> Sorry for not being clear, but what I was referring to is
> making the decision about how to read ahead by what is already
> in the page cache. It has a number of benefits that database
> people are after as it allows multiple threads using
> pread/pwrite to obtain the benefits of readahead.
Ah, OK. Sorry for being so dense ;-)
Yeah, that would be an improvement for knfsd too. The current scheme
can only manage readahead for 1 reader per inode.
Are there any records of a more detailed discussion of how to go about
implementing such a readahead strategy for Linux?
Cheers,
Trond
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/