On Mon, Jul 1, 2019 at 8:34 PM Jason Dillaman <jdillama@xxxxxxxxxx> wrote:
>
> On Tue, Jun 25, 2019 at 10:44 AM Ilya Dryomov <idryomov@xxxxxxxxx> wrote:
> >
> > Since the dawn of time it had been assumed that a single object request
> > spawns a single OSD request. This is already impacting copyup: instead
> > of sending empty and current snapc copyups together, we wait for empty
> > snapc OSD request to complete in order to reassign obj_req->osd_req
> > with current snapc OSD request. Looking further, updating potentially
> > hundreds of snapshot object maps serially is a non-starter.
> >
> > Replace obj_req->osd_req pointer with obj_req->osd_reqs list. Use
> > osd_req->r_unsafe_item for linkage -- it's used by the filesystem for
> > a similar purpose.
>
> Nit: just curious on the history of "r_unsafe_item"'s name. Since it
> would be re-used twice for an osd request list, should (could) it be
> renamed?
This is from when we had safe and unsafe replies (commit vs ack). It
has since become a private list item for use by libceph clients. I'll
rename it to r_private_item.
Thanks,
Ilya
