Messages in this thread | | | From | Linus Torvalds <> | Date | Fri, 9 Sep 2016 08:31:27 -0700 | Subject | Re: [RFC PATCH 0/4] Reduce tree_lock contention during swap and reclaim of a single file v1 |
| |
On Fri, Sep 9, 2016 at 2:59 AM, Mel Gorman <mgorman@techsingularity.net> wrote: > > The progression of this series has been unsatisfactory.
Yeah, I have to say that I particularly don't like patch #1. It's some rather nasty complexity for dubious gains, and holding the lock for longer times might have downsides.
And the numbers seem to not necessarily be in favor of patch #3 either, which I would have otherwise been predisposed to like (ie it looks fairly targeted and not very complex).
#2 seems trivially correct but largely irrelevant.
So I think this series is one of those "we need to find that it makes a big positive impact" to make sense.
Linus
| |