953p23146398.html > Sent from the openbsd user - misc mailing list archive at Nabble.com.
Re: Slow SATA write speeds with SMB
Or write the support yourself... -Original Message- From: owner-m...@openbsd.org [mailto:owner-m...@openbsd.org] On Behalf Of Syntic Sent: Monday, April 20, 2009 4:50 PM To: misc@openbsd.org Subject: Re: Slow SATA write speeds with SMB So from what I can tell... my chipset is crap and nobody wants to develop/fix AHCI support for it, so I either buy a new motherboard, or give up and use IDE rather than AHCI? :) Marco Peereboom wrote: > > On Tue, Apr 21, 2009 at 12:06:18AM +0200, frantisek holop wrote: >> hmm, on Mon, Apr 20, 2009 at 02:48:15PM -0500, Marco Peereboom said that >> > > some of the devs really need to give up their thinkpads and start >> > > buying cheap msi or other stuff with amd and nvidia monstrosities :] >> > >> > Right, dealing with hardware that is unreliable on a daily basis is >> > exactly what I need. I mean I am totally not busy at all so what is a >> > random reboot here and there anyway. >> >> all hw is unrealible to some degree, that's why we make backups. >> i am sure there are lenovo models that pack some shitty components.. >> my thinkpad had it's own peculiarities (apm not working was one of them). > > I don't use stinkpads either ;-) > >> and once again, for the record. that was a joke. there is a smiley. >> geez. i know it's monday but loosen up a bit > > You need to go write some acpi code and tell me again to loosen up. > Once you have taken a few bites of that shittaco tell me again how funny > this is. > >> >> -f >> -- >> windows error: 004 erroneous error. nothing wrong. > > > -- View this message in context: http://www.nabble.com/Slow-SATA-write-speeds-with-SMB-tp23130953p23146398.htm l Sent from the openbsd user - misc mailing list archive at Nabble.com.
Re: Slow SATA write speeds with SMB
So from what I can tell... my chipset is crap and nobody wants to develop/fix AHCI support for it, so I either buy a new motherboard, or give up and use IDE rather than AHCI? :) Marco Peereboom wrote: > > On Tue, Apr 21, 2009 at 12:06:18AM +0200, frantisek holop wrote: >> hmm, on Mon, Apr 20, 2009 at 02:48:15PM -0500, Marco Peereboom said that >> > > some of the devs really need to give up their thinkpads and start >> > > buying cheap msi or other stuff with amd and nvidia monstrosities :] >> > >> > Right, dealing with hardware that is unreliable on a daily basis is >> > exactly what I need. I mean I am totally not busy at all so what is a >> > random reboot here and there anyway. >> >> all hw is unrealible to some degree, that's why we make backups. >> i am sure there are lenovo models that pack some shitty components.. >> my thinkpad had it's own peculiarities (apm not working was one of them). > > I don't use stinkpads either ;-) > >> and once again, for the record. that was a joke. there is a smiley. >> geez. i know it's monday but loosen up a bit > > You need to go write some acpi code and tell me again to loosen up. > Once you have taken a few bites of that shittaco tell me again how funny > this is. > >> >> -f >> -- >> windows error: 004 erroneous error. nothing wrong. > > > -- View this message in context: http://www.nabble.com/Slow-SATA-write-speeds-with-SMB-tp23130953p23146398.html Sent from the openbsd user - misc mailing list archive at Nabble.com.
Re: Slow SATA write speeds with SMB
On Tue, Apr 21, 2009 at 12:29:20AM +0200, frantisek holop wrote: > hmm, on Mon, Apr 20, 2009 at 05:19:05PM -0500, Tony Abernethy said that > > frantisek holop wrote: > > > all hw is unrealible to some degree, > > ... and all degrees of unreliability are equivalent? > > Methinks some people like stuff that is LESS unreliable. > > Even going so far as to make an OS that is LESS unreliable. > > not that i disagree, but sometimes, it is enough to be unreliable once. > > and reliable hw tends to make one sloppy and not think of > worst case scenarios :] That is the biggest load of bullshit i have heard in a long time > > -f > -- > want to forget all your troubles? wear tight shoes.
Re: Slow SATA write speeds with SMB
frantisek holop wrote: > hmm, on Mon, Apr 20, 2009 at 05:19:05PM -0500, Tony Abernethy > said that > > frantisek holop wrote: > > > all hw is unrealible to some degree, > > ... and all degrees of unreliability are equivalent? > > Methinks some people like stuff that is LESS unreliable. > > Even going so far as to make an OS that is LESS unreliable. > > not that i disagree, but sometimes, it is enough to be > unreliable once. > > and reliable hw tends to make one sloppy and not think of > worst case scenarios :] > > -f > -- > want to forget all your troubles? wear tight shoes. > The voice of experience?
Re: Slow SATA write speeds with SMB
hmm, on Mon, Apr 20, 2009 at 05:19:05PM -0500, Tony Abernethy said that > frantisek holop wrote: > > all hw is unrealible to some degree, > ... and all degrees of unreliability are equivalent? > Methinks some people like stuff that is LESS unreliable. > Even going so far as to make an OS that is LESS unreliable. not that i disagree, but sometimes, it is enough to be unreliable once. and reliable hw tends to make one sloppy and not think of worst case scenarios :] -f -- want to forget all your troubles? wear tight shoes.
Re: Slow SATA write speeds with SMB
frantisek holop wrote: > all hw is unrealible to some degree, ... and all degrees of unreliability are equivalent? Methinks some people like stuff that is LESS unreliable. Even going so far as to make an OS that is LESS unreliable.
Re: Slow SATA write speeds with SMB
On Tue, Apr 21, 2009 at 12:06:18AM +0200, frantisek holop wrote: > hmm, on Mon, Apr 20, 2009 at 02:48:15PM -0500, Marco Peereboom said that > > > some of the devs really need to give up their thinkpads and start > > > buying cheap msi or other stuff with amd and nvidia monstrosities :] > > > > Right, dealing with hardware that is unreliable on a daily basis is > > exactly what I need. I mean I am totally not busy at all so what is a > > random reboot here and there anyway. > > all hw is unrealible to some degree, that's why we make backups. > i am sure there are lenovo models that pack some shitty components.. > my thinkpad had it's own peculiarities (apm not working was one of them). I don't use stinkpads either ;-) > and once again, for the record. that was a joke. there is a smiley. > geez. i know it's monday but loosen up a bit You need to go write some acpi code and tell me again to loosen up. Once you have taken a few bites of that shittaco tell me again how funny this is. > > -f > -- > windows error: 004 erroneous error. nothing wrong.
Re: Slow SATA write speeds with SMB
hmm, on Mon, Apr 20, 2009 at 02:48:15PM -0500, Marco Peereboom said that > > some of the devs really need to give up their thinkpads and start > > buying cheap msi or other stuff with amd and nvidia monstrosities :] > > Right, dealing with hardware that is unreliable on a daily basis is > exactly what I need. I mean I am totally not busy at all so what is a > random reboot here and there anyway. all hw is unrealible to some degree, that's why we make backups. i am sure there are lenovo models that pack some shitty components.. my thinkpad had it's own peculiarities (apm not working was one of them). and once again, for the record. that was a joke. there is a smiley. geez. i know it's monday but loosen up a bit -f -- windows error: 004 erroneous error. nothing wrong.
Re: Slow SATA write speeds with SMB
hmm, on Mon, Apr 20, 2009 at 01:33:25PM -0600, Bob Beck said that > > some of the devs really need to give up their thinkpads and start > > buying cheap msi or other stuff with amd and nvidia monstrosities :] > > > > Yeah... you're like... the guy who is sits outside the estwing > factory hitting his balls with an estwing hammer - telling everyone > who comes in and out that it fucking hurts like hell and they shold > give up on those nails and things and start hitting their balls so > they can fix the hammer so it hurts less... > > We'll get right on that.. > > Hope your balls get better soon. Bob, always the funny guy. if you can't let a joke go, you are the one hitting your balls. -f -- bad is never good until worse happens.
Re: Slow SATA write speeds with SMB
On Mon, Apr 20, 2009 at 01:33:25PM -0600, Bob Beck wrote: > > some of the devs really need to give up their thinkpads and start > > buying cheap msi or other stuff with amd and nvidia monstrosities :] > > > > Yeah... you're like... the guy who is sits outside the estwing > factory hitting his balls with an estwing hammer - telling everyone > who comes in and out that it fucking hurts like hell and they shold > give up on those nails and things and start hitting their balls so > they can fix the hammer so it hurts less... > > We'll get right on that.. > > Hope your balls get better soon. estwing? i think not. more like some low grade foundry in China.. -- Christopher Linn | By no means shall either the CEC System Administrator II | or MTU be held in any way liable Center for Experimental Computation | for any opinions or conjecture I Michigan Technological University | hold to or imply to hold herein.
Re: Slow SATA write speeds with SMB
> some of the devs really need to give up their thinkpads and start > buying cheap msi or other stuff with amd and nvidia monstrosities :] Right, dealing with hardware that is unreliable on a daily basis is exactly what I need. I mean I am totally not busy at all so what is a random reboot here and there anyway.
Re: Slow SATA write speeds with SMB
> some of the devs really need to give up their thinkpads and start > buying cheap msi or other stuff with amd and nvidia monstrosities :] > Yeah... you're like... the guy who is sits outside the estwing factory hitting his balls with an estwing hammer - telling everyone who comes in and out that it fucking hurts like hell and they shold give up on those nails and things and start hitting their balls so they can fix the hammer so it hurts less... We'll get right on that.. Hope your balls get better soon.
Re: Slow SATA write speeds with SMB
hmm, on Mon, Apr 20, 2009 at 09:30:58PM +1000, Kristian Rooke said that > ahci0 at pci0 dev 14 function 0 "NVIDIA MCP73 AHCI" rev 0xa2: irq 11, AHCI MCP77 is also unsupported. but there was a patch floating about on tech@ regarding ahci. my notebook is quite unusable at the moment so i can't test patches. it has 44k interrupts a second and everything takes forever. some of the devs really need to give up their thinkpads and start buying cheap msi or other stuff with amd and nvidia monstrosities :] -f -- raising your voice does not reinforce your argument.
Re: Slow SATA write speeds with SMB
The 2 SATA drives are currently connected to SATA port 1 & 2 (so the BIOS tells me). I just connected another SATA drive to port number 4 and the same occured for that drive too. There are no further details following the scsibus0 line. ahci0 at pci0 dev 14 function 0 "NVIDIA MCP73 AHCI" rev 0xa2: irq 11, AHCI 1.1 ahci0: failed to start command DMA on port 0, disabling ahci0: failed to start command DMA on port 2, disabling ahci0: failed to start command DMA on port 3, disabling <- scsibus0 at ahci0: 32 targets, initiator 32 I found some information about a bug with my Nvidia chipset and FreeBSD, which refers to SATA drives - http://www.nabble.com/i386-129542:-FreeBSD-7.1-RC1-installer-cannot-find-WD-SATA-hard-drive-with-MCP73M01H1-mainboard-(MCP73-SATA-controller)-td20928904.html Do you think there could be a relationship there (even though it's a different plaform? On Mon, Apr 20, 2009 at 8:23 PM, Anathae Townsend wrote: > I'm not an expert by any means when it comes to OpenBSD, > AHCI, or SATA, but here are some shots in the dark. > > Does your machine have four SATA ports on it? Can you > identify which of the four ports your two SATA drives are > plugged into? Can you add additional SATA drives and see > if these errors are resolved or multiplied? > > First guess is that the AHCI method for deciding which ports > have SATA devices attached is not working properly on your > motherboard/chipset. Second guess is that the chipset or > motherboard has some problems with DMA happening the way > that the ahci device expects it to work. > > Are there any sd devices listed after the scsibus0 line? > > something like this? > > scsibus1 at umass0: 2 targets, initiator 0 > sd0 at scsibus1 targ 1 lun 0: 4.08> SCSI0 0/direct removable > sd0: drive offline > sd1 at scsibus1 targ 1 lun 1: 4.08> SCSI0 0/direct removable > sd1: drive offline > sd2 at scsibus1 targ 1 lun 2: 4.08> SCSI0 0/direct removable > sd2: drive offline > sd3 at scsibus1 targ 1 lun 3: 4.08> SCSI0 0/direct removable > sd3: drive offline > > > Kristian Rooke Wrote > > Thanks for the suggestions. > > > > I checked the BIOS configuration and it appears that the SATA > > controller was > > set to IDE (not sure how that happened). I have now set it to AHCI, but > > I am > > seeing another error in dmesg > > > > ahci0 at pci0 dev 14 function 0 "NVIDIA MCP73 AHCI" rev 0xa2: irq 11, > > AHCI > > 1.1 > > ahci0: failed to start command DMA on port 0, disabling > > ahci0: failed to start command DMA on port 2, disabling > > scsibus0 at ahci0: 32 targets, initiator 32 > > > > Does this mean that AHCI on my m/b is not supported in OpenBSD? > > Any other thoughts?
Re: Slow SATA write speeds with SMB
I'm not an expert by any means when it comes to OpenBSD, AHCI, or SATA, but here are some shots in the dark. Does your machine have four SATA ports on it? Can you identify which of the four ports your two SATA drives are plugged into? Can you add additional SATA drives and see if these errors are resolved or multiplied? First guess is that the AHCI method for deciding which ports have SATA devices attached is not working properly on your motherboard/chipset. Second guess is that the chipset or motherboard has some problems with DMA happening the way that the ahci device expects it to work. Are there any sd devices listed after the scsibus0 line? something like this? scsibus1 at umass0: 2 targets, initiator 0 sd0 at scsibus1 targ 1 lun 0: SCSI0 0/direct removable sd0: drive offline sd1 at scsibus1 targ 1 lun 1: SCSI0 0/direct removable sd1: drive offline sd2 at scsibus1 targ 1 lun 2: SCSI0 0/direct removable sd2: drive offline sd3 at scsibus1 targ 1 lun 3: SCSI0 0/direct removable sd3: drive offline Kristian Rooke Wrote > Thanks for the suggestions. > > I checked the BIOS configuration and it appears that the SATA > controller was > set to IDE (not sure how that happened). I have now set it to AHCI, but > I am > seeing another error in dmesg > > ahci0 at pci0 dev 14 function 0 "NVIDIA MCP73 AHCI" rev 0xa2: irq 11, > AHCI > 1.1 > ahci0: failed to start command DMA on port 0, disabling > ahci0: failed to start command DMA on port 2, disabling > scsibus0 at ahci0: 32 targets, initiator 32 > > Does this mean that AHCI on my m/b is not supported in OpenBSD? > Any other thoughts?
Re: Slow SATA write speeds with SMB
Thanks for the suggestions. I checked the BIOS configuration and it appears that the SATA controller was set to IDE (not sure how that happened). I have now set it to AHCI, but I am seeing another error in dmesg ahci0 at pci0 dev 14 function 0 "NVIDIA MCP73 AHCI" rev 0xa2: irq 11, AHCI 1.1 ahci0: failed to start command DMA on port 0, disabling ahci0: failed to start command DMA on port 2, disabling scsibus0 at ahci0: 32 targets, initiator 32 Does this mean that AHCI on my m/b is not supported in OpenBSD? Any other thoughts? On Mon, Apr 20, 2009 at 7:40 PM, Anathae Townsend wrote: > [Quote] > pciide1 at pci0 dev 14 function 0 "NVIDIA MCP73 AHCI" rev 0xa2: DMA > (unsupported), channel 0 wired to native-PCI, channel 1 wired to native-PCI > [end quote] > > The AHCI implementation on your mb is not supported by the version of > OpenBSD > you are using. > > That, or it is configured to something other than true AHCI by the bios. > I'd > suggest checking to see if you have mode options for it in your bios and > see > if that moves it from being a wd? drive (driven by pciide) to a sd? drive > (driven by the AHCI driver)
Re: Slow SATA write speeds with SMB
Just noticed this, thought I'd quickly give you the following tip : On Mon, Apr 20, 2009 at 03:40:35AM -0600, Anathae Townsend wrote: | [Quote] | pciide1 at pci0 dev 14 function 0 "NVIDIA MCP73 AHCI" rev 0xa2: DMA | (unsupported), channel 0 wired to native-PCI, channel 1 wired to native-PCI | [end quote] Try forcing the pciide driver to use DMA by setting flags to 0x0001. See pciide(4) for details (and the caveats listed there). Procede with care to avoid dataloss (make backups etc), but this has helped me a couple of times already. To set this, boot -c and in UKC use 'change pciide' to alter the flags value (keep all other things as they are). If this works for your machine, you can use config(8) from your booted machine to configure this permanently (remember to re-do this step after each upgrade). Paul 'WEiRD' de Weerd -- >[<++>-]<+++.>+++[<-->-]<.>+++[<+ +++>-]<.>++[<>-]<+.--.[-] http://www.weirdnet.nl/
Re: Slow SATA write speeds with SMB
[Quote] pciide1 at pci0 dev 14 function 0 "NVIDIA MCP73 AHCI" rev 0xa2: DMA (unsupported), channel 0 wired to native-PCI, channel 1 wired to native-PCI [end quote] The AHCI implementation on your mb is not supported by the version of OpenBSD you are using. That, or it is configured to something other than true AHCI by the bios. I'd suggest checking to see if you have mode options for it in your bios and see if that moves it from being a wd? drive (driven by pciide) to a sd? drive (driven by the AHCI driver)
Re: Slow SATA write speeds with SMB
Kristian Rooke wrote: > Hi Alexander, > > I was more than happy to dump the whole dmesg, but I just didn't want to put > too much into my first message. I have yet to see anyone complaining about too much information. ;-) Nevertheless, AFAICS (which is rather limited), it seems your wd2 disk (which I assume is the problematic one) is attached as an IDE device but is missing the corresponding wd0/wd1 line: wd1(pciide0:0:1): using PIO mode 4, Ultra-DMA mode 5 My guess would be that the mainboard is using some (possibly crappy) IDE/SATA converter that, at least from OpenBSD's point of view, does not support anything but the basics, causing the bad result. Regarding FTP/SMB differences, I guess that could come from differences in the protocols and how they do their disk access etc. As noted, my knowledge is not great at these kind of things, so ACK's, NAK's and/or corrections would still be appreciated. :-) /Alexander > > Please find the full dmesg below: > > OpenBSD 4.4 (GENERIC) #1021: Tue Aug 12 17:16:55 MDT 2008 > dera...@i386.openbsd.org:/usr/src/sys/arch/i386/compile/GENERIC > cpu0: Intel(R) Core(TM)2 Duo CPU E7200 @ 2.53GHz ("GenuineIntel" 686-class) > 2.54 GHz > cpu0: > FPU,V86,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,CFLUSH,DS,ACPI,MMX,FXSR,SSE,SSE2,SS,HTT,TM,SBF,SSE3,MWAIT,DS-CPL,EST,TM2,CX16,xTPR > cpu0: unknown i686 EBL_CR_POWERON value 3 (0x424c) > real mem = 2010673152 (1917MB) > avail mem = 1935548416 (1845MB) > mainbus0 at root > bios0 at mainbus0: AT/286+ BIOS, date 09/02/08, BIOS32 rev. 0 @ 0xf1df0, > SMBIOS rev. 2.5 @ 0xf (50 entries) > bios0: vendor Phoenix Technologies, LTD version "ASUS P5N-EM HDMI ACPI BIOS > Revision 0401" date 09/02/2008 > bios0: ASUSTeK Computer INC. P5N-EM HDMI > apm0 at bios0: Power Management spec V1.2 (slowidle) > apm0: AC on, battery charge unknown > acpi at bios0 function 0x0 not configured > pcibios0 at bios0: rev 3.0 @ 0xf/0xde74 > pcibios0: PCI IRQ Routing Table rev 1.0 @ 0xfddb0/192 (10 entries) > pcibios0: PCI Exclusive IRQs: 5 10 11 > pcibios0: no compatible PCI ICU found > pcibios0: Warning, unable to fix up PCI interrupt routing > pcibios0: PCI bus #4 is the last bus > bios0: ROM list: 0xc/0xde00 0xd/0x4000! 0xd4000/0x1000 > cpu0 at mainbus0 > cpu0: EST: unknown system bus clock > pci0 at mainbus0 bus 0: configuration mode 1 (no bios) > pchb0 at pci0 dev 0 function 0 vendor "NVIDIA", unknown product 0x07c1 rev > 0xa2 > "NVIDIA MCP73 Memory" rev 0xa2 at pci0 dev 0 function 1 not configured > "NVIDIA MCP73 Memory" rev 0xa1 at pci0 dev 1 function 0 not configured > "NVIDIA MCP73 Memory" rev 0xa1 at pci0 dev 1 function 1 not configured > "NVIDIA MCP73 Memory" rev 0xa1 at pci0 dev 1 function 2 not configured > "NVIDIA MCP73 Memory" rev 0xa1 at pci0 dev 1 function 3 not configured > "NVIDIA MCP73 Memory" rev 0xa1 at pci0 dev 1 function 4 not configured > "NVIDIA MCP73 Memory" rev 0xa1 at pci0 dev 1 function 5 not configured > "NVIDIA MCP73 Memory" rev 0xa1 at pci0 dev 1 function 6 not configured > "NVIDIA MCP73 Memory" rev 0xa1 at pci0 dev 2 function 0 not configured > pcib0 at pci0 dev 3 function 0 "NVIDIA MCP73 ISA" rev 0xa2 > nviic0 at pci0 dev 3 function 1 "NVIDIA MCP73 SMBus" rev 0xa1 > iic0 at nviic0 > spdmem0 at iic0 addr 0x50: 1GB DDR2 SDRAM non-parity PC2-6400CL5 > spdmem1 at iic0 addr 0x52: 1GB DDR2 SDRAM non-parity PC2-6400CL5 > iic1 at nviic0 > "NVIDIA MCP73 Memory" rev 0xa1 at pci0 dev 3 function 2 not configured > "NVIDIA MCP73 Memory" rev 0xa1 at pci0 dev 3 function 4 not configured > ohci0 at pci0 dev 4 function 0 "NVIDIA MCP73 USB" rev 0xa1: irq 10, version > 1.0, legacy support > ehci0 at pci0 dev 4 function 1 "NVIDIA MCP73 USB" rev 0xa1: irq 11 > usb0 at ehci0: USB revision 2.0 > uhub0 at usb0 "NVIDIA EHCI root hub" rev 2.00/1.00 addr 1 > pciide0 at pci0 dev 8 function 0 "NVIDIA MCP73 IDE" rev 0xa1: DMA, channel 0 > configured to compatibility, channel 1 configured to compatibility > wd0 at pciide0 channel 0 drive 0: > wd0: 16-sector PIO, LBA48, 305245MB, 625142448 sectors > wd1 at pciide0 channel 0 drive 1: > wd1: 16-sector PIO, LBA48, 715404MB, 1465149168 sectors > wd0(pciide0:0:0): using PIO mode 4, Ultra-DMA mode 5 > wd1(pciide0:0:1): using PIO mode 4, Ultra-DMA mode 5 > pciide0: channel 1 ignored (disabled) > azalia0 at pci0 dev 9 function 0 "NVIDIA MCP73 HD Audio" rev 0xa1: irq 5 > azalia0: /usr/src/sys/dev/pci/azalia.c/1348 invalid PCM format: 0x > azalia0: codec[s]: Realtek ALC883, NVIDIA/0x8001, using Realtek ALC883 > audio0 at azalia0 > ppb0 at pci0 dev 10 function 0 "NVIDIA MCP73 PCIE" rev 0xa1 > pci1 at ppb0 bus 1 > rl0 at pci1 dev 5 function 0 "Realtek 8139" rev 0x10: irq 10, address > 00:40:f4:1d:22:8c > rlphy0 at rl0 phy 0: RTL internal PHY > em0 at pci1 dev 6 function 0 "Intel PRO/1000GT (82541GI)" rev 0x05: irq 11, > address 00:0e:0c:81:65:5a > ppb1 at pci0 dev 11 function 0 "NVIDIA MCP73 PCIE" rev 0xa1 > pci2 at ppb1 bus 2 > ppb2 at pci0 dev 12 function
Re: Slow SATA write speeds with SMB
: 00 0x0010: BAR mem 32bit addr: 0xed00 0x0014: BAR mem prefetchable 64bit addr: 0xd000 0x001c: BAR mem 64bit addr: 0xee00 0x0024: BAR empty () 0x0028: Cardbus CIS: 0x002c: Subsystem Vendor ID: 1043 Product ID: 82ae 0x0030: Expansion ROM Base Address: 0x0038: 0x003c: Interrupt Pin: 01 Line: 0a Min Gnt: 00 Max Lat: 00 0x0048: Capability 0x01: Power Management 0x0050: Capability 0x05: Message Signaled Interrupts (MSI) 1:5:0: Realtek 8139 0x: Vendor ID: 10ec Product ID: 8139 0x0004: Command: 0007 Status ID: 0290 0x0008: Class: 02 Subclass: 00 Interface: 00 Revision: 10 0x000c: BIST: 00 Header Type: 00 Latency Timer: 20 Cache Line Size: 00 0x0010: BAR io addr: 0xcc00 0x0014: BAR mem 32bit addr: 0xefbff000 0x0018: BAR empty () 0x001c: BAR empty () 0x0020: BAR empty () 0x0024: BAR empty () 0x0028: Cardbus CIS: 0x002c: Subsystem Vendor ID: a0a0 Product ID: 0027 0x0030: Expansion ROM Base Address: 0x0038: 0x003c: Interrupt Pin: 01 Line: 0a Min Gnt: 20 Max Lat: 40 0x0050: Capability 0x01: Power Management 1:6:0: Intel PRO/1000GT (82541GI) 0x: Vendor ID: 8086 Product ID: 107c 0x0004: Command: 0007 Status ID: 0230 0x0008: Class: 02 Subclass: 00 Interface: 00 Revision: 05 0x000c: BIST: 00 Header Type: 00 Latency Timer: 20 Cache Line Size: 08 0x0010: BAR mem 32bit addr: 0xefbc 0x0014: BAR mem 32bit addr: 0xefba 0x0018: BAR io addr: 0xcf00 0x001c: BAR empty () 0x0020: BAR empty () 0x0024: BAR empty () 0x0028: Cardbus CIS: 0x002c: Subsystem Vendor ID: 8086 Product ID: 1376 0x0030: Expansion ROM Base Address: efb8 0x0038: 0x003c: Interrupt Pin: 01 Line: 0b Min Gnt: ff Max Lat: 00 0x00dc: Capability 0x01: Power Management 0x00e4: Capability 0x07: PCI-X Jonathan Gray wrote: > > Well you don't have dma on wd2. > Include the output of pcidump -v and I'll try cook up a diff. > > On Sun, Apr 19, 2009 at 11:16:55PM -0700, Syntic wrote: >> Hi there, >> >> I recently installed OpenBSD on one of my servers and I have noticed that >> I >> am experiencing slow SATA write speeds when using SMB to copy files >> across >> my network. >> >> I currently have 1xSATA disk & 2xPATA disks in my server. >> When I copy files across my network (GigE) to my PATA disk, I am seeing >> approx 600Mbps, however when I copy to the SATA disk I only see approx >> 125Mbps. >> I also noticed that the CPU utilization (for SMBd) is at about 90% when >> copying to the SATA disk, but only hovers around 10% when copying the >> PATA >> disk. >> I thought this may have been a driver issue with SATA, therefore causing >> the >> increased CPU when copying. But I copied some files across to the same >> SATA >> disk using FTP instead and the CPU stayed quite low and the write speeds >> were approx 600Mbps. >> >> Does anybody have any ideas what may be causing the issues? >> >> I have provided some info from dmesg below which may be of use. >> >> cpu0: Intel(R) Core(TM)2 Duo CPU E7200 @ 2.53GHz ("GenuineIntel" >> 686-class) >> 2.54 GHz >> bios0 at mainbus0: AT/286+ BIOS, date 09/02/08, BIOS32 rev. 0 @ 0xf1df0, >> SMBIOS rev. 2.5 @ 0xf (50 entries) >> bios0: vendor Phoenix Technologies, LTD version "ASUS P5N-EM HDMI ACPI >> BIOS >> Revision 0401" date 09/02/2008 >> bios0: ASUSTeK Computer INC. P5N-EM HDMI >> spdmem0 at iic0 addr 0x50: 1GB DDR2 SDRAM non-parity PC2-6400CL5 >> spdmem1 at iic0 addr 0x52: 1GB DDR2 SDRAM non-parity PC2-6400CL5 >> pciide0 at pci0 dev 8 function 0 "NVIDIA MCP73 IDE" rev 0xa1: DMA, >> channel 0 >> configured to compatibility, channel 1 configured to compatibility >> pciide1 at pci0 dev 14 function 0 "NVIDIA MCP73 AHCI" rev 0xa2: DMA >> (unsupported), channel 0 wired to native-PCI, channel 1 wired to >> native-PCI >> wd0 at pciide0 channel 0 drive 0: >> wd0: 16-sector PIO, LBA48, 305245MB, 625142448 sectors >> wd1 at pciide0 channel 0 drive 1: >> wd1: 16-sector PIO, LBA48, 715404MB, 1465149168 sectors >> wd0(pciide0:0:0): using PIO mode 4, Ultra-DMA mode 5 >> wd1(pciide0:0:1): using PIO mode 4, Ultra-DMA mode 5 >> wd2 at pciide1 channel 0 drive 0: >> wd2: 16-sector PIO, LBA48, 1430799MB, 2930277168 sectors >> >&
Re: Slow SATA write speeds with SMB
Hi Alexander, I was more than happy to dump the whole dmesg, but I just didn't want to put too much into my first message. Please find the full dmesg below: OpenBSD 4.4 (GENERIC) #1021: Tue Aug 12 17:16:55 MDT 2008 dera...@i386.openbsd.org:/usr/src/sys/arch/i386/compile/GENERIC cpu0: Intel(R) Core(TM)2 Duo CPU E7200 @ 2.53GHz ("GenuineIntel" 686-class) 2.54 GHz cpu0: FPU,V86,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,CFLUSH,DS,ACPI,MMX,FXSR,SSE,SSE2,SS,HTT,TM,SBF,SSE3,MWAIT,DS-CPL,EST,TM2,CX16,xTPR cpu0: unknown i686 EBL_CR_POWERON value 3 (0x424c) real mem = 2010673152 (1917MB) avail mem = 1935548416 (1845MB) mainbus0 at root bios0 at mainbus0: AT/286+ BIOS, date 09/02/08, BIOS32 rev. 0 @ 0xf1df0, SMBIOS rev. 2.5 @ 0xf (50 entries) bios0: vendor Phoenix Technologies, LTD version "ASUS P5N-EM HDMI ACPI BIOS Revision 0401" date 09/02/2008 bios0: ASUSTeK Computer INC. P5N-EM HDMI apm0 at bios0: Power Management spec V1.2 (slowidle) apm0: AC on, battery charge unknown acpi at bios0 function 0x0 not configured pcibios0 at bios0: rev 3.0 @ 0xf/0xde74 pcibios0: PCI IRQ Routing Table rev 1.0 @ 0xfddb0/192 (10 entries) pcibios0: PCI Exclusive IRQs: 5 10 11 pcibios0: no compatible PCI ICU found pcibios0: Warning, unable to fix up PCI interrupt routing pcibios0: PCI bus #4 is the last bus bios0: ROM list: 0xc/0xde00 0xd/0x4000! 0xd4000/0x1000 cpu0 at mainbus0 cpu0: EST: unknown system bus clock pci0 at mainbus0 bus 0: configuration mode 1 (no bios) pchb0 at pci0 dev 0 function 0 vendor "NVIDIA", unknown product 0x07c1 rev 0xa2 "NVIDIA MCP73 Memory" rev 0xa2 at pci0 dev 0 function 1 not configured "NVIDIA MCP73 Memory" rev 0xa1 at pci0 dev 1 function 0 not configured "NVIDIA MCP73 Memory" rev 0xa1 at pci0 dev 1 function 1 not configured "NVIDIA MCP73 Memory" rev 0xa1 at pci0 dev 1 function 2 not configured "NVIDIA MCP73 Memory" rev 0xa1 at pci0 dev 1 function 3 not configured "NVIDIA MCP73 Memory" rev 0xa1 at pci0 dev 1 function 4 not configured "NVIDIA MCP73 Memory" rev 0xa1 at pci0 dev 1 function 5 not configured "NVIDIA MCP73 Memory" rev 0xa1 at pci0 dev 1 function 6 not configured "NVIDIA MCP73 Memory" rev 0xa1 at pci0 dev 2 function 0 not configured pcib0 at pci0 dev 3 function 0 "NVIDIA MCP73 ISA" rev 0xa2 nviic0 at pci0 dev 3 function 1 "NVIDIA MCP73 SMBus" rev 0xa1 iic0 at nviic0 spdmem0 at iic0 addr 0x50: 1GB DDR2 SDRAM non-parity PC2-6400CL5 spdmem1 at iic0 addr 0x52: 1GB DDR2 SDRAM non-parity PC2-6400CL5 iic1 at nviic0 "NVIDIA MCP73 Memory" rev 0xa1 at pci0 dev 3 function 2 not configured "NVIDIA MCP73 Memory" rev 0xa1 at pci0 dev 3 function 4 not configured ohci0 at pci0 dev 4 function 0 "NVIDIA MCP73 USB" rev 0xa1: irq 10, version 1.0, legacy support ehci0 at pci0 dev 4 function 1 "NVIDIA MCP73 USB" rev 0xa1: irq 11 usb0 at ehci0: USB revision 2.0 uhub0 at usb0 "NVIDIA EHCI root hub" rev 2.00/1.00 addr 1 pciide0 at pci0 dev 8 function 0 "NVIDIA MCP73 IDE" rev 0xa1: DMA, channel 0 configured to compatibility, channel 1 configured to compatibility wd0 at pciide0 channel 0 drive 0: wd0: 16-sector PIO, LBA48, 305245MB, 625142448 sectors wd1 at pciide0 channel 0 drive 1: wd1: 16-sector PIO, LBA48, 715404MB, 1465149168 sectors wd0(pciide0:0:0): using PIO mode 4, Ultra-DMA mode 5 wd1(pciide0:0:1): using PIO mode 4, Ultra-DMA mode 5 pciide0: channel 1 ignored (disabled) azalia0 at pci0 dev 9 function 0 "NVIDIA MCP73 HD Audio" rev 0xa1: irq 5 azalia0: /usr/src/sys/dev/pci/azalia.c/1348 invalid PCM format: 0x azalia0: codec[s]: Realtek ALC883, NVIDIA/0x8001, using Realtek ALC883 audio0 at azalia0 ppb0 at pci0 dev 10 function 0 "NVIDIA MCP73 PCIE" rev 0xa1 pci1 at ppb0 bus 1 rl0 at pci1 dev 5 function 0 "Realtek 8139" rev 0x10: irq 10, address 00:40:f4:1d:22:8c rlphy0 at rl0 phy 0: RTL internal PHY em0 at pci1 dev 6 function 0 "Intel PRO/1000GT (82541GI)" rev 0x05: irq 11, address 00:0e:0c:81:65:5a ppb1 at pci0 dev 11 function 0 "NVIDIA MCP73 PCIE" rev 0xa1 pci2 at ppb1 bus 2 ppb2 at pci0 dev 12 function 0 "NVIDIA MCP73 PCIE" rev 0xa1 pci3 at ppb2 bus 3 ppb3 at pci0 dev 13 function 0 "NVIDIA MCP73 PCIE" rev 0xa1 pci4 at ppb3 bus 4 pciide1 at pci0 dev 14 function 0 "NVIDIA MCP73 AHCI" rev 0xa2: DMA (unsupported), channel 0 wired to native-PCI, channel 1 wired to native-PCI pciide1: using irq 11 for native-PCI interrupt wd2 at pciide1 channel 0 drive 0: wd2: 16-sector PIO, LBA48, 1430799MB, 2930277168 sectors atapiscsi0 at pciide1 channel 0 drive 1 scsibus0 at atapiscsi0: 2 targets, initiator 7 cd0 at scsibus0 targ 0 lun 0: ATAPI 5/cdrom removable pciide1: channel 1 ignored (not responding; disabled or no drives?) nfe0 at pci0 dev 15 function 0 "NVIDIA MCP73 LAN" rev 0xa2: irq 15, address 00:1f:c6:dd:d3:64 rgephy0 at nfe0 phy 1: RTL8169S/8110S PHY, rev. 2 vga1 at pci0 dev 16 function 0 vendor "NVIDIA", unknown product 0x07e1 rev 0xa2 wsdisplay0 at vga1 mux 1: console (80x25, vt100 emulation) wsdisplay0: screen 1-5 added (80x25, vt100 emulation) drm at vga1
Re: Slow SATA write speeds with SMB
Well you don't have dma on wd2. Include the output of pcidump -v and I'll try cook up a diff. On Sun, Apr 19, 2009 at 11:16:55PM -0700, Syntic wrote: > Hi there, > > I recently installed OpenBSD on one of my servers and I have noticed that I > am experiencing slow SATA write speeds when using SMB to copy files across > my network. > > I currently have 1xSATA disk & 2xPATA disks in my server. > When I copy files across my network (GigE) to my PATA disk, I am seeing > approx 600Mbps, however when I copy to the SATA disk I only see approx > 125Mbps. > I also noticed that the CPU utilization (for SMBd) is at about 90% when > copying to the SATA disk, but only hovers around 10% when copying the PATA > disk. > I thought this may have been a driver issue with SATA, therefore causing the > increased CPU when copying. But I copied some files across to the same SATA > disk using FTP instead and the CPU stayed quite low and the write speeds > were approx 600Mbps. > > Does anybody have any ideas what may be causing the issues? > > I have provided some info from dmesg below which may be of use. > > cpu0: Intel(R) Core(TM)2 Duo CPU E7200 @ 2.53GHz ("GenuineIntel" 686-class) > 2.54 GHz > bios0 at mainbus0: AT/286+ BIOS, date 09/02/08, BIOS32 rev. 0 @ 0xf1df0, > SMBIOS rev. 2.5 @ 0xf (50 entries) > bios0: vendor Phoenix Technologies, LTD version "ASUS P5N-EM HDMI ACPI BIOS > Revision 0401" date 09/02/2008 > bios0: ASUSTeK Computer INC. P5N-EM HDMI > spdmem0 at iic0 addr 0x50: 1GB DDR2 SDRAM non-parity PC2-6400CL5 > spdmem1 at iic0 addr 0x52: 1GB DDR2 SDRAM non-parity PC2-6400CL5 > pciide0 at pci0 dev 8 function 0 "NVIDIA MCP73 IDE" rev 0xa1: DMA, channel 0 > configured to compatibility, channel 1 configured to compatibility > pciide1 at pci0 dev 14 function 0 "NVIDIA MCP73 AHCI" rev 0xa2: DMA > (unsupported), channel 0 wired to native-PCI, channel 1 wired to native-PCI > wd0 at pciide0 channel 0 drive 0: > wd0: 16-sector PIO, LBA48, 305245MB, 625142448 sectors > wd1 at pciide0 channel 0 drive 1: > wd1: 16-sector PIO, LBA48, 715404MB, 1465149168 sectors > wd0(pciide0:0:0): using PIO mode 4, Ultra-DMA mode 5 > wd1(pciide0:0:1): using PIO mode 4, Ultra-DMA mode 5 > wd2 at pciide1 channel 0 drive 0: > wd2: 16-sector PIO, LBA48, 1430799MB, 2930277168 sectors > > Thanks, > Kristian > > -- > View this message in context: > http://www.nabble.com/Slow-SATA-write-speeds-with-SMB-tp23130953p23130953.html > Sent from the openbsd user - misc mailing list archive at Nabble.com.
Re: Slow SATA write speeds with SMB
Syntic wrote: > Hi there, > > I recently installed OpenBSD on one of my servers and I have noticed that I > am experiencing slow SATA write speeds when using SMB to copy files across > my network. > > I currently have 1xSATA disk & 2xPATA disks in my server. > When I copy files across my network (GigE) to my PATA disk, I am seeing > approx 600Mbps, however when I copy to the SATA disk I only see approx > 125Mbps. > I also noticed that the CPU utilization (for SMBd) is at about 90% when > copying to the SATA disk, but only hovers around 10% when copying the PATA > disk. > I thought this may have been a driver issue with SATA, therefore causing the > increased CPU when copying. But I copied some files across to the same SATA > disk using FTP instead and the CPU stayed quite low and the write speeds > were approx 600Mbps. > > Does anybody have any ideas what may be causing the issues? > > I have provided some info from dmesg below which may be of use. sata disks normally (if not always) show up as sd's. You have 3 wd's. That makes me confused and lead to believe you might be running a very old OpenBSD version, something I cannot conclude from the partial dmesg you included. Since you obviously have some issues you do not know how to handle, ALWAYS INCLUDE THE ENTIRE DMESG and do not make any assumptions of what would be necessary or not. Cheers, Alexander > > cpu0: Intel(R) Core(TM)2 Duo CPU E7200 @ 2.53GHz ("GenuineIntel" 686-class) > 2.54 GHz > bios0 at mainbus0: AT/286+ BIOS, date 09/02/08, BIOS32 rev. 0 @ 0xf1df0, > SMBIOS rev. 2.5 @ 0xf (50 entries) > bios0: vendor Phoenix Technologies, LTD version "ASUS P5N-EM HDMI ACPI BIOS > Revision 0401" date 09/02/2008 > bios0: ASUSTeK Computer INC. P5N-EM HDMI > spdmem0 at iic0 addr 0x50: 1GB DDR2 SDRAM non-parity PC2-6400CL5 > spdmem1 at iic0 addr 0x52: 1GB DDR2 SDRAM non-parity PC2-6400CL5 > pciide0 at pci0 dev 8 function 0 "NVIDIA MCP73 IDE" rev 0xa1: DMA, channel 0 > configured to compatibility, channel 1 configured to compatibility > pciide1 at pci0 dev 14 function 0 "NVIDIA MCP73 AHCI" rev 0xa2: DMA > (unsupported), channel 0 wired to native-PCI, channel 1 wired to native-PCI > wd0 at pciide0 channel 0 drive 0: > wd0: 16-sector PIO, LBA48, 305245MB, 625142448 sectors > wd1 at pciide0 channel 0 drive 1: > wd1: 16-sector PIO, LBA48, 715404MB, 1465149168 sectors > wd0(pciide0:0:0): using PIO mode 4, Ultra-DMA mode 5 > wd1(pciide0:0:1): using PIO mode 4, Ultra-DMA mode 5 > wd2 at pciide1 channel 0 drive 0: > wd2: 16-sector PIO, LBA48, 1430799MB, 2930277168 sectors > > Thanks, > Kristian
Slow SATA write speeds with SMB
Hi there, I recently installed OpenBSD on one of my servers and I have noticed that I am experiencing slow SATA write speeds when using SMB to copy files across my network. I currently have 1xSATA disk & 2xPATA disks in my server. When I copy files across my network (GigE) to my PATA disk, I am seeing approx 600Mbps, however when I copy to the SATA disk I only see approx 125Mbps. I also noticed that the CPU utilization (for SMBd) is at about 90% when copying to the SATA disk, but only hovers around 10% when copying the PATA disk. I thought this may have been a driver issue with SATA, therefore causing the increased CPU when copying. But I copied some files across to the same SATA disk using FTP instead and the CPU stayed quite low and the write speeds were approx 600Mbps. Does anybody have any ideas what may be causing the issues? I have provided some info from dmesg below which may be of use. cpu0: Intel(R) Core(TM)2 Duo CPU E7200 @ 2.53GHz ("GenuineIntel" 686-class) 2.54 GHz bios0 at mainbus0: AT/286+ BIOS, date 09/02/08, BIOS32 rev. 0 @ 0xf1df0, SMBIOS rev. 2.5 @ 0xf (50 entries) bios0: vendor Phoenix Technologies, LTD version "ASUS P5N-EM HDMI ACPI BIOS Revision 0401" date 09/02/2008 bios0: ASUSTeK Computer INC. P5N-EM HDMI spdmem0 at iic0 addr 0x50: 1GB DDR2 SDRAM non-parity PC2-6400CL5 spdmem1 at iic0 addr 0x52: 1GB DDR2 SDRAM non-parity PC2-6400CL5 pciide0 at pci0 dev 8 function 0 "NVIDIA MCP73 IDE" rev 0xa1: DMA, channel 0 configured to compatibility, channel 1 configured to compatibility pciide1 at pci0 dev 14 function 0 "NVIDIA MCP73 AHCI" rev 0xa2: DMA (unsupported), channel 0 wired to native-PCI, channel 1 wired to native-PCI wd0 at pciide0 channel 0 drive 0: wd0: 16-sector PIO, LBA48, 305245MB, 625142448 sectors wd1 at pciide0 channel 0 drive 1: wd1: 16-sector PIO, LBA48, 715404MB, 1465149168 sectors wd0(pciide0:0:0): using PIO mode 4, Ultra-DMA mode 5 wd1(pciide0:0:1): using PIO mode 4, Ultra-DMA mode 5 wd2 at pciide1 channel 0 drive 0: wd2: 16-sector PIO, LBA48, 1430799MB, 2930277168 sectors Thanks, Kristian -- View this message in context: http://www.nabble.com/Slow-SATA-write-speeds-with-SMB-tp23130953p23130953.html Sent from the openbsd user - misc mailing list archive at Nabble.com.