> Another thing I've been wondering about is options.minra. I find the
> documentation a bit thin, shall we say. If the 'aggressive read ahead'
> mentioned in the documentation is *per file*, it's probably a good
> thing for a NetApp used as a News spool - since you normally retrieve
> a whole article at a time.
It depends. We're working on more complete documentation on this and
other issues for netnews, but the quick answer is as follows:
Look at the "cache age" field in the output of sysstat on the
filer during a time of heavy load. If it's not close to zero,
fiddling with minra probably won't help and may hurt.
If the cache age *is* close to zero, do you have lots of users
accessing news via slow connections (e.g., modems) reading lots
of large articles (e.g., alt.binaries.*)? If yes, and you can't
add any more memory, there's a good chance you'll benefit from
options minra on
Otherwise, it probably won't help, but you may want to give it a
try anyway.
Aggressive read ahead is per file. The problem is that very slow
users (the connections, not the humans, though some of them may be
slow too ;-)) will trigger the read ahead during sequential reads,
but if there's enough memory contention, all that work will be for
naught because the data won't actually be requested until after it
has been tossed out of the cache in favor of more recent requests.
Pushed hard enough, the CPU will max out as it busily thrashes
memory, doing little useful work in the process.
-- Karl
This archive was generated by hypermail 2b29 : Tue Jan 04 2000 - 10:19:14 EST