> -----Original Message----- > From: Bartlomiej Zolnierkiewicz [mailto:b.zolnierkie@xxxxxxxxxxx] > Sent: Wednesday, October 4, 2017 12:40 PM > To: Linus Walleij <linus.walleij@xxxxxxxxxx> > Cc: Hunter, Adrian <adrian.hunter@xxxxxxxxx>; Ulf Hansson > <ulf.hansson@xxxxxxxxxx>; linux-mmc <linux-mmc@xxxxxxxxxxxxxxx>; linux- > block <linux-block@xxxxxxxxxxxxxxx>; linux-kernel <linux- > kernel@xxxxxxxxxxxxxxx>; Bough Chen <haibo.chen@xxxxxxx>; Alex > Lemberg <alex.lemberg@xxxxxxxxxxx>; Nowak, Mateusz > <mateusz.nowak@xxxxxxxxx>; Yuliy Izrailov <Yuliy.Izrailov@xxxxxxxxxxx>; > Jaehoon Chung <jh80.chung@xxxxxxxxxxx>; Dong Aisheng > <dongas86@xxxxxxxxx>; Das Asutosh <asutoshd@xxxxxxxxxxxxxx>; > Zhangfei Gao <zhangfei.gao@xxxxxxxxx>; Sahitya Tummala > <stummala@xxxxxxxxxxxxxx>; Harjani Ritesh <riteshh@xxxxxxxxxxxxxx>; > Venu Byravarasu <vbyravarasu@xxxxxxxxxx>; Shawn Lin <shawn.lin@rock- > chips.com>; Christoph Hellwig <hch@xxxxxx> > Subject: Re: [PATCH V9 13/15] mmc: block: Add CQE and blk-mq support > > > Hi, > > On Wednesday, October 04, 2017 09:39:45 AM Linus Walleij wrote: > > On Fri, Sep 22, 2017 at 2:37 PM, Adrian Hunter <adrian.hunter@xxxxxxxxx> > wrote: > > > > > Add CQE support to the block driver, including: > > > - optionally using DCMD for flush requests > > > - "manually" issuing discard requests > > > - issuing read / write requests to the CQE > > > - supporting block-layer timeouts > > > - handling recovery > > > - supporting re-tuning > > > > > > CQE offers 25% - 50% better random multi-threaded I/O. There is a > > > slight (e.g. 2%) drop in sequential read speed but no observable > > > change to sequential write. > > > > > > CQE automatically sends the commands to complete requests. However > > > it only supports reads / writes and so-called "direct commands" > > > (DCMD). Furthermore DCMD is limited to one command at a time, but > discards require 3 commands. > > > That makes issuing discards through CQE very awkward, but some CQE's > > > don't support DCMD anyway. So for discards, the existing non-CQE > > > approach is taken, where the mmc core code issues the 3 commands one > at a time i.e. > > > mmc_erase(). Where DCMD is used, is for issuing flushes. > > > > > > For host controllers without CQE support, blk-mq support is extended > > > to synchronous reads/writes or, if the host supports > > > CAP_WAIT_WHILE_BUSY, asynchonous reads/writes. The advantage of > > > asynchronous reads/writes is that it allows the preparation of the > > > next request while the current request is in progress. > > > > > > Signed-off-by: Adrian Hunter <adrian.hunter@xxxxxxxxx> > > > > I am trying to wrap my head around this large patch. The size makes it > > hard but I am doing my best. > > I also think that this patch should be split on two patches. The 1st one > introducing blk-mq and the 2nd one adding CQE support. > > [ I don't agree that they make more sense together, on the contrary, > it is very difficult to properly analyze blk-mq changes on their > own while there are mixed with CQE related ones. ] The CQE and non-CQE code paths are clearly marked. But maybe you are asking what the code would look like if we *never* had to support CQE. And my point is we *do* have to support CQE. Do you have any questions about the code?
