Dear users/developers, I am trying to install the xenomai real-time linux on a gumstix overo fire with an omap3530. After some starting problems, I succeed to patch the 2.6.33 kernel and run some latency tests with normal worst case latencies ~60us. However, the overall worst case latency is very bad (5ms), because i occasionally get spurious interrupt errors like this: Spurious irq 95: 0xffffffdf, please flush posted write for irq 86 Spurious irq 95: 0xffffffdf, please flush posted write for irq 86 I then tried the precompiled development images (http://cumulus.gumstix.org/images/angstrom/developer/), which use kernel 2.6.39, but I also get these messages there. To reproduce the error, I did the following: 1.) Boot: Linux overo 2.6.39 #1 Mon Aug 15 19:04:09 PDT 2011 armv7l GNU/Linux booting from SD card. 2.) dd if=/dev/zero of=ddfile bs=100000 count=1000 --> creates a 1GB file in /home/root 3.) connect to wireless: iwconfig wlan0 mode ad-hoc iwconfig wlan0 essid myovero ifconfig wlan0 192.168.1.33 netmask 255.255.255.0 up 4.)a) then pull via scp ddfile onto your dev. machine. scp scp username@192.168.1.33:/home/root/ddfile . 4.)b) at the same time create a second empty file on the sd-card: dd if=/dev/zero of=ddfile2 bs=100000 count=4000 --> output in dmesg: Spurious irq 95: 0xffffffdf, please flush posted write for irq 86 Spurious irq 95: 0xffffffdf, please flush posted write for irq 86 whenever i write a new file that is bigger then the first one, I get two instances of this message: Spurious irq 95: 0xffffffdf, please flush posted write for irq 86 Spurious irq 95: 0xffffffdf, please flush posted write for irq 86 Spurious irq 95: 0xffffffdf, please flush posted write for irq 86 Spurious irq 95: 0xffffffdf, please flush posted write for irq 86 Spurious irq 95: 0xffffffdf, please flush posted write for irq 86 Spurious irq 95: 0xffffffdf, please flush posted write for irq 86 I am not sure if it is related to the SD-reader driver, or the wireless (libertas_SDIO) driver, or only the combination of both. This issue seemed to have already existed in previous kernel versions, there are many posts on the web, some of them saying it has been fixed in kernel version >2.6.30, which seems however not apply to the linux-omap3-2.6.39 kernel. The latest message about spurious irqs that i could find is related to kernel 3.0-rc1. Has anyone running an kernel-3.0 on an omap3530 (perhaps overo fire) and could try to reproduce? Or is there a specific patch to resolve this? I was not able to reproduce this on the NAND-flash, but it is also to small to make large continous data transfers. Any help with this is appreciated. Regards, Manfred -- 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
