The checksum one is a seperate issue. Let me explain that since its a bit
of a casual thing to say about someones research work without justification.
Right now we compute the checksum in kernel space.
If the checksum is wrong the other end will drop the frames
o Therefore the checksum is not trust critical data.
This has an important implication, you can take the whole clever page
management model being discussed and replace it with a single change
send_checksumis(fd, buf, len, flags)
since you know that the application lying is not a security violation.
Thats great, now the application can manage arbitary sized objects and can
itself do the RFC tricks for checksum adjustment on small data changes, it
can chain data and checksum some non static bits.
Oh and I suspect its < 100 lines of code to add to the OS. Now that one
_is_ a win. Consider the high performance ftp server keeping a checksum cache
of the commonly downloaded files. Zab is going to like this.
Alan
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/