On Thu, Jan 04, 2018 at 09:17:36AM +0800, Huang, Ying wrote: > > Maybe, but in this particular case, I would prefer to go with something > > more conventional unless there is strong evidence that it's an improvement > > (which I doubt in this case given the cost of migration overall and the > > corner case of migrating a dirty page). > > So you like page_lock() more than RCU?
In this instance, yes. > Is there any problem of RCU? > The object to be protected isn't clear? > It's not clear what object is being protected or how it's protected and it's not the usual means a mapping is pinned. Furthermore, in the event a page is being truncated, we really do not want to bother doing any migration work for compaction purposes as it's a waste. -- Mel Gorman SUSE Labs
