Dirty words on linux-kernel

Jamie Lokier (lk@tantalophile.demon.co.uk)
Sat, 10 Aug 2002 20:30:04 +0100


Sorry folks, but I found this bounce from a message I sent to
linux-kernel both funny and slightly disturbing. Note that the bounce
comes from a subscriber to linux-kernel, not the mailing list
management! (:-)

Subject: ScanMail Message: To Sender, sensitive content found and action taken.
From: System Attendant <WLVEXC01-SA@digitalinsight.com>

Trend SMEX Content Filter has detected sensitive content.

Place = Linus Torvalds; Andrew Morton; lkml;
Sender = Jamie Lokier
Subject = Re: [patch 6/12] hold atomic kmaps across generic_file_read
Delivery Time = August 10, 2002 (Saturday) 10:59:18
Policy = Dirty Words
Action on this mail = Quarantine message

Warning message from administrator:
Sender, Content filter has detected a sensitive e-mail.

I wonder if anyone can spot "Dirty Words" in the text below! (I don't
see any). The bounce doesn't say which message; it must be one of the
two below.

enjoy,
-- Jamie

----------------- possible dirty talk #1 --------------------

Linus Torvalds wrote:
> Imagine doing a
>
> fstat(fd..)
> buf = aligned_malloc(st->st_size)
> read(fd, buf, st->st_size);
>
> and having it magically populate the VM directly with the whole file
> mapping, with _one_ failed page fault. And the above is actually a fairly
> common thing. See how many people have tried to optimize using mmap vs
> read, and what they _all_ really wanted was this "populate the pages in
> one go" thing.

This will only provide the performance benefic when `aligned_malloc'
return "fresh" memory, i.e. memory that has never been written to.

Assuming most programs use plain old `malloc', which could be taught to
align nicely, then the optimisation might occur when a program starts
up, but later on it's more likely to return memory which has been
written to and previously freed. So the performance becomes
unpredictable.

But it's a nice way to optimise if you are _deliberately_ optimising a
user space program. First call mmap() to get some fresh pages, then
call read() to fill them. Slower on kernels without the optimisation,
fast on kernels with it. :-)

-- Jamie

----------------- possible dirty talk #2 --------------------

Linus Torvalds wrote:
> For people like that, wouldn't it be nice to just be able to tell them: if
> you do X, we guarantee that you'll get optimal zero-copy performance for
> reading a file.

Don't forget to include the need for mmap(... MAP_ANON ...) prior to the
read.

Given the user will need to establish a new mapping anyway, why pussy
foot around with subtleties? Just add a MAP_PREFAULT flag to mmap(),
which reads the whole file and maps it before returning.

-- Jamie
-
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/