Re: [ck] Re: -mm merge plans for 2.6.23

[Nick Piggin]

Jos Poortvliet wrote:

> Nick
> has been talking about 'fixing the updatedb thing' for years now, no patch
> yet.

Wrong Nick, I think.

First I heard about the updatedb problem was a few months ago with people
saying updatedb was causing their system to swap (that is, swap prefetching
helped after updatedb). I haven't been able to even try to fix it because I
can't reproduce it (I'm sitting on a machine with 256MB RAM), and nobody
has wanted to help me.


> Besides, he won't fix OO.o nor all other userspace stuff - so 
> actually,
> he does NOT even promise an alternative. Not that I think fixing updatedb
> would be cool, btw - it sure would, but it's no reason not to include swap
> prefetch - it's mostly unrelated.
>
> I think everyone with >1 gb ram should stop saying 'I don't need it' 
> because
> that's obvious for that hardware. Just like ppl having a dual- or quadcore
> shouldn't even talk about scheduler interactivity stuff...

Actually there are people with >1GB of ram who are saying it helps. Why do
you want to shut people out of the discussion?


> Desktop users want it, tests show it works, there is no alternative and the
> maybe-promised-one won't even fix all cornercases. It's small, mostly
> selfcontained. There is a maintainer. It's been stable for a long time. 
> It's
> been in MM for a long time.
>
> Yet it doesn't make it. Andrew says 'some ppl have objections' (he means
> Nick) and he doesn't see an advantage in it (at least 4 gig ram, right,
> Andrew?).
>
> Do I miss things?

You could try constructively contributing?


> Apparently, it didn't get in yet - and I find it hard to believe Andrew
> holds swapprefetch for reasons like the above. So it must be something 
> else.
>
>
> Nick is saying tests have already proven swap prefetch to be helpfull,
> that's not the problem. He calls the requirements to get in 'fuzzy'. OK.

The test I have seen is the one that forces a huge amount of memory to
swap out, waits, then touches it. That speeds up, and that's fine. That's
a good sanity test to ensure it is working. Beyond that there are other
considerations to getting something merged.

--
SUSE Labs, Novell Inc.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/