Messages in this thread | | | Date | Fri, 11 Sep 2015 22:15:29 -0400 | From | Chris Mason <> | Subject | Re: [PATCH] fs-writeback: drop wb->list_lock during blk_finish_plug() |
| |
On Fri, Sep 11, 2015 at 05:52:27PM -0700, Linus Torvalds wrote: > On Fri, Sep 11, 2015 at 4:36 PM, Linus Torvalds > <torvalds@linux-foundation.org> wrote: > > > > Are we really ok with waiting synchronously for an inode while holding > > the plug? No chance of deadlock (waiting for IO that we've plugged)? > > That issue is true even of the current code, though, and I have _not_ > > really thought that through, it's just a worry. > > Never mind. We still flush the plug on explicit scheduling events. I > wonder why I thought we got rid of that. Some kind of "senior moment",
But flushing on schedule is a little different. It ends up calling blk_schedule_flush_plug() which will hand off work to kblockd through blk_run_queue_async()
Not a huge deal, but if we're scheduling to wait for that IO, we should really run the plug ourselves so that we're not waiting for kblockd too.
-chris
| |