>-----Original Message----- >From: Premi, Sanjeev [mailto:premi@xxxxxx] >Sent: November 6, 2009 9:18 AM >To: Weng, Wending; linux-omap@xxxxxxxxxxxxxxx >Subject: RE: The latest 2.6.32.rc5 is very slow >> -----Original Message----- >> From: linux-omap-owner@xxxxxxxxxxxxxxx >> [mailto:linux-omap-owner@xxxxxxxxxxxxxxx] On Behalf Of Weng, Wending >> Sent: Friday, November 06, 2009 7:36 PM >> To: linux-omap@xxxxxxxxxxxxxxx >> Subject: The latest 2.6.32.rc5 is very slow >> >> Hi All, >> >> I have an omap3evm based system, it was running PSP >> 1.0.0., everything works fine. Recently, I upgraded the BSP >[sp] That would be kernel version 2.6.22-18? That's correct. >> to the latest 2.6.32.rc5, it's very much straight forward. >> However, there is a major performance degradation, the system >[sp] How are you measuring performance degradation? My system is a map based application, it responds much slower for all user input, I can feel it. I did some specific testings, for instance, write a short string to the console, usually, it takes less than 1 us for BSP 1.0.0, but the latest BSP will take 30 us or 60 us, the latency always goes up by 30 us. The display call(printf) is translated into sys_write in kernel, I measure its execution latency, indeed, it's 30 or 60 us, even I add spin_lock_irqsave and spin_lock_irqrestore to make sure it will not be disturbed. It doesn't take so much time to execute sys_write, I suspect it's interrupted by DMA or some bus lock. >> is almost not usable. Has Anybody experienced similar >> performance problems? What are potential reasons? >> >> Wending Weng >> >> -- >> To unsubscribe from this list: send the line "unsubscribe >> linux-omap" in >> the body of a message to majordomo@xxxxxxxxxxxxxxx >> More majordomo info at http://vger.kernel.org/majordomo-info.html >> >> -- To unsubscribe from this list: send the line "unsubscribe linux-omap" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
