From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Date: Fri, 6 Mar 2009 20:03:50 +0100 From: Jens Axboe To: Geert Uytterhoeven Subject: Re: [PATCH/RFC] ps3/block: Add ps3vram-ng driver for accessing video RAM as block device Message-ID: <20090306190350.GD11787@kernel.dk> References: <20090305083701.GQ11787@kernel.dk> <20090305110940.GY11787@kernel.dk> <20090306074639.GN11787@kernel.dk> <20090306125832.GX11787@kernel.dk> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: Cc: Arnd Bergmann , Linux Kernel Development , Jim Paris , Linux/PPC Development , linux-mtd@lists.infradead.org, Vivien Chappelier , David Woodhouse , Cell Broadband Engine OSS Development List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Fri, Mar 06 2009, Geert Uytterhoeven wrote: > On Fri, 6 Mar 2009, Jens Axboe wrote: > > On Fri, Mar 06 2009, Geert Uytterhoeven wrote: > > > On Fri, 6 Mar 2009, Jens Axboe wrote: > > > > On Thu, Mar 05 2009, Geert Uytterhoeven wrote: > > > > > But then I noticed ps3vram_make_request() may be called concurrently, > > > > > so I had to add a mutex to avoid data corruption. This slows the > > > > > driver down, and in the end, the version with a thread turns out to be > > > > > ca. 1% faster. The version without a thread is about 50 lines less > > > > > code, though. > > > > > > > > That is correct, ->make_request_fn may get reentered. I'm not surprised > > > > that performance dropped if you just shoved everything under a mutex. > > > > You could be a little more smart and queue concurrent bio's for > > > > processing when the current one is complete though, there are several > > > > approaches there that be a lot faster than going all the way through the > > > > IO stack and scheduler just to avoid concurrency. > > > > > > Yes, using a spinlock and queueing requests on a list if the driver is > > > busy can be done after 2.6.29... > > > > Certainly. Even just replacing your current mutex with a spinlock during > > the memcpy() would surely be a lot faster. Or even just grabbing the > > mutex before calling into the write for the duration of the bio. The way > > you do it is certain context switch death :-) > > It's not just the memcpy(). ps3vram_{up,down}load() call msleep(), so > I cannot use a spinlock. Ah right, I hadn't looked close enough. But putting the mutex_lock() outside of the bio_for_each_segment() is going to be much faster than getting/releasing it for each segment. -- Jens Axboe