Date: Mon, 24 Dec 2012 22:13:10 -0500 From: Scott Long <scott4long@yahoo.com> To: Ian Lepore <freebsd@damnhippie.dyndns.org> Cc: powerpc@freebsd.org, marcel@freebsd.org, mips@freebsd.org, John Baldwin <jhb@freebsd.org>, "mav@freebsd.org Motin" <mav@freebsd.org>, "attilio@FreeBSD.org Rao" <attilio@freebsd.org>, Jeff Roberson <jroberson@jroberson.net>, sparc64@freebsd.org, arm@freebsd.org, kib@freebsd.org Subject: Re: Call for testing and review, busdma changes Message-ID: <2D98F70D-4031-4860-BABB-1F4663896234@yahoo.com> In-Reply-To: <1356390225.1129.217.camel@revolution.hippie.lan> References: <alpine.BSF.2.00.1212080841370.4081@desktop> <1355077061.87661.320.camel@revolution.hippie.lan> <alpine.BSF.2.00.1212090840080.4081@desktop> <1355085250.87661.345.camel@revolution.hippie.lan> <alpine.BSF.2.00.1212231418120.2005@desktop> <1356381775.1129.181.camel@revolution.hippie.lan> <alpine.BSF.2.00.1212241104040.2005@desktop> <1356390225.1129.217.camel@revolution.hippie.lan>
next in thread | previous in thread | raw e-mail | index | archive | help
On Dec 24, 2012, at 6:03 PM, Ian Lepore <freebsd@damnhippie.dyndns.org> = wrote: >=20 > Yeah, I've done some low-level storage driver stuff myself (mmc/sd) = and > I can see how easy the deferred load solutions are to implement in = that > sort of driver that's already structured to operate asychronously. = I'm > not very familiar with how network hardware drivers interface with the > rest of the network stack. I have some idea, I'm just not sure of all > the subtleties involved and whether there are any implications for > something like a deferred load. >=20 > This is one of those situations where I tend to say to myself... the > folks who designed this stuff and imposed the "no deferred load" > restriction on mbufs and uio but not other cases were not stupid or > lazy, so they must have had some other reason. I'd want to know what > that was before I went too far with trying to undo it. >=20 Deferring is expensive from a latency standpoint. For disks, this = latency was comparatively small (until recent advances in SSD), so it = didn't matter, but it did matter with network devices. Also, network = drivers already had the concept of dropping mbufs due to resource = shortages, and the strict requirement of guaranteed transactions with = storage didn't apply. Deferring and freezing queues to guarantee = delivery order is a pain in the ass, so the decision was made that it = was cheaper to drop an mbuf on a resource shortage rather than defer. = As for uio's, they're the neglected part of the API and there's really = been no formal direction or master plan put into their evolution. = Anyways, that's my story and I'm sticking to it =3D-) Also, eliminating the concept of deferred load from mbufs then freed us = to look at ways to make the load operation cheaper. There's a lot of = code in _bus_dmamap_load_buffer() that is expensive, but a big one was = the indirect function pointer for the callback in the load wrappers. = The extra storage for filling in the temporary s/g list was also looked = at. Going with direct loads allowed me to remove these and reduce most = of the speed penalties. >=20 >>>=20 >>> Still unresolved is what to do about the remaining cases -- attempts = to >>> do dma in arbitrary buffers not obtained from bus_dmamem_alloc() = which >>> are not aligned and padded appropriately. There was some discussion = a >>> while back, but no clear resolution. I decided not to get bogged = down >>> by that fact and to fix the mbuf and allocated-buffer situations = that we >>> know how to deal with for now. >>=20 Why would these allocations not be handled as normal dynamic buffers = would with bus_dmamap_load()? Scott
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?2D98F70D-4031-4860-BABB-1F4663896234>