Segfault during network calls
Hello colleagues, We have a strange problem with our multi-threaded SMTP client: at very heavy load (e.g. 150 threads, each with a pool of 5 persistent connections) it sometimes receives SIGSEGV while making network kernel calls (mostly in "recvfrom" for both TCP and UDP, but also in "connect"). This happens for both 2.2.12 and 2.4.4 kernels on a Celeron 600 machine (no SMP) with glibc 2.1.3. The kernel logs do not show any problems, yet the application program gets killed. This happens MORE frequently if we increase the number of file descriptors available to the process (using "ulimit -n"), which suggests some resource utilisation problem in the kernel (?) E.g., is there a compiled-in upper bound on the total number of sockets which can be created by all processes? (I could not find SOCK_ARRAY_SIZE in 2.4.4). Any ideas would be very much appreciated. Thank you very much in advance, Dr. Leonid A. Timochouk Computing Laboratory University of Kent at Canterbury - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Problem with dmfe
Hello, I have installed Linux 2.4.4 on our remotely-administered dedicated Web server (600MHz Celeron), and strange effects occurred with the Davicom DM9102 network card. It was active but apparently VERY slow, 85% packet loss in ping. I could connect to the machine but could not do anything useful. The system had to be rebooted into the previous configuration (2.2.12) which works fine. I then examined the kernel logs for 2.4.4 and found the following: PCI: Using IRQ router PIIX [8086/2420] at 00:1f.0 PCI: Found IRQ 3 for device 00:01.0 eth0: Davicom DM9102 at 0xc000, 00:d0:09:1e:61:51, IRQ 3 Thus, device 00:01.0 (video card) shares IRQ with the net card. Could it be the source of the problem? Under 2.2.12, pciutils show the following info for these devices: 00:01.0 VGA compatible controller: Intel Corporation 82810 CGC [Chipset Graphics Controller] (rev 02) (prog-if 00 [VGA]) Subsystem: Intel Corporation: Unknown device 7121 Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B- Status: Cap+ 66Mhz+ UDF- FastB2B+ ParErr- DEVSEL=medium >TAbort- SERR- TAbort- SERR- http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
FIXED: Problem with dmfe
> It could be an IRQ routing problem. It could be a dmfe driver > problem. Does > using the tulip driver in 2.4.x with it make it any happier ? The problem was fixed by using the 2.4-specific driver (dm9xs.c) provided by Davicom at http://www.davicom.com.tw/download/download_driver.asp instead of dmfe.c. I am still not sure what was the exact cause of trouble with the original driver. Dr. Leonid Timochouk Computing Laboratory University of Kent at Canterbury, England - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
