Slashdot Mirror

← Back to Domains

Domain: vanrein.org

Stories and comments across the archive that link to vanrein.org.

Comments · 22

  1. Re:RAID(?) for RAM by trayrace · · Score: 1 · on Reliability of Computer Memory?

    Well, if you are using Linux, you could probably use this. And yes, it's just cheaper for the manufacturer to throw the broken modules away instead of replacing the defective RAM chips.

  2. Re:Workaround bad memory howto (linux only) by Anonymous Coward · · Score: 0 · on Reliability of Computer Memory?

    That's the 01d sk001 wasteful way, here's the new clean way http://rick.vanrein.org/linux/badram/(Linux only)

  3. Re:RAID(?) for RAM by Mr+Z · · Score: 1 · on Reliability of Computer Memory?

    Actually, it's not uncommon for large RAM arrays to have "row repair" and "column repair". The RAM array has more rows and columns than are required to provide the rated capacity. During manufacturing testing, they remap some of these to work around defects and increase yield. So, if you're still seeing faults after the production tests have mapped away the obvious faults, I think you're signing yourself up for a bit of pain.

    As I recall memtest86 would output a report of the failing locations that you could give to the Linux kernel, telling it what locations to use and to avoid.

    Seems like a colossal waste of time to me. If you're not concerned about performance, then it's a question of how much your time's worth. You can get 2GB for $23 and probably less if you spent more than 5 seconds looking like I did. If you spend more than a couple hours futzing with your flaky system to remap all your bad RAM, even if your time is only worth minimum wage, you quickly cross the "worth it" threshold.

  4. Re:What is the point? by Ant+P. · · Score: 1 · on Japanese Scientists Develop Long-Life Flash Memory

    you also don't have to discard the whole chip if a single cell fails - like you do if a single cell fails in a RAM chip.

    Says who?

  5. Re:Memtest86 by Wonko+the+Sane · · Score: 1 · on Computer Voodoo?
    There's code in Linux to allow it to work with known-bad RAM, you just need to tell it the address range to avoid and the VM subsystem marks that as not for use, kind of like a disk drive mapping out a bad sector.

    I used that before, because it sucks to to throw away 4 GB of ram. It's a seperate patch, though. My kernel was all kinds of haphazard: badram + reiser4 + binary nvidia + vesafb-tng
  6. Lotsa cheap ram! by imroy · · Score: 3, Informative · on Firms Get Away with Selling Untested DRAM

    Solution:

    1. Compile a Linux kernel with the BadRAM patch.
    2. Run Memtest86+ to get a list of bad areas.
    3. Profit!... erm, I mean a Linux system with lots of cheap ram!
  7. If you're stuck with one of these... by Anonymous Coward · · Score: 5, Informative · on Firms Get Away with Selling Untested DRAM

    Here is the obligitory Memtest86 post. It's a great program, and chances are that you might already have a copy on your Linux install CD depending on the distro. There are even kernel patches that allow you to avoid the bad bits if they are isolated enough.

  8. Re:Already being done... by Ed+Avis · · Score: 5, Interesting · on Faulty Chips Might Just be 'Good Enough'

    If it's just RAM, and the defects are just the odd bad location here and there, then BadRAM could help. The main difficulty is getting the support loaded early enough, e.g. at installation time. DIMMs could have their own defect list and a way for the motherboard to query it.

  9. Re:Sweet. by Ed+Avis · · Score: 1 · on Infineon To Pay $160 Million For Fixing RAM Prices

    Why bother? Why not just mark the few bad addresses and stop using them? It doesn't matter if your one gibibit memory chip is actually 0.9999997 Gib because a few 4k pages have to be mapped out by the OS. See BadRAM.

  10. Imperfect electronics by bill_mcgonigle · · Score: 1 · on Why We Fall Apart

    You don't buy a multi cpu system with 2 cpus dead on arrival

    I suspect IBM's eFuse is at least partially a way to improve yields. If we don't need 'perfect' electronics they might get cheaper. Linux can work around bad RAM chips, too.

  11. Re:Obligatory... by pantherace · · Score: 1 · on Mars Rover Spirit Back Online

    Another Obligatory:Bad RAM Patch for Linux

  12. Re:WEB/FTP by emptybody · · Score: 4, Informative · on Paul Mockapetris On The Future of DNS

    Actually, there already are provisions for this.
    The SRV record, defined in rfc2782, is used to store a HOST:PORT pair

    When will browsers (or anything else for that matter) start supporting this???

    Here is a (possibly outdated) list of software that supports the SRV record.

  13. Look here. by Anonymous Coward · · Score: 0 · on FreeBSD Looking for People with Lots of RAM

    http://rick.vanrein.org/linux/badram/

    So far as I know, no BSD (well, doublecheck NetBSD) has implemented such a thing, probably mostly out of the 'treat your systems as you would production machines' attitude. So hey, use Linux on your box with bad RAM, and FreeBSD on your *good* hardware. ;)

  14. Badram by RainbowSix · · Score: 1 · on Salvaging Defective DRAM

    This is probably a good place to mention badram, the linux kernel patch that lets you use slightly defective memory modules.

    You can use memtest to generate a list of bad areas in ram, and the badram patch reserves those blocks of memory on boot such that nobody can ever use them, effectively giving you a working stick of ram, only a little bit smaller than it is marked for.

    If you're like me, you have a couple of cheapo sticks from who knows where that don't exactly work, and this patch is perfect for reviving those sticks.

  15. Using broken RAM with Linux - BadRAM, memtest86 by Anonymous Coward · · Score: 0, Redundant · on Salvaging Defective DRAM

    BadRAM is a Linux kernel patch for defective RAM modules support. With defective RAM, I mean RAM which has some bits wrong at some (known) addresses.

    Normally, such RAM is considered useless and thrown away; the larger RAMs get, the higher the chances of failing addresses. With ever growing RAM sizes, it would therefore be pleasant to have an alternative to discarding of defective RAM chips.

    By the way, memtest86 is a free x86 memory diagnostic, which can be configured to produce BadRAM patterns

  16. Alternatively, you could use the... by Ari+Rahikkala · · Score: 5, Informative · on Salvaging Defective DRAM

    BadRAM patch.

  17. bad ram patch for linux by Anonymous Coward · · Score: 4, Interesting · on Salvaging Defective DRAM

    Summary: This page proposes an approach to support RAMs with defective addresses, This may open interesting business perspectives, where those RAMs can be sold under a white label for less money rather than discarded of without any profit.

    the url is:

    http://rick.vanrein.org/linux/badram/

  18. Re:Interesting... but no by glitchvern · · Score: 3, Informative · on Mirror Listings Though TXT DNS Records?
    DNS is supposed to provide nameIP mappings, in an application-neutral fashion.

    Then what are these mx records being used to relay mail. That's not exactly application neutral. You can place any random text you want to in a dns record. If you do a host -a you will occasionally come across people who have thrown completely random shit into their dns record. The A record is what is used to resolve a hostname to an ip address. Here is a list of other record types from nslookup(1):
    A the host's Internet address.
    CNAME the canonical name for an alias.
    HINFO the host CPU and operating system type.
    MX the mail exchanger.
    NS the name server for the named zone.
    SOA the domain's ``start-of-authority'' information.
    TXT the text information.
    WKS the supported well-known services.

    Other types (ANY, AXFR, MB, MD, MF, NULL) are described in the RFC-1035 document.

    I seem to recall something about jabber using a dns record similar to mx. A quick google search comes up with this page that claims both ldap and jabber use srv records and that jabber formerly used the mx record.

    So yeah, dns, more than just ip addresses and hostnames.
  19. Re:Geez, a MS mouse works only on windows. by nesthigh · · Score: 1, Offtopic · on Microsoft Intellimice and Bluetooth Issues?
    You may want to try these patches for your keyboard. If you like using console much, this kernel patch is pretty cool. You may need to play with the keycodes a bit, but either will work, and you won't need to wait for Logitech to write itouch software.

    next

  20. Wha...? by xenoweeno · · Score: 5, Funny · on Judge Says Paypal's Arbitration Rules Unfair

    There can't be that many people who think that PayPal sucks!

  21. Linux ``bad ram'' patch by lightray · · Score: 1 · on Cool Linux Tricks With Atlas

    Why bother replacing the failed DIMM module when you can just install the ``badram'' kernel patch that will let Linux work around bad bits in a memory module? Don't let a few bad bits spoil an entire module... (-:

  22. Re:The "Windows snapshot" is FUD... by tempest303 · · Score: 3 · on Alan Cox on a Chip
    Well, BSODs aren't FUD for me; they're quite factual. I'm forced to dual boot b between Linux and Windows, and I have *never* had the Linux kernel die on me. I can't, however, say the same thing for the Win2k side of things. While it's light years beyond NT in terms of stability, it's still not the rock that Linux is and has been, at least for me.

    As for Linux performing better when RAM craps out? I beg to differ! Check out BadRAM. (that's http://rick.vanrein.org/linux/badram/ for the goatsex-wary) While it won't prevent problems from crashing if some addresses go bad while the machine is booted, after the very next reboot, the RAM you have will be "good" all over again!

    BadRAM was featured in a /. article a while back as well http://www.slashdot.org/articles/00/10/25/1448233. shtml