> -----Original Message----- > From: Jim Rees [mailto:rees@xxxxxxxxx] > Sent: Tuesday, September 20, 2011 8:29 PM > To: Myklebust, Trond > Cc: Benny Halevy; linux-nfs@xxxxxxxxxxxxxxx; peter honeyman > Subject: Re: [PATCH 2/3] pnfs: introduce pnfs private workqueue > > Trond Myklebust wrote: > > On Mon, 2011-09-19 at 23:18 -0400, Jim Rees wrote: > > From: Peng Tao <bergwolf@xxxxxxxxx> > > > > For layoutdriver io done functions, default workqueue is not a good place > as > > the code is executed in IO path. So add a pnfs private workqueue to > handle > > them. > > > > Also change block and object layout code to make use of this private > > workqueue. > > > > Wait, what???? > > Why is the I/O path (i.e. the nfsiod queue) inappropriate for > layoutdriver io_done functions? > > I thought you were the one who asked for this, here: > http://www.spinics.net/lists/linux-nfs/msg22771.html > > But looking back on it now, the IO path has changed and I can't tell if the > argument still holds. You are reading too much into what I said. The fact that we shouldn't use the 'hot' nfs/rpciod workqueues doesn't imply that we need a completely separate pnfs workqueue. We already have plenty of generic workqueues and even context threads: why aren't they sufficient? Trond -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
