Re: Weird file corruption?
On Wed, Jan 13, 1999 at 05:26:40PM -0500, Brian Feldman wrote: ... How could it be memory when it's written to disk, extracted, then after a nearly full build read again? Why would it extract completely the first time with no errors? I had this exact same problem when evaluating pentium motherboards a while back. One of my (parity!) simms was marginal [later verified with a simm checker], but it was not noticed until after I made one corrupt archive [and deleted the originals]. Luckily, both the simm and the motherboard were still returnable. This also verified for me that most Intel chipsets for pentium do not use parity even if available. -- Zach Heilig z...@uffdaonline.net / Zach Heilig z...@gaffaneys.com To Unsubscribe: send mail to majord...@freebsd.org with unsubscribe freebsd-current in the body of the message
Re: Weird file corruption?
On Fri, 15 Jan 1999, Zach Heilig wrote: On Wed, Jan 13, 1999 at 05:26:40PM -0500, Brian Feldman wrote: ... How could it be memory when it's written to disk, extracted, then after a nearly full build read again? Why would it extract completely the first time with no errors? I had this exact same problem when evaluating pentium motherboards a while back. One of my (parity!) simms was marginal [later verified with a simm checker], but it was not noticed until after I made one corrupt archive [and deleted the originals]. Luckily, both the simm and the motherboard were still returnable. Good to know I am looking in the right place. I switched my timings from Turbo to Normal (I have 2 EDO/2 FP), and now it seems to past tests, but I think I did see a few bytes get corrupted in an image in netscape... ah well, so you'd recommend finding someone with a SIMM checker? This also verified for me that most Intel chipsets for pentium do not use parity even if available. -- Zach Heilig z...@uffdaonline.net / Zach Heilig z...@gaffaneys.com Brian Feldman_ __ ___ ___ ___ gr...@unixhelp.org _ __ ___ | _ ) __| \ http://www.freebsd.org/ _ __ ___ | _ \__ \ |) | FreeBSD: The Power to Serve! _ __ ___ _ |___/___/___/ To Unsubscribe: send mail to majord...@freebsd.org with unsubscribe freebsd-current in the body of the message
Re: Weird file corruption?
On Fri, Jan 15, 1999 at 02:51:01PM -0500, Brian Feldman wrote: Good to know I am looking in the right place. I switched my timings from Turbo to Normal (I have 2 EDO/2 FP), and now it seems to past tests, but I think I did see a few bytes get corrupted in an image in netscape... ah well, so you'd recommend finding someone with a SIMM checker? Except simm checkers don't always catch errors, so if the simm passes, there still is no guarantee (but simm checkers do weed out obvious duds quicker than trying in a system). Unfortunately, there is no conclusive test [that I know about] to prove a simm is good. The best test I know is to use emperical evidence based on how the system acts with or without the suspect simm. Even better is to only use motherboards that support parity and/or ECC, with parity/ecc simms/dimms. Then you catch most problems right away, rather than scratching your head (and doing the if I twiddle this knob, it seems to reduce the problem... I think). -- Zach Heilig z...@uffdaonline.net / Zach Heilig z...@gaffaneys.com To Unsubscribe: send mail to majord...@freebsd.org with unsubscribe freebsd-current in the body of the message
Re: Weird file corruption?
Zach Heilig z...@uffdaonline.net wrote: Except simm checkers don't always catch errors, so if the simm passes, there still is no guarantee (but simm checkers do weed out obvious duds quicker than trying in a system). Unfortunately, there is no conclusive test [that I know about] to prove a simm is good. I'd agree with that. The guts of a DRAM (or any type) is high-speed analog circuitry with delicate multi-phase clocking (the external clocks and selects are internally subdivided into maybe 20 phases). There can be pattern-sensitive crosstalk between rows or columns that depends on inter-access timings - or even how long since a particular row was refreshed. I suspect it's impossible to prove that a SIMM is good - there are two many combinations to test. Even better is to only use motherboards that support parity and/or ECC, with parity/ecc simms/dimms. This is the only practical way to detect memory problems. A subsidiary problem is that, unlike say Solaris, FreeBSD doesn't automatically report ECC errors. Without this, your memory controller can be furiously correcting a hard single-bit error and die when it glitches to a double-bit error. Someone did post a script that checked and cleared the relevant register in an i440 several months ago, but I seem to have mislaid both the script and reference :-(. Peter To Unsubscribe: send mail to majord...@freebsd.org with unsubscribe freebsd-current in the body of the message