[ adding Ross and Jan ] On Sun, Jul 23, 2017 at 7:04 AM, Rik van Riel <riel@xxxxxxxxxx> wrote: > On Sat, 2017-07-22 at 12:34 -0700, Dan Williams wrote: >> On Fri, Jul 21, 2017 at 8:58 AM, Stefan Hajnoczi <stefanha@xxxxxxxxxx >> > wrote: >> > >> > Maybe the NVDIMM folks can comment on this idea. >> >> I think it's unworkable to use the flush hints as a guest-to-host >> fsync mechanism. That mechanism was designed to flush small memory >> controller buffers, not large swaths of dirty memory. What about >> running the guests in a writethrough cache mode to avoid needing >> dirty >> cache management altogether? Either way I think you need to use >> device-dax on the host, or one of the two work-in-progress filesystem >> mechanisms (synchronous-faults or S_IOMAP_FROZEN) to avoid need any >> metadata coordination between guests and the host. > > The thing Pankaj is looking at is to use the DAX mechanisms > inside the guest (disk image as memory mapped nvdimm area), > with that disk image backed by a regular storage device on > the host. > > The goal is to increase density of guests, by moving page > cache into the host (where it can be easily reclaimed). > > If we assume the guests will be backed by relatively fast > SSDs, a "whole device flush" from filesystem journaling > code (issued where the filesystem issues a barrier or > disk cache flush today) may be just what we need to make > that work. Ok, apologies, I indeed had some pieces of the proposal confused. However, it still seems like the storage interface is not capable of expressing what is needed, because the operation that is needed is a range flush. In the guest you want the DAX page dirty tracking to communicate range flush information to the host, but there's no readily available block i/o semantic that software running on top of the fake pmem device can use to communicate with the host. Instead you want to intercept the dax_flush() operation and turn it into a queued request on the host. In 4.13 we have turned this dax_flush() operation into an explicit driver call. That seems a better interface to modify than trying to map block-storage flush-cache / force-unit-access commands to this host request. The additional piece you would need to consider is whether to track all writes in addition to mmap writes in the guest as DAX-page-cache dirtying events, or arrange for every dax_copy_from_iter() operation() to also queue a sync on the host, but that essentially turns the host page cache into a pseudo write-through mode.
