I'm haven't gotten to many comments back from the last set of patches. So I imagine that people are okay with the interface and the general code. The next submission will probably rename the call to preadv6/pwritev6 just to follow the interface ... but I don't think they'll be any other changes; so no need to wait on me. How should we go about packaging this up for mainline inclusion? Additionally, I've been testing it with out application in and in the test environment we've a 30% reduction in average response time. We might be kind of a best case since we do a fair amount of CPU / IO bound work overlapped and this lets us skip the threadpool queue in a huge chunk of the cases. But the gains are real... for a real application. On Wed, Oct 1, 2014 at 5:04 PM, Christoph Hellwig <hch@xxxxxx> wrote: > Hi Miklos, > > attached are the patches that go on top of your > "[RFC v3 0/4] vfs: Non-blockling buffered fs read (page cache only)" > series. The first one adds RWF_NONBLOCK to XFS, the other two > add a new RWF_DSYNC flag that adds a per-operation O_DSYNC flag. > -- Milosz Tanski CTO 16 East 34th Street, 15th floor New York, NY 10016 p: 646-253-9055 e: milosz@xxxxxxxxx -- To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
