>> No, the real reason is that for new features like this - features that >> I don't really see myself using personally and that I'm not all that >> personally excited about - I *really* want others to pipe up with >> "yes, we're using this, and yes, we want this to be merged". >> >> It doesn't seem to be huge, which is great, but the deathly silence of >> nobody speaking up and saying "yes please", makes me go "ok, I won't >> pull if nobody speaks up for the feature". Hey Linus. A couple of folks here and in the past replies shared their thoughts, but I don't think I said anything beyond dry technical details. So I am really really excited about this. I think this "memory-that-is-not-your-old-memory" is an aspect of technology that is going to evolve in interesting ways. The same way that SSDs kicked the notion that "we have tons of milliseconds to do stuff before it hits the platter" without costing a lot of money, the PCIe memory cards (or whatever marketing name is used), PCIe inter-machine links, or even on the embedded side of stuffing more in less, offer fantastic opportunities. The frontswap provides a means to bridge a lot of these technologies and share common concepts among them - there is the compression for the embedded world, there is de-duplication for the starving virtualization world, there is memory sharing across nodes, and in my crystal ball I see are those PCIe memory cards being used too. It is really fun and invigorating and this patchset provides the basic underpinnings for a lot of it. So yes please pull! git://git.kernel.org/pub/scm/linux/kernel/git/konrad/mm.git stable/frontswap.v16-tag Thanks! -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/ Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>