Re: [RFC] mm:prototype for the updated swapoff implementation

[One Thousand Gnomes]

> Do you have situations in which swapoff is taking an unacceptable
> amount of time?  If so, please update the changelog to provide full
> details on this, with before-and-after timing measurements.

Yes - because now and then (about once a month) with 3.10 or so + and
encrypted swap my box with 16GB RAM gets into a weird 'slow swapping'
state and only swapoff/swapon gets it back to sanity.

In those cases (and in general) swapoff can take half an hour to run.

There is a reproducer for the swap hang at
https://bugzilla.kernel.org/show_bug.cgi?id=62321

The case I see in normal use (gimp of 1200dpi+ A3 images) hits a crawl
not a hang and does recover but only if you swapoff/swapon again

Alan
--
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/