Re: innd mmap bug in 2.4.0-test12

From: Chris Wedgwood (cw@f00f.org)
Date: Mon Dec 25 2000 - 23:50:57 EST


On Mon, Dec 25, 2000 at 01:42:33AM -0800, Linus Torvalds wrote:

    We just don't write them out. Because right now the only thing
    that writes out dirty pages is memory pressure. "sync()",
    "fsync()" and "fdatasync()" will happily ignore dirty pages
    completely. The thing that made me overlook that simple thing in
    testing was that I was testing the new VM stuff under heavy VM
    load - to shake out any bugs.

Does this mean anyone using test13-pre4 should also expect to see
data not being flushed on shutdown?

I'm not seeing data loss (or it's not obvious if I am) but wonder if
I should make a application to run before halt to allocate and walk
all available memory as an interim?

  --cw

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Sun Dec 31 2000 - 21:00:08 EST