Intel Atom S1260 (SuperServer 5017A-EF)

[Paul B. Henson]

I'm looking at a supermicro SuperServer 5017A-EF for openbsd purposes,
it's got an Intel atom S1260 SoC, Marvell 88SE9230 SATA, and i350AM2 dual
gig interfaces.

It looks like i350 support shipped in 5.2, and I'm pretty sure the
Marvell chip is AHCI compliant, so I'd think that would be ok, but I'm
leery about the SoC, I can't find any references to openbsd running on
this specific chip or any atom based SoC for that matter and I'd hate to
buy a box that didn't run openbsd well :(.

Any feedback on this particular server, this atom SoC in specific, or
even a general opinion on how well this might work out much appreciated :).

Thanks much...

[Sebastian Benoit]

Post by Paul B. Henson
I'm looking at a supermicro SuperServer 5017A-EF for openbsd purposes,
it's got an Intel atom S1260 SoC, Marvell 88SE9230 SATA, and i350AM2 dual
gig interfaces.
It looks like i350 support shipped in 5.2, and I'm pretty sure the
Marvell chip is AHCI compliant, so I'd think that would be ok, but I'm
leery about the SoC, I can't find any references to openbsd running on
this specific chip or any atom based SoC for that matter and I'd hate to
buy a box that didn't run openbsd well :(.

Don't buy this one (yet). The Marvell 88SE9230 SATA does not work.
i know cause i have one ;-)

The earlier 5017A-* machines are ok.

/B.

Post by Paul B. Henson
Any feedback on this particular server, this atom SoC in specific, or
even a general opinion on how well this might work out much appreciated :).
Thanks much...

--

[Paul B. Henson]

Post by Sebastian Benoit
Don't buy this one (yet). The Marvell 88SE9230 SATA does not work.
i know cause i have one ;-)

Arg, disappointing, but I'm glad I thought to check before buying :). Do
you know if anybody's working on it? So much for "standard" AHCI <sigh>,
does it not find it, or find it but crap out? Do all the other
components work ok? I could temporarily stick a PCI SATA card in it to
get by until the onboard SATA is supported if all the other pieces are
happy. Does anybody have any suggestions for a good/cheap 2 port SATA
PCI card that supports openbsd?

Post by Sebastian Benoit
The earlier 5017A-* machines are ok.

Hmm, the only other 5017A model I see doesn't have IPMI.

Thanks for the help...

[Sebastian Benoit]

Post by Paul B. Henson

Post by Sebastian Benoit
Don't buy this one (yet). The Marvell 88SE9230 SATA does not work.
i know cause i have one ;-)

Arg, disappointing, but I'm glad I thought to check before buying :). Do
you know if anybody's working on it?

no.

Post by Paul B. Henson
So much for "standard" AHCI <sigh>,
does it not find it, or find it but crap out? Do all the other
components work ok? I could temporarily stick a PCI SATA card in it to
get by until the onboard SATA is supported if all the other pieces are
happy. Does anybody have any suggestions for a good/cheap 2 port SATA
PCI card that supports openbsd?

Post by Sebastian Benoit
The earlier 5017A-* machines are ok.

Hmm, the only other 5017A model I see doesn't have IPMI.

sorry, i mispoke, i meant 5015A-* and they dont have a dedicated ipmi port.

anyway, dmesg attached, if someone cares. i'm not going to do anything more
with it.

OpenBSD 5.4-current (RAMDISK_CD) #107: Sun Nov 10 23:00:53 MST 2013
***@amd64.openbsd.org:/usr/src/sys/arch/amd64/compile/RAMDISK_CD
real mem = 4261289984 (4063MB)
avail mem = 4142940160 (3951MB)
mainbus0 at root
bios0 at mainbus0: SMBIOS rev. 2.7 @ 0xe94c0 (23 entries)
bios0: vendor American Megatrends Inc. version "1.0b" date 04/26/2013
bios0: Supermicro X9SBAA
acpi0 at bios0: rev 2
acpi0: sleep states S0 S4 S5
acpi0: tables DSDT FACP APIC FPDT MCFG HPET SPMI EINJ ERST HEST BERT
acpimadt0 at acpi0 addr 0xfee00000: PC-AT compat
cpu0 at mainbus0: apid 0 (boot processor)
cpu0: Intel(R) Atom(TM) CPU S1260 @ 2.00GHz, 1995.21 MHz
cpu0: FPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,CF
LUSH,DS,ACPI,MMX,FXSR,SSE,SSE2,SS,HTT,TM,PBE,SSE3,DTES64,MWAIT,DS-CPL,VMX,EST,TM
2,SSSE3,CX16,xTPR,PDCM,MOVBE,NXE,LONG,LAHF,PERF,ITSC
cpu0: 512KB 64b/line 8-way L2 cache
cpu0: apic clock running at 99MHz
cpu at mainbus0: not configured
cpu at mainbus0: not configured
cpu at mainbus0: not configured
ioapic0 at mainbus0: apid 2 pa 0xfec00000, version 20, 24 pins
acpiprt0 at acpi0: bus 0 (PCI0)
acpiprt1 at acpi0: bus 1 (PRP1)
acpiprt2 at acpi0: bus 2 (PRP2)
acpiprt3 at acpi0: bus 4 (P3P4)
pci0 at mainbus0 bus 0
pchb0 at pci0 dev 0 function 0 vendor "Intel", unknown product 0x0c75 rev 0x02
ppb0 at pci0 dev 1 function 0 vendor "Intel", unknown product 0x0c46 rev 0x02
pci1 at ppb0 bus 1
ahci0 at pci1 dev 0 function 0 vendor "Marvell", unknown product 0x9230 rev 0x10: msi, AHCI 1.2
scsibus0 at ahci0: 32 targets
ahci0: failed to stop port, cannot softreset
ahci0: failed to stop port, cannot softreset
ahci0: failed to stop port, cannot softreset
ahci0: failed to stop port, cannot softreset
ppb1 at pci0 dev 2 function 0 vendor "Intel", unknown product 0x0c47 rev 0x02
pci2 at ppb1 bus 2 vendor "Renesas", unknown product 0x0014 (class serial bus subclass USB, rev 0x03) at pci2 dev 0 function 0 not configured
ppb2 at pci0 dev 3 function 0 vendor "Intel", unknown product 0x0c48 rev 0x02
pci3 at ppb2 bus 3
ppb3 at pci3 dev 0 function 0 vendor "Newbridge", unknown product 0x8113 rev 0x01
pci4 at ppb3 bus 4
em0 at pci4 dev 0 function 0 "Intel 82541GI" rev 0x05: apic 2 int 21, address 90:e2:ba:53:11:fd
vga1 at pci4 dev 3 function 0 "Matrox MGA G200eW" rev 0x0a
wsdisplay0 at vga1 mux 1: console (80x25, vt100 emulation)
ppb4 at pci0 dev 4 function 0 vendor "Intel", unknown product 0x0c49 rev 0x02
pci5 at ppb4 bus 5
em1 at pci5 dev 0 function 0 "Intel I350" rev 0x01: msi, address 00:25:90:c7:b4:48
em2 at pci5 dev 0 function 1 "Intel I350" rev 0x01: msi, address 00:25:90:c7:b4:49
vendor "Intel", unknown product 0x0c54 (class system unknown subclass 0x06, rev 0x02) at pci0 dev 14 function 0 not configured
vendor "Intel", unknown product 0x0c59 (class system subclass miscellaneous, rev 0x02) at pci0 dev 19 function 0 not configured
vendor "Intel", unknown product 0x0c5a (class system subclass miscellaneous, rev 0x02) at pci0 dev 19 function 1 not configured
vendor "Intel", unknown product 0x0c5f (class communications subclass serial, rev 0x02) at pci0 dev 20 function 0 not configured
vendor "Intel", unknown product 0x0c60 (class bridge subclass ISA, rev 0x02) at pci0 dev 31 function 0 not configured
isa0 at mainbus0
com0 at isa0 port 0x3f8/8 irq 4: ns16550a, 16 byte fifo
com1 at isa0 port 0x2f8/8 irq 3: ns16550a, 16 byte fifo
com1: console
softraid0 at root
scsibus1 at softraid0: 256 targets
PXE boot MAC address 00:25:90:c7:b4:48, interface em1
root on rd0a swap on rd0b dump on rd0b

[Paul B. Henson]

Post by Sebastian Benoit
sorry, i mispoke, i meant 5015A-* and they dont have a dedicated ipmi port.

Oh, yah, I've actually got one of those, it's been working great. I was
actually planning on replacing it with this newer one, which supports
more memory and has more power, and reallocate it to another task.

Post by Sebastian Benoit
anyway, dmesg attached, if someone cares. i'm not going to do anything more
with it.
cpu0: apic clock running at 99MHz
cpu at mainbus0: not configured
cpu at mainbus0: not configured
cpu at mainbus0: not configured
ahci0: failed to stop port, cannot softreset

Hmm, not very promising, it didn't even initialize all four cores. The
ahci error is one of the things the freebsd driver works around, the
crappy marvell chipset breaks spec on the reset function.

Lots of "unknowns" and "unconfigured" in that dmesg :(, guess I need to
find another option. Least I found out before I bought it, thanks much
for the heads up.

[Paul B. Henson]

Post by Paul B. Henson

Post by Sebastian Benoit
sorry, i mispoke, i meant 5015A-* and they dont have a dedicated ipmi port.

Oh, yah, I've actually got one of those, it's been working great. I was
actually planning on replacing it with this newer one, which supports
more memory and has more power, and reallocate it to another task.

I forgot to mention, but the newer one also supports ECC memory, which
is a plus.

[Carsten Larsen]

Post by Paul B. Henson
Does anybody have any suggestions for a good/cheap 2 port SATA
PCI card that supports openbsd?

Maybe just buy the previous model 5015A-*? I have been running one of
those for some years now and it works like a charm. From their website I
see it has reached End-of-Life though.

HW is standard Intel. specs from FreeBSD dmesg:


Timecounter "i8254" frequency 1193182 Hz quality 0
CPU: Intel(R) Atom(TM) CPU D525 @ 1.80GHz (1807.21-MHz 686-class CPU)
Origin = "GenuineIntel" Id = 0x106ca Family = 6 Model = 1c
Stepping = 10
Features=0xbfebfbff<FPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,CLFLUSH,DTS,ACPI,MMX,FXSR,SSE,SSE2,SS,HTT,TM,PBE>
Features2=0x40e31d<SSE3,DTES64,MON,DS_CPL,TM2,SSSE3,CX16,xTPR,PDCM,MOVBE>
AMD Features=0x20100000<NX,LM>
AMD Features2=0x1<LAHF>
TSC: P-state invariant
real memory = 4294967296 (4096 MB)
avail memory = 3145445376 (2999 MB)
ACPI APIC Table: <121710 APIC1048>
FreeBSD/SMP: Multiprocessor System Detected: 4 CPUs
FreeBSD/SMP: 1 package(s) x 2 core(s) x 2 HTT threads
cpu0 (BSP): APIC ID: 0
cpu1 (AP/HT): APIC ID: 1
cpu2 (AP): APIC ID: 2
cpu3 (AP/HT): APIC ID: 3
ioapic0: Changing APIC ID to 4
ioapic0 <Version 2.0> irqs 0-23 on motherboard
kbd1 at kbdmux0
acpi0: <SMCI > on motherboard
acpi0: Overriding SCI Interrupt from IRQ 9 to IRQ 20
acpi0: [ITHREAD]
acpi0: Power Button (fixed)
acpi0: reservation of fee00000, 1000 (3) failed
acpi0: reservation of 0, a0000 (3) failed
acpi0: reservation of 100000, bff00000 (3) failed
Timecounter "ACPI-fast" frequency 3579545 Hz quality 1000
acpi_timer0: <24-bit timer at 3.579545MHz> port 0x808-0x80b on acpi0
cpu0: <ACPI CPU> on acpi0
cpu1: <ACPI CPU> on acpi0
cpu2: <ACPI CPU> on acpi0
cpu3: <ACPI CPU> on acpi0
pcib0: <ACPI Host-PCI bridge> port 0xcf8-0xcff on acpi0
pci0: <ACPI PCI bus> on pcib0
uhci0: <Intel 82801I (ICH9) USB controller> port 0xcc00-0xcc1f irq 16 at
device 26.0 on pci0
uhci0: [ITHREAD]
uhci0: LegSup = 0x2f00
usbus0 on uhci0
uhci1: <Intel 82801I (ICH9) USB controller> port 0xc880-0xc89f irq 21 at
device 26.1 on pci0
uhci1: [ITHREAD]
uhci1: LegSup = 0x2f00
usbus1 on uhci1
uhci2: <Intel 82801I (ICH9) USB controller> port 0xc800-0xc81f irq 19 at
device 26.2 on pci0
uhci2: [ITHREAD]
uhci2: LegSup = 0x2f00
usbus2 on uhci2
ehci0: <Intel 82801I (ICH9) USB 2.0 controller> mem
0xfebfbc00-0xfebfbfff irq 18 at device 26.7 on pci0
ehci0: [ITHREAD]
usbus3: EHCI version 1.0
usbus3 on ehci0
pcib1: <ACPI PCI-PCI bridge> irq 17 at device 28.0 on pci0
pci1: <ACPI PCI bus> on pcib1
pcib2: <ACPI PCI-PCI bridge> irq 17 at device 28.4 on pci0
pci2: <ACPI PCI bus> on pcib2
em0: <Intel(R) PRO/1000 Network Connection 7.3.7> port 0xdc00-0xdc1f mem
0xfe9e0000-0xfe9fffff,0xfe9dc000-0xfe9dffff irq 16 at device 0.0 on pci2
em0: Using MSIX interrupts with 3 vectors
em0: [ITHREAD]
em0: [ITHREAD]
em0: [ITHREAD]
em0: Ethernet address: 00:25:90:38:2d:e4
pcib3: <ACPI PCI-PCI bridge> irq 16 at device 28.5 on pci0
pci3: <ACPI PCI bus> on pcib3
em1: <Intel(R) PRO/1000 Network Connection 7.3.7> port 0xec00-0xec1f mem
0xfeae0000-0xfeafffff,0xfeadc000-0xfeadffff irq 17 at device 0.0 on pci3
em1: Using MSIX interrupts with 3 vectors
em1: [ITHREAD]
em1: [ITHREAD]
em1: [ITHREAD]
em1: Ethernet address: 00:25:90:38:2d:e5
uhci3: <Intel 82801I (ICH9) USB controller> port 0xc480-0xc49f irq 23 at
device 29.0 on pci0
uhci3: [ITHREAD]
uhci3: LegSup = 0x2f00
usbus4 on uhci3
uhci4: <Intel 82801I (ICH9) USB controller> port 0xc400-0xc41f irq 19 at
device 29.1 on pci0
uhci4: [ITHREAD]
uhci4: LegSup = 0x2f00
usbus5 on uhci4
uhci5: <Intel 82801I (ICH9) USB controller> port 0xc080-0xc09f irq 18 at
device 29.2 on pci0
uhci5: [ITHREAD]
uhci5: LegSup = 0x2f00
usbus6 on uhci5
ehci1: <Intel 82801I (ICH9) USB 2.0 controller> mem
0xfebfb800-0xfebfbbff irq 23 at device 29.7 on pci0
ehci1: [ITHREAD]
usbus7: EHCI version 1.0
usbus7 on ehci1
pcib4: <ACPI PCI-PCI bridge> at device 30.0 on pci0
pci4: <ACPI PCI bus> on pcib4
vgapci0: <VGA-compatible display> mem
0xfc000000-0xfcffffff,0xfdffc000-0xfdffffff,0xfe000000-0xfe7fffff irq 17
at device 4.0 on pci4
isab0: <PCI-ISA bridge> at device 31.0 on pci0
isa0: <ISA bus> on isab0
atapci0: <Intel ICH8 SATA300 controller> port
0xb480-0xb487,0xc000-0xc003,0xbc00-0xbc07,0xb880-0xb883,0xb800-0xb81f
mem 0xfebfb000-0xfebfb7ff irq 19 at device 31.2 on pci0
atapci0: [ITHREAD]
atapci0: AHCI called from vendor specific driver
atapci0: AHCI v1.20 controller with 6 3Gbps ports, PM not supported
ata2: <ATA channel> at channel 0 on atapci0
ata2: [ITHREAD]
ata3: <ATA channel> at channel 1 on atapci0
ata3: [ITHREAD]
ata4: <ATA channel> at channel 2 on atapci0
ata4: [ITHREAD]
ata5: <ATA channel> at channel 3 on atapci0
ata5: [ITHREAD]
ata6: <ATA channel> at channel 4 on atapci0
ata6: [ITHREAD]
ata7: <ATA channel> at channel 5 on atapci0
ata7: [ITHREAD]
pci0: <serial bus, SMBus> at device 31.3 (no driver attached)
acpi_button0: <Power Button> on acpi0
atrtc0: <AT realtime clock> port 0x70-0x71 irq 8 on acpi0
uart0: <16550 or compatible> port 0x3f8-0x3ff irq 4 flags 0x10 on acpi0
uart0: [FILTER]
uart1: <16550 or compatible> port 0x2f8-0x2ff irq 3 on acpi0
uart1: [FILTER]
acpi_hpet0: <High Precision Event Timer> iomem 0xfed00000-0xfed003ff on
acpi0
Timecounter "HPET" frequency 14318180 Hz quality 900
pmtimer0 on isa0
orm0: <ISA Option ROM> at iomem 0xc0000-0xc7fff pnpid ORM0000 on isa0
sc0: <System console> at flags 0x100 on isa0
sc0: VGA <16 virtual consoles, flags=0x300>
vga0: <Generic ISA VGA> at port 0x3c0-0x3df iomem 0xa0000-0xbffff on isa0
ata0: <ATA channel> at port 0x1f0-0x1f7,0x3f6 irq 14 on isa0
ata0: [ITHREAD]
ata1: <ATA channel> at port 0x170-0x177,0x376 irq 15 on isa0
ata1: [ITHREAD]
atkbdc0: <Keyboard controller (i8042)> at port 0x60,0x64 on isa0
atkbd0: <AT Keyboard> irq 1 on atkbdc0
kbd0 at atkbd0
atkbd0: [GIANT-LOCKED]
atkbd0: [ITHREAD]
ppc0: parallel port not found.
p4tcc0: <CPU Frequency Thermal Control> on cpu0
p4tcc1: <CPU Frequency Thermal Control> on cpu1
p4tcc2: <CPU Frequency Thermal Control> on cpu2
p4tcc3: <CPU Frequency Thermal Control> on cpu3
Timecounters tick every 1.000 msec
usbus0: 12Mbps Full Speed USB v1.0
usbus1: 12Mbps Full Speed USB v1.0
usbus2: 12Mbps Full Speed USB v1.0
usbus3: 480Mbps High Speed USB v2.0
usbus4: 12Mbps Full Speed USB v1.0
usbus5: 12Mbps Full Speed USB v1.0
usbus6: 12Mbps Full Speed USB v1.0
usbus7: 480Mbps High Speed USB v2.0

[Paul B. Henson]

Post by Carsten Larsen
Maybe just buy the previous model 5015A-*? I have been running one of
those for some years now and it works like a charm. From their website I
see it has reached End-of-Life though.

I've actually got one of those, as you say, I've been very happy with
it. I was looking for a newer model with more power and a separate IPMI
port. Guess I've got to keep looking...

[Paul B. Henson]

Post by Sebastian Benoit
Don't buy this one (yet). The Marvell 88SE9230 SATA does not work.
i know cause i have one ;-)

Hmm, looks like support was added in FreeBSD back in June 2012:

http://lists.freebsd.org/pipermail/svn-src-stable-9/2012-June/002131.html

so hopefully it wouldn't be to hard for somebody with the right skill
set (unfortunately not me when it comes to low level drivers <sigh>) to
tune it up for openbsd. Looking at the backstory behind that commit:

http://forums.freebsd.org/showthread.php?t=32563

evidentally marvell doesn't follow the AHCI spec very well and the
freebsd driver has workarounds for various quirks. Stupid marvell :(,
too bad supermicro didn't use a better sata chip.

Poking through the freebsd code, it looks like it has a workaround for
"Marvell controllers do not wait for readyness" which appears to be
adding in an extra delay when the controller is reset, and "Some weird
controllers do not return signature in FIS receive area. Read it from
PxSIG register.", which copies some results from a different location
overwriting what was copied in from the standard location. Other than
that, I don't see any other kludges, the rest is just the standard ahci
stuff. I see the openbsd ahci driver is completely different than the
freebsd one, so dunno how easily such workarounds could be implemented.

[Chris Cappuccio]

Post by Paul B. Henson

Post by Sebastian Benoit
Don't buy this one (yet). The Marvell 88SE9230 SATA does not work.
i know cause i have one ;-)

http://lists.freebsd.org/pipermail/svn-src-stable-9/2012-June/002131.html
so hopefully it wouldn't be to hard for somebody with the right skill
set (unfortunately not me when it comes to low level drivers <sigh>) to
http://forums.freebsd.org/showthread.php?t=32563
evidentally marvell doesn't follow the AHCI spec very well and the
freebsd driver has workarounds for various quirks. Stupid marvell :(,
too bad supermicro didn't use a better sata chip.

Not directly related to these new chips, but, check this out:

http://archives.neohapsis.com/archives/openbsd/2007-10/2418.html

It's very old. This patch did not make it into the driver and I have
no idea if those chips work through some other change, or not. Likely
not. These older chips must be really buggy pieces of shit if you have
to disable NCQ.

[Paul B. Henson]

Post by Chris Cappuccio
It's very old. This patch did not make it into the driver and I have
no idea if those chips work through some other change, or not. Likely
not. These older chips must be really buggy pieces of shit if you have
to disable NCQ.

Bleh. I can definitely see the openbsd philosophy leaning towards not
supporting crap ;). The two workarounds in freebsd for this newer marvell
sata chipset don't seem quite as egregious, but I'm not really a low level
driver guy...