From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ivo Manca Subject: I2c-i801 interrupt support (was: Re: i2c-i801: Regression between 2.6.22.9 & 2.6.23.9) Date: Fri, 08 Feb 2008 17:22:33 +0100 Message-ID: <47AC81C9.3020907@gmail.com> References: <20080109135341.461688d1@hyperion.delvare> <4784D068.8080401@gmail.com> <20080109154216.3cec6053@hyperion.delvare> <47850DDB.5080101@gmail.com> <20080110150917.646c2677@hyperion.delvare> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20080110150917.646c2677-ig7AzVSIIG7kN2dkZ6Wm7A@public.gmane.org> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: i2c-bounces-GZX6beZjE8VD60Wz+7aTrA@public.gmane.org Errors-To: i2c-bounces-GZX6beZjE8VD60Wz+7aTrA@public.gmane.org To: Jean Delvare Cc: Oleg Ryjkov , i2c-GZX6beZjE8VD60Wz+7aTrA@public.gmane.org, Hans de Goede List-Id: linux-i2c@vger.kernel.org Hey Jean, Jean Delvare wrote: > Hi Ivo, > > > I am very interested in this as well. I have several ICH3-M, ICH5 and > ICH7-based systems here for testing as soon as you have something good > enough to be published. > > For devices which support the block buffer (i.e. ICH4 and later), > Oleg's patch improved speed dramatically for block transactions > already. I don't think that you will win much with interrupts here, > except maybe for HZ=100. I think that you will win a lot more on short > transactions, where polled mode has to wait for at least one jiffie > (and more like 2 on practice) and interrupt mode could be one or two > orders of magnitude faster than this. For hardware monitoring chips > with a lot of registers (e.g. LM85 or ADM1026) the speedup should be > very visible. > > Sadly I haven't been able to test this improvement due to lack of (available) hardware. The last test showed a bug which crashes the controller but I think I've already fixed it. Luckily, Hans de Goede arranged a spare PC which I can use for testing and development. I hope to pick it up soon and development should speed up then! So, thanks to the HHS (Hague University) for making a system available for testing and thanks to Hans for arranging this! > What value of HZ are you using? It matters for polled mode. From the > figures above I'd guess HZ=1000. Try again with HZ=250 or even HZ=100 > if you want more impressive figures ;) > Default, so 1000 I suppose. >> New driver: >> (time 25x i2cdump -s) >> ./bla (i2c-dump 25x) >> real 0m24.215s >> user 0m0.013s >> sys 0m0.175s >> -- >> I2C_SMBUS_QUICK(nodev) 0.00112 >> I2C_SMBUS_QUICK 0.00112 >> I2C_SMBUS_BYTE 0.00110 >> I2C_SMBUS_BYTE_DATA 0.00113 >> I2C_SMBUS_WORD_DATA 0.00108 >> > > So that would be a 2x improvement for short transactions at HZ=1000... > and 20x at HZ=100. Very nice :) > Seems quite nice yes, let's just hope I/we can get it stable enough! Ivo _______________________________________________ i2c mailing list i2c-GZX6beZjE8VD60Wz+7aTrA@public.gmane.org http://lists.lm-sensors.org/mailman/listinfo/i2c