October 2006 - openSUSE AMD64 - openSUSE Mailing Lists

IOMMU...PCI memory hole...MTRR...I give up.
by David W. Hankins 26 May '07

26 May '07

I have an MSI K8D-Master-F motherboard with two Opteron 244's. It recently got retasked as a desktop machine due to another system's failure...I thought the little ATI Rage built into the motherboard would make more than a sufficient 2d desktop type framebuffer, and as far as other stuff inside this box... this should be a pretty kick ass, high performance workstation. But I can literally watch the screen redraw if I switch virtual desktops. Painfully slow. Thinking this was just some crippled built-in video bug, I threw in an old nVidia card we had lying around in one of the regular PCI slots. Slightly slower, if you can believe it. I think this: mtrr: type mismatch for e5000000,1000000 old: uncachable new: write-combining And of course this: $ cat /proc/mtrr reg00: base=0xc0000000 (3072MB), size=1024MB: uncachable, count=1 reg01: base=0x00000000 ( 0MB), size=4096MB: write-back, count=1 Has something to do with it (and may also explain why I'm getting less than stellar performance out of other PCI devices, such as the RAID array that has a 128MB memory region the driver directly reads and writes on). The above is with the nVidia PCI card inserted, the built-in ATI card would also emit a similar mtrr rejection message, just the address is different, and the system would only list 512MB uncachable without the nVidia. Also notice that there's 4GB installed in this machine, in 2 2GB DIMMs installed in one bank together. And yet the BIOS map: BIOS-provided physical RAM map: BIOS-e820: 0000000000000000 - 000000000009fc00 (usable) BIOS-e820: 000000000009fc00 - 00000000000a0000 (reserved) BIOS-e820: 00000000000e0000 - 0000000000100000 (reserved) BIOS-e820: 0000000000100000 - 00000000bfff0000 (usable) BIOS-e820: 00000000bfff0000 - 00000000bffff000 (ACPI data) BIOS-e820: 00000000bffff000 - 00000000c0000000 (ACPI NVS) BIOS-e820: 00000000ff7c0000 - 0000000100000000 (reserved) Lists nothing beyond the 4GB mark where that memory might reasonably have been moved to. Assuming this is just a neglectful BIOS, I tried setting 'mem=4G' and 'memmap=1G@4G' kernel options, to define the 1GB 'hole' I presume is being placed here, and which got me this added line to dmesg: user: 0000000100000000 - 0000000140000000 (usable) But still only 3GB available. To add even more insult to rising injury, I noticed while looking through dmesg that the IOMMU is being disabled. It appears the value being advertised by the CPU's: CPU 0: aperture @ 1b80000000 size 128 MB Is being rejected because it lies (WELL) above the 4GB mark. I've been going through archives and I'm not finding anything that looks like actionable advice. The latest BIOS MSI's webpage lists for this motherboard is 1.1: already installed. It has no option for 'pci hole: software'. The only options I'm finding are memory bank interleaving (which I tried disabling), and 'Disabled/Best-Fit/Absolute' settings for the IOMMU, as well as its aperture size (128M, which I might increase if it would be used rather than ignored...). One post in the archive that matched on motherboard make and model looks confused to me, because he refers to his BIOS as AWARD 2.0, but the only BIOS MSI puts out for this board is AMI (versioned 1.1). In summary what I'd like to know is: 1) Where is the 'go fast' button? re: pci video that's slower than even isa video should be (and presumably similar performance problems on other PCI devices). 2) How do I get the last 25% of my memory back? 3) How do I get the system to put the IOMMU somewhere in the range it stole under 4G (so Linux can use it)? Can Linux move this on its own accord? Thanks in advance for any and all help. -- David W. Hankins "If you don't do it right the first time, Software Engineer you'll just have to do it again." Internet Systems Consortium, Inc. -- Jack T. Hankins

5 13

Major chornic compile problem
by Dan Sawyer 02 Nov '06

02 Nov '06

Hey all - Has anyone run into a major compile stumbling block because of a poorly-compiled libx11.a? Even when building programs with then --enable-static flag in suse 10.1 64bit I get this error on almost everything. I've searched for weeks, but haven't been able to find a fix anywhere online, and I'm very reluctant to attempt to hand-complie Xorg. Here's the error: ve/usr/lib64/gcc/x86_64-suse-linux/4.1.0/../../../../x86_64-suse-linux/bin/ld : /usr/lib64/libX11.a(ChProp.o): relocation R_X86_64_32 against `a local symbol' can not be used when making a shared object; recompile with -fPIC /usr/lib64/libX11.a: could not read symbols: Bad value collect2: ld returned 1 exit status --- ANY help at all would be much appreciated. Thanks! -Dan Sawyer ArtisticWhispers Productions

7 9

Suse Linux 10.1, Acer Aspire, wrong memory size !!
by guru shashi 31 Oct '06

31 Oct '06

Hello all, I have been using Suse Linux 10.1 (x84_64) on an Acer Aspire 5002 (amd64). I upgraded my RAM recently to 1 GB. But after booting if i check the meminfo ... I was stunned to see only ~ 876 MB shown in under /proc/meminfo. >From Googling ... I found out that HIGHMEM is enabled upto 4GB and this uses up 128 MB for some virtual memory mapping. However this is applicable only to x86 and not my laptop. Output of /proc/meminfo: MemTotal: 897788 kB ~ 876.74609375 MemFree: 297824 kB Buffers: 49688 kB Cached: 387296 kB SwapCached: 0 kB Active: 258160 kB Inactive: 289436 kB HighTotal: 0 kB HighFree: 0 kB LowTotal: 897788 kB LowFree: 297824 kB SwapTotal: 1060280 kB SwapFree: 1060280 kB Dirty: 84 kB Writeback: 0 kB Mapped: 184180 kB Slab: 32384 kB CommitLimit: 1509172 kB Committed_AS: 252224 kB PageTables: 5480 kB VmallocTotal: 34359738367 kB VmallocUsed: 9260 kB VmallocChunk: 34359728159 kB HugePages_Total: 0 HugePages_Free: 0 Hugepagesize: 2048 kB The on board AGP card on the laptop consumes 64MB. Following is the information I see from dmesg: Linux version 2.6.16.13-4-default (geeko@buildhost) (gcc version 4.1.0 (SUSE Linux)) #1 Wed May 3 04:53:23 UTC 2006 BIOS-provided physical RAM map: BIOS-e820: 0000000000000000 - 000000000009f400 (usable) BIOS-e820: 000000000009f400 - 00000000000a0000 (reserved) BIOS-e820: 00000000000dc000 - 0000000000100000 (reserved) BIOS-e820: 0000000000100000 - 000000003bef0000 (usable) BIOS-e820: 000000003bef0000 - 000000003befa000 (ACPI data) BIOS-e820: 000000003befa000 - 000000003bf00000 (ACPI NVS) BIOS-e820: 000000003bf00000 - 0000000040000000 (reserved) BIOS-e820: 00000000fff00000 - 0000000100000000 (reserved) ACPI: RSDP (v000 PTLTD ) @ 0x00000000000f7f60 ACPI: RSDT (v001 PTLTD RSDT 0x06040000 LTP 0x00000000) @ 0x000000003bef61be ACPI: FADT (v001 SiS 755F 0x06040000 PTL 0x000f4240) @ 0x000000003bef9e5f ACPI: SSDT (v001 PTLTD POWERNOW 0x06040000 LTP 0x00000001) @ 0x000000003bef9ed3 ACPI: MADT (v001 PTLTD APIC 0x06040000 LTP 0x00000000) @ 0x000000003bef9f88 ACPI: BOOT (v001 PTLTD $SBFTBL$ 0x06040000 LTP 0x00000001) @ 0x000000003bef9fd8 ACPI: DSDT (v001 PTLTD 755 0x06040000 MSFT 0x0100000e) @ 0x0000000000000000 On node 0 totalpages: 241214 DMA zone: 3122 pages, LIFO batch:0 DMA32 zone: 238092 pages, LIFO batch:31 Normal zone: 0 pages, LIFO batch:0 HighMem zone: 0 pages, LIFO batch:0 ... .... ... ... Inode-cache hash table entries: 65536 (order: 7, 524288 bytes) Memory: 894636k/981952k available (1728k kernel code, 86400k reserved, 767k data, 164k init) Calibrating delay using timer specific routine.. 3203.81 BogoMIPS (lpj=6407638) Security Framework v1.0.0 initialized Mount-cache hash table entries: 256 CPU: L1 I Cache: 64K (64 bytes/line), D cache 64K (64 bytes/line) CPU: L2 Cache: 1024K (64 bytes/line) CPU: AMD Turion(tm) 64 Mobile Technology ML-30 stepping 02 checking if image is initramfs... it is Freeing initrd memory: 2456k freed Is there anyway I can use the complete 1GB of RAM .. Thanks in Advance, -- Best Regardz, Guru

1 0

ACPI.
by Walter Kerkhofs 30 Oct '06

30 Oct '06

Hi, When shutting down the computer I always saw a warning in red about acpid, so i decided to do something about it. I ran as root /usr/sbin/sensors-detect, and choose to use the option to configure for the ISA port. This than generated the configuration lines for my system, wich I have to copy to two seperate files. The first line is this: #I2C module options alias char-major-89 i2c-dev And I have to copy this in /etc/modprobe.conf, but besides this file there is also this file /etc/modprobe.conf.local. This confused me because in /etc/modprobe.conf is a line that says to put local configuration in /etc/modprobe.conf.laocal. Where must I put the generated lines in ? Because I now have a warning that says in red: acpid lm-sensors. And where do I have to put these lines: #I2C adapter drivers modprobe i2c-viapro modprobe i2c-isa #I2C chip drivers modprobe eeprom #Warning the required module smbus-arp is not currently installed on your system. #For status of 2.6 kernel ports see htpp://secure.netroedge.com/~Im78/supported.html #If driver is built-in to the kernel, or unavailable, comment out the following line. modprobe smbus-arp modprobe w83627hf #sleep 2 # optional /usr/bin/sensors -s # recommended Again I have to put these lines in /etc/rc, I found these files: /etc/rc.d.README /etc/rc.splash /etc/rc.status But no /etc/rc. Desktop SUSE Linux 10.0 x86_64: Processor: AMD Athlon 64 3000+ 256 MB DDR. Memory: 512 MB DDR. Graphics card: Nvidia GeForce FX 5700 LE 256 MB DDR. Motherboard: Asus K8V Deluxe. Thanks in advance. Greetings, Walter Kerkhofs -- www.opensuse.org www.kde.org http://amarok.kde.org www.digikam.org http://nl.openoffice.org

3 6

SWAT under 64-bit SuSE 10.0 and 10.1
by Constantine 'Gus' Fantanas 27 Oct '06

27 Oct '06

Is the SWAT package (SAMBA graphical configurator) available for the 64-bit SuSE 10.0 and 10.1? I don't think it is available from any repository. CF -- Running 64-bit Linux on AMD64

2 1

Missing db41-32bit-4.1.25-91.2.x86_64.rpm on install media?
by Darren Davis 26 Oct '06

26 Oct '06

Hello all, Looking at the install media for SLES 10 x86_64 there seems to be a missing RPM. If you look at the RPMs for Berkeley DB, you will see we provide a 32bit version for db40 and db42, but not for db41. db40-32bit-4.0.14-165.2.x86_64.rpm db40-4.0.14-165.2.x86_64.rpm db40-devel-4.0.14-165.2.x86_64.rpm db41-4.1.25-91.2.x86_64.rpm db41-devel-4.1.25-91.2.x86_64.rpm db42-32bit-4.2.52-20.2.x86_64.rpm db42-4.2.52-20.2.x86_64.rpm db42-devel-4.2.52-20.2.x86_64.rpm I was wondering if this was deliberate or an accident? If deliberate, what was the reason? If an accident, where does a customer find the official version? Thanks, Darren

1 0

32 to 64 bit
by James Lockie 25 Oct '06

25 Oct '06

Does this seem reasonable? http://blogs.adobe.com/penguin.swf/2006/10/whats_so_difficult_64bit_editi.h…

2 1

about K8 sampling function
by eshsf 23 Oct '06

23 Oct '06

Hi, I am examining about performance sampling with K8(AMD64) now. I know that there is PEBS in Intel Pentium4. And I read "BIOS and Kernel Developer's Guide(#26094) '10 Performance Monitoring'" and "Programmer's Manual Vol2(#24593) '13.3 Performance Optimization'" to examine whether K8(AMD64) implement it. However, there was not the description like it. Do anyone know whether there is the function that is an equivalent or the same as it in K8(AMD64)? eshsf

2 2

Dual Core S939, AM2 or - ugh - Core 2 Duo?
by Harald Milz 17 Oct '06

17 Oct '06

Hi, I'm planning to upgrade my 3200+ system to a dual core CPU, either S939 on my existing board which runs fine, AM2 (which would require changing mobo, memory and graphics card) or a Core 2 Duo (same). Any pros or cons from a Linux standpoint? I know the usual hardware reviews like tomshardware or Anandtech but they say little about Linux. Any while we're at it, which AM2 or 775 board has a usable SPDIF input? I would like to spare my sound card ... checked all the usual suspects here as well but no luck. -- Tax reform means "Don't tax you, don't tax me, tax that fellow behind the tree." -- Russell Long

1 0

Windows media / AMD64
by Olav Pettershagen 11 Oct '06

11 Oct '06

Hello there, Did anyone else notice? I thought that watching Windows media with 64 bit versions of xine and kaffeine was out of the question because the codecs is 32 bit, but after a recent upgrade from packman I CAN watch e.g. wmv on my 64 bit. I don't think codecs are upgraded/changed so have the 64 packages been tweaked in some way to be able to use 32 bit codecs? -- Olav http://home.online.no/~olav.pet/current_view.jpg

2 2