From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from bombadil.infradead.org ([65.50.211.133]:46258 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751341AbdISUe6 (ORCPT ); Tue, 19 Sep 2017 16:34:58 -0400 Date: Tue, 19 Sep 2017 13:34:57 -0700 From: Christoph Hellwig Subject: Re: io_submit() blocks for writes for substantial amount of time Message-ID: <20170919203457.GB731@infradead.org> References: <20170919122704.GA3487@bfoster.bfoster> <20170919145827.GA21523@infradead.org> <04cb3ee7-e7d5-6bba-6adb-8ac1c28e68dc@scylladb.com> <20170919173955.GB8139@dhcp-41-131.bos.redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20170919173955.GB8139@dhcp-41-131.bos.redhat.com> Sender: linux-xfs-owner@vger.kernel.org List-ID: List-Id: xfs To: Brian Foster Cc: Avi Kivity , Christoph Hellwig , Tomasz Grabiec , linux-xfs@vger.kernel.org On Tue, Sep 19, 2017 at 01:39:55PM -0400, Brian Foster wrote: > I'm not sure what difference it makes regardless. We still have to wait > for an allocation to complete before we can issue an I/O. IIRC, the old > defer allocs to a wq thing was more about saving stack space than > providing async behavior. At least in theory we could do the allocation from one workqueue and submit the I/O from the next one. Except for the lack of modern workqueues that is what the historic AIO code in RHEL2.1 (and maybe 3.0, but I'm not sure did).