One theory is the bad CPU screwed up the previous kernel, which might explain why it suddenly had problems when it was fine for weeks before that. Then again.. how does a bad CPU permanently screw up a kernel image?

Quite possible - some years ago our Win server had one buggy (non-ECC) memory module. After a sudden crash, a plenty of files in C:\\WINDOWS\\system32\\ (and somewhere else too) got some errorneous characters (more exactly, few bits) in their names and the system refused to boot.

The solution was to locate and replace the bad memory module, install the same system on some other machine, compare the directory trees and rename the broken file names - everything was then running fine.

Peter

One theory is the bad CPU screwed up the previous kernel, which might explain why it suddenly had problems when it was fine for weeks before that. Then again.. how does a bad CPU permanently screw up a kernel image?

Quite possible - some years ago our Win server had one buggy (non-ECC) memory module. After a sudden crash, a plenty of files in C:\\WINDOWS\\system32\\ (and somewhere else too) got some errorneous characters (more exactly, few bits) in their names and the system refused to boot.

The solution was to locate and replace the bad memory module, install the same system on some other machine, compare the directory trees and rename the broken file names - everything was then running fine.

Peter

[off topic]
Welcome back to the Boards Peter . . . ;O
[on topic]

---

BOINC Wiki . . .

Science Status Page . . .

Are Scarecrow's cowboys capable of handling both types of endians?

Tell the big ones to line up, and the little ones to bunch up.... we'll whoop 'em all.

How's it going, Peter?

Are Scarecrow's cowboys capable of handling both types of endians?

Tell the big ones to line up, and the little ones to bunch up.... we'll whoop 'em all.

I see you have them under controll.

How's it going, Peter?

Yippeeeeeee!
Less time recently for virtual life, just scratching some projects' boards. But still enough interest for the area.

Peter

[snip]
Dell replaced the bad CPU in isaac, which fixed one problem, but we were still having unexplained crashes when using the latest xen kernel. However a new kernel came out and we upgraded to that this morning and so far so good. One theory is the bad CPU screwed up the previous kernel, which might explain why it suddenly had problems when it was fine for weeks before that. Then again.. how does a bad CPU permanently screw up a kernel image?

[snip]
- Matt

One possibility is that the "bad" CPU overwrote part of the kernal in memory, in a "swapping" module (it comes into memory and gets re-written to disk, repeatedly) and the error propigated (like, maybe, it was a disk drive driver routine...)

I've seen this happen, in my experience. (in much older OS's - IBM's DOS/MS, OSMVT, etc.) Finding the cause was always frustrating, and quite slow...

---

.

Hello, from Albany, CA!...

[snip]
Dell replaced the bad CPU in isaac, which fixed one problem, but we were still having unexplained crashes when using the latest xen kernel. However a new kernel came out and we upgraded to that this morning and so far so good. One theory is the bad CPU screwed up the previous kernel, which might explain why it suddenly had problems when it was fine for weeks before that. Then again.. how does a bad CPU permanently screw up a kernel image?

[snip]
- Matt

One possibility is that the "bad" CPU overwrote part of the kernal in memory, in a "swapping" module (it comes into memory and gets re-written to disk, repeatedly) and the error propigated (like, maybe, it was a disk drive driver routine...)

I've seen this happen, in my experience. (in much older OS's - IBM's DOS/MS, OSMVT, etc.) Finding the cause was always frustrating, and quite slow...

Also remember that software raid is the norm there, (a conscious decision.)

Also remember that software raid is the norm there, (a conscious decision.)

In this case, hardware RAID. There's no "norm" as much as what works best with what we got.

- Matt

---

-- BOINC/SETI@home network/web/science/development person
-- "Any idiot can have a good idea. What is hard is to do it." - Jeanne-Claude