* [Xenomai-help] awful latencies (~110us)
@ 2007-10-05 7:52 CHABAL David
2007-10-05 8:30 ` Gilles Chanteperdrix
0 siblings, 1 reply; 30+ messages in thread
From: CHABAL David @ 2007-10-05 7:52 UTC (permalink / raw)
To: xenomai
[-- Attachment #1: Type: text/plain, Size: 1363 bytes --]
Hello all,
My box is a Pentium III 733 Mhz/256Mo with Linux 2.6.20 and Xenomai 2.3.3.
When I run the latency test included in the testsuite, I get some
horrible results like:
RTT| 00:01:04 (periodic user-mode task, 100 us period, priority 99)
RTH|-----lat min|-----lat avg|-----lat max|-overrun|----lat best|---lat
worst
RTD| 4.640| 12.243| 80.454| 0| 3.716|
110.990
RTD| 8.652| 13.133| 86.014| 0| 3.716| ...
RTD| 4.050| 13.324| 89.186| 0| 3.716|
110.990
---|------------|------------|------------|--------|-------------------------
RTS| 3.716| 11.499| 110.990| 0| 00:01:22/00:01:22
I expect about 30us.
I have tried many kernel configurations without significant results
(always about 120us).
- BIOS USB Legacy is disabled.
- idle=pool is added to the boot line.
- linux kernel is minimalist
- Ipipe/xenomai debug features have a minor impact
- sometimes, the latency is negative.
I have noticed a better latency (max: ~31us) with the network disabled
(ifdown eth0), and a deterioration immediatly after typing ifup (~120us,
like above). (Usually, I connect this box through Exceed. I have other
PC with Xenomai and it is without consequence on their latency tests).
If someone has a clue, I get it !!
Thanks in advance,
David
[-- Attachment #2: config.txt --]
[-- Type: text/plain, Size: 26373 bytes --]
#
# Automatically generated make config: don't edit
# Linux kernel version: 2.6.20
# Fri Jan 5 09:20:24 2007
#
CONFIG_X86_32=y
CONFIG_GENERIC_TIME=y
CONFIG_LOCKDEP_SUPPORT=y
CONFIG_STACKTRACE_SUPPORT=y
CONFIG_SEMAPHORE_SLEEPERS=y
CONFIG_X86=y
CONFIG_MMU=y
CONFIG_GENERIC_ISA_DMA=y
CONFIG_GENERIC_IOMAP=y
CONFIG_GENERIC_BUG=y
CONFIG_GENERIC_HWEIGHT=y
CONFIG_ARCH_MAY_HAVE_PC_FDC=y
CONFIG_DMI=y
CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
#
# Code maturity level options
#
# CONFIG_EXPERIMENTAL is not set
CONFIG_BROKEN_ON_SMP=y
CONFIG_INIT_ENV_ARG_LIMIT=32
#
# General setup
#
CONFIG_LOCALVERSION=""
# CONFIG_LOCALVERSION_AUTO is not set
CONFIG_SWAP=y
CONFIG_SYSVIPC=y
# CONFIG_IPC_NS is not set
CONFIG_BSD_PROCESS_ACCT=y
CONFIG_BSD_PROCESS_ACCT_V3=y
# CONFIG_TASKSTATS is not set
# CONFIG_UTS_NS is not set
CONFIG_AUDIT=y
CONFIG_AUDITSYSCALL=y
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
CONFIG_SYSFS_DEPRECATED=y
CONFIG_RELAY=y
CONFIG_INITRAMFS_SOURCE=""
CONFIG_SYSCTL=y
# CONFIG_EMBEDDED is not set
CONFIG_UID16=y
CONFIG_SYSCTL_SYSCALL=y
CONFIG_KALLSYMS=y
CONFIG_KALLSYMS_EXTRA_PASS=y
CONFIG_HOTPLUG=y
CONFIG_PRINTK=y
CONFIG_BUG=y
CONFIG_ELF_CORE=y
CONFIG_BASE_FULL=y
CONFIG_FUTEX=y
CONFIG_EPOLL=y
CONFIG_SHMEM=y
CONFIG_SLAB=y
CONFIG_VM_EVENT_COUNTERS=y
CONFIG_RT_MUTEXES=y
# CONFIG_TINY_SHMEM is not set
CONFIG_BASE_SMALL=0
# CONFIG_SLOB is not set
#
# Loadable module support
#
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
# CONFIG_MODVERSIONS is not set
# CONFIG_MODULE_SRCVERSION_ALL is not set
CONFIG_KMOD=y
#
# Block layer
#
CONFIG_BLOCK=y
CONFIG_LBD=y
CONFIG_BLK_DEV_IO_TRACE=y
CONFIG_LSF=y
#
# IO Schedulers
#
CONFIG_IOSCHED_NOOP=y
CONFIG_IOSCHED_AS=y
CONFIG_IOSCHED_DEADLINE=y
CONFIG_IOSCHED_CFQ=y
CONFIG_DEFAULT_AS=y
# CONFIG_DEFAULT_DEADLINE is not set
# CONFIG_DEFAULT_CFQ is not set
# CONFIG_DEFAULT_NOOP is not set
CONFIG_DEFAULT_IOSCHED="anticipatory"
#
# Real-time sub-system
#
CONFIG_XENOMAI=y
CONFIG_XENO_OPT_NUCLEUS=y
CONFIG_XENO_OPT_PERVASIVE=y
CONFIG_XENO_OPT_ISHIELD=y
# CONFIG_XENO_OPT_RPIDISABLE is not set
CONFIG_XENO_OPT_PIPELINE_HEAD=y
CONFIG_XENO_OPT_PIPE=y
CONFIG_XENO_OPT_PIPE_NRDEV=32
CONFIG_XENO_OPT_REGISTRY=y
CONFIG_XENO_OPT_REGISTRY_NRSLOTS=512
CONFIG_XENO_OPT_SYS_HEAPSZ=128
CONFIG_XENO_OPT_STATS=y
CONFIG_XENO_OPT_DEBUG=y
# CONFIG_XENO_OPT_DEBUG_NUCLEUS is not set
# CONFIG_XENO_OPT_DEBUG_QUEUES is not set
CONFIG_XENO_OPT_WATCHDOG=y
#
# Timing
#
# CONFIG_XENO_OPT_TIMING_PERIODIC is not set
CONFIG_XENO_OPT_TIMING_PERIOD=0
CONFIG_XENO_OPT_TIMING_TIMERLAT=0
CONFIG_XENO_OPT_TIMING_SCHEDLAT=0
#
# Scalability
#
# CONFIG_XENO_OPT_SCALABLE_SCHED is not set
CONFIG_XENO_OPT_TIMER_LIST=y
# CONFIG_XENO_OPT_TIMER_HEAP is not set
# CONFIG_XENO_OPT_TIMER_WHEEL is not set
#
# Shared interrupts
#
CONFIG_XENO_OPT_SHIRQ_LEVEL=y
# CONFIG_XENO_OPT_SHIRQ_EDGE is not set
#
# Machine
#
CONFIG_XENO_HW_FPU=y
#
# NMI watchdog
#
#
# SMI workaround
#
# CONFIG_XENO_HW_SMI_DETECT_DISABLE is not set
CONFIG_XENO_HW_SMI_DETECT=y
CONFIG_XENO_HW_SMI_WORKAROUND=y
CONFIG_XENO_HW_SMI_ALL=y
#
# Interfaces
#
CONFIG_XENO_SKIN_NATIVE=y
CONFIG_XENO_OPT_NATIVE_PIPE=y
CONFIG_XENO_OPT_NATIVE_PIPE_BUFSZ=4096
CONFIG_XENO_OPT_NATIVE_REGISTRY=y
CONFIG_XENO_OPT_NATIVE_SEM=y
CONFIG_XENO_OPT_NATIVE_EVENT=y
CONFIG_XENO_OPT_NATIVE_MUTEX=y
CONFIG_XENO_OPT_NATIVE_COND=y
CONFIG_XENO_OPT_NATIVE_QUEUE=y
CONFIG_XENO_OPT_NATIVE_HEAP=y
CONFIG_XENO_OPT_NATIVE_ALARM=y
CONFIG_XENO_OPT_NATIVE_MPS=y
CONFIG_XENO_OPT_NATIVE_INTR=y
# CONFIG_XENO_SKIN_POSIX is not set
# CONFIG_XENO_SKIN_PSOS is not set
# CONFIG_XENO_SKIN_UITRON is not set
# CONFIG_XENO_SKIN_VRTX is not set
# CONFIG_XENO_SKIN_VXWORKS is not set
# CONFIG_XENO_SKIN_RTAI is not set
CONFIG_XENO_SKIN_RTDM=y
CONFIG_XENO_OPT_RTDM_FILDES=128
CONFIG_XENO_OPT_DEBUG_RTDM=y
#
# Drivers
#
#
# Serial drivers
#
CONFIG_XENO_DRIVERS_16550A=y
#
# Testing drivers
#
CONFIG_XENO_DRIVERS_TIMERBENCH=y
CONFIG_XENO_DRIVERS_IRQBENCH=y
CONFIG_XENO_DRIVERS_SWITCHTEST=y
#
# CAN drivers
#
# CONFIG_XENO_DRIVERS_CAN is not set
#
# Processor type and features
#
# CONFIG_SMP is not set
CONFIG_X86_PC=y
# CONFIG_X86_ELAN is not set
# CONFIG_X86_VOYAGER is not set
# CONFIG_X86_NUMAQ is not set
# CONFIG_X86_SUMMIT is not set
# CONFIG_X86_BIGSMP is not set
# CONFIG_X86_VISWS is not set
# CONFIG_X86_GENERICARCH is not set
# CONFIG_X86_ES7000 is not set
# CONFIG_M386 is not set
# CONFIG_M486 is not set
# CONFIG_M586 is not set
# CONFIG_M586TSC is not set
# CONFIG_M586MMX is not set
# CONFIG_M686 is not set
# CONFIG_MPENTIUMII is not set
CONFIG_MPENTIUMIII=y
# CONFIG_MPENTIUMM is not set
# CONFIG_MCORE2 is not set
# CONFIG_MPENTIUM4 is not set
# CONFIG_MK6 is not set
# CONFIG_MK7 is not set
# CONFIG_MK8 is not set
# CONFIG_MCRUSOE is not set
# CONFIG_MEFFICEON is not set
# CONFIG_MWINCHIPC6 is not set
# CONFIG_MWINCHIP2 is not set
# CONFIG_MWINCHIP3D is not set
# CONFIG_MGEODEGX1 is not set
# CONFIG_MGEODE_LX is not set
# CONFIG_MCYRIXIII is not set
# CONFIG_MVIAC3_2 is not set
CONFIG_X86_GENERIC=y
CONFIG_X86_CMPXCHG=y
CONFIG_X86_XADD=y
CONFIG_X86_L1_CACHE_SHIFT=7
CONFIG_RWSEM_XCHGADD_ALGORITHM=y
# CONFIG_ARCH_HAS_ILOG2_U32 is not set
# CONFIG_ARCH_HAS_ILOG2_U64 is not set
CONFIG_GENERIC_CALIBRATE_DELAY=y
CONFIG_X86_WP_WORKS_OK=y
CONFIG_X86_INVLPG=y
CONFIG_X86_BSWAP=y
CONFIG_X86_POPAD_OK=y
CONFIG_X86_CMPXCHG64=y
CONFIG_X86_GOOD_APIC=y
CONFIG_X86_INTEL_USERCOPY=y
CONFIG_X86_USE_PPRO_CHECKSUM=y
CONFIG_X86_TSC=y
CONFIG_HPET_TIMER=y
CONFIG_HPET_EMULATE_RTC=y
# CONFIG_PREEMPT_NONE is not set
CONFIG_PREEMPT_VOLUNTARY=y
# CONFIG_PREEMPT is not set
CONFIG_IPIPE=y
# CONFIG_X86_UP_APIC is not set
CONFIG_X86_MCE=y
# CONFIG_X86_MCE_NONFATAL is not set
CONFIG_VM86=y
# CONFIG_TOSHIBA is not set
# CONFIG_I8K is not set
# CONFIG_X86_REBOOTFIXUPS is not set
CONFIG_MICROCODE=m
CONFIG_MICROCODE_OLD_INTERFACE=y
CONFIG_X86_MSR=m
CONFIG_X86_CPUID=m
#
# Firmware Drivers
#
CONFIG_EDD=y
# CONFIG_DELL_RBU is not set
# CONFIG_DCDBAS is not set
CONFIG_NOHIGHMEM=y
# CONFIG_HIGHMEM4G is not set
# CONFIG_HIGHMEM64G is not set
CONFIG_PAGE_OFFSET=0xC0000000
CONFIG_ARCH_POPULATES_NODE_MAP=y
CONFIG_FLATMEM=y
CONFIG_FLAT_NODE_MEM_MAP=y
# CONFIG_SPARSEMEM_STATIC is not set
CONFIG_SPLIT_PTLOCK_CPUS=4
# CONFIG_RESOURCES_64BIT is not set
# CONFIG_MATH_EMULATION is not set
# CONFIG_MTRR is not set
CONFIG_SECCOMP=y
# CONFIG_HZ_100 is not set
# CONFIG_HZ_250 is not set
# CONFIG_HZ_300 is not set
CONFIG_HZ_1000=y
CONFIG_HZ=1000
CONFIG_KEXEC=y
CONFIG_PHYSICAL_START=0x100000
CONFIG_PHYSICAL_ALIGN=0x100000
CONFIG_COMPAT_VDSO=y
#
# Power management options (ACPI, APM)
#
# CONFIG_PM is not set
#
# ACPI (Advanced Configuration and Power Interface) Support
#
#
# CPU Frequency scaling
#
# CONFIG_CPU_FREQ is not set
#
# Bus options (PCI, PCMCIA, EISA, MCA, ISA)
#
CONFIG_PCI=y
# CONFIG_PCI_GOBIOS is not set
# CONFIG_PCI_GOMMCONFIG is not set
# CONFIG_PCI_GODIRECT is not set
CONFIG_PCI_GOANY=y
CONFIG_PCI_BIOS=y
CONFIG_PCI_DIRECT=y
# CONFIG_PCIEPORTBUS is not set
CONFIG_ISA_DMA_API=y
CONFIG_ISA=y
# CONFIG_EISA is not set
# CONFIG_MCA is not set
# CONFIG_SCx200 is not set
#
# PCCARD (PCMCIA/CardBus) support
#
# CONFIG_PCCARD is not set
#
# PCI Hotplug Support
#
#
# Executable file formats
#
CONFIG_BINFMT_ELF=y
CONFIG_BINFMT_AOUT=m
CONFIG_BINFMT_MISC=m
#
# Networking
#
CONFIG_NET=y
#
# Networking options
#
# CONFIG_NETDEBUG is not set
CONFIG_PACKET=y
CONFIG_PACKET_MMAP=y
CONFIG_UNIX=y
# CONFIG_NET_KEY is not set
CONFIG_INET=y
# CONFIG_IP_MULTICAST is not set
# CONFIG_IP_ADVANCED_ROUTER is not set
CONFIG_IP_FIB_HASH=y
# CONFIG_IP_PNP is not set
# CONFIG_NET_IPIP is not set
# CONFIG_NET_IPGRE is not set
# CONFIG_SYN_COOKIES is not set
# CONFIG_INET_AH is not set
# CONFIG_INET_ESP is not set
# CONFIG_INET_IPCOMP is not set
# CONFIG_INET_XFRM_TUNNEL is not set
# CONFIG_INET_TUNNEL is not set
# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
# CONFIG_INET_XFRM_MODE_TUNNEL is not set
# CONFIG_INET_XFRM_MODE_BEET is not set
# CONFIG_INET_DIAG is not set
# CONFIG_TCP_CONG_ADVANCED is not set
CONFIG_TCP_CONG_CUBIC=y
CONFIG_DEFAULT_TCP_CONG="cubic"
# CONFIG_IPV6 is not set
# CONFIG_INET6_XFRM_TUNNEL is not set
# CONFIG_INET6_TUNNEL is not set
# CONFIG_NETWORK_SECMARK is not set
# CONFIG_NETFILTER is not set
# CONFIG_BRIDGE is not set
# CONFIG_VLAN_8021Q is not set
# CONFIG_DECNET is not set
# CONFIG_LLC2 is not set
# CONFIG_IPX is not set
# CONFIG_ATALK is not set
#
# QoS and/or fair queueing
#
# CONFIG_NET_SCHED is not set
#
# Network testing
#
# CONFIG_NET_PKTGEN is not set
# CONFIG_HAMRADIO is not set
# CONFIG_IRDA is not set
# CONFIG_BT is not set
# CONFIG_IEEE80211 is not set
#
# Device Drivers
#
#
# Generic Driver Options
#
CONFIG_STANDALONE=y
CONFIG_PREVENT_FIRMWARE_BUILD=y
CONFIG_FW_LOADER=y
# CONFIG_SYS_HYPERVISOR is not set
#
# Connector - unified userspace <-> kernelspace linker
#
CONFIG_CONNECTOR=m
#
# Memory Technology Devices (MTD)
#
# CONFIG_MTD is not set
#
# Parallel port support
#
# CONFIG_PARPORT is not set
#
# Plug and Play support
#
CONFIG_PNP=y
CONFIG_PNP_DEBUG=y
#
# Protocols
#
CONFIG_ISAPNP=y
#
# Block devices
#
# CONFIG_BLK_DEV_FD is not set
# CONFIG_BLK_DEV_XD is not set
# CONFIG_BLK_CPQ_DA is not set
# CONFIG_BLK_CPQ_CISS_DA is not set
# CONFIG_BLK_DEV_DAC960 is not set
# CONFIG_BLK_DEV_COW_COMMON is not set
# CONFIG_BLK_DEV_LOOP is not set
# CONFIG_BLK_DEV_NBD is not set
# CONFIG_BLK_DEV_SX8 is not set
# CONFIG_BLK_DEV_UB is not set
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_COUNT=16
CONFIG_BLK_DEV_RAM_SIZE=32000
CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024
CONFIG_BLK_DEV_INITRD=y
CONFIG_CDROM_PKTCDVD=y
CONFIG_CDROM_PKTCDVD_BUFFERS=8
# CONFIG_ATA_OVER_ETH is not set
#
# Misc devices
#
# CONFIG_SGI_IOC4 is not set
#
# ATA/ATAPI/MFM/RLL support
#
CONFIG_IDE=y
CONFIG_BLK_DEV_IDE=y
#
# Please see Documentation/ide.txt for help/info on IDE drives
#
# CONFIG_BLK_DEV_IDE_SATA is not set
# CONFIG_BLK_DEV_HD_IDE is not set
CONFIG_BLK_DEV_IDEDISK=y
CONFIG_IDEDISK_MULTI_MODE=y
CONFIG_BLK_DEV_IDECD=y
# CONFIG_BLK_DEV_IDEFLOPPY is not set
# CONFIG_IDE_TASK_IOCTL is not set
#
# IDE chipset support/bugfixes
#
CONFIG_IDE_GENERIC=m
# CONFIG_BLK_DEV_CMD640 is not set
# CONFIG_BLK_DEV_IDEPNP is not set
CONFIG_BLK_DEV_IDEPCI=y
CONFIG_IDEPCI_SHARE_IRQ=y
CONFIG_BLK_DEV_OFFBOARD=y
CONFIG_BLK_DEV_GENERIC=y
# CONFIG_BLK_DEV_RZ1000 is not set
CONFIG_BLK_DEV_IDEDMA_PCI=y
# CONFIG_BLK_DEV_IDEDMA_FORCED is not set
# CONFIG_IDEDMA_PCI_AUTO is not set
# CONFIG_BLK_DEV_AEC62XX is not set
# CONFIG_BLK_DEV_ALI15X3 is not set
# CONFIG_BLK_DEV_AMD74XX is not set
# CONFIG_BLK_DEV_ATIIXP is not set
# CONFIG_BLK_DEV_CMD64X is not set
# CONFIG_BLK_DEV_TRIFLEX is not set
# CONFIG_BLK_DEV_CY82C693 is not set
# CONFIG_BLK_DEV_CS5530 is not set
# CONFIG_BLK_DEV_CS5535 is not set
# CONFIG_BLK_DEV_HPT34X is not set
# CONFIG_BLK_DEV_HPT366 is not set
# CONFIG_BLK_DEV_JMICRON is not set
# CONFIG_BLK_DEV_SC1200 is not set
CONFIG_BLK_DEV_PIIX=y
# CONFIG_BLK_DEV_IT821X is not set
# CONFIG_BLK_DEV_NS87415 is not set
# CONFIG_BLK_DEV_PDC202XX_OLD is not set
# CONFIG_BLK_DEV_PDC202XX_NEW is not set
# CONFIG_BLK_DEV_SVWKS is not set
# CONFIG_BLK_DEV_SIIMAGE is not set
# CONFIG_BLK_DEV_SIS5513 is not set
# CONFIG_BLK_DEV_SLC90E66 is not set
# CONFIG_BLK_DEV_TRM290 is not set
# CONFIG_BLK_DEV_VIA82CXXX is not set
# CONFIG_IDE_ARM is not set
# CONFIG_IDE_CHIPSETS is not set
CONFIG_BLK_DEV_IDEDMA=y
# CONFIG_IDEDMA_IVB is not set
# CONFIG_IDEDMA_AUTO is not set
# CONFIG_BLK_DEV_HD is not set
#
# SCSI device support
#
# CONFIG_RAID_ATTRS is not set
# CONFIG_SCSI is not set
# CONFIG_SCSI_NETLINK is not set
#
# Serial ATA (prod) and Parallel ATA (experimental) drivers
#
# CONFIG_ATA is not set
#
# Old CD-ROM drivers (not SCSI, not IDE)
#
# CONFIG_CD_NO_IDESCSI is not set
#
# Multi-device support (RAID and LVM)
#
# CONFIG_MD is not set
#
# Fusion MPT device support
#
# CONFIG_FUSION is not set
#
# IEEE 1394 (FireWire) support
#
# CONFIG_IEEE1394 is not set
#
# I2O device support
#
CONFIG_I2O=m
CONFIG_I2O_LCT_NOTIFY_ON_CHANGES=y
CONFIG_I2O_EXT_ADAPTEC=y
# CONFIG_I2O_CONFIG is not set
# CONFIG_I2O_BUS is not set
# CONFIG_I2O_BLOCK is not set
# CONFIG_I2O_PROC is not set
#
# Network device support
#
CONFIG_NETDEVICES=y
# CONFIG_DUMMY is not set
# CONFIG_BONDING is not set
# CONFIG_EQUALIZER is not set
# CONFIG_TUN is not set
# CONFIG_NET_SB1000 is not set
#
# ARCnet devices
#
# CONFIG_ARCNET is not set
#
# PHY device support
#
# CONFIG_PHYLIB is not set
#
# Ethernet (10 or 100Mbit)
#
CONFIG_NET_ETHERNET=y
CONFIG_MII=y
# CONFIG_HAPPYMEAL is not set
# CONFIG_SUNGEM is not set
# CONFIG_CASSINI is not set
CONFIG_NET_VENDOR_3COM=y
# CONFIG_EL1 is not set
# CONFIG_EL2 is not set
# CONFIG_ELPLUS is not set
# CONFIG_EL3 is not set
# CONFIG_3C515 is not set
CONFIG_VORTEX=y
# CONFIG_TYPHOON is not set
# CONFIG_LANCE is not set
# CONFIG_NET_VENDOR_SMC is not set
# CONFIG_NET_VENDOR_RACAL is not set
#
# Tulip family network device support
#
# CONFIG_NET_TULIP is not set
# CONFIG_DEPCA is not set
# CONFIG_HP100 is not set
# CONFIG_NET_ISA is not set
# CONFIG_NET_PCI is not set
#
# Ethernet (1000 Mbit)
#
# CONFIG_ACENIC is not set
# CONFIG_DL2K is not set
# CONFIG_E1000 is not set
# CONFIG_NS83820 is not set
# CONFIG_HAMACHI is not set
# CONFIG_R8169 is not set
# CONFIG_SIS190 is not set
# CONFIG_SKGE is not set
# CONFIG_SKY2 is not set
# CONFIG_SK98LIN is not set
# CONFIG_TIGON3 is not set
# CONFIG_BNX2 is not set
# CONFIG_QLA3XXX is not set
#
# Ethernet (10000 Mbit)
#
# CONFIG_CHELSIO_T1 is not set
# CONFIG_IXGB is not set
# CONFIG_S2IO is not set
# CONFIG_MYRI10GE is not set
# CONFIG_NETXEN_NIC is not set
#
# Token Ring devices
#
# CONFIG_TR is not set
#
# Wireless LAN (non-hamradio)
#
# CONFIG_NET_RADIO is not set
#
# Wan interfaces
#
CONFIG_WAN=y
CONFIG_HOSTESS_SV11=m
CONFIG_COSA=m
CONFIG_LANMEDIA=m
CONFIG_SEALEVEL_4021=m
CONFIG_HDLC=m
CONFIG_HDLC_RAW=m
CONFIG_HDLC_RAW_ETH=m
CONFIG_HDLC_CISCO=m
CONFIG_HDLC_FR=m
CONFIG_HDLC_PPP=m
#
# X.25/LAPB support is disabled
#
CONFIG_PCI200SYN=m
CONFIG_WANXL=m
CONFIG_PC300=m
#
# Cyclades-PC300 MLPPP support is disabled.
#
#
# Refer to the file README.mlppp, provided by PC300 package.
#
CONFIG_N2=m
CONFIG_C101=m
CONFIG_FARSYNC=m
CONFIG_DSCC4=m
CONFIG_DSCC4_PCISYNC=y
CONFIG_DSCC4_PCI_RST=y
CONFIG_DLCI=m
CONFIG_DLCI_COUNT=24
CONFIG_DLCI_MAX=8
# CONFIG_SDLA is not set
CONFIG_SBNI=m
CONFIG_SBNI_MULTILINE=y
# CONFIG_FDDI is not set
# CONFIG_PPP is not set
# CONFIG_SLIP is not set
# CONFIG_NETPOLL is not set
# CONFIG_NET_POLL_CONTROLLER is not set
#
# ISDN subsystem
#
# CONFIG_ISDN is not set
#
# Telephony Support
#
# CONFIG_PHONE is not set
#
# Input device support
#
CONFIG_INPUT=y
# CONFIG_INPUT_FF_MEMLESS is not set
#
# Userland interfaces
#
CONFIG_INPUT_MOUSEDEV=y
# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
# CONFIG_INPUT_JOYDEV is not set
# CONFIG_INPUT_TSDEV is not set
# CONFIG_INPUT_EVDEV is not set
# CONFIG_INPUT_EVBUG is not set
#
# Input Device Drivers
#
CONFIG_INPUT_KEYBOARD=y
CONFIG_KEYBOARD_ATKBD=y
# CONFIG_KEYBOARD_SUNKBD is not set
# CONFIG_KEYBOARD_LKKBD is not set
# CONFIG_KEYBOARD_XTKBD is not set
# CONFIG_KEYBOARD_NEWTON is not set
# CONFIG_KEYBOARD_STOWAWAY is not set
CONFIG_INPUT_MOUSE=y
CONFIG_MOUSE_PS2=y
# CONFIG_MOUSE_SERIAL is not set
# CONFIG_MOUSE_INPORT is not set
# CONFIG_MOUSE_LOGIBM is not set
# CONFIG_MOUSE_PC110PAD is not set
# CONFIG_MOUSE_VSXXXAA is not set
# CONFIG_INPUT_JOYSTICK is not set
# CONFIG_INPUT_TOUCHSCREEN is not set
# CONFIG_INPUT_MISC is not set
#
# Hardware I/O ports
#
CONFIG_SERIO=y
CONFIG_SERIO_I8042=y
CONFIG_SERIO_SERPORT=m
CONFIG_SERIO_CT82C710=m
CONFIG_SERIO_PCIPS2=m
CONFIG_SERIO_LIBPS2=y
CONFIG_SERIO_RAW=m
# CONFIG_GAMEPORT is not set
#
# Character devices
#
CONFIG_VT=y
CONFIG_VT_CONSOLE=y
CONFIG_HW_CONSOLE=y
# CONFIG_VT_HW_CONSOLE_BINDING is not set
# CONFIG_SERIAL_NONSTANDARD is not set
#
# Serial drivers
#
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_SERIAL_8250_PCI=y
CONFIG_SERIAL_8250_PNP=y
CONFIG_SERIAL_8250_NR_UARTS=4
CONFIG_SERIAL_8250_RUNTIME_UARTS=4
CONFIG_SERIAL_8250_EXTENDED=y
# CONFIG_SERIAL_8250_MANY_PORTS is not set
CONFIG_SERIAL_8250_SHARE_IRQ=y
# CONFIG_SERIAL_8250_DETECT_IRQ is not set
# CONFIG_SERIAL_8250_RSA is not set
#
# Non-8250 serial port support
#
CONFIG_SERIAL_CORE=y
CONFIG_SERIAL_CORE_CONSOLE=y
# CONFIG_SERIAL_JSM is not set
CONFIG_UNIX98_PTYS=y
CONFIG_LEGACY_PTYS=y
CONFIG_LEGACY_PTY_COUNT=256
#
# IPMI
#
# CONFIG_IPMI_HANDLER is not set
#
# Watchdog Cards
#
# CONFIG_WATCHDOG is not set
CONFIG_HW_RANDOM=m
CONFIG_HW_RANDOM_INTEL=m
# CONFIG_HW_RANDOM_AMD is not set
# CONFIG_HW_RANDOM_GEODE is not set
# CONFIG_HW_RANDOM_VIA is not set
CONFIG_NVRAM=m
CONFIG_RTC=y
# CONFIG_DTLK is not set
# CONFIG_R3964 is not set
# CONFIG_APPLICOM is not set
CONFIG_AGP=y
# CONFIG_AGP_ALI is not set
# CONFIG_AGP_ATI is not set
# CONFIG_AGP_AMD is not set
# CONFIG_AGP_AMD64 is not set
CONFIG_AGP_INTEL=m
# CONFIG_AGP_NVIDIA is not set
# CONFIG_AGP_SIS is not set
# CONFIG_AGP_SWORKS is not set
# CONFIG_AGP_VIA is not set
# CONFIG_AGP_EFFICEON is not set
# CONFIG_DRM is not set
# CONFIG_MWAVE is not set
# CONFIG_PC8736x_GPIO is not set
# CONFIG_NSC_GPIO is not set
# CONFIG_CS5535_GPIO is not set
# CONFIG_RAW_DRIVER is not set
# CONFIG_HANGCHECK_TIMER is not set
#
# TPM devices
#
#
# I2C support
#
CONFIG_I2C=m
CONFIG_I2C_CHARDEV=m
#
# I2C Algorithms
#
CONFIG_I2C_ALGOBIT=m
# CONFIG_I2C_ALGOPCF is not set
CONFIG_I2C_ALGOPCA=m
#
# I2C Hardware Bus support
#
CONFIG_I2C_ALI1535=m
CONFIG_I2C_ALI15X3=m
CONFIG_I2C_AMD756=m
CONFIG_I2C_AMD8111=m
# CONFIG_I2C_ELEKTOR is not set
CONFIG_I2C_I801=m
CONFIG_I2C_I810=m
CONFIG_I2C_PIIX4=m
CONFIG_I2C_NFORCE2=m
CONFIG_I2C_PARPORT_LIGHT=m
CONFIG_I2C_PROSAVAGE=m
# CONFIG_SCx200_ACB is not set
CONFIG_I2C_SIS5595=m
CONFIG_I2C_SIS630=m
CONFIG_I2C_SIS96X=m
CONFIG_I2C_VIAPRO=m
CONFIG_I2C_VOODOO3=m
CONFIG_I2C_PCA_ISA=m
#
# Miscellaneous I2C Chip support
#
# CONFIG_I2C_DEBUG_CORE is not set
# CONFIG_I2C_DEBUG_ALGO is not set
# CONFIG_I2C_DEBUG_BUS is not set
# CONFIG_I2C_DEBUG_CHIP is not set
#
# SPI support
#
# CONFIG_SPI is not set
# CONFIG_SPI_MASTER is not set
#
# Dallas's 1-wire bus
#
# CONFIG_W1 is not set
#
# Hardware Monitoring support
#
# CONFIG_HWMON is not set
# CONFIG_HWMON_VID is not set
#
# Multimedia devices
#
# CONFIG_VIDEO_DEV is not set
#
# Digital Video Broadcasting Devices
#
# CONFIG_DVB is not set
# CONFIG_USB_DABUSB is not set
#
# Graphics support
#
CONFIG_FIRMWARE_EDID=y
CONFIG_FB=y
# CONFIG_FB_DDC is not set
CONFIG_FB_CFB_FILLRECT=y
CONFIG_FB_CFB_COPYAREA=y
CONFIG_FB_CFB_IMAGEBLIT=y
# CONFIG_FB_MACMODES is not set
# CONFIG_FB_BACKLIGHT is not set
CONFIG_FB_MODE_HELPERS=y
CONFIG_FB_TILEBLITTING=y
# CONFIG_FB_CIRRUS is not set
# CONFIG_FB_PM2 is not set
# CONFIG_FB_CYBER2000 is not set
# CONFIG_FB_ARC is not set
# CONFIG_FB_ASILIANT is not set
# CONFIG_FB_IMSTT is not set
CONFIG_FB_VGA16=m
CONFIG_FB_VESA=y
# CONFIG_FB_HGA is not set
# CONFIG_FB_S1D13XXX is not set
# CONFIG_FB_NVIDIA is not set
# CONFIG_FB_RIVA is not set
# CONFIG_FB_MATROX is not set
# CONFIG_FB_RADEON is not set
# CONFIG_FB_ATY128 is not set
# CONFIG_FB_ATY is not set
# CONFIG_FB_SIS is not set
# CONFIG_FB_NEOMAGIC is not set
# CONFIG_FB_KYRO is not set
# CONFIG_FB_3DFX is not set
# CONFIG_FB_VOODOO1 is not set
# CONFIG_FB_CYBLA is not set
# CONFIG_FB_TRIDENT is not set
# CONFIG_FB_VIRTUAL is not set
#
# Console display driver support
#
CONFIG_VGA_CONSOLE=y
# CONFIG_VGACON_SOFT_SCROLLBACK is not set
CONFIG_VIDEO_SELECT=y
# CONFIG_MDA_CONSOLE is not set
CONFIG_DUMMY_CONSOLE=y
CONFIG_FRAMEBUFFER_CONSOLE=y
# CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set
CONFIG_FONTS=y
CONFIG_FONT_8x8=y
CONFIG_FONT_8x16=y
# CONFIG_FONT_6x11 is not set
# CONFIG_FONT_7x14 is not set
# CONFIG_FONT_PEARL_8x8 is not set
# CONFIG_FONT_ACORN_8x8 is not set
# CONFIG_FONT_MINI_4x6 is not set
# CONFIG_FONT_SUN8x16 is not set
# CONFIG_FONT_SUN12x22 is not set
# CONFIG_FONT_10x18 is not set
#
# Logo configuration
#
CONFIG_LOGO=y
CONFIG_LOGO_LINUX_MONO=y
CONFIG_LOGO_LINUX_VGA16=y
CONFIG_LOGO_LINUX_CLUT224=y
# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
#
# Sound
#
# CONFIG_SOUND is not set
#
# HID Devices
#
CONFIG_HID=y
#
# USB support
#
CONFIG_USB_ARCH_HAS_HCD=y
CONFIG_USB_ARCH_HAS_OHCI=y
CONFIG_USB_ARCH_HAS_EHCI=y
CONFIG_USB=y
# CONFIG_USB_DEBUG is not set
#
# Miscellaneous USB options
#
# CONFIG_USB_DEVICEFS is not set
#
# USB Host Controller Drivers
#
# CONFIG_USB_EHCI_HCD is not set
# CONFIG_USB_ISP116X_HCD is not set
# CONFIG_USB_OHCI_HCD is not set
CONFIG_USB_UHCI_HCD=y
# CONFIG_USB_SL811_HCD is not set
#
# USB Device Class drivers
#
# CONFIG_USB_ACM is not set
# CONFIG_USB_PRINTER is not set
#
# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
#
#
# may also be needed; see USB_STORAGE Help for more information
#
# CONFIG_USB_LIBUSUAL is not set
#
# USB Input Devices
#
CONFIG_USB_HID=y
# CONFIG_USB_HIDINPUT_POWERBOOK is not set
# CONFIG_USB_HIDDEV is not set
# CONFIG_USB_AIPTEK is not set
# CONFIG_USB_WACOM is not set
# CONFIG_USB_ACECAD is not set
# CONFIG_USB_KBTAB is not set
# CONFIG_USB_POWERMATE is not set
# CONFIG_USB_TOUCHSCREEN is not set
# CONFIG_USB_XPAD is not set
# CONFIG_USB_ATI_REMOTE is not set
# CONFIG_USB_ATI_REMOTE2 is not set
# CONFIG_USB_APPLETOUCH is not set
#
# USB Imaging devices
#
#
# USB Network Adapters
#
# CONFIG_USB_KAWETH is not set
# CONFIG_USB_PEGASUS is not set
# CONFIG_USB_USBNET_MII is not set
# CONFIG_USB_USBNET is not set
CONFIG_USB_MON=y
#
# USB port drivers
#
#
# USB Serial Converter support
#
# CONFIG_USB_SERIAL is not set
#
# USB Miscellaneous drivers
#
# CONFIG_USB_EMI62 is not set
# CONFIG_USB_EMI26 is not set
# CONFIG_USB_LCD is not set
# CONFIG_USB_LED is not set
# CONFIG_USB_CYPRESS_CY7C63 is not set
# CONFIG_USB_CYTHERM is not set
# CONFIG_USB_PHIDGET is not set
# CONFIG_USB_IDMOUSE is not set
# CONFIG_USB_FTDI_ELAN is not set
# CONFIG_USB_APPLEDISPLAY is not set
# CONFIG_USB_LD is not set
# CONFIG_USB_TRANCEVIBRATOR is not set
#
# USB DSL modem support
#
#
# USB Gadget Support
#
# CONFIG_USB_GADGET is not set
#
# MMC/SD Card support
#
# CONFIG_MMC is not set
#
# LED devices
#
# CONFIG_NEW_LEDS is not set
#
# LED drivers
#
#
# LED Triggers
#
#
# InfiniBand support
#
# CONFIG_INFINIBAND is not set
#
# EDAC - error detection and reporting (RAS) (EXPERIMENTAL)
#
#
# Real Time Clock
#
#
# DMA Engine support
#
# CONFIG_DMA_ENGINE is not set
#
# DMA Clients
#
#
# DMA Devices
#
#
# Virtualization
#
#
# File systems
#
# CONFIG_EXT2_FS is not set
CONFIG_EXT3_FS=m
CONFIG_EXT3_FS_XATTR=y
CONFIG_EXT3_FS_POSIX_ACL=y
CONFIG_EXT3_FS_SECURITY=y
CONFIG_JBD=m
# CONFIG_JBD_DEBUG is not set
CONFIG_FS_MBCACHE=m
# CONFIG_REISERFS_FS is not set
# CONFIG_JFS_FS is not set
CONFIG_FS_POSIX_ACL=y
# CONFIG_XFS_FS is not set
# CONFIG_OCFS2_FS is not set
# CONFIG_MINIX_FS is not set
# CONFIG_ROMFS_FS is not set
# CONFIG_INOTIFY is not set
# CONFIG_QUOTA is not set
CONFIG_DNOTIFY=y
# CONFIG_AUTOFS_FS is not set
# CONFIG_AUTOFS4_FS is not set
CONFIG_FUSE_FS=y
CONFIG_GENERIC_ACL=y
#
# CD-ROM/DVD Filesystems
#
CONFIG_ISO9660_FS=y
# CONFIG_JOLIET is not set
# CONFIG_ZISOFS is not set
# CONFIG_UDF_FS is not set
#
# DOS/FAT/NT Filesystems
#
# CONFIG_MSDOS_FS is not set
# CONFIG_VFAT_FS is not set
# CONFIG_NTFS_FS is not set
#
# Pseudo filesystems
#
CONFIG_PROC_FS=y
CONFIG_PROC_KCORE=y
CONFIG_PROC_SYSCTL=y
CONFIG_SYSFS=y
CONFIG_TMPFS=y
CONFIG_TMPFS_POSIX_ACL=y
CONFIG_HUGETLBFS=y
CONFIG_HUGETLB_PAGE=y
CONFIG_RAMFS=y
#
# Miscellaneous filesystems
#
# CONFIG_HFSPLUS_FS is not set
# CONFIG_CRAMFS is not set
# CONFIG_VXFS_FS is not set
# CONFIG_HPFS_FS is not set
# CONFIG_QNX4FS_FS is not set
# CONFIG_SYSV_FS is not set
# CONFIG_UFS_FS is not set
#
# Network File Systems
#
# CONFIG_NFS_FS is not set
# CONFIG_NFSD is not set
# CONFIG_SMB_FS is not set
# CONFIG_CIFS is not set
# CONFIG_NCP_FS is not set
# CONFIG_CODA_FS is not set
#
# Partition Types
#
# CONFIG_PARTITION_ADVANCED is not set
CONFIG_MSDOS_PARTITION=y
#
# Native Language Support
#
CONFIG_NLS=y
CONFIG_NLS_DEFAULT="iso8859-1"
CONFIG_NLS_CODEPAGE_437=m
# CONFIG_NLS_CODEPAGE_737 is not set
# CONFIG_NLS_CODEPAGE_775 is not set
# CONFIG_NLS_CODEPAGE_850 is not set
CONFIG_NLS_CODEPAGE_852=m
# CONFIG_NLS_CODEPAGE_855 is not set
# CONFIG_NLS_CODEPAGE_857 is not set
# CONFIG_NLS_CODEPAGE_860 is not set
# CONFIG_NLS_CODEPAGE_861 is not set
# CONFIG_NLS_CODEPAGE_862 is not set
# CONFIG_NLS_CODEPAGE_863 is not set
# CONFIG_NLS_CODEPAGE_864 is not set
# CONFIG_NLS_CODEPAGE_865 is not set
# CONFIG_NLS_CODEPAGE_866 is not set
# CONFIG_NLS_CODEPAGE_869 is not set
# CONFIG_NLS_CODEPAGE_936 is not set
# CONFIG_NLS_CODEPAGE_950 is not set
# CONFIG_NLS_CODEPAGE_932 is not set
# CONFIG_NLS_CODEPAGE_949 is not set
# CONFIG_NLS_CODEPAGE_874 is not set
# CONFIG_NLS_ISO8859_8 is not set
CONFIG_NLS_CODEPAGE_1250=m
CONFIG_NLS_CODEPAGE_1251=m
CONFIG_NLS_ASCII=m
CONFIG_NLS_ISO8859_1=m
# CONFIG_NLS_ISO8859_2 is not set
# CONFIG_NLS_ISO8859_3 is not set
# CONFIG_NLS_ISO8859_4 is not set
# CONFIG_NLS_ISO8859_5 is not set
# CONFIG_NLS_ISO8859_6 is not set
# CONFIG_NLS_ISO8859_7 is not set
# CONFIG_NLS_ISO8859_9 is not set
# CONFIG_NLS_ISO8859_13 is not set
# CONFIG_NLS_ISO8859_14 is not set
# CONFIG_NLS_ISO8859_15 is not set
# CONFIG_NLS_KOI8_R is not set
# CONFIG_NLS_KOI8_U is not set
CONFIG_NLS_UTF8=m
#
# Kernel hacking
#
CONFIG_TRACE_IRQFLAGS_SUPPORT=y
# CONFIG_PRINTK_TIME is not set
CONFIG_ENABLE_MUST_CHECK=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_UNUSED_SYMBOLS=y
CONFIG_DEBUG_FS=y
# CONFIG_HEADERS_CHECK is not set
CONFIG_IPIPE_DEBUG=y
CONFIG_IPIPE_DEBUG_CONTEXT=y
CONFIG_IPIPE_TRACE=y
CONFIG_IPIPE_TRACE_ENABLE=y
CONFIG_IPIPE_TRACE_MCOUNT=y
CONFIG_IPIPE_TRACE_IRQSOFF=y
CONFIG_IPIPE_TRACE_SHIFT=14
# CONFIG_IPIPE_TRACE_VMALLOC is not set
CONFIG_IPIPE_TRACE_PANIC=y
CONFIG_IPIPE_TRACE_ENABLE_VALUE=1
# CONFIG_DEBUG_KERNEL is not set
CONFIG_LOG_BUF_SHIFT=14
CONFIG_DEBUG_BUGVERBOSE=y
CONFIG_FRAME_POINTER=y
CONFIG_EARLY_PRINTK=y
CONFIG_DOUBLEFAULT=y
#
# Security options
#
# CONFIG_KEYS is not set
# CONFIG_SECURITY is not set
#
# Cryptographic options
#
# CONFIG_CRYPTO is not set
#
# Library routines
#
CONFIG_BITREVERSE=y
CONFIG_CRC_CCITT=m
CONFIG_CRC16=m
CONFIG_CRC32=y
CONFIG_LIBCRC32C=m
CONFIG_AUDIT_GENERIC=y
CONFIG_PLIST=y
CONFIG_IOMAP_COPY=y
CONFIG_GENERIC_HARDIRQS=y
CONFIG_GENERIC_IRQ_PROBE=y
CONFIG_X86_BIOS_REBOOT=y
CONFIG_KTIME_SCALAR=y
[-- Attachment #3: dmesg --]
[-- Type: text/plain, Size: 9043 bytes --]
Linux version 2.6.20 (root@domain.hid) (gcc version 4.1.1 20060724 (prerelease) (4.1.1-3mdk)) #31 Thu Oct 4 16:33:33 CEST 2007
BIOS-provided physical RAM map:
sanitize start
sanitize end
copy_e820_map() start: 0000000000000000 size: 000000000009f800 end: 000000000009f800 type: 1
copy_e820_map() type is E820_RAM
copy_e820_map() start: 000000000009f800 size: 0000000000000800 end: 00000000000a0000 type: 2
copy_e820_map() start: 00000000000e5c00 size: 000000000001a400 end: 0000000000100000 type: 2
copy_e820_map() start: 0000000000100000 size: 000000000fdf0000 end: 000000000fef0000 type: 1
copy_e820_map() type is E820_RAM
copy_e820_map() start: 000000000fef0000 size: 000000000000fc00 end: 000000000feffc00 type: 3
copy_e820_map() start: 000000000feffc00 size: 0000000000000400 end: 000000000ff00000 type: 4
copy_e820_map() start: 000000000ff00000 size: 0000000000100000 end: 0000000010000000 type: 2
copy_e820_map() start: 00000000fff00000 size: 0000000000100000 end: 0000000100000000 type: 2
BIOS-e820: 0000000000000000 - 000000000009f800 (usable)
BIOS-e820: 000000000009f800 - 00000000000a0000 (reserved)
BIOS-e820: 00000000000e5c00 - 0000000000100000 (reserved)
BIOS-e820: 0000000000100000 - 000000000fef0000 (usable)
BIOS-e820: 000000000fef0000 - 000000000feffc00 (ACPI data)
BIOS-e820: 000000000feffc00 - 000000000ff00000 (ACPI NVS)
BIOS-e820: 000000000ff00000 - 0000000010000000 (reserved)
BIOS-e820: 00000000fff00000 - 0000000100000000 (reserved)
254MB LOWMEM available.
Entering add_active_range(0, 0, 65264) 0 entries of 256 used
Zone PFN ranges:
DMA 0 -> 4096
Normal 4096 -> 65264
early_node_map[1] active PFN ranges
0: 0 -> 65264
On node 0 totalpages: 65264
DMA zone: 32 pages used for memmap
DMA zone: 0 pages reserved
DMA zone: 4064 pages, LIFO batch:0
Normal zone: 477 pages used for memmap
Normal zone: 60691 pages, LIFO batch:15
DMI 2.2 present.
Allocating PCI resources starting at 20000000 (gap: 10000000:eff00000)
Detected 731.008 MHz processor.
Built 1 zonelists. Total pages: 64755
Kernel command line: auto BOOT_IMAGE=2.6.20 root=305 resume=/dev/hda1 idle=pool
Enabling fast FPU save and restore... done.
Enabling unmasked SIMD FPU exception support... done.
Initializing CPU#0
PID hash table entries: 1024 (order: 10, 4096 bytes)
I-pipe 1.8-06: pipeline enabled.
Console: colour VGA+ 80x25
Dentry cache hash table entries: 32768 (order: 5, 131072 bytes)
Inode-cache hash table entries: 16384 (order: 4, 65536 bytes)
Memory: 255452k/261056k available (1779k kernel code, 5112k reserved, 536k data, 176k init, 0k highmem)
virtual kernel memory layout:
fixmap : 0xffffd000 - 0xfffff000 ( 8 kB)
vmalloc : 0xd0800000 - 0xffffb000 ( 759 MB)
lowmem : 0xc0000000 - 0xcfef0000 ( 254 MB)
.init : 0xc0346000 - 0xc0372000 ( 176 kB)
.data : 0xc02bce99 - 0xc03431ac ( 536 kB)
.text : 0xc0100000 - 0xc02bce99 (1779 kB)
Checking if this processor honours the WP bit even in supervisor mode... Ok.
Calibrating delay using timer specific routine.. 1462.94 BogoMIPS (lpj=2925886)
Mount-cache hash table entries: 512
CPU: After generic identify, caps: 0383f9ff 00000000 00000000 00000000 00000000 00000000 00000000
CPU: L1 I cache: 16K, L1 D cache: 16K
CPU: L2 cache: 256K
CPU: After all inits, caps: 0383f9ff 00000000 00000000 00000040 00000000 00000000 00000000
Intel machine check architecture supported.
Intel machine check reporting enabled on CPU#0.
Compat vDSO mapped to ffffe000.
CPU: Intel Pentium III (Coppermine) stepping 06
Checking 'hlt' instruction... OK.
NET: Registered protocol family 16
PCI: PCI BIOS revision 2.10 entry at 0xfd9ae, last bus=1
PCI: Using configuration type 1
Setting up standard PCI resources
Linux Plug and Play Support v0.97 (c) Adam Belay
usbcore: registered new interface driver usbfs
usbcore: registered new interface driver hub
usbcore: registered new device driver usb
PCI: Probing PCI hardware
PCI: Probing PCI hardware (bus 00)
Boot video device is 0000:00:02.0
PCI quirk: region 1000-107f claimed by ICH4 ACPI/GPIO/TCO
PCI quirk: region 1180-11bf claimed by ICH4 GPIO
PCI: Transparent bridge - 0000:00:1e.0
PCI: Using IRQ router PIIX/ICH [8086/2410] at 0000:00:1f.0
PCI: setting IRQ 11 as level-triggered
PCI: Found IRQ 11 for device 0000:00:1f.2
pnp: the driver 'system' has been registered
PCI: Ignore bogus resource 6 [0:0] of 0000:00:02.0
PCI: Bridge: 0000:00:1e.0
IO window: 2000-2fff
MEM window: ec100000-ec1fffff
PREFETCH window: 20000000-200fffff
PCI: Setting latency timer of device 0000:00:1e.0 to 64
NET: Registered protocol family 2
IP route cache hash table entries: 2048 (order: 1, 8192 bytes)
TCP established hash table entries: 8192 (order: 3, 32768 bytes)
TCP bind hash table entries: 4096 (order: 2, 16384 bytes)
TCP: Hash tables configured (established 8192 bind 4096)
TCP reno registered
checking if image is initramfs... it is
Freeing initrd memory: 120k freed
audit: initializing netlink socket (disabled)
audit(1167985878.464:1): initialized
audit: cannot initialize inotify handle
I-pipe: Domain Xenomai registered.
Xenomai: hal/x86 started.
I-pipe: Domain IShield registered.
Xenomai: real-time nucleus v2.3.3 (Summer Song) loaded.
Xenomai: SMI-enabled chipset found, enabling SMI workaround.
Xenomai: starting native API services.
Xenomai: starting RTDM services.
Total HugeTLB memory allocated, 0
io scheduler noop registered
io scheduler anticipatory registered (default)
io scheduler deadline registered
io scheduler cfq registered
isapnp: Scanning for PnP cards...
isapnp: No Plug & Play device found
Real Time Clock Driver v1.12ac
Linux agpgart interface v0.101 (c) Dave Jones
Serial: 8250/16550 driver $Revision: 1.90 $ 4 ports, IRQ sharing enabled
serial8250: ttyS0 at I/O 0x3f8 (irq = 4) is a 16550A
serial8250: ttyS1 at I/O 0x2f8 (irq = 3) is a 16550A
pnp: the driver 'serial' has been registered
RAMDISK driver initialized: 16 RAM disks of 32000K size 1024 blocksize
PCI: setting IRQ 5 as level-triggered
PCI: Found IRQ 5 for device 0000:01:04.0
3c59x: Donald Becker and others. www.scyld.com/network/vortex.html
0000:01:04.0: 3Com PCI 3c905C Tornado at d0982000.
Uniform Multi-Platform E-IDE driver Revision: 7.00alpha2
ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx
ICH: IDE controller at PCI slot 0000:00:1f.1
ICH: chipset revision 2
ICH: not 100% native mode: will probe irqs later
ide0: BM-DMA at 0x1800-0x1807, BIOS settings: hda:pio, hdb:DMA
ide1: BM-DMA at 0x1808-0x180f, BIOS settings: hdc:DMA, hdd:pio
Probing IDE interface ide0...
hda: Maxtor 31024H1, ATA DISK drive
hdb: ST310211A, ATA DISK drive
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
Probing IDE interface ide1...
hdc: CD-540E, ATAPI CD/DVD-ROM drive
ide1 at 0x170-0x177,0x376 on irq 15
hda: max request size: 128KiB
hda: 19746720 sectors (10110 MB) w/2048KiB Cache, CHS=19590/16/63, UDMA(66)
hda: cache flushes not supported
hda: hda1 hda2 < hda5 >
hdb: max request size: 128KiB
hdb: 19541088 sectors (10005 MB) w/512KiB Cache, CHS=19386/16/63, UDMA(66)
hdb: cache flushes not supported
hdb: hdb1 hdb2 < hdb5 hdb6 hdb7 >
USB Universal Host Controller Interface driver v3.0
PCI: Enabling device 0000:00:1f.2 (0000 -> 0001)
PCI: Found IRQ 11 for device 0000:00:1f.2
PCI: Setting latency timer of device 0000:00:1f.2 to 64
uhci_hcd 0000:00:1f.2: UHCI Host Controller
uhci_hcd 0000:00:1f.2: new USB bus registered, assigned bus number 1
uhci_hcd 0000:00:1f.2: irq 11, io base 0x00001820
usb usb1: configuration #1 chosen from 1 choice
hub 1-0:1.0: USB hub found
hub 1-0:1.0: 2 ports detected
pnp: the driver 'i8042 kbd' has been registered
pnp: the driver 'i8042 aux' has been registered
pnp: the driver 'i8042 kbd' has been unregistered
pnp: the driver 'i8042 aux' has been unregistered
PNP: No PS/2 controller found. Probing ports directly.
serio: i8042 KBD port at 0x60,0x64 irq 1
serio: i8042 AUX port at 0x60,0x64 irq 12
mice: PS/2 mouse device common for all mice
pnp: the driver 'irqbench' has been registered
TCP cubic registered
NET: Registered protocol family 1
NET: Registered protocol family 17
Using IPI Shortcut mode
Time: tsc clocksource has been installed.
BIOS EDD facility v0.16 2004-Jun-25, 2 devices found
Freeing unused kernel memory: 176k freed
kjournald starting. Commit interval 5 seconds
EXT3-fs: mounted filesystem with ordered data mode.
input: ImPS/2 Logitech Wheel Mouse as /class/input/input0
input: AT Translated Set 2 keyboard as /class/input/input1
agpgart: Detected an Intel i815 Chipset.
agpgart: AGP aperture is 64M @ 0xf0000000
EXT3 FS on hda5, internal journal
Adding 273064k swap on /dev/hda1. Priority:-1 extents:1 across:273064k
kjournald starting. Commit interval 5 seconds
EXT3 FS on hdb1, internal journal
EXT3-fs: mounted filesystem with ordered data mode.
kjournald starting. Commit interval 5 seconds
EXT3 FS on hdb5, internal journal
EXT3-fs: mounted filesystem with ordered data mode.
hdc: ATAPI 40X CD-ROM drive, 128kB Cache
Uniform CD-ROM driver Revision: 3.20
eth0: setting full-duplex.
[-- Attachment #4: interrupts --]
[-- Type: text/plain, Size: 439 bytes --]
CPU0
0: 125337 XT-PIC-XT timer
1: 16 XT-PIC-XT i8042
2: 0 XT-PIC-XT cascade
5: 214682 XT-PIC-XT eth0
8: 1 XT-PIC-XT rtc
11: 0 XT-PIC-XT uhci_hcd:usb1
12: 131 XT-PIC-XT i8042
14: 29438 XT-PIC-XT ide0
15: 4120 XT-PIC-XT ide1
NMI: 0
ERR: 0
[-- Attachment #5: max --]
[-- Type: text/plain, Size: 2427 bytes --]
I-pipe worst-case tracing service on 2.6.20/ipipe-1.8-06
------------------------------------------------------------
******** WARNING ********
The following debugging options will increase the observed latencies:
o CONFIG_XENO_OPT_DEBUG
Begin: 190142984429 cycles, Trace Points: 21 (-10/+1), Length: 63 us
Calibrated minimum trace-point overhead: 0.248 us
+--------------- Hard IRQs ('|': locked)
| +- Delay flag ('+': > 1 us, '!': > 10 us)
| |
Type Time Function (Parent)
func -5 ipipe_check_context (dev_hard_start_xmit)
func -4 skb_clone (dev_hard_start_xmit)
func -4 kmem_cache_alloc (skb_clone)
func -4 ipipe_check_context (kmem_cache_alloc)
func -3 __ipipe_restore_root (kmem_cache_alloc)
func -3 __ipipe_unstall_root (__ipipe_restore_root)
|begin -3 __ipipe_unstall_root (__ipipe_restore_root)
|end -2 __ipipe_unstall_root (__ipipe_restore_root)
func -2 packet_rcv_spkt (dev_hard_start_xmit)
func -1 strlcpy (packet_rcv_spkt)
>|begin 0 common_interrupt (__ipipe_trace)
:|func 0 __ipipe_handle_irq (common_interrupt)
:|func 0 __ipipe_ack_irq (__ipipe_handle_irq)
:|func 1 __ipipe_ack_level_irq (__ipipe_ack_irq)
:|func 1 mask_and_ack_8259A (__ipipe_ack_level_irq)
:|func 1! __ipipe_spin_lock_irqsave (mask_and_ack_8259A)
:|func 29 __ipipe_spin_unlock_irqrestore (mask_and_ack_8259A)
:|func 29 __ipipe_dispatch_wired (__ipipe_handle_irq)
:|func 29 xnintr_clock_handler (__ipipe_dispatch_wired)
:|func 30 xnintr_irq_handler (xnintr_clock_handler)
:|func 30 xnpod_announce_tick (xnintr_irq_handler)
:|func 30 xntimer_do_tick_aperiodic (xnpod_announce_tick)
:|func 31 xnthread_periodic_handler (xntimer_do_tick_aperiodic)
:|func 31 xnpod_resume_thread (xnthread_periodic_handler)
:|[ 3813] 32! xnpod_resume_thread (xnthread_periodic_handler)
:|func 60 xnpod_schedule (xnintr_irq_handler)
:|[ 3391] 60+ xnpod_schedule (xnintr_irq_handler)
:|func 62 __switch_to (xnpod_schedule)
:|[ 3813] 62 xnpod_schedule (xnpod_suspend_thread)
:|func 63 __ipipe_restore_pipeline_head (xnpod_wait_thread_period)
<|end 63 __ipipe_restore_pipeline_head (xnpod_wait_thread_period)
|begin 64 __ipipe_dispatch_event (__ipipe_syscall_root)
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-05 7:52 [Xenomai-help] awful latencies (~110us) CHABAL David
@ 2007-10-05 8:30 ` Gilles Chanteperdrix
2007-10-05 9:04 ` CHABAL David
0 siblings, 1 reply; 30+ messages in thread
From: Gilles Chanteperdrix @ 2007-10-05 8:30 UTC (permalink / raw)
To: CHABAL David; +Cc: xenomai
On 10/5/07, CHABAL David <david.chabal@domain.hid> wrote:
> Hello all,
>
> My box is a Pentium III 733 Mhz/256Mo with Linux 2.6.20 and Xenomai 2.3.3.
>
> When I run the latency test included in the testsuite, I get some
> horrible results like:
>
> RTT| 00:01:04 (periodic user-mode task, 100 us period, priority 99)
> RTH|-----lat min|-----lat avg|-----lat max|-overrun|----lat best|---lat
> worst
> RTD| 4.640| 12.243| 80.454| 0| 3.716|
> 110.990
> RTD| 8.652| 13.133| 86.014| 0| 3.716| ...
> RTD| 4.050| 13.324| 89.186| 0| 3.716|
> 110.990
> ---|------------|------------|------------|--------|-------------------------
> RTS| 3.716| 11.499| 110.990| 0| 00:01:22/00:01:22
>
> I expect about 30us.
>
> I have tried many kernel configurations without significant results
> (always about 120us).
>
> - BIOS USB Legacy is disabled.
> - idle=pool is added to the boot line.
It is idle=poll, not idle=pool
> - linux kernel is minimalist
You should enable ACPI except the ACPI "processor" module.
> - Ipipe/xenomai debug features have a minor impact
> - sometimes, the latency is negative.
>
> I have noticed a better latency (max: ~31us) with the network disabled
> (ifdown eth0), and a deterioration immediatly after typing ifup (~120us,
> like above). (Usually, I connect this box through Exceed. I have other
> PC with Xenomai and it is without consequence on their latency tests).
I do not know what is Exceed, but if you are running an X-server, you
may try the noaccel option, as explained in the TROUBLESHOOTING guide.
--
Gilles Chanteperdrix
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-05 8:30 ` Gilles Chanteperdrix
@ 2007-10-05 9:04 ` CHABAL David
2007-10-05 9:20 ` Philippe Gerum
0 siblings, 1 reply; 30+ messages in thread
From: CHABAL David @ 2007-10-05 9:04 UTC (permalink / raw)
To: Gilles Chanteperdrix; +Cc: xenomai
[-- Attachment #1: Type: text/plain, Size: 2596 bytes --]
Gilles Chanteperdrix a écrit :
> On 10/5/07, CHABAL David <david.chabal@domain.hid> wrote:
>> Hello all,
>>
>> My box is a Pentium III 733 Mhz/256Mo with Linux 2.6.20 and Xenomai 2.3.3.
>>
>> When I run the latency test included in the testsuite, I get some
>> horrible results like:
>>
>> RTT| 00:01:04 (periodic user-mode task, 100 us period, priority 99)
>> RTH|-----lat min|-----lat avg|-----lat max|-overrun|----lat best|---lat
>> worst
>> RTD| 4.640| 12.243| 80.454| 0| 3.716|
>> 110.990
>> RTD| 8.652| 13.133| 86.014| 0| 3.716| ...
>> RTD| 4.050| 13.324| 89.186| 0| 3.716|
>> 110.990
>> ---|------------|------------|------------|--------|-------------------------
>> RTS| 3.716| 11.499| 110.990| 0| 00:01:22/00:01:22
>>
>> I expect about 30us.
>>
>> I have tried many kernel configurations without significant results
>> (always about 120us).
>>
>> - BIOS USB Legacy is disabled.
>> - idle=pool is added to the boot line.
> It is idle=poll, not idle=pool
>
Ooops, mistyping: corrected.
>> - linux kernel is minimalist
>
> You should enable ACPI except the ACPI "processor" module.
>
Done, I enclose my new .config.
The new run gives:
RTT| 00:01:04 (periodic user-mode task, 100 us period, priority 99)
RTH|-----lat min|-----lat avg|-----lat max|-overrun|----lat best|---lat
worst
RTD| 8.439| 10.350| 71.044| 0| 3.087|
112.476
RTD| 8.210| 10.522| 82.353| 0| 3.087|
112.476
RTD| 8.462| 10.489| 88.594| 0| 3.087|
112.476
---|------------|------------|------------|--------|-------------------------
RTS| 3.087| 9.994| 112.476| 0| 00:01:06/00:01:06
There is not significant difference.
>> - Ipipe/xenomai debug features have a minor impact
>> - sometimes, the latency is negative.
>>
>> I have noticed a better latency (max: ~31us) with the network disabled
>> (ifdown eth0), and a deterioration immediatly after typing ifup (~120us,
>> like above). (Usually, I connect this box through Exceed. I have other
>> PC with Xenomai and it is without consequence on their latency tests).
>
> I do not know what is Exceed, but if you are running an X-server, you
> may try the noaccel option, as explained in the TROUBLESHOOTING guide.
>
Exceed is a commercial X-server for Windows, may be causing a network
overload (?).
I already set the noaccel option before, without success.
David
[-- Attachment #2: config2.txt --]
[-- Type: text/plain, Size: 27125 bytes --]
#
# Automatically generated make config: don't edit
# Linux kernel version: 2.6.20
# Fri Jan 5 10:43:35 2007
#
CONFIG_X86_32=y
CONFIG_GENERIC_TIME=y
CONFIG_LOCKDEP_SUPPORT=y
CONFIG_STACKTRACE_SUPPORT=y
CONFIG_SEMAPHORE_SLEEPERS=y
CONFIG_X86=y
CONFIG_MMU=y
CONFIG_GENERIC_ISA_DMA=y
CONFIG_GENERIC_IOMAP=y
CONFIG_GENERIC_BUG=y
CONFIG_GENERIC_HWEIGHT=y
CONFIG_ARCH_MAY_HAVE_PC_FDC=y
CONFIG_DMI=y
CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
#
# Code maturity level options
#
# CONFIG_EXPERIMENTAL is not set
CONFIG_BROKEN_ON_SMP=y
CONFIG_INIT_ENV_ARG_LIMIT=32
#
# General setup
#
CONFIG_LOCALVERSION=""
# CONFIG_LOCALVERSION_AUTO is not set
CONFIG_SWAP=y
CONFIG_SYSVIPC=y
# CONFIG_IPC_NS is not set
CONFIG_BSD_PROCESS_ACCT=y
CONFIG_BSD_PROCESS_ACCT_V3=y
# CONFIG_TASKSTATS is not set
# CONFIG_UTS_NS is not set
CONFIG_AUDIT=y
CONFIG_AUDITSYSCALL=y
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
CONFIG_SYSFS_DEPRECATED=y
CONFIG_RELAY=y
CONFIG_INITRAMFS_SOURCE=""
CONFIG_SYSCTL=y
# CONFIG_EMBEDDED is not set
CONFIG_UID16=y
CONFIG_SYSCTL_SYSCALL=y
CONFIG_KALLSYMS=y
CONFIG_KALLSYMS_EXTRA_PASS=y
CONFIG_HOTPLUG=y
CONFIG_PRINTK=y
CONFIG_BUG=y
CONFIG_ELF_CORE=y
CONFIG_BASE_FULL=y
CONFIG_FUTEX=y
CONFIG_EPOLL=y
CONFIG_SHMEM=y
CONFIG_SLAB=y
CONFIG_VM_EVENT_COUNTERS=y
CONFIG_RT_MUTEXES=y
# CONFIG_TINY_SHMEM is not set
CONFIG_BASE_SMALL=0
# CONFIG_SLOB is not set
#
# Loadable module support
#
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
# CONFIG_MODVERSIONS is not set
# CONFIG_MODULE_SRCVERSION_ALL is not set
CONFIG_KMOD=y
#
# Block layer
#
CONFIG_BLOCK=y
CONFIG_LBD=y
CONFIG_BLK_DEV_IO_TRACE=y
CONFIG_LSF=y
#
# IO Schedulers
#
CONFIG_IOSCHED_NOOP=y
CONFIG_IOSCHED_AS=y
CONFIG_IOSCHED_DEADLINE=y
CONFIG_IOSCHED_CFQ=y
CONFIG_DEFAULT_AS=y
# CONFIG_DEFAULT_DEADLINE is not set
# CONFIG_DEFAULT_CFQ is not set
# CONFIG_DEFAULT_NOOP is not set
CONFIG_DEFAULT_IOSCHED="anticipatory"
#
# Real-time sub-system
#
CONFIG_XENOMAI=y
CONFIG_XENO_OPT_NUCLEUS=y
CONFIG_XENO_OPT_PERVASIVE=y
CONFIG_XENO_OPT_ISHIELD=y
# CONFIG_XENO_OPT_RPIDISABLE is not set
CONFIG_XENO_OPT_PIPELINE_HEAD=y
CONFIG_XENO_OPT_PIPE=y
CONFIG_XENO_OPT_PIPE_NRDEV=32
CONFIG_XENO_OPT_REGISTRY=y
CONFIG_XENO_OPT_REGISTRY_NRSLOTS=512
CONFIG_XENO_OPT_SYS_HEAPSZ=128
CONFIG_XENO_OPT_STATS=y
CONFIG_XENO_OPT_DEBUG=y
# CONFIG_XENO_OPT_DEBUG_NUCLEUS is not set
# CONFIG_XENO_OPT_DEBUG_QUEUES is not set
CONFIG_XENO_OPT_WATCHDOG=y
#
# Timing
#
# CONFIG_XENO_OPT_TIMING_PERIODIC is not set
CONFIG_XENO_OPT_TIMING_PERIOD=0
CONFIG_XENO_OPT_TIMING_TIMERLAT=0
CONFIG_XENO_OPT_TIMING_SCHEDLAT=0
#
# Scalability
#
# CONFIG_XENO_OPT_SCALABLE_SCHED is not set
CONFIG_XENO_OPT_TIMER_LIST=y
# CONFIG_XENO_OPT_TIMER_HEAP is not set
# CONFIG_XENO_OPT_TIMER_WHEEL is not set
#
# Shared interrupts
#
CONFIG_XENO_OPT_SHIRQ_LEVEL=y
# CONFIG_XENO_OPT_SHIRQ_EDGE is not set
#
# Machine
#
CONFIG_XENO_HW_FPU=y
#
# NMI watchdog
#
#
# SMI workaround
#
# CONFIG_XENO_HW_SMI_DETECT_DISABLE is not set
CONFIG_XENO_HW_SMI_DETECT=y
CONFIG_XENO_HW_SMI_WORKAROUND=y
CONFIG_XENO_HW_SMI_ALL=y
#
# Interfaces
#
CONFIG_XENO_SKIN_NATIVE=y
CONFIG_XENO_OPT_NATIVE_PIPE=y
CONFIG_XENO_OPT_NATIVE_PIPE_BUFSZ=4096
CONFIG_XENO_OPT_NATIVE_REGISTRY=y
CONFIG_XENO_OPT_NATIVE_SEM=y
CONFIG_XENO_OPT_NATIVE_EVENT=y
CONFIG_XENO_OPT_NATIVE_MUTEX=y
CONFIG_XENO_OPT_NATIVE_COND=y
CONFIG_XENO_OPT_NATIVE_QUEUE=y
CONFIG_XENO_OPT_NATIVE_HEAP=y
CONFIG_XENO_OPT_NATIVE_ALARM=y
CONFIG_XENO_OPT_NATIVE_MPS=y
CONFIG_XENO_OPT_NATIVE_INTR=y
# CONFIG_XENO_SKIN_POSIX is not set
# CONFIG_XENO_SKIN_PSOS is not set
# CONFIG_XENO_SKIN_UITRON is not set
# CONFIG_XENO_SKIN_VRTX is not set
# CONFIG_XENO_SKIN_VXWORKS is not set
# CONFIG_XENO_SKIN_RTAI is not set
CONFIG_XENO_SKIN_RTDM=y
CONFIG_XENO_OPT_RTDM_FILDES=128
CONFIG_XENO_OPT_DEBUG_RTDM=y
#
# Drivers
#
#
# Serial drivers
#
CONFIG_XENO_DRIVERS_16550A=y
#
# Testing drivers
#
CONFIG_XENO_DRIVERS_TIMERBENCH=y
CONFIG_XENO_DRIVERS_IRQBENCH=y
CONFIG_XENO_DRIVERS_SWITCHTEST=y
#
# CAN drivers
#
# CONFIG_XENO_DRIVERS_CAN is not set
#
# Processor type and features
#
# CONFIG_SMP is not set
CONFIG_X86_PC=y
# CONFIG_X86_ELAN is not set
# CONFIG_X86_VOYAGER is not set
# CONFIG_X86_NUMAQ is not set
# CONFIG_X86_SUMMIT is not set
# CONFIG_X86_BIGSMP is not set
# CONFIG_X86_VISWS is not set
# CONFIG_X86_GENERICARCH is not set
# CONFIG_X86_ES7000 is not set
# CONFIG_M386 is not set
# CONFIG_M486 is not set
# CONFIG_M586 is not set
# CONFIG_M586TSC is not set
# CONFIG_M586MMX is not set
# CONFIG_M686 is not set
# CONFIG_MPENTIUMII is not set
CONFIG_MPENTIUMIII=y
# CONFIG_MPENTIUMM is not set
# CONFIG_MCORE2 is not set
# CONFIG_MPENTIUM4 is not set
# CONFIG_MK6 is not set
# CONFIG_MK7 is not set
# CONFIG_MK8 is not set
# CONFIG_MCRUSOE is not set
# CONFIG_MEFFICEON is not set
# CONFIG_MWINCHIPC6 is not set
# CONFIG_MWINCHIP2 is not set
# CONFIG_MWINCHIP3D is not set
# CONFIG_MGEODEGX1 is not set
# CONFIG_MGEODE_LX is not set
# CONFIG_MCYRIXIII is not set
# CONFIG_MVIAC3_2 is not set
CONFIG_X86_GENERIC=y
CONFIG_X86_CMPXCHG=y
CONFIG_X86_XADD=y
CONFIG_X86_L1_CACHE_SHIFT=7
CONFIG_RWSEM_XCHGADD_ALGORITHM=y
# CONFIG_ARCH_HAS_ILOG2_U32 is not set
# CONFIG_ARCH_HAS_ILOG2_U64 is not set
CONFIG_GENERIC_CALIBRATE_DELAY=y
CONFIG_X86_WP_WORKS_OK=y
CONFIG_X86_INVLPG=y
CONFIG_X86_BSWAP=y
CONFIG_X86_POPAD_OK=y
CONFIG_X86_CMPXCHG64=y
CONFIG_X86_GOOD_APIC=y
CONFIG_X86_INTEL_USERCOPY=y
CONFIG_X86_USE_PPRO_CHECKSUM=y
CONFIG_X86_TSC=y
CONFIG_HPET_TIMER=y
CONFIG_HPET_EMULATE_RTC=y
# CONFIG_PREEMPT_NONE is not set
CONFIG_PREEMPT_VOLUNTARY=y
# CONFIG_PREEMPT is not set
CONFIG_IPIPE=y
# CONFIG_X86_UP_APIC is not set
CONFIG_X86_MCE=y
# CONFIG_X86_MCE_NONFATAL is not set
CONFIG_VM86=y
# CONFIG_TOSHIBA is not set
# CONFIG_I8K is not set
# CONFIG_X86_REBOOTFIXUPS is not set
CONFIG_MICROCODE=m
CONFIG_MICROCODE_OLD_INTERFACE=y
CONFIG_X86_MSR=m
CONFIG_X86_CPUID=m
#
# Firmware Drivers
#
CONFIG_EDD=y
# CONFIG_DELL_RBU is not set
# CONFIG_DCDBAS is not set
CONFIG_NOHIGHMEM=y
# CONFIG_HIGHMEM4G is not set
# CONFIG_HIGHMEM64G is not set
CONFIG_PAGE_OFFSET=0xC0000000
CONFIG_ARCH_POPULATES_NODE_MAP=y
CONFIG_FLATMEM=y
CONFIG_FLAT_NODE_MEM_MAP=y
# CONFIG_SPARSEMEM_STATIC is not set
CONFIG_SPLIT_PTLOCK_CPUS=4
# CONFIG_RESOURCES_64BIT is not set
# CONFIG_MATH_EMULATION is not set
# CONFIG_MTRR is not set
# CONFIG_EFI is not set
CONFIG_SECCOMP=y
# CONFIG_HZ_100 is not set
# CONFIG_HZ_250 is not set
# CONFIG_HZ_300 is not set
CONFIG_HZ_1000=y
CONFIG_HZ=1000
CONFIG_KEXEC=y
CONFIG_PHYSICAL_START=0x100000
CONFIG_PHYSICAL_ALIGN=0x100000
CONFIG_COMPAT_VDSO=y
#
# Power management options (ACPI, APM)
#
CONFIG_PM=y
# CONFIG_PM_LEGACY is not set
# CONFIG_PM_DEBUG is not set
# CONFIG_PM_SYSFS_DEPRECATED is not set
# CONFIG_SOFTWARE_SUSPEND is not set
#
# ACPI (Advanced Configuration and Power Interface) Support
#
CONFIG_ACPI=y
CONFIG_ACPI_SLEEP=y
CONFIG_ACPI_SLEEP_PROC_FS=y
# CONFIG_ACPI_SLEEP_PROC_SLEEP is not set
CONFIG_ACPI_AC=y
CONFIG_ACPI_BATTERY=y
CONFIG_ACPI_BUTTON=y
# CONFIG_ACPI_VIDEO is not set
CONFIG_ACPI_FAN=y
# CONFIG_ACPI_PROCESSOR is not set
# CONFIG_ACPI_ASUS is not set
# CONFIG_ACPI_IBM is not set
# CONFIG_ACPI_TOSHIBA is not set
CONFIG_ACPI_BLACKLIST_YEAR=0
# CONFIG_ACPI_DEBUG is not set
CONFIG_ACPI_EC=y
CONFIG_ACPI_POWER=y
CONFIG_ACPI_SYSTEM=y
CONFIG_X86_PM_TIMER=y
#
# APM (Advanced Power Management) BIOS Support
#
# CONFIG_APM is not set
#
# CPU Frequency scaling
#
# CONFIG_CPU_FREQ is not set
#
# Bus options (PCI, PCMCIA, EISA, MCA, ISA)
#
CONFIG_PCI=y
# CONFIG_PCI_GOBIOS is not set
# CONFIG_PCI_GOMMCONFIG is not set
# CONFIG_PCI_GODIRECT is not set
CONFIG_PCI_GOANY=y
CONFIG_PCI_BIOS=y
CONFIG_PCI_DIRECT=y
CONFIG_PCI_MMCONFIG=y
# CONFIG_PCIEPORTBUS is not set
CONFIG_ISA_DMA_API=y
CONFIG_ISA=y
# CONFIG_EISA is not set
# CONFIG_MCA is not set
# CONFIG_SCx200 is not set
#
# PCCARD (PCMCIA/CardBus) support
#
# CONFIG_PCCARD is not set
#
# PCI Hotplug Support
#
#
# Executable file formats
#
CONFIG_BINFMT_ELF=y
CONFIG_BINFMT_AOUT=m
CONFIG_BINFMT_MISC=m
#
# Networking
#
CONFIG_NET=y
#
# Networking options
#
# CONFIG_NETDEBUG is not set
CONFIG_PACKET=y
CONFIG_PACKET_MMAP=y
CONFIG_UNIX=y
# CONFIG_NET_KEY is not set
CONFIG_INET=y
# CONFIG_IP_MULTICAST is not set
# CONFIG_IP_ADVANCED_ROUTER is not set
CONFIG_IP_FIB_HASH=y
# CONFIG_IP_PNP is not set
# CONFIG_NET_IPIP is not set
# CONFIG_NET_IPGRE is not set
# CONFIG_SYN_COOKIES is not set
# CONFIG_INET_AH is not set
# CONFIG_INET_ESP is not set
# CONFIG_INET_IPCOMP is not set
# CONFIG_INET_XFRM_TUNNEL is not set
# CONFIG_INET_TUNNEL is not set
# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
# CONFIG_INET_XFRM_MODE_TUNNEL is not set
# CONFIG_INET_XFRM_MODE_BEET is not set
# CONFIG_INET_DIAG is not set
# CONFIG_TCP_CONG_ADVANCED is not set
CONFIG_TCP_CONG_CUBIC=y
CONFIG_DEFAULT_TCP_CONG="cubic"
# CONFIG_IPV6 is not set
# CONFIG_INET6_XFRM_TUNNEL is not set
# CONFIG_INET6_TUNNEL is not set
# CONFIG_NETWORK_SECMARK is not set
# CONFIG_NETFILTER is not set
# CONFIG_BRIDGE is not set
# CONFIG_VLAN_8021Q is not set
# CONFIG_DECNET is not set
# CONFIG_LLC2 is not set
# CONFIG_IPX is not set
# CONFIG_ATALK is not set
#
# QoS and/or fair queueing
#
# CONFIG_NET_SCHED is not set
#
# Network testing
#
# CONFIG_NET_PKTGEN is not set
# CONFIG_HAMRADIO is not set
# CONFIG_IRDA is not set
# CONFIG_BT is not set
# CONFIG_IEEE80211 is not set
#
# Device Drivers
#
#
# Generic Driver Options
#
CONFIG_STANDALONE=y
CONFIG_PREVENT_FIRMWARE_BUILD=y
CONFIG_FW_LOADER=y
# CONFIG_SYS_HYPERVISOR is not set
#
# Connector - unified userspace <-> kernelspace linker
#
CONFIG_CONNECTOR=m
#
# Memory Technology Devices (MTD)
#
# CONFIG_MTD is not set
#
# Parallel port support
#
# CONFIG_PARPORT is not set
#
# Plug and Play support
#
CONFIG_PNP=y
CONFIG_PNP_DEBUG=y
#
# Protocols
#
CONFIG_ISAPNP=y
#
# Block devices
#
# CONFIG_BLK_DEV_FD is not set
# CONFIG_BLK_DEV_XD is not set
# CONFIG_BLK_CPQ_DA is not set
# CONFIG_BLK_CPQ_CISS_DA is not set
# CONFIG_BLK_DEV_DAC960 is not set
# CONFIG_BLK_DEV_COW_COMMON is not set
# CONFIG_BLK_DEV_LOOP is not set
# CONFIG_BLK_DEV_NBD is not set
# CONFIG_BLK_DEV_SX8 is not set
# CONFIG_BLK_DEV_UB is not set
CONFIG_BLK_DEV_RAM=y
CONFIG_BLK_DEV_RAM_COUNT=16
CONFIG_BLK_DEV_RAM_SIZE=32000
CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024
CONFIG_BLK_DEV_INITRD=y
CONFIG_CDROM_PKTCDVD=y
CONFIG_CDROM_PKTCDVD_BUFFERS=8
# CONFIG_ATA_OVER_ETH is not set
#
# Misc devices
#
# CONFIG_SGI_IOC4 is not set
#
# ATA/ATAPI/MFM/RLL support
#
CONFIG_IDE=y
CONFIG_BLK_DEV_IDE=y
#
# Please see Documentation/ide.txt for help/info on IDE drives
#
# CONFIG_BLK_DEV_IDE_SATA is not set
# CONFIG_BLK_DEV_HD_IDE is not set
CONFIG_BLK_DEV_IDEDISK=y
CONFIG_IDEDISK_MULTI_MODE=y
CONFIG_BLK_DEV_IDECD=y
# CONFIG_BLK_DEV_IDEFLOPPY is not set
# CONFIG_IDE_TASK_IOCTL is not set
#
# IDE chipset support/bugfixes
#
CONFIG_IDE_GENERIC=m
# CONFIG_BLK_DEV_CMD640 is not set
# CONFIG_BLK_DEV_IDEPNP is not set
CONFIG_BLK_DEV_IDEPCI=y
CONFIG_IDEPCI_SHARE_IRQ=y
CONFIG_BLK_DEV_OFFBOARD=y
CONFIG_BLK_DEV_GENERIC=y
# CONFIG_BLK_DEV_RZ1000 is not set
CONFIG_BLK_DEV_IDEDMA_PCI=y
# CONFIG_BLK_DEV_IDEDMA_FORCED is not set
# CONFIG_IDEDMA_PCI_AUTO is not set
# CONFIG_BLK_DEV_AEC62XX is not set
# CONFIG_BLK_DEV_ALI15X3 is not set
# CONFIG_BLK_DEV_AMD74XX is not set
# CONFIG_BLK_DEV_ATIIXP is not set
# CONFIG_BLK_DEV_CMD64X is not set
# CONFIG_BLK_DEV_TRIFLEX is not set
# CONFIG_BLK_DEV_CY82C693 is not set
# CONFIG_BLK_DEV_CS5530 is not set
# CONFIG_BLK_DEV_CS5535 is not set
# CONFIG_BLK_DEV_HPT34X is not set
# CONFIG_BLK_DEV_HPT366 is not set
# CONFIG_BLK_DEV_JMICRON is not set
# CONFIG_BLK_DEV_SC1200 is not set
CONFIG_BLK_DEV_PIIX=y
# CONFIG_BLK_DEV_IT821X is not set
# CONFIG_BLK_DEV_NS87415 is not set
# CONFIG_BLK_DEV_PDC202XX_OLD is not set
# CONFIG_BLK_DEV_PDC202XX_NEW is not set
# CONFIG_BLK_DEV_SVWKS is not set
# CONFIG_BLK_DEV_SIIMAGE is not set
# CONFIG_BLK_DEV_SIS5513 is not set
# CONFIG_BLK_DEV_SLC90E66 is not set
# CONFIG_BLK_DEV_TRM290 is not set
# CONFIG_BLK_DEV_VIA82CXXX is not set
# CONFIG_IDE_ARM is not set
# CONFIG_IDE_CHIPSETS is not set
CONFIG_BLK_DEV_IDEDMA=y
# CONFIG_IDEDMA_IVB is not set
# CONFIG_IDEDMA_AUTO is not set
# CONFIG_BLK_DEV_HD is not set
#
# SCSI device support
#
# CONFIG_RAID_ATTRS is not set
# CONFIG_SCSI is not set
# CONFIG_SCSI_NETLINK is not set
#
# Serial ATA (prod) and Parallel ATA (experimental) drivers
#
# CONFIG_ATA is not set
#
# Old CD-ROM drivers (not SCSI, not IDE)
#
# CONFIG_CD_NO_IDESCSI is not set
#
# Multi-device support (RAID and LVM)
#
# CONFIG_MD is not set
#
# Fusion MPT device support
#
# CONFIG_FUSION is not set
#
# IEEE 1394 (FireWire) support
#
# CONFIG_IEEE1394 is not set
#
# I2O device support
#
CONFIG_I2O=m
CONFIG_I2O_LCT_NOTIFY_ON_CHANGES=y
CONFIG_I2O_EXT_ADAPTEC=y
# CONFIG_I2O_CONFIG is not set
# CONFIG_I2O_BUS is not set
# CONFIG_I2O_BLOCK is not set
# CONFIG_I2O_PROC is not set
#
# Network device support
#
CONFIG_NETDEVICES=y
# CONFIG_DUMMY is not set
# CONFIG_BONDING is not set
# CONFIG_EQUALIZER is not set
# CONFIG_TUN is not set
# CONFIG_NET_SB1000 is not set
#
# ARCnet devices
#
# CONFIG_ARCNET is not set
#
# PHY device support
#
# CONFIG_PHYLIB is not set
#
# Ethernet (10 or 100Mbit)
#
CONFIG_NET_ETHERNET=y
CONFIG_MII=y
# CONFIG_HAPPYMEAL is not set
# CONFIG_SUNGEM is not set
# CONFIG_CASSINI is not set
CONFIG_NET_VENDOR_3COM=y
# CONFIG_EL1 is not set
# CONFIG_EL2 is not set
# CONFIG_ELPLUS is not set
# CONFIG_EL3 is not set
# CONFIG_3C515 is not set
CONFIG_VORTEX=y
# CONFIG_TYPHOON is not set
# CONFIG_LANCE is not set
# CONFIG_NET_VENDOR_SMC is not set
# CONFIG_NET_VENDOR_RACAL is not set
#
# Tulip family network device support
#
# CONFIG_NET_TULIP is not set
# CONFIG_DEPCA is not set
# CONFIG_HP100 is not set
# CONFIG_NET_ISA is not set
# CONFIG_NET_PCI is not set
#
# Ethernet (1000 Mbit)
#
# CONFIG_ACENIC is not set
# CONFIG_DL2K is not set
# CONFIG_E1000 is not set
# CONFIG_NS83820 is not set
# CONFIG_HAMACHI is not set
# CONFIG_R8169 is not set
# CONFIG_SIS190 is not set
# CONFIG_SKGE is not set
# CONFIG_SKY2 is not set
# CONFIG_SK98LIN is not set
# CONFIG_TIGON3 is not set
# CONFIG_BNX2 is not set
# CONFIG_QLA3XXX is not set
#
# Ethernet (10000 Mbit)
#
# CONFIG_CHELSIO_T1 is not set
# CONFIG_IXGB is not set
# CONFIG_S2IO is not set
# CONFIG_MYRI10GE is not set
# CONFIG_NETXEN_NIC is not set
#
# Token Ring devices
#
# CONFIG_TR is not set
#
# Wireless LAN (non-hamradio)
#
# CONFIG_NET_RADIO is not set
#
# Wan interfaces
#
CONFIG_WAN=y
CONFIG_HOSTESS_SV11=m
CONFIG_COSA=m
CONFIG_LANMEDIA=m
CONFIG_SEALEVEL_4021=m
CONFIG_HDLC=m
CONFIG_HDLC_RAW=m
CONFIG_HDLC_RAW_ETH=m
CONFIG_HDLC_CISCO=m
CONFIG_HDLC_FR=m
CONFIG_HDLC_PPP=m
#
# X.25/LAPB support is disabled
#
CONFIG_PCI200SYN=m
CONFIG_WANXL=m
CONFIG_PC300=m
#
# Cyclades-PC300 MLPPP support is disabled.
#
#
# Refer to the file README.mlppp, provided by PC300 package.
#
CONFIG_N2=m
CONFIG_C101=m
CONFIG_FARSYNC=m
CONFIG_DSCC4=m
CONFIG_DSCC4_PCISYNC=y
CONFIG_DSCC4_PCI_RST=y
CONFIG_DLCI=m
CONFIG_DLCI_COUNT=24
CONFIG_DLCI_MAX=8
# CONFIG_SDLA is not set
CONFIG_SBNI=m
CONFIG_SBNI_MULTILINE=y
# CONFIG_FDDI is not set
# CONFIG_PPP is not set
# CONFIG_SLIP is not set
# CONFIG_NETPOLL is not set
# CONFIG_NET_POLL_CONTROLLER is not set
#
# ISDN subsystem
#
# CONFIG_ISDN is not set
#
# Telephony Support
#
# CONFIG_PHONE is not set
#
# Input device support
#
CONFIG_INPUT=y
# CONFIG_INPUT_FF_MEMLESS is not set
#
# Userland interfaces
#
CONFIG_INPUT_MOUSEDEV=y
# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
# CONFIG_INPUT_JOYDEV is not set
# CONFIG_INPUT_TSDEV is not set
# CONFIG_INPUT_EVDEV is not set
# CONFIG_INPUT_EVBUG is not set
#
# Input Device Drivers
#
CONFIG_INPUT_KEYBOARD=y
CONFIG_KEYBOARD_ATKBD=y
# CONFIG_KEYBOARD_SUNKBD is not set
# CONFIG_KEYBOARD_LKKBD is not set
# CONFIG_KEYBOARD_XTKBD is not set
# CONFIG_KEYBOARD_NEWTON is not set
# CONFIG_KEYBOARD_STOWAWAY is not set
CONFIG_INPUT_MOUSE=y
CONFIG_MOUSE_PS2=y
# CONFIG_MOUSE_SERIAL is not set
# CONFIG_MOUSE_INPORT is not set
# CONFIG_MOUSE_LOGIBM is not set
# CONFIG_MOUSE_PC110PAD is not set
# CONFIG_MOUSE_VSXXXAA is not set
# CONFIG_INPUT_JOYSTICK is not set
# CONFIG_INPUT_TOUCHSCREEN is not set
# CONFIG_INPUT_MISC is not set
#
# Hardware I/O ports
#
CONFIG_SERIO=y
CONFIG_SERIO_I8042=y
CONFIG_SERIO_SERPORT=m
CONFIG_SERIO_CT82C710=m
CONFIG_SERIO_PCIPS2=m
CONFIG_SERIO_LIBPS2=y
CONFIG_SERIO_RAW=m
# CONFIG_GAMEPORT is not set
#
# Character devices
#
CONFIG_VT=y
CONFIG_VT_CONSOLE=y
CONFIG_HW_CONSOLE=y
# CONFIG_VT_HW_CONSOLE_BINDING is not set
# CONFIG_SERIAL_NONSTANDARD is not set
#
# Serial drivers
#
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_SERIAL_8250_PCI=y
CONFIG_SERIAL_8250_PNP=y
CONFIG_SERIAL_8250_NR_UARTS=4
CONFIG_SERIAL_8250_RUNTIME_UARTS=4
CONFIG_SERIAL_8250_EXTENDED=y
# CONFIG_SERIAL_8250_MANY_PORTS is not set
CONFIG_SERIAL_8250_SHARE_IRQ=y
# CONFIG_SERIAL_8250_DETECT_IRQ is not set
# CONFIG_SERIAL_8250_RSA is not set
#
# Non-8250 serial port support
#
CONFIG_SERIAL_CORE=y
CONFIG_SERIAL_CORE_CONSOLE=y
# CONFIG_SERIAL_JSM is not set
CONFIG_UNIX98_PTYS=y
CONFIG_LEGACY_PTYS=y
CONFIG_LEGACY_PTY_COUNT=256
#
# IPMI
#
# CONFIG_IPMI_HANDLER is not set
#
# Watchdog Cards
#
# CONFIG_WATCHDOG is not set
CONFIG_HW_RANDOM=m
CONFIG_HW_RANDOM_INTEL=m
# CONFIG_HW_RANDOM_AMD is not set
# CONFIG_HW_RANDOM_GEODE is not set
# CONFIG_HW_RANDOM_VIA is not set
CONFIG_NVRAM=m
CONFIG_RTC=y
# CONFIG_DTLK is not set
# CONFIG_R3964 is not set
# CONFIG_APPLICOM is not set
CONFIG_AGP=y
# CONFIG_AGP_ALI is not set
# CONFIG_AGP_ATI is not set
# CONFIG_AGP_AMD is not set
# CONFIG_AGP_AMD64 is not set
CONFIG_AGP_INTEL=m
# CONFIG_AGP_NVIDIA is not set
# CONFIG_AGP_SIS is not set
# CONFIG_AGP_SWORKS is not set
# CONFIG_AGP_VIA is not set
# CONFIG_AGP_EFFICEON is not set
# CONFIG_DRM is not set
# CONFIG_MWAVE is not set
# CONFIG_PC8736x_GPIO is not set
# CONFIG_NSC_GPIO is not set
# CONFIG_CS5535_GPIO is not set
# CONFIG_RAW_DRIVER is not set
# CONFIG_HPET is not set
# CONFIG_HANGCHECK_TIMER is not set
#
# TPM devices
#
#
# I2C support
#
CONFIG_I2C=m
CONFIG_I2C_CHARDEV=m
#
# I2C Algorithms
#
CONFIG_I2C_ALGOBIT=m
# CONFIG_I2C_ALGOPCF is not set
CONFIG_I2C_ALGOPCA=m
#
# I2C Hardware Bus support
#
CONFIG_I2C_ALI1535=m
CONFIG_I2C_ALI15X3=m
CONFIG_I2C_AMD756=m
CONFIG_I2C_AMD8111=m
# CONFIG_I2C_ELEKTOR is not set
CONFIG_I2C_I801=m
CONFIG_I2C_I810=m
CONFIG_I2C_PIIX4=m
CONFIG_I2C_NFORCE2=m
CONFIG_I2C_PARPORT_LIGHT=m
CONFIG_I2C_PROSAVAGE=m
# CONFIG_SCx200_ACB is not set
CONFIG_I2C_SIS5595=m
CONFIG_I2C_SIS630=m
CONFIG_I2C_SIS96X=m
CONFIG_I2C_VIAPRO=m
CONFIG_I2C_VOODOO3=m
CONFIG_I2C_PCA_ISA=m
#
# Miscellaneous I2C Chip support
#
# CONFIG_I2C_DEBUG_CORE is not set
# CONFIG_I2C_DEBUG_ALGO is not set
# CONFIG_I2C_DEBUG_BUS is not set
# CONFIG_I2C_DEBUG_CHIP is not set
#
# SPI support
#
# CONFIG_SPI is not set
# CONFIG_SPI_MASTER is not set
#
# Dallas's 1-wire bus
#
# CONFIG_W1 is not set
#
# Hardware Monitoring support
#
# CONFIG_HWMON is not set
# CONFIG_HWMON_VID is not set
#
# Multimedia devices
#
# CONFIG_VIDEO_DEV is not set
#
# Digital Video Broadcasting Devices
#
# CONFIG_DVB is not set
# CONFIG_USB_DABUSB is not set
#
# Graphics support
#
CONFIG_FIRMWARE_EDID=y
CONFIG_FB=y
# CONFIG_FB_DDC is not set
CONFIG_FB_CFB_FILLRECT=y
CONFIG_FB_CFB_COPYAREA=y
CONFIG_FB_CFB_IMAGEBLIT=y
# CONFIG_FB_MACMODES is not set
# CONFIG_FB_BACKLIGHT is not set
CONFIG_FB_MODE_HELPERS=y
CONFIG_FB_TILEBLITTING=y
# CONFIG_FB_CIRRUS is not set
# CONFIG_FB_PM2 is not set
# CONFIG_FB_CYBER2000 is not set
# CONFIG_FB_ARC is not set
# CONFIG_FB_ASILIANT is not set
# CONFIG_FB_IMSTT is not set
CONFIG_FB_VGA16=m
CONFIG_FB_VESA=y
# CONFIG_FB_HGA is not set
# CONFIG_FB_S1D13XXX is not set
# CONFIG_FB_NVIDIA is not set
# CONFIG_FB_RIVA is not set
# CONFIG_FB_MATROX is not set
# CONFIG_FB_RADEON is not set
# CONFIG_FB_ATY128 is not set
# CONFIG_FB_ATY is not set
# CONFIG_FB_SIS is not set
# CONFIG_FB_NEOMAGIC is not set
# CONFIG_FB_KYRO is not set
# CONFIG_FB_3DFX is not set
# CONFIG_FB_VOODOO1 is not set
# CONFIG_FB_CYBLA is not set
# CONFIG_FB_TRIDENT is not set
# CONFIG_FB_VIRTUAL is not set
#
# Console display driver support
#
CONFIG_VGA_CONSOLE=y
# CONFIG_VGACON_SOFT_SCROLLBACK is not set
CONFIG_VIDEO_SELECT=y
# CONFIG_MDA_CONSOLE is not set
CONFIG_DUMMY_CONSOLE=y
CONFIG_FRAMEBUFFER_CONSOLE=y
# CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set
CONFIG_FONTS=y
CONFIG_FONT_8x8=y
CONFIG_FONT_8x16=y
# CONFIG_FONT_6x11 is not set
# CONFIG_FONT_7x14 is not set
# CONFIG_FONT_PEARL_8x8 is not set
# CONFIG_FONT_ACORN_8x8 is not set
# CONFIG_FONT_MINI_4x6 is not set
# CONFIG_FONT_SUN8x16 is not set
# CONFIG_FONT_SUN12x22 is not set
# CONFIG_FONT_10x18 is not set
#
# Logo configuration
#
CONFIG_LOGO=y
CONFIG_LOGO_LINUX_MONO=y
CONFIG_LOGO_LINUX_VGA16=y
CONFIG_LOGO_LINUX_CLUT224=y
# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
#
# Sound
#
# CONFIG_SOUND is not set
#
# HID Devices
#
CONFIG_HID=y
#
# USB support
#
CONFIG_USB_ARCH_HAS_HCD=y
CONFIG_USB_ARCH_HAS_OHCI=y
CONFIG_USB_ARCH_HAS_EHCI=y
CONFIG_USB=y
# CONFIG_USB_DEBUG is not set
#
# Miscellaneous USB options
#
# CONFIG_USB_DEVICEFS is not set
#
# USB Host Controller Drivers
#
# CONFIG_USB_EHCI_HCD is not set
# CONFIG_USB_ISP116X_HCD is not set
# CONFIG_USB_OHCI_HCD is not set
CONFIG_USB_UHCI_HCD=y
# CONFIG_USB_SL811_HCD is not set
#
# USB Device Class drivers
#
# CONFIG_USB_ACM is not set
# CONFIG_USB_PRINTER is not set
#
# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
#
#
# may also be needed; see USB_STORAGE Help for more information
#
# CONFIG_USB_LIBUSUAL is not set
#
# USB Input Devices
#
CONFIG_USB_HID=y
# CONFIG_USB_HIDINPUT_POWERBOOK is not set
# CONFIG_USB_HIDDEV is not set
# CONFIG_USB_AIPTEK is not set
# CONFIG_USB_WACOM is not set
# CONFIG_USB_ACECAD is not set
# CONFIG_USB_KBTAB is not set
# CONFIG_USB_POWERMATE is not set
# CONFIG_USB_TOUCHSCREEN is not set
# CONFIG_USB_XPAD is not set
# CONFIG_USB_ATI_REMOTE is not set
# CONFIG_USB_ATI_REMOTE2 is not set
# CONFIG_USB_APPLETOUCH is not set
#
# USB Imaging devices
#
#
# USB Network Adapters
#
# CONFIG_USB_KAWETH is not set
# CONFIG_USB_PEGASUS is not set
# CONFIG_USB_USBNET_MII is not set
# CONFIG_USB_USBNET is not set
CONFIG_USB_MON=y
#
# USB port drivers
#
#
# USB Serial Converter support
#
# CONFIG_USB_SERIAL is not set
#
# USB Miscellaneous drivers
#
# CONFIG_USB_EMI62 is not set
# CONFIG_USB_EMI26 is not set
# CONFIG_USB_LCD is not set
# CONFIG_USB_LED is not set
# CONFIG_USB_CYPRESS_CY7C63 is not set
# CONFIG_USB_CYTHERM is not set
# CONFIG_USB_PHIDGET is not set
# CONFIG_USB_IDMOUSE is not set
# CONFIG_USB_FTDI_ELAN is not set
# CONFIG_USB_APPLEDISPLAY is not set
# CONFIG_USB_LD is not set
# CONFIG_USB_TRANCEVIBRATOR is not set
#
# USB DSL modem support
#
#
# USB Gadget Support
#
# CONFIG_USB_GADGET is not set
#
# MMC/SD Card support
#
# CONFIG_MMC is not set
#
# LED devices
#
# CONFIG_NEW_LEDS is not set
#
# LED drivers
#
#
# LED Triggers
#
#
# InfiniBand support
#
# CONFIG_INFINIBAND is not set
#
# EDAC - error detection and reporting (RAS) (EXPERIMENTAL)
#
#
# Real Time Clock
#
#
# DMA Engine support
#
# CONFIG_DMA_ENGINE is not set
#
# DMA Clients
#
#
# DMA Devices
#
#
# Virtualization
#
#
# File systems
#
# CONFIG_EXT2_FS is not set
CONFIG_EXT3_FS=m
CONFIG_EXT3_FS_XATTR=y
CONFIG_EXT3_FS_POSIX_ACL=y
CONFIG_EXT3_FS_SECURITY=y
CONFIG_JBD=m
# CONFIG_JBD_DEBUG is not set
CONFIG_FS_MBCACHE=m
# CONFIG_REISERFS_FS is not set
# CONFIG_JFS_FS is not set
CONFIG_FS_POSIX_ACL=y
# CONFIG_XFS_FS is not set
# CONFIG_OCFS2_FS is not set
# CONFIG_MINIX_FS is not set
# CONFIG_ROMFS_FS is not set
# CONFIG_INOTIFY is not set
# CONFIG_QUOTA is not set
CONFIG_DNOTIFY=y
# CONFIG_AUTOFS_FS is not set
# CONFIG_AUTOFS4_FS is not set
CONFIG_FUSE_FS=y
CONFIG_GENERIC_ACL=y
#
# CD-ROM/DVD Filesystems
#
CONFIG_ISO9660_FS=y
# CONFIG_JOLIET is not set
# CONFIG_ZISOFS is not set
# CONFIG_UDF_FS is not set
#
# DOS/FAT/NT Filesystems
#
# CONFIG_MSDOS_FS is not set
# CONFIG_VFAT_FS is not set
# CONFIG_NTFS_FS is not set
#
# Pseudo filesystems
#
CONFIG_PROC_FS=y
CONFIG_PROC_KCORE=y
CONFIG_PROC_SYSCTL=y
CONFIG_SYSFS=y
CONFIG_TMPFS=y
CONFIG_TMPFS_POSIX_ACL=y
CONFIG_HUGETLBFS=y
CONFIG_HUGETLB_PAGE=y
CONFIG_RAMFS=y
#
# Miscellaneous filesystems
#
# CONFIG_HFSPLUS_FS is not set
# CONFIG_CRAMFS is not set
# CONFIG_VXFS_FS is not set
# CONFIG_HPFS_FS is not set
# CONFIG_QNX4FS_FS is not set
# CONFIG_SYSV_FS is not set
# CONFIG_UFS_FS is not set
#
# Network File Systems
#
# CONFIG_NFS_FS is not set
# CONFIG_NFSD is not set
# CONFIG_SMB_FS is not set
# CONFIG_CIFS is not set
# CONFIG_NCP_FS is not set
# CONFIG_CODA_FS is not set
#
# Partition Types
#
# CONFIG_PARTITION_ADVANCED is not set
CONFIG_MSDOS_PARTITION=y
#
# Native Language Support
#
CONFIG_NLS=y
CONFIG_NLS_DEFAULT="iso8859-1"
CONFIG_NLS_CODEPAGE_437=m
# CONFIG_NLS_CODEPAGE_737 is not set
# CONFIG_NLS_CODEPAGE_775 is not set
# CONFIG_NLS_CODEPAGE_850 is not set
CONFIG_NLS_CODEPAGE_852=m
# CONFIG_NLS_CODEPAGE_855 is not set
# CONFIG_NLS_CODEPAGE_857 is not set
# CONFIG_NLS_CODEPAGE_860 is not set
# CONFIG_NLS_CODEPAGE_861 is not set
# CONFIG_NLS_CODEPAGE_862 is not set
# CONFIG_NLS_CODEPAGE_863 is not set
# CONFIG_NLS_CODEPAGE_864 is not set
# CONFIG_NLS_CODEPAGE_865 is not set
# CONFIG_NLS_CODEPAGE_866 is not set
# CONFIG_NLS_CODEPAGE_869 is not set
# CONFIG_NLS_CODEPAGE_936 is not set
# CONFIG_NLS_CODEPAGE_950 is not set
# CONFIG_NLS_CODEPAGE_932 is not set
# CONFIG_NLS_CODEPAGE_949 is not set
# CONFIG_NLS_CODEPAGE_874 is not set
# CONFIG_NLS_ISO8859_8 is not set
CONFIG_NLS_CODEPAGE_1250=m
CONFIG_NLS_CODEPAGE_1251=m
CONFIG_NLS_ASCII=m
CONFIG_NLS_ISO8859_1=m
# CONFIG_NLS_ISO8859_2 is not set
# CONFIG_NLS_ISO8859_3 is not set
# CONFIG_NLS_ISO8859_4 is not set
# CONFIG_NLS_ISO8859_5 is not set
# CONFIG_NLS_ISO8859_6 is not set
# CONFIG_NLS_ISO8859_7 is not set
# CONFIG_NLS_ISO8859_9 is not set
# CONFIG_NLS_ISO8859_13 is not set
# CONFIG_NLS_ISO8859_14 is not set
# CONFIG_NLS_ISO8859_15 is not set
# CONFIG_NLS_KOI8_R is not set
# CONFIG_NLS_KOI8_U is not set
CONFIG_NLS_UTF8=m
#
# Kernel hacking
#
CONFIG_TRACE_IRQFLAGS_SUPPORT=y
# CONFIG_PRINTK_TIME is not set
CONFIG_ENABLE_MUST_CHECK=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_UNUSED_SYMBOLS=y
CONFIG_DEBUG_FS=y
# CONFIG_HEADERS_CHECK is not set
CONFIG_IPIPE_DEBUG=y
CONFIG_IPIPE_DEBUG_CONTEXT=y
CONFIG_IPIPE_TRACE=y
CONFIG_IPIPE_TRACE_ENABLE=y
CONFIG_IPIPE_TRACE_MCOUNT=y
CONFIG_IPIPE_TRACE_IRQSOFF=y
CONFIG_IPIPE_TRACE_SHIFT=14
# CONFIG_IPIPE_TRACE_VMALLOC is not set
CONFIG_IPIPE_TRACE_PANIC=y
CONFIG_IPIPE_TRACE_ENABLE_VALUE=1
# CONFIG_DEBUG_KERNEL is not set
CONFIG_LOG_BUF_SHIFT=14
CONFIG_DEBUG_BUGVERBOSE=y
CONFIG_FRAME_POINTER=y
CONFIG_EARLY_PRINTK=y
CONFIG_DOUBLEFAULT=y
#
# Security options
#
# CONFIG_KEYS is not set
# CONFIG_SECURITY is not set
#
# Cryptographic options
#
# CONFIG_CRYPTO is not set
#
# Library routines
#
CONFIG_BITREVERSE=y
CONFIG_CRC_CCITT=m
CONFIG_CRC16=m
CONFIG_CRC32=y
CONFIG_LIBCRC32C=m
CONFIG_AUDIT_GENERIC=y
CONFIG_PLIST=y
CONFIG_IOMAP_COPY=y
CONFIG_GENERIC_HARDIRQS=y
CONFIG_GENERIC_IRQ_PROBE=y
CONFIG_X86_BIOS_REBOOT=y
CONFIG_KTIME_SCALAR=y
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-05 9:04 ` CHABAL David
@ 2007-10-05 9:20 ` Philippe Gerum
2007-10-05 10:29 ` CHABAL David
0 siblings, 1 reply; 30+ messages in thread
From: Philippe Gerum @ 2007-10-05 9:20 UTC (permalink / raw)
To: CHABAL David; +Cc: xenomai
On Fri, 2007-10-05 at 11:04 +0200, CHABAL David wrote:
> Gilles Chanteperdrix a écrit :
> > On 10/5/07, CHABAL David <david.chabal@domain.hid> wrote:
> >> Hello all,
> >>
> >> My box is a Pentium III 733 Mhz/256Mo with Linux 2.6.20 and Xenomai
> 2.3.3.
> >>
> >> When I run the latency test included in the testsuite, I get some
> >> horrible results like:
> >>
You first need to upgrade your Adeos patch in order to avoid a deadly
tracer issue in earlier versions:
http://download.gna.org/adeos/patches/v2.6/i386/older/adeos-ipipe-2.6.20-i386-1.8-08.patch
Then, please switch on CONFIG_IPIPE_TRACE, CONFIG_IPIPE_TRACE_MCOUNT,
CONFIG_IPIPE_TRACE_IRQSOFF, and eventually run the following on the
target kernel:
# echo 1 > /proc/ipipe/trace/enable
# /usr/xenomai/bin/latency -f
... wait for a high latency ...
# echo 128 > /proc/ipipe/trace/back_trace_points
# cat /proc/ipipe/trace/frozen
Sending us back the output of the last command would help.
--
Philippe.
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-05 9:20 ` Philippe Gerum
@ 2007-10-05 10:29 ` CHABAL David
2007-10-05 12:35 ` Jan Kiszka
2007-10-05 14:02 ` Philippe Gerum
0 siblings, 2 replies; 30+ messages in thread
From: CHABAL David @ 2007-10-05 10:29 UTC (permalink / raw)
To: rpm; +Cc: xenomai
[-- Attachment #1: Type: text/plain, Size: 1631 bytes --]
Philippe Gerum a écrit :
> On Fri, 2007-10-05 at 11:04 +0200, CHABAL David wrote:
>> Gilles Chanteperdrix a écrit :
>>> On 10/5/07, CHABAL David <david.chabal@domain.hid> wrote:
>>>> Hello all,
>>>>
>>>> My box is a Pentium III 733 Mhz/256Mo with Linux 2.6.20 and Xenomai
>> 2.3.3.
>>>> When I run the latency test included in the testsuite, I get some
>>>> horrible results like:
>>>>
>
> You first need to upgrade your Adeos patch in order to avoid a deadly
> tracer issue in earlier versions:
> http://download.gna.org/adeos/patches/v2.6/i386/older/adeos-ipipe-2.6.20-i386-1.8-08.patch
>
> Then, please switch on CONFIG_IPIPE_TRACE, CONFIG_IPIPE_TRACE_MCOUNT,
> CONFIG_IPIPE_TRACE_IRQSOFF, and eventually run the following on the
> target kernel:
>
> # echo 1 > /proc/ipipe/trace/enable
> # /usr/xenomai/bin/latency -f
> ... wait for a high latency ...
> # echo 128 > /proc/ipipe/trace/back_trace_points
> # cat /proc/ipipe/trace/frozen
>
> Sending us back the output of the last command would help.
>
Gilles and Philippe, thank you for your help.
The results below come from a patched kernel with adeos 1.8.08:
RTT| 00:07:22 (periodic user-mode task, 100 us period, priority 99)
RTH|-----lat min|-----lat avg|-----lat max|-overrun|----lat best|---lat
worst
RTD| 4.722| 12.411| 93.529| 0| 3.129|
122.269
RTD| 4.347| 13.690| 93.802| 0| 3.129|
122.269
---|------------|------------|------------|--------|-------------------------
RTS| 3.129| 10.194| 122.269| 0| 00:07:24/00:07:24
David
[-- Attachment #2: frozen --]
[-- Type: text/plain, Size: 8581 bytes --]
I-pipe frozen back-tracing service on 2.6.20/ipipe-1.8-08
------------------------------------------------------------
******** WARNING ********
The following debugging options will increase the observed latencies:
o CONFIG_XENO_OPT_DEBUG
Freeze: 620918235066 cycles, Trace Points: 128 (+10)
Calibrated minimum trace-point overhead: 0.248 us
+--------------- Hard IRQs ('|': locked)
| +- Delay flag ('+': > 1 us, '!': > 10 us)
| |
Type Time Function (Parent)
: func -145 iowrite16 (issue_and_wait)
: func -144+ ioread16 (issue_and_wait)
: func -137+ ioread32 (boomerang_start_xmit)
: func -136 iowrite16 (boomerang_start_xmit)
: func -136 __ipipe_restore_root (boomerang_start_xmit)
: func -135 __ipipe_unstall_root (__ipipe_restore_root)
:|begin -135 __ipipe_unstall_root (__ipipe_restore_root)
:|end -135 __ipipe_unstall_root (__ipipe_restore_root)
: func -134 ipipe_check_context (boomerang_start_xmit)
: func -134 ipipe_check_context (__qdisc_run)
: func -133 ipipe_check_context (__qdisc_run)
: func -133 pfifo_fast_dequeue (__qdisc_run)
: func -133 ipipe_check_context (dev_queue_xmit)
: func -132 local_bh_enable (dev_queue_xmit)
: func -132 ipipe_check_context (local_bh_enable)
: func -132 update_send_head (__tcp_push_pending_frames)
: func -131 tcp_init_tso_segs (__tcp_push_pending_frames)
: func -131 tcp_set_skb_tso_segs (tcp_init_tso_segs)
: func -131 tcp_transmit_skb (__tcp_push_pending_frames)
: func -130 skb_clone (tcp_transmit_skb)
: func -129 __tcp_select_window (tcp_transmit_skb)
: func -129 tcp_v4_send_check (tcp_transmit_skb)
: func -128 ip_queue_xmit (tcp_transmit_skb)
: func -128 __sk_dst_check (ip_queue_xmit)
: func -127 ip_output (ip_queue_xmit)
: func -127 dev_queue_xmit (ip_output)
: func -127 local_bh_disable (dev_queue_xmit)
: func -126 ipipe_check_context (dev_queue_xmit)
: func -126 pfifo_fast_enqueue (dev_queue_xmit)
: func -126 __qdisc_run (dev_queue_xmit)
: func -125 pfifo_fast_dequeue (__qdisc_run)
: func -125 ipipe_check_context (__qdisc_run)
: func -125 ipipe_check_context (__qdisc_run)
: func -124 dev_hard_start_xmit (__qdisc_run)
: func -124 ipipe_check_context (dev_hard_start_xmit)
: func -124 skb_clone (dev_hard_start_xmit)
: func -123 kmem_cache_alloc (skb_clone)
: func -123 ipipe_check_context (kmem_cache_alloc)
: func -123 __ipipe_restore_root (kmem_cache_alloc)
: func -123 __ipipe_unstall_root (__ipipe_restore_root)
:|begin -122 __ipipe_unstall_root (__ipipe_restore_root)
:|end -122 __ipipe_unstall_root (__ipipe_restore_root)
: func -121 packet_rcv_spkt (dev_hard_start_xmit)
: func -121 strlcpy (packet_rcv_spkt)
: func -121 sock_queue_rcv_skb (packet_rcv_spkt)
: func -120 local_bh_disable (sock_queue_rcv_skb)
: func -120 sk_run_filter (sock_queue_rcv_skb)
: func -119 local_bh_enable (sock_queue_rcv_skb)
: func -119 ipipe_check_context (local_bh_enable)
: func -119 kfree_skb (packet_rcv_spkt)
: func -119 __kfree_skb (kfree_skb)
: func -118 kfree_skbmem (__kfree_skb)
: func -118 skb_release_data (kfree_skbmem)
: func -117 kmem_cache_free (kfree_skbmem)
: func -117 ipipe_check_context (kmem_cache_free)
: func -117 __ipipe_restore_root (kmem_cache_free)
: func -117 __ipipe_unstall_root (__ipipe_restore_root)
:|begin -116 __ipipe_unstall_root (__ipipe_restore_root)
:|end -116 __ipipe_unstall_root (__ipipe_restore_root)
: func -115 ipipe_check_context (dev_hard_start_xmit)
: func -115 boomerang_start_xmit (dev_hard_start_xmit)
: func -115 ipipe_check_context (boomerang_start_xmit)
: func -114 ipipe_check_context (boomerang_start_xmit)
: func -114 issue_and_wait (boomerang_start_xmit)
: func -114 iowrite16 (issue_and_wait)
: func -113! ioread16 (issue_and_wait)
:|begin -84 common_interrupt (ioread16)
:|func -83 __ipipe_handle_irq (common_interrupt)
:|func -83 __ipipe_ack_irq (__ipipe_handle_irq)
:|func -82 __ipipe_ack_level_irq (__ipipe_ack_irq)
:|func -82 mask_and_ack_8259A (__ipipe_ack_level_irq)
:|func -82+ __ipipe_spin_lock_irqsave (mask_and_ack_8259A)
:|func -78 __ipipe_spin_unlock_irqrestore (mask_and_ack_8259A)
:|func -78 __ipipe_dispatch_wired (__ipipe_handle_irq)
:|func -77 xnintr_clock_handler (__ipipe_dispatch_wired)
:|func -77 xnintr_irq_handler (xnintr_clock_handler)
:|func -77 xnpod_announce_tick (xnintr_irq_handler)
:|func -76 xntimer_do_tick_aperiodic (xnpod_announce_tick)
:|func -76 xnthread_periodic_handler (xntimer_do_tick_aperiodic)
:|func -76 xnpod_resume_thread (xnthread_periodic_handler)
:|[ 3937] -75+ xnpod_resume_thread (xnthread_periodic_handler)
:|func -72 xnpod_schedule (xnintr_irq_handler)
:|[ 3497] -72+ xnpod_schedule (xnintr_irq_handler)
:|func -71 __switch_to (xnpod_schedule)
:|[ 3937] -70 xnpod_schedule (xnpod_suspend_thread)
:|func -70 __ipipe_restore_pipeline_head (xnpod_wait_thread_period)
:|end -69+ __ipipe_restore_pipeline_head (xnpod_wait_thread_period)
:|begin -63 common_interrupt (__ipipe_restore_pipeline_head)
:|func -62 __ipipe_handle_irq (common_interrupt)
:|func -62 __ipipe_ack_irq (__ipipe_handle_irq)
:|func -62 __ipipe_ack_level_irq (__ipipe_ack_irq)
:|func -61 mask_and_ack_8259A (__ipipe_ack_level_irq)
:|func -61! __ipipe_spin_lock_irqsave (mask_and_ack_8259A)
:|func -40 __ipipe_spin_unlock_irqrestore (mask_and_ack_8259A)
:|func -40 __ipipe_walk_pipeline (__ipipe_handle_irq)
:|end -39+ common_interrupt (__ipipe_restore_pipeline_head)
:|begin -32 common_interrupt (__ipipe_restore_pipeline_head)
:|func -32 __ipipe_handle_irq (common_interrupt)
:|func -31 __ipipe_ack_irq (__ipipe_handle_irq)
:|func -31 __ipipe_ack_level_irq (__ipipe_ack_irq)
:|func -31 mask_and_ack_8259A (__ipipe_ack_level_irq)
:|func -30+ __ipipe_spin_lock_irqsave (mask_and_ack_8259A)
:|func -25 __ipipe_spin_unlock_irqrestore (mask_and_ack_8259A)
:|func -24 __ipipe_dispatch_wired (__ipipe_handle_irq)
:|func -24 xnintr_clock_handler (__ipipe_dispatch_wired)
:|func -23 xnintr_irq_handler (xnintr_clock_handler)
:|func -23 xnpod_announce_tick (xnintr_irq_handler)
:|func -23 xntimer_do_tick_aperiodic (xnpod_announce_tick)
:|func -22+ xnthread_periodic_handler (xntimer_do_tick_aperiodic)
:|func -13 rthal_irq_host_pend (xnintr_irq_handler)
:|func -13 __ipipe_schedule_irq (rthal_irq_host_pend)
:|func -12 __ipipe_walk_pipeline (__ipipe_handle_irq)
:|end -12 common_interrupt (__ipipe_restore_pipeline_head)
:|begin -11 __ipipe_dispatch_event (__ipipe_syscall_root)
:|end -11+ __ipipe_dispatch_event (__ipipe_syscall_root)
: func -8 __ipipe_syscall_root (system_call)
: func -7 __ipipe_dispatch_event (__ipipe_syscall_root)
:|begin -7 __ipipe_dispatch_event (__ipipe_syscall_root)
:|end -6 __ipipe_dispatch_event (__ipipe_syscall_root)
: func -6+ hisyscall_event (__ipipe_dispatch_event)
: func -5+ xnshadow_sys_trace (hisyscall_event)
: func -4 ipipe_trace_frozen_reset (xnshadow_sys_trace)
: func -3 __ipipe_global_path_lock (ipipe_trace_frozen_reset)
: func -3 __ipipe_spin_lock_irqsave (__ipipe_global_path_lock)
:|begin -2+ __ipipe_spin_lock_irqsave (__ipipe_global_path_lock)
:|func 0 __ipipe_spin_unlock_irqcomplete (__ipipe_global_path_unlock)
:|end 0 __ipipe_spin_unlock_irqcomplete (__ipipe_global_path_unlock)
< freeze 0 xnshadow_sys_trace (hisyscall_event)
|begin 0 __ipipe_dispatch_event (__ipipe_syscall_root)
|end 0 __ipipe_dispatch_event (__ipipe_syscall_root)
func 1 __ipipe_syscall_root (system_call)
func 2 __ipipe_dispatch_event (__ipipe_syscall_root)
|begin 2 __ipipe_dispatch_event (__ipipe_syscall_root)
|end 2 __ipipe_dispatch_event (__ipipe_syscall_root)
func 3 hisyscall_event (__ipipe_dispatch_event)
func 3 __rt_task_wait_period (hisyscall_event)
func 3 rt_task_wait_period (__rt_task_wait_period)
func 4 xnpod_wait_thread_period (rt_task_wait_period)
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-05 10:29 ` CHABAL David
@ 2007-10-05 12:35 ` Jan Kiszka
2007-10-05 14:02 ` Philippe Gerum
1 sibling, 0 replies; 30+ messages in thread
From: Jan Kiszka @ 2007-10-05 12:35 UTC (permalink / raw)
To: CHABAL David; +Cc: xenomai
CHABAL David wrote:
> Philippe Gerum a écrit :
>> On Fri, 2007-10-05 at 11:04 +0200, CHABAL David wrote:
>>> Gilles Chanteperdrix a écrit :
>>>> On 10/5/07, CHABAL David <david.chabal@domain.hid> wrote:
>>>>> Hello all,
>>>>>
>>>>> My box is a Pentium III 733 Mhz/256Mo with Linux 2.6.20 and Xenomai
>>> 2.3.3.
>>>>> When I run the latency test included in the testsuite, I get some
>>>>> horrible results like:
>>>>>
>>
>> You first need to upgrade your Adeos patch in order to avoid a deadly
>> tracer issue in earlier versions:
>> http://download.gna.org/adeos/patches/v2.6/i386/older/adeos-ipipe-2.6.20-i386-1.8-08.patch
>>
>>
>> Then, please switch on CONFIG_IPIPE_TRACE, CONFIG_IPIPE_TRACE_MCOUNT,
>> CONFIG_IPIPE_TRACE_IRQSOFF, and eventually run the following on the
>> target kernel:
>>
>> # echo 1 > /proc/ipipe/trace/enable
>> # /usr/xenomai/bin/latency -f
>> ... wait for a high latency ...
>> # echo 128 > /proc/ipipe/trace/back_trace_points
>> # cat /proc/ipipe/trace/frozen
echo 1 > /proc/ipipe/trace/verbose is also useful (think I'm going to
write a patch to make this default on...).
>>
>> Sending us back the output of the last command would help.
>>
> Gilles and Philippe, thank you for your help.
>
> The results below come from a patched kernel with adeos 1.8.08:
>
>
> RTT| 00:07:22 (periodic user-mode task, 100 us period, priority 99)
> RTH|-----lat min|-----lat avg|-----lat max|-overrun|----lat best|---lat
> worst
> RTD| 4.722| 12.411| 93.529| 0| 3.129| 122.269
> RTD| 4.347| 13.690| 93.802| 0| 3.129| 122.269
> ---|------------|------------|------------|--------|-------------------------
>
> RTS| 3.129| 10.194| 122.269| 0| 00:07:24/00:07:24
>
>
>
> David
>
>
> ------------------------------------------------------------------------
>
> I-pipe frozen back-tracing service on 2.6.20/ipipe-1.8-08
> ------------------------------------------------------------
>
> ******** WARNING ********
> The following debugging options will increase the observed latencies:
> o CONFIG_XENO_OPT_DEBUG
>
> Freeze: 620918235066 cycles, Trace Points: 128 (+10)
> Calibrated minimum trace-point overhead: 0.248 us
>
> +--------------- Hard IRQs ('|': locked)
> | +- Delay flag ('+': > 1 us, '!': > 10 us)
> | |
> Type Time Function (Parent)
> : func -145 iowrite16 (issue_and_wait)
> : func -144+ ioread16 (issue_and_wait)
> : func -137+ ioread32 (boomerang_start_xmit)
> : func -136 iowrite16 (boomerang_start_xmit)
> : func -136 __ipipe_restore_root (boomerang_start_xmit)
> : func -135 __ipipe_unstall_root (__ipipe_restore_root)
> :|begin -135 __ipipe_unstall_root (__ipipe_restore_root)
> :|end -135 __ipipe_unstall_root (__ipipe_restore_root)
> : func -134 ipipe_check_context (boomerang_start_xmit)
> : func -134 ipipe_check_context (__qdisc_run)
> : func -133 ipipe_check_context (__qdisc_run)
> : func -133 pfifo_fast_dequeue (__qdisc_run)
> : func -133 ipipe_check_context (dev_queue_xmit)
> : func -132 local_bh_enable (dev_queue_xmit)
> : func -132 ipipe_check_context (local_bh_enable)
> : func -132 update_send_head (__tcp_push_pending_frames)
> : func -131 tcp_init_tso_segs (__tcp_push_pending_frames)
> : func -131 tcp_set_skb_tso_segs (tcp_init_tso_segs)
> : func -131 tcp_transmit_skb (__tcp_push_pending_frames)
> : func -130 skb_clone (tcp_transmit_skb)
> : func -129 __tcp_select_window (tcp_transmit_skb)
> : func -129 tcp_v4_send_check (tcp_transmit_skb)
> : func -128 ip_queue_xmit (tcp_transmit_skb)
> : func -128 __sk_dst_check (ip_queue_xmit)
> : func -127 ip_output (ip_queue_xmit)
> : func -127 dev_queue_xmit (ip_output)
> : func -127 local_bh_disable (dev_queue_xmit)
> : func -126 ipipe_check_context (dev_queue_xmit)
> : func -126 pfifo_fast_enqueue (dev_queue_xmit)
> : func -126 __qdisc_run (dev_queue_xmit)
> : func -125 pfifo_fast_dequeue (__qdisc_run)
> : func -125 ipipe_check_context (__qdisc_run)
> : func -125 ipipe_check_context (__qdisc_run)
> : func -124 dev_hard_start_xmit (__qdisc_run)
> : func -124 ipipe_check_context (dev_hard_start_xmit)
> : func -124 skb_clone (dev_hard_start_xmit)
> : func -123 kmem_cache_alloc (skb_clone)
> : func -123 ipipe_check_context (kmem_cache_alloc)
> : func -123 __ipipe_restore_root (kmem_cache_alloc)
> : func -123 __ipipe_unstall_root (__ipipe_restore_root)
> :|begin -122 __ipipe_unstall_root (__ipipe_restore_root)
> :|end -122 __ipipe_unstall_root (__ipipe_restore_root)
> : func -121 packet_rcv_spkt (dev_hard_start_xmit)
> : func -121 strlcpy (packet_rcv_spkt)
> : func -121 sock_queue_rcv_skb (packet_rcv_spkt)
> : func -120 local_bh_disable (sock_queue_rcv_skb)
> : func -120 sk_run_filter (sock_queue_rcv_skb)
> : func -119 local_bh_enable (sock_queue_rcv_skb)
> : func -119 ipipe_check_context (local_bh_enable)
> : func -119 kfree_skb (packet_rcv_spkt)
> : func -119 __kfree_skb (kfree_skb)
> : func -118 kfree_skbmem (__kfree_skb)
> : func -118 skb_release_data (kfree_skbmem)
> : func -117 kmem_cache_free (kfree_skbmem)
> : func -117 ipipe_check_context (kmem_cache_free)
> : func -117 __ipipe_restore_root (kmem_cache_free)
> : func -117 __ipipe_unstall_root (__ipipe_restore_root)
> :|begin -116 __ipipe_unstall_root (__ipipe_restore_root)
> :|end -116 __ipipe_unstall_root (__ipipe_restore_root)
> : func -115 ipipe_check_context (dev_hard_start_xmit)
> : func -115 boomerang_start_xmit (dev_hard_start_xmit)
> : func -115 ipipe_check_context (boomerang_start_xmit)
> : func -114 ipipe_check_context (boomerang_start_xmit)
> : func -114 issue_and_wait (boomerang_start_xmit)
> : func -114 iowrite16 (issue_and_wait)
> : func -113! ioread16 (issue_and_wait)
> :|begin -84 common_interrupt (ioread16)
Here we already see 30 us (!) between the last function entry and the
IRQ acceptance. That point to some hardware impact on latency, e.g. slow
buses or large DMA bursts.
> :|func -83 __ipipe_handle_irq (common_interrupt)
> :|func -83 __ipipe_ack_irq (__ipipe_handle_irq)
> :|func -82 __ipipe_ack_level_irq (__ipipe_ack_irq)
> :|func -82 mask_and_ack_8259A (__ipipe_ack_level_irq)
If you have a reasonable motherboard, try to turn on Local APIC and
IO-APIC. That will avoid a bit overhead due to PIC fiddling.
> :|func -82+ __ipipe_spin_lock_irqsave (mask_and_ack_8259A)
> :|func -78 __ipipe_spin_unlock_irqrestore (mask_and_ack_8259A)
> :|func -78 __ipipe_dispatch_wired (__ipipe_handle_irq)
> :|func -77 xnintr_clock_handler (__ipipe_dispatch_wired)
> :|func -77 xnintr_irq_handler (xnintr_clock_handler)
> :|func -77 xnpod_announce_tick (xnintr_irq_handler)
> :|func -76 xntimer_do_tick_aperiodic (xnpod_announce_tick)
> :|func -76 xnthread_periodic_handler (xntimer_do_tick_aperiodic)
> :|func -76 xnpod_resume_thread (xnthread_periodic_handler)
> :|[ 3937] -75+ xnpod_resume_thread (xnthread_periodic_handler)
This is likely the wakeup call to your measurement thread (verbose mode
would tell us more).
> :|func -72 xnpod_schedule (xnintr_irq_handler)
> :|[ 3497] -72+ xnpod_schedule (xnintr_irq_handler)
> :|func -71 __switch_to (xnpod_schedule)
> :|[ 3937] -70 xnpod_schedule (xnpod_suspend_thread)
> :|func -70 __ipipe_restore_pipeline_head (xnpod_wait_thread_period)
> :|end -69+ __ipipe_restore_pipeline_head (xnpod_wait_thread_period)
> :|begin -63 common_interrupt (__ipipe_restore_pipeline_head)
Some disturbing IRQ between wakeup and measurement. Maybe some HD
activity, or an IRQ from the NIC, or you hit the keyboard, or...
> :|func -62 __ipipe_handle_irq (common_interrupt)
> :|func -62 __ipipe_ack_irq (__ipipe_handle_irq)
> :|func -62 __ipipe_ack_level_irq (__ipipe_ack_irq)
> :|func -61 mask_and_ack_8259A (__ipipe_ack_level_irq)
> :|func -61! __ipipe_spin_lock_irqsave (mask_and_ack_8259A)
> :|func -40 __ipipe_spin_unlock_irqrestore (mask_and_ack_8259A)
> :|func -40 __ipipe_walk_pipeline (__ipipe_handle_irq)
> :|end -39+ common_interrupt (__ipipe_restore_pipeline_head)
> :|begin -32 common_interrupt (__ipipe_restore_pipeline_head)
And another IRQ!
> :|func -32 __ipipe_handle_irq (common_interrupt)
> :|func -31 __ipipe_ack_irq (__ipipe_handle_irq)
> :|func -31 __ipipe_ack_level_irq (__ipipe_ack_irq)
> :|func -31 mask_and_ack_8259A (__ipipe_ack_level_irq)
> :|func -30+ __ipipe_spin_lock_irqsave (mask_and_ack_8259A)
> :|func -25 __ipipe_spin_unlock_irqrestore (mask_and_ack_8259A)
> :|func -24 __ipipe_dispatch_wired (__ipipe_handle_irq)
> :|func -24 xnintr_clock_handler (__ipipe_dispatch_wired)
> :|func -23 xnintr_irq_handler (xnintr_clock_handler)
> :|func -23 xnpod_announce_tick (xnintr_irq_handler)
> :|func -23 xntimer_do_tick_aperiodic (xnpod_announce_tick)
> :|func -22+ xnthread_periodic_handler (xntimer_do_tick_aperiodic)
> :|func -13 rthal_irq_host_pend (xnintr_irq_handler)
Ah, it's the Linux host tick. That's normal, one has to consider this
for the worst case.
> :|func -13 __ipipe_schedule_irq (rthal_irq_host_pend)
> :|func -12 __ipipe_walk_pipeline (__ipipe_handle_irq)
> :|end -12 common_interrupt (__ipipe_restore_pipeline_head)
> :|begin -11 __ipipe_dispatch_event (__ipipe_syscall_root)
> :|end -11+ __ipipe_dispatch_event (__ipipe_syscall_root)
> : func -8 __ipipe_syscall_root (system_call)
> : func -7 __ipipe_dispatch_event (__ipipe_syscall_root)
> :|begin -7 __ipipe_dispatch_event (__ipipe_syscall_root)
> :|end -6 __ipipe_dispatch_event (__ipipe_syscall_root)
> : func -6+ hisyscall_event (__ipipe_dispatch_event)
> : func -5+ xnshadow_sys_trace (hisyscall_event)
And here we finally found the time to run latency code and measure the
delay. All in all, a reasonable code path, maybe one can tune a bit here
and there, but the general pattern is expected.
> : func -4 ipipe_trace_frozen_reset (xnshadow_sys_trace)
> : func -3 __ipipe_global_path_lock (ipipe_trace_frozen_reset)
> : func -3 __ipipe_spin_lock_irqsave (__ipipe_global_path_lock)
> :|begin -2+ __ipipe_spin_lock_irqsave (__ipipe_global_path_lock)
> :|func 0 __ipipe_spin_unlock_irqcomplete (__ipipe_global_path_unlock)
> :|end 0 __ipipe_spin_unlock_irqcomplete (__ipipe_global_path_unlock)
> < freeze 0 xnshadow_sys_trace (hisyscall_event)
> |begin 0 __ipipe_dispatch_event (__ipipe_syscall_root)
> |end 0 __ipipe_dispatch_event (__ipipe_syscall_root)
> func 1 __ipipe_syscall_root (system_call)
> func 2 __ipipe_dispatch_event (__ipipe_syscall_root)
> |begin 2 __ipipe_dispatch_event (__ipipe_syscall_root)
> |end 2 __ipipe_dispatch_event (__ipipe_syscall_root)
> func 3 hisyscall_event (__ipipe_dispatch_event)
> func 3 __rt_task_wait_period (hisyscall_event)
> func 3 rt_task_wait_period (__rt_task_wait_period)
> func 4 xnpod_wait_thread_period (rt_task_wait_period)
>
Jan
--
Siemens AG, Corporate Technology, CT SE 2
Corporate Competence Center Embedded Linux
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-05 10:29 ` CHABAL David
2007-10-05 12:35 ` Jan Kiszka
@ 2007-10-05 14:02 ` Philippe Gerum
2007-10-08 12:46 ` CHABAL David
1 sibling, 1 reply; 30+ messages in thread
From: Philippe Gerum @ 2007-10-05 14:02 UTC (permalink / raw)
To: CHABAL David; +Cc: xenomai
On Fri, 2007-10-05 at 12:29 +0200, CHABAL David wrote:
> : func -114 ipipe_check_context (boomerang_start_xmit)
> : func -114 issue_and_wait (boomerang_start_xmit)
> : func -114 iowrite16 (issue_and_wait)
> : func -113! ioread16 (issue_and_wait)
> :|begin -84 common_interrupt (ioread16)
The Vortex driver does some brute force polling on the slow path, when
the adapter does not acknowledge the last command sent fast enough. It
seems your CPU is burning a lot of horsepower idling on this loop.
> :|func -83 __ipipe_handle_irq (common_interrupt)
> :|func -83 __ipipe_ack_irq (__ipipe_handle_irq)
> :|func -82 __ipipe_ack_level_irq (__ipipe_ack_irq)
> :|func -82 mask_and_ack_8259A (__ipipe_ack_level_irq)
> :|func -82+ __ipipe_spin_lock_irqsave (mask_and_ack_8259A)
> :|func -78 __ipipe_spin_unlock_irqrestore (mask_and_ack_8259A)
> :|func -78 __ipipe_dispatch_wired (__ipipe_handle_irq)
> :|func -77 xnintr_clock_handler (__ipipe_dispatch_wired)
> :|func -77 xnintr_irq_handler (xnintr_clock_handler)
> :|func -77 xnpod_announce_tick (xnintr_irq_handler)
> :|func -76 xntimer_do_tick_aperiodic (xnpod_announce_tick)
> :|func -76 xnthread_periodic_handler
> (xntimer_do_tick_aperiodic)
> :|func -76 xnpod_resume_thread (xnthread_periodic_handler)
> :|[ 3937] -75+ xnpod_resume_thread (xnthread_periodic_handler)
> :|func -72 xnpod_schedule (xnintr_irq_handler)
> :|[ 3497] -72+ xnpod_schedule (xnintr_irq_handler)
> :|func -71 __switch_to (xnpod_schedule)
> :|[ 3937] -70 xnpod_schedule (xnpod_suspend_thread)
> :|func -70 __ipipe_restore_pipeline_head
> (xnpod_wait_thread_period)
> :|end -69+ __ipipe_restore_pipeline_head
> (xnpod_wait_thread_period)
> :|begin -63 common_interrupt (__ipipe_restore_pipeline_head)
> :|func -62 __ipipe_handle_irq (common_interrupt)
> :|func -62 __ipipe_ack_irq (__ipipe_handle_irq)
> :|func -62 __ipipe_ack_level_irq (__ipipe_ack_irq)
> :|func -61 mask_and_ack_8259A (__ipipe_ack_level_irq)
> :|func -61! __ipipe_spin_lock_irqsave (mask_and_ack_8259A)
> :|func -40 __ipipe_spin_unlock_irqrestore (mask_and_ack_8259A)
20 us spent acknowledging the interrupt is damned slow. Any "spurious
8259A interrupt" message haunting your kernel log so far?
The sampling task is properly rescheduled after ~15us since the timer
interrupt receipt, problem is that other interrupts are preempting the
awaken task again and again before it has a chance to run. I wonder if
something fishy is not going on with the fast timer acknowledge, or the
network card. Could you:
- send us the output of /proc/interrupts
- try the patch below which should prevent any acknowledge nesting
errors at PIC level,
--- arch/i386/kernel/i8259.c~ 2007-09-16 16:54:34.000000000 +0200
+++ arch/i386/kernel/i8259.c 2007-10-05 15:47:41.000000000 +0200
@@ -176,11 +176,9 @@
goto spurious_8259A_irq;
#ifdef CONFIG_IPIPE
if (irq == 0) {
- /* Fast timer ack -- don't mask (unless supposedly
- spurious) */
- outb(0x20,PIC_MASTER_CMD);
- spin_unlock_irqrestore(&i8259A_lock, flags);
- return;
+ outb(0x60,PIC_MASTER_CMD); /* 'Specific EOI to master */
+ spin_unlock_irqrestore(&i8259A_lock, flags);
+ return;
}
#endif /* CONFIG_IPIPE */
cached_irq_mask |= irqmask;
--
Philippe.
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-05 14:02 ` Philippe Gerum
@ 2007-10-08 12:46 ` CHABAL David
2007-10-10 11:30 ` Philippe Gerum
0 siblings, 1 reply; 30+ messages in thread
From: CHABAL David @ 2007-10-08 12:46 UTC (permalink / raw)
To: rpm; +Cc: xenomai
[-- Attachment #1: Type: text/plain, Size: 3853 bytes --]
Philippe Gerum a écrit :
> On Fri, 2007-10-05 at 12:29 +0200, CHABAL David wrote:
>
>> : func -114 ipipe_check_context (boomerang_start_xmit)
>> : func -114 issue_and_wait (boomerang_start_xmit)
>> : func -114 iowrite16 (issue_and_wait)
>> : func -113! ioread16 (issue_and_wait)
>> :|begin -84 common_interrupt (ioread16)
>
> The Vortex driver does some brute force polling on the slow path, when
> the adapter does not acknowledge the last command sent fast enough. It
> seems your CPU is burning a lot of horsepower idling on this loop.
>
(I enabled Local Apic and IO apic according to Jan's post.)
I tried with a new NIC (RLT8139, PCI) instead of the on-board 3com, and
the latency test is not too bad, it reaches 57.074us.
>> :|func -83 __ipipe_handle_irq (common_interrupt)
>> :|func -83 __ipipe_ack_irq (__ipipe_handle_irq)
>> :|func -82 __ipipe_ack_level_irq (__ipipe_ack_irq)
>> :|func -82 mask_and_ack_8259A (__ipipe_ack_level_irq)
>> :|func -82+ __ipipe_spin_lock_irqsave (mask_and_ack_8259A)
>> :|func -78 __ipipe_spin_unlock_irqrestore (mask_and_ack_8259A)
>> :|func -78 __ipipe_dispatch_wired (__ipipe_handle_irq)
>> :|func -77 xnintr_clock_handler (__ipipe_dispatch_wired)
>> :|func -77 xnintr_irq_handler (xnintr_clock_handler)
>> :|func -77 xnpod_announce_tick (xnintr_irq_handler)
>> :|func -76 xntimer_do_tick_aperiodic (xnpod_announce_tick)
>> :|func -76 xnthread_periodic_handler
>> (xntimer_do_tick_aperiodic)
>> :|func -76 xnpod_resume_thread (xnthread_periodic_handler)
>> :|[ 3937] -75+ xnpod_resume_thread (xnthread_periodic_handler)
>> :|func -72 xnpod_schedule (xnintr_irq_handler)
>> :|[ 3497] -72+ xnpod_schedule (xnintr_irq_handler)
>> :|func -71 __switch_to (xnpod_schedule)
>> :|[ 3937] -70 xnpod_schedule (xnpod_suspend_thread)
>> :|func -70 __ipipe_restore_pipeline_head
>> (xnpod_wait_thread_period)
>> :|end -69+ __ipipe_restore_pipeline_head
>> (xnpod_wait_thread_period)
>> :|begin -63 common_interrupt (__ipipe_restore_pipeline_head)
>> :|func -62 __ipipe_handle_irq (common_interrupt)
>> :|func -62 __ipipe_ack_irq (__ipipe_handle_irq)
>> :|func -62 __ipipe_ack_level_irq (__ipipe_ack_irq)
>> :|func -61 mask_and_ack_8259A (__ipipe_ack_level_irq)
>> :|func -61! __ipipe_spin_lock_irqsave (mask_and_ack_8259A)
>> :|func -40 __ipipe_spin_unlock_irqrestore (mask_and_ack_8259A)
>
> 20 us spent acknowledging the interrupt is damned slow. Any "spurious
> 8259A interrupt" message haunting your kernel log so far?
>
No, I don't have it in my syslog.
> The sampling task is properly rescheduled after ~15us since the timer
> interrupt receipt, problem is that other interrupts are preempting the
> awaken task again and again before it has a chance to run. I wonder if
> something fishy is not going on with the fast timer acknowledge, or the
> network card. Could you:
>
> - send us the output of /proc/interrupts
> - try the patch below which should prevent any acknowledge nesting
> errors at PIC level,
>
The files enclosed are generated with the 3com NIC, your patch and
local/IO APIC.
RTT| 00:15:25 (periodic user-mode task, 100 us period, priority 99)
RTH|-----lat min|-----lat avg|-----lat max|-overrun|----lat best|---lat
worst
RTD| 7.481| 10.336| 61.240| 0| 5.320|
87.833
RTD| 7.501| 10.159| 65.242| 0| 5.320|
87.833
---|------------|------------|------------|--------|-------------------------
RTS| 5.320| 9.203| 87.833| 0| 00:15:27/00:15:27
Regards,
David
[-- Attachment #2: frozen --]
[-- Type: text/plain, Size: 13173 bytes --]
I-pipe frozen back-tracing service on 2.6.20/ipipe-1.8-08
------------------------------------------------------------
******** WARNING ********
The following debugging options will increase the observed latencies:
o CONFIG_XENO_OPT_DEBUG
Freeze: 4268773560534 cycles, Trace Points: 128 (+10)
Calibrated minimum trace-point overhead: 0.247 us
+----- Hard IRQs ('|': locked)
|+---- <unused>
||+--- Xenomai
|||+-- IShield
||||+- Linux ('*': domain stalled, '+': current, '#': current+stalled)
||||| +---------- Delay flag ('+': > 1 us, '!': > 10 us)
||||| | +- NMI noise ('N')
||||| | |
Type User Val. Time Delay Function (Parent)
: +func -138 0.681 __tcp_select_window+0xe (tcp_transmit_skb+0x19b)
: +func -137 0.523 tcp_v4_send_check+0x14 (tcp_transmit_skb+0x45a)
: +func -137 0.301 ip_queue_xmit+0xe (tcp_transmit_skb+0x3b0)
: +func -137 0.698 __sk_dst_check+0x11 (ip_queue_xmit+0x29e)
: +func -136 0.539 ip_output+0xe (ip_queue_xmit+0x1ac)
: +func -135 0.325 dev_queue_xmit+0xe (ip_output+0x10b)
: +func -135 0.284 local_bh_disable+0x8 (dev_queue_xmit+0x43)
: +func -135 0.382 ipipe_check_context+0xc (dev_queue_xmit+0x5d)
: +func -134 0.374 pfifo_fast_enqueue+0xa (dev_queue_xmit+0x71)
: +func -134 0.293 __qdisc_run+0xe (dev_queue_xmit+0x1df)
: +func -134 0.346 pfifo_fast_dequeue+0x9 (__qdisc_run+0x99)
: +func -133 0.342 ipipe_check_context+0xc (__qdisc_run+0x10a)
: +func -133 0.263 ipipe_check_context+0xc (__qdisc_run+0x54)
: +func -133 0.265 dev_hard_start_xmit+0xe (__qdisc_run+0x64)
: +func -132 0.326 ipipe_check_context+0xc (dev_hard_start_xmit+0x4f)
: +func -132 0.382 skb_clone+0xe (dev_hard_start_xmit+0xa9)
: +func -132 0.267 kmem_cache_alloc+0x14 (skb_clone+0x3c)
: +func -131 0.290 ipipe_check_context+0xc (kmem_cache_alloc+0x27)
: #func -131 0.284 __ipipe_restore_root+0x8 (kmem_cache_alloc+0x68)
: #func -131 0.379 __ipipe_unstall_root+0x8 (__ipipe_restore_root+0x1b)
:| #begin 0x80000000 -131 0.331 __ipipe_unstall_root+0x4b (__ipipe_restore_root+0x1b)
:| +end 0x80000000 -130 0.612 __ipipe_unstall_root+0x3a (__ipipe_restore_root+0x1b)
: +func -130 0.295 packet_rcv_spkt+0x14 (dev_hard_start_xmit+0xfe)
: +func -129 0.468 strlcpy+0x14 (packet_rcv_spkt+0x8e)
: +func -129 0.265 sock_queue_rcv_skb+0x14 (packet_rcv_spkt+0xa0)
: +func -129 0.285 local_bh_disable+0x8 (sock_queue_rcv_skb+0x45)
: +func -128 0.595 sk_run_filter+0x14 (sock_queue_rcv_skb+0x5c)
: +func -128 0.370 local_bh_enable+0xb (sock_queue_rcv_skb+0xd5)
: +func -127 0.296 ipipe_check_context+0xc (local_bh_enable+0x49)
: +func -127 0.260 kfree_skb+0x8 (packet_rcv_spkt+0xab)
: +func -127 0.301 __kfree_skb+0x11 (kfree_skb+0x1e)
: +func -126 0.459 kfree_skbmem+0x9 (__kfree_skb+0x47)
: +func -126 0.330 skb_release_data+0xa (kfree_skbmem+0x10)
: +func -126 0.260 kmem_cache_free+0xe (kfree_skbmem+0x3d)
: +func -125 0.278 ipipe_check_context+0xc (kmem_cache_free+0x40)
: #func -125 0.356 __ipipe_restore_root+0x8 (kmem_cache_free+0x84)
: #func -125 0.308 __ipipe_unstall_root+0x8 (__ipipe_restore_root+0x1b)
:| #begin 0x80000000 -124 0.310 __ipipe_unstall_root+0x4b (__ipipe_restore_root+0x1b)
:| +end 0x80000000 -124 0.441 __ipipe_unstall_root+0x3a (__ipipe_restore_root+0x1b)
: +func -124 0.387 ipipe_check_context+0xc (dev_hard_start_xmit+0x10d)
: +func -123 0.348 boomerang_start_xmit+0xe (dev_hard_start_xmit+0x1cb)
: +func -123 0.301 ipipe_check_context+0xc (boomerang_start_xmit+0x123)
: #func -123 0.303 ipipe_check_context+0xc (boomerang_start_xmit+0x163)
: #func -122 0.349 issue_and_wait+0xe (boomerang_start_xmit+0x170)
: #func -122 0.349 iowrite16+0x8 (issue_and_wait+0x2a)
: #func -122! 12.419 ioread16+0x8 (issue_and_wait+0x45)
: #func -109+ 1.352 ioread32+0x8 (boomerang_start_xmit+0x188)
: #func -108 0.418 iowrite16+0x8 (boomerang_start_xmit+0x1c9)
: #func -107 0.336 __ipipe_restore_root+0x8 (boomerang_start_xmit+0x1d0)
: #func -107 0.316 __ipipe_unstall_root+0x8 (__ipipe_restore_root+0x1b)
:| #begin 0x80000000 -107 0.310 __ipipe_unstall_root+0x4b (__ipipe_restore_root+0x1b)
:| +end 0x80000000 -106 0.464 __ipipe_unstall_root+0x3a (__ipipe_restore_root+0x1b)
: +func -106 0.439 ipipe_check_context+0xc (boomerang_start_xmit+0x1da)
: +func -106 0.267 ipipe_check_context+0xc (__qdisc_run+0x134)
: +func -105 0.296 ipipe_check_context+0xc (__qdisc_run+0x7a)
: +func -105 0.484 pfifo_fast_dequeue+0x9 (__qdisc_run+0x99)
: +func -105 0.265 ipipe_check_context+0xc (dev_queue_xmit+0x93)
: +func -104 0.275 local_bh_enable+0xb (dev_queue_xmit+0xa1)
: +func -104 0.357 ipipe_check_context+0xc (local_bh_enable+0x49)
: +func -104 0.408 update_send_head+0xa (tcp_push_one+0xca)
: +func -103 0.374 tcp_cwnd_validate+0x8 (tcp_push_one+0xd4)
: +func -103 0.310 __alloc_skb+0xe (tcp_sendmsg+0x36c)
: +func -103 0.267 kmem_cache_alloc+0x14 (__alloc_skb+0x30)
: +func -102 0.349 ipipe_check_context+0xc (kmem_cache_alloc+0x8a)
: +func -102 0.267 cond_resched+0x8 (kmem_cache_alloc+0x8f)
: +func -102 0.286 ipipe_check_context+0xc (kmem_cache_alloc+0x27)
: #func -101 0.284 __ipipe_restore_root+0x8 (kmem_cache_alloc+0x68)
: #func -101 0.372 __ipipe_unstall_root+0x8 (__ipipe_restore_root+0x1b)
:| #begin 0x80000000 -101 0.310 __ipipe_unstall_root+0x4b (__ipipe_restore_root+0x1b)
:| +end 0x80000000 -100 0.344 __ipipe_unstall_root+0x3a (__ipipe_restore_root+0x1b)
: +func -100 0.331 __kmalloc+0xe (__alloc_skb+0x4d)
: +func -100 0.363 ipipe_check_context+0xc (__kmalloc+0xb2)
: +func -99 0.269 cond_resched+0x8 (__kmalloc+0xb7)
: +func -99 0.280 ipipe_check_context+0xc (__kmalloc+0x4e)
: #func -99 0.286 __ipipe_restore_root+0x8 (__kmalloc+0x8a)
: #func -99 0.377 __ipipe_unstall_root+0x8 (__ipipe_restore_root+0x1b)
:| #begin 0x80000000 -98 0.374 __ipipe_unstall_root+0x4b (__ipipe_restore_root+0x1b)
:| +end 0x80000000 -98+ 1.428 __ipipe_unstall_root+0x3a (__ipipe_restore_root+0x1b)
:| +begin 0xffffff16 -96 0.349 ipipe_ipi3+0x2e (__alloc_skb+0xdd)
:| +func -96 0.396 __ipipe_handle_irq+0x14 (ipipe_ipi3+0x33)
:| +func -96 0.312 __ipipe_ack_apic+0x8 (__ipipe_handle_irq+0xaf)
:| +func -95 0.454 __ipipe_dispatch_wired+0x16 (__ipipe_handle_irq+0x68)
:| # func -95 0.329 xnintr_clock_handler+0x8 (__ipipe_dispatch_wired+0x9f)
:| # func -95 0.400 xnintr_irq_handler+0xe (xnintr_clock_handler+0x17)
:| # func -94 0.312 xnpod_announce_tick+0x8 (xnintr_irq_handler+0x3b)
:| # func -94 0.497 xntimer_do_tick_aperiodic+0xe (xnpod_announce_tick+0xf)
:| # func -93 0.301 xnthread_periodic_handler+0x8 (xntimer_do_tick_aperiodic+0x217)
:| # func -93 0.375 xnpod_resume_thread+0xe (xnthread_periodic_handler+0x2c)
:| # [ 4196] samplin 99 -93 0.933 xnpod_resume_thread+0x56 (xnthread_periodic_handler+0x2c)
:| # func -92 0.327 xnpod_schedule+0xe (xnintr_irq_handler+0x135)
:| # [ 3457] konsole -1 -91+ 1.299 xnpod_schedule+0x90 (xnintr_irq_handler+0x135)
:| # func -90 0.639 __switch_to+0xe (xnpod_schedule+0x493)
:| # [ 4196] samplin 99 -89 0.642 xnpod_schedule+0x56b (xnpod_suspend_thread+0x18b)
:| # func -89 0.353 __ipipe_restore_pipeline_head+0x12 (xnpod_wait_thread_period+0x12b)
:| + end 0x80000000 -88+ 1.363 __ipipe_restore_pipeline_head+0x5c (xnpod_wait_thread_period+0x12b)
:| + begin 0xfffffffa -87 0.530 common_interrupt+0x29 (__ipipe_restore_pipeline_head+0x60)
:| + func -87 0.454 __ipipe_handle_irq+0x14 (common_interrupt+0x2e)
:| + func -86 0.263 __ipipe_ack_irq+0x8 (__ipipe_handle_irq+0x151)
:| + func -86 0.307 __ipipe_ack_level_irq+0x12 (__ipipe_ack_irq+0x19)
:| + func -86 0.352 mask_and_ack_8259A+0x14 (__ipipe_ack_level_irq+0x22)
:| + func -85! 30.267 __ipipe_spin_lock_irqsave+0x9 (mask_and_ack_8259A+0x29)
:| # func -55 0.385 __ipipe_spin_unlock_irqrestore+0x9 (mask_and_ack_8259A+0x73)
:| + func -54 0.349 __ipipe_walk_pipeline+0xe (__ipipe_handle_irq+0x81)
:| + end 0xfffffffa -54+ 2.204 common_interrupt+0x38 (__ipipe_restore_pipeline_head+0x60)
:| + begin 0xfffffff1 -52 0.331 common_interrupt+0x29 (__ipipe_restore_pipeline_head+0x60)
:| + func -52 0.804 __ipipe_handle_irq+0x14 (common_interrupt+0x2e)
:| + func -51 0.371 __ipipe_ack_irq+0x8 (__ipipe_handle_irq+0x151)
:| + func -50 0.321 __ipipe_ack_level_irq+0x12 (__ipipe_ack_irq+0x19)
:| + func -50 0.252 mask_and_ack_8259A+0x14 (__ipipe_ack_level_irq+0x22)
:| + func -50! 38.784 __ipipe_spin_lock_irqsave+0x9 (mask_and_ack_8259A+0x29)
:| # func -11 0.367 __ipipe_spin_unlock_irqrestore+0x9 (mask_and_ack_8259A+0x73)
:| + func -11 0.346 __ipipe_walk_pipeline+0xe (__ipipe_handle_irq+0x81)
:| + end 0xfffffff1 -10 0.715 common_interrupt+0x38 (__ipipe_restore_pipeline_head+0x60)
:| + begin 0x80000001 -10 0.351 __ipipe_dispatch_event+0x180 (__ipipe_syscall_root+0x44)
:| + end 0x80000001 -9+ 3.002 __ipipe_dispatch_event+0x154 (__ipipe_syscall_root+0x44)
: + func -6 0.349 __ipipe_syscall_root+0xa (system_call+0x29)
: + func -6 0.297 __ipipe_dispatch_event+0xe (__ipipe_syscall_root+0x44)
:| + begin 0x80000001 -6 0.383 __ipipe_dispatch_event+0x1a0 (__ipipe_syscall_root+0x44)
:| + end 0x80000001 -5 0.292 __ipipe_dispatch_event+0x18f (__ipipe_syscall_root+0x44)
: + func -5+ 1.207 hisyscall_event+0x14 (__ipipe_dispatch_event+0xb5)
: + func -4+ 1.024 xnshadow_sys_trace+0x16 (hisyscall_event+0x189)
: + func -3 0.569 ipipe_trace_frozen_reset+0x9 (xnshadow_sys_trace+0xd7)
: + func -2 0.259 __ipipe_global_path_lock+0x8 (ipipe_trace_frozen_reset+0x13)
: + func -2 0.355 __ipipe_spin_lock_irqsave+0x9 (__ipipe_global_path_lock+0x12)
:| + begin 0x80000001 -2+ 1.393 __ipipe_spin_lock_irqsave+0x3d (__ipipe_global_path_lock+0x12)
:| # func 0 0.297 __ipipe_spin_unlock_irqcomplete+0x9 (__ipipe_global_path_unlock+0x63)
:| + end 0x80000001 0 0.360 __ipipe_spin_unlock_irqcomplete+0x2e (__ipipe_global_path_unlock+0x63)
< + freeze 0x00015719 0 0.605 xnshadow_sys_trace+0xa0 (hisyscall_event+0x189)
| + begin 0x80000001 0 0.316 __ipipe_dispatch_event+0x180 (__ipipe_syscall_root+0x44)
| + end 0x80000001 0 0.989 __ipipe_dispatch_event+0x154 (__ipipe_syscall_root+0x44)
+ func 1 0.310 __ipipe_syscall_root+0xa (system_call+0x29)
+ func 2 0.571 __ipipe_dispatch_event+0xe (__ipipe_syscall_root+0x44)
| + begin 0xffffff16 2 0.289 ipipe_ipi3+0x2e (__ipipe_dispatch_event+0x15)
| + func 3 0.312 __ipipe_handle_irq+0x14 (ipipe_ipi3+0x33)
| + func 3 0.319 __ipipe_ack_apic+0x8 (__ipipe_handle_irq+0xaf)
| + func 3 0.367 __ipipe_dispatch_wired+0x16 (__ipipe_handle_irq+0x68)
| # func 4 0.289 xnintr_clock_handler+0x8 (__ipipe_dispatch_wired+0x9f)
| # func 4 0.000 xnintr_irq_handler+0xe (xnintr_clock_handler+0x17)
[-- Attachment #3: interrupts --]
[-- Type: text/plain, Size: 536 bytes --]
CPU0
0: 6338539 XT-PIC-XT timer, rthal_broadcast_timer
1: 16 XT-PIC-XT i8042
2: 0 XT-PIC-XT cascade
5: 788889 XT-PIC-XT eth0
8: 1 XT-PIC-XT rtc
9: 2 XT-PIC-XT acpi
11: 0 XT-PIC-XT uhci_hcd:usb1
12: 131 XT-PIC-XT i8042
14: 36800 XT-PIC-XT ide0
15: 55176 XT-PIC-XT ide1
NMI: 10227
LOC: 6338432
ERR: 0
MIS: 0
[-- Attachment #4: dmesg.txt --]
[-- Type: text/plain, Size: 10628 bytes --]
Linux version 2.6.20 (root@domain.hid) (gcc version 4.1.1 20060724 (prerelease) (4.1.1-3mdk)) #6 Mon Oct 8 12:35:41 CEST 2007
BIOS-provided physical RAM map:
sanitize start
sanitize end
copy_e820_map() start: 0000000000000000 size: 000000000009f800 end: 000000000009f800 type: 1
copy_e820_map() type is E820_RAM
copy_e820_map() start: 000000000009f800 size: 0000000000000800 end: 00000000000a0000 type: 2
copy_e820_map() start: 00000000000e5c00 size: 000000000001a400 end: 0000000000100000 type: 2
copy_e820_map() start: 0000000000100000 size: 000000000fdf0000 end: 000000000fef0000 type: 1
copy_e820_map() type is E820_RAM
copy_e820_map() start: 000000000fef0000 size: 000000000000fc00 end: 000000000feffc00 type: 3
copy_e820_map() start: 000000000feffc00 size: 0000000000000400 end: 000000000ff00000 type: 4
copy_e820_map() start: 000000000ff00000 size: 0000000000100000 end: 0000000010000000 type: 2
copy_e820_map() start: 00000000fff00000 size: 0000000000100000 end: 0000000100000000 type: 2
BIOS-e820: 0000000000000000 - 000000000009f800 (usable)
BIOS-e820: 000000000009f800 - 00000000000a0000 (reserved)
BIOS-e820: 00000000000e5c00 - 0000000000100000 (reserved)
BIOS-e820: 0000000000100000 - 000000000fef0000 (usable)
BIOS-e820: 000000000fef0000 - 000000000feffc00 (ACPI data)
BIOS-e820: 000000000feffc00 - 000000000ff00000 (ACPI NVS)
BIOS-e820: 000000000ff00000 - 0000000010000000 (reserved)
BIOS-e820: 00000000fff00000 - 0000000100000000 (reserved)
254MB LOWMEM available.
Entering add_active_range(0, 0, 65264) 0 entries of 256 used
Zone PFN ranges:
DMA 0 -> 4096
Normal 4096 -> 65264
early_node_map[1] active PFN ranges
0: 0 -> 65264
On node 0 totalpages: 65264
DMA zone: 32 pages used for memmap
DMA zone: 0 pages reserved
DMA zone: 4064 pages, LIFO batch:0
Normal zone: 477 pages used for memmap
Normal zone: 60691 pages, LIFO batch:15
DMI 2.2 present.
ACPI: RSDP (v000 PTLTD ) @ 0x000f7380
ACPI: RSDT (v001 PTLTD RSDT 0x06040000 LTP 0x00000000) @ 0x0fefcece
ACPI: FADT (v001 HP HPBDD_IP 0x06040000 PTL 0x000f4240) @ 0x0feffb8c
ACPI: DSDT (v001 INTEL Whitney 0x06040000 MSFT 0x0100000b) @ 0x00000000
ACPI: PM-Timer IO Port: 0x1008
Allocating PCI resources starting at 20000000 (gap: 10000000:eff00000)
Detected 731.008 MHz processor.
Built 1 zonelists. Total pages: 64755
Kernel command line: auto BOOT_IMAGE=2.6.20 root=305 lapic resume=/dev/hda1 idle=poll
using polling idle threads.
Local APIC disabled by BIOS -- reenabling.
Found and enabled local APIC!
mapped APIC to ffffd000 (fee00000)
Enabling fast FPU save and restore... done.
Enabling unmasked SIMD FPU exception support... done.
Initializing CPU#0
PID hash table entries: 1024 (order: 10, 4096 bytes)
I-pipe 1.8-08: pipeline enabled.
Console: colour VGA+ 80x25
Dentry cache hash table entries: 32768 (order: 5, 131072 bytes)
Inode-cache hash table entries: 16384 (order: 4, 65536 bytes)
Memory: 253396k/261056k available (2006k kernel code, 7168k reserved, 2228k data, 204k init, 0k highmem)
virtual kernel memory layout:
fixmap : 0xfffb7000 - 0xfffff000 ( 288 kB)
vmalloc : 0xd0800000 - 0xfffb5000 ( 759 MB)
lowmem : 0xc0000000 - 0xcfef0000 ( 254 MB)
.init : 0xc0526000 - 0xc0559000 ( 204 kB)
.data : 0xc02f5aaf - 0xc0522b2c (2228 kB)
.text : 0xc0100000 - 0xc02f5aaf (2006 kB)
Checking if this processor honours the WP bit even in supervisor mode... Ok.
Calibrating delay using timer specific routine.. 1462.43 BogoMIPS (lpj=731218)
Mount-cache hash table entries: 512
CPU: After generic identify, caps: 0383fbff 00000000 00000000 00000000 00000000 00000000 00000000
CPU: L1 I cache: 16K, L1 D cache: 16K
CPU: L2 cache: 256K
CPU: After all inits, caps: 0383fbff 00000000 00000000 00000040 00000000 00000000 00000000
Intel machine check architecture supported.
Intel machine check reporting enabled on CPU#0.
Compat vDSO mapped to ffffe000.
CPU: Intel Pentium III (Coppermine) stepping 06
Checking 'hlt' instruction... OK.
ACPI: Core revision 20060707
ACPI: setting ELCR to 0200 (from 0e20)
NET: Registered protocol family 16
ACPI: bus type pci registered
PCI: PCI BIOS revision 2.10 entry at 0xfd9ae, last bus=1
PCI: Using configuration type 1
Setting up standard PCI resources
ACPI: Interpreter enabled
ACPI: Using PIC for interrupt routing
ACPI: PCI Root Bridge [PCI0] (0000:00)
PCI: Probing PCI hardware (bus 00)
Boot video device is 0000:00:02.0
PCI quirk: region 1000-107f claimed by ICH4 ACPI/GPIO/TCO
PCI quirk: region 1180-11bf claimed by ICH4 GPIO
PCI: Transparent bridge - 0000:00:1e.0
ACPI: PCI Interrupt Routing Table [\_SB_.PCI0._PRT]
ACPI: PCI Interrupt Link [LNKA] (IRQs 3 4 5 7 9 *10 11 12 14 15)
ACPI: PCI Interrupt Link [LNKB] (IRQs 3 4 5 7 *9 10 11 12 14 15)
ACPI: PCI Interrupt Link [LNKC] (IRQs 3 4 *5 7 9 10 11 12 14 15)
ACPI: PCI Interrupt Link [LNKD] (IRQs 3 4 5 7 9 10 *11 12 14 15)
ACPI: PCI Interrupt Routing Table [\_SB_.PCI0.HUB_._PRT]
Linux Plug and Play Support v0.97 (c) Adam Belay
usbcore: registered new interface driver usbfs
usbcore: registered new interface driver hub
usbcore: registered new device driver usb
PCI: Using ACPI for IRQ routing
PCI: If a device doesn't work, try "pci=routeirq". If it helps, post a report
pnp: the driver 'system' has been registered
PCI: Ignore bogus resource 6 [0:0] of 0000:00:02.0
PCI: Bridge: 0000:00:1e.0
IO window: 2000-2fff
MEM window: ec100000-ec1fffff
PREFETCH window: 20000000-200fffff
PCI: Setting latency timer of device 0000:00:1e.0 to 64
NET: Registered protocol family 2
IP route cache hash table entries: 2048 (order: 1, 8192 bytes)
TCP established hash table entries: 8192 (order: 3, 32768 bytes)
TCP bind hash table entries: 4096 (order: 2, 16384 bytes)
TCP: Hash tables configured (established 8192 bind 4096)
TCP reno registered
checking if image is initramfs... it is
Freeing initrd memory: 120k freed
audit: initializing netlink socket (disabled)
audit(1191839887.687:1): initialized
audit: cannot initialize inotify handle
I-pipe: Domain Xenomai registered.
Xenomai: hal/x86 started.
I-pipe: Domain IShield registered.
Xenomai: real-time nucleus v2.3.3 (Summer Song) loaded.
Xenomai: SMI-enabled chipset found, enabling SMI workaround.
Xenomai: starting native API services.
Xenomai: starting RTDM services.
Total HugeTLB memory allocated, 0
fuse init (API version 7.8)
io scheduler noop registered
io scheduler anticipatory registered (default)
io scheduler deadline registered
io scheduler cfq registered
input: Power Button (FF) as /class/input/input0
ACPI: Power Button (FF) [PWRF]
input: Power Button (CM) as /class/input/input1
ACPI: Power Button (CM) [PWRB]
isapnp: Scanning for PnP cards...
isapnp: No Plug & Play device found
Real Time Clock Driver v1.12ac
Linux agpgart interface v0.101 (c) Dave Jones
Serial: 8250/16550 driver $Revision: 1.90 $ 4 ports, IRQ sharing enabled
serial8250: ttyS0 at I/O 0x3f8 (irq = 4) is a 16550A
serial8250: ttyS1 at I/O 0x2f8 (irq = 3) is a 16550A
pnp: the driver 'serial' has been registered
RAMDISK driver initialized: 16 RAM disks of 32000K size 1024 blocksize
ACPI: PCI Interrupt Link [LNKC] enabled at IRQ 5
PCI: setting IRQ 5 as level-triggered
ACPI: PCI Interrupt 0000:01:04.0[A] -> Link [LNKC] -> GSI 5 (level, low) -> IRQ 5
3c59x: Donald Becker and others. www.scyld.com/network/vortex.html
0000:01:04.0: 3Com PCI 3c905C Tornado at d0806400.
Uniform Multi-Platform E-IDE driver Revision: 7.00alpha2
ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx
ICH: IDE controller at PCI slot 0000:00:1f.1
ICH: chipset revision 2
ICH: not 100% native mode: will probe irqs later
ide0: BM-DMA at 0x1800-0x1807, BIOS settings: hda:pio, hdb:DMA
ide1: BM-DMA at 0x1808-0x180f, BIOS settings: hdc:DMA, hdd:pio
Probing IDE interface ide0...
hda: Maxtor 31024H1, ATA DISK drive
hdb: ST310211A, ATA DISK drive
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
Probing IDE interface ide1...
hdc: CD-540E, ATAPI CD/DVD-ROM drive
ide1 at 0x170-0x177,0x376 on irq 15
hda: max request size: 128KiB
hda: 19746720 sectors (10110 MB) w/2048KiB Cache, CHS=19590/16/63, UDMA(66)
hda: cache flushes not supported
hda: hda1 hda2 < hda5 >
hdb: max request size: 128KiB
hdb: 19541088 sectors (10005 MB) w/512KiB Cache, CHS=19386/16/63, UDMA(66)
hdb: cache flushes not supported
hdb: hdb1 hdb2 < hdb5 hdb6 hdb7 >
hdc: ATAPI 40X CD-ROM drive, 128kB Cache, UDMA(33)
Uniform CD-ROM driver Revision: 3.20
USB Universal Host Controller Interface driver v3.0
PCI: Enabling device 0000:00:1f.2 (0000 -> 0001)
ACPI: PCI Interrupt Link [LNKD] enabled at IRQ 11
PCI: setting IRQ 11 as level-triggered
ACPI: PCI Interrupt 0000:00:1f.2[D] -> Link [LNKD] -> GSI 11 (level, low) -> IRQ 11
PCI: Setting latency timer of device 0000:00:1f.2 to 64
uhci_hcd 0000:00:1f.2: UHCI Host Controller
uhci_hcd 0000:00:1f.2: new USB bus registered, assigned bus number 1
uhci_hcd 0000:00:1f.2: irq 11, io base 0x00001820
usb usb1: configuration #1 chosen from 1 choice
hub 1-0:1.0: USB hub found
hub 1-0:1.0: 2 ports detected
usbcore: registered new interface driver usbhid
drivers/usb/input/hid-core.c: v2.6:USB HID core driver
pnp: the driver 'i8042 kbd' has been registered
pnp: the driver 'i8042 aux' has been registered
pnp: the driver 'i8042 kbd' has been unregistered
pnp: the driver 'i8042 aux' has been unregistered
PNP: No PS/2 controller found. Probing ports directly.
serio: i8042 KBD port at 0x60,0x64 irq 1
serio: i8042 AUX port at 0x60,0x64 irq 12
mice: PS/2 mouse device common for all mice
pnp: the driver 'irqbench' has been registered
TCP cubic registered
NET: Registered protocol family 1
NET: Registered protocol family 17
Testing NMI watchdog ... OK.
Using IPI Shortcut mode
Time: tsc clocksource has been installed.
ACPI: (supports S0 S1 S4 S5)
BIOS EDD facility v0.16 2004-Jun-25, 2 devices found
Freeing unused kernel memory: 204k freed
kjournald starting. Commit interval 5 seconds
EXT3-fs: mounted filesystem with ordered data mode.
input: ImPS/2 Logitech Wheel Mouse as /class/input/input2
input: AT Translated Set 2 keyboard as /class/input/input3
agpgart: Detected an Intel i815 Chipset.
agpgart: AGP aperture is 64M @ 0xf0000000
EXT3 FS on hda5, internal journal
Adding 273064k swap on /dev/hda1. Priority:-1 extents:1 across:273064k
kjournald starting. Commit interval 5 seconds
EXT3 FS on hdb1, internal journal
EXT3-fs: mounted filesystem with ordered data mode.
kjournald starting. Commit interval 5 seconds
EXT3 FS on hdb5, internal journal
EXT3-fs: mounted filesystem with ordered data mode.
eth0: setting half-duplex.
eth0: setting full-duplex.
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-08 12:46 ` CHABAL David
@ 2007-10-10 11:30 ` Philippe Gerum
2007-10-12 14:05 ` CHABAL David
0 siblings, 1 reply; 30+ messages in thread
From: Philippe Gerum @ 2007-10-10 11:30 UTC (permalink / raw)
To: CHABAL David; +Cc: xenomai
On Mon, 2007-10-08 at 14:46 +0200, CHABAL David wrote:
> :| #begin 0x80000000 -98 0.374 __ipipe_unstall_root+0x4b
> (__ipipe_restore_root+0x1b)
> :| +end 0x80000000 -98+ 1.428 __ipipe_unstall_root+0x3a
> (__ipipe_restore_root+0x1b)
> :| +begin 0xffffff16 -96 0.349 ipipe_ipi3+0x2e (__alloc_skb
> +0xdd)
That's your timer interrupt when the LAPIC is enabled.
> :| +func -96 0.396 __ipipe_handle_irq+0x14
> (ipipe_ipi3+0x33)
> :| +func -96 0.312 __ipipe_ack_apic+0x8
> (__ipipe_handle_irq+0xaf)
> :| +func -95 0.454 __ipipe_dispatch_wired+0x16
> (__ipipe_handle_irq+0x68)
> :| # func -95 0.329 xnintr_clock_handler+0x8
> (__ipipe_dispatch_wired+0x9f)
> :| # func -95 0.400 xnintr_irq_handler+0xe
> (xnintr_clock_handler+0x17)
> :| # func -94 0.312 xnpod_announce_tick+0x8
> (xnintr_irq_handler+0x3b)
> :| # func -94 0.497 xntimer_do_tick_aperiodic+0xe
> (xnpod_announce_tick+0xf)
> :| # func -93 0.301 xnthread_periodic_handler+0x8
> (xntimer_do_tick_aperiodic+0x217)
> :| # func -93 0.375 xnpod_resume_thread+0xe
> (xnthread_periodic_handler+0x2c)
> :| # [ 4196] samplin 99 -93 0.933 xnpod_resume_thread+0x56
> (xnthread_periodic_handler+0x2c)
> :| # func -92 0.327 xnpod_schedule+0xe
> (xnintr_irq_handler+0x135)
> :| # [ 3457] konsole -1 -91+ 1.299 xnpod_schedule+0x90
> (xnintr_irq_handler+0x135)
> :| # func -90 0.639 __switch_to+0xe
> (xnpod_schedule+0x493)
> :| # [ 4196] samplin 99 -89 0.642 xnpod_schedule+0x56b
> (xnpod_suspend_thread+0x18b)
> :| # func -89 0.353 __ipipe_restore_pipeline_head
> +0x12 (xnpod_wait_thread_period+0x12b)
> :| + end 0x80000000 -88+ 1.363 __ipipe_restore_pipeline_head
> +0x5c (xnpod_wait_thread_period+0x12b)
> :| + begin 0xfffffffa -87 0.530 common_interrupt+0x29
> (__ipipe_restore_pipeline_head+0x60)
Then a NIC interrupt is caught before the just awaken task gets back to
user-space.
> :| + func -87 0.454 __ipipe_handle_irq+0x14
> (common_interrupt+0x2e)
> :| + func -86 0.263 __ipipe_ack_irq+0x8
> (__ipipe_handle_irq+0x151)
> :| + func -86 0.307 __ipipe_ack_level_irq+0x12
> (__ipipe_ack_irq+0x19)
> :| + func -86 0.352 mask_and_ack_8259A+0x14
> (__ipipe_ack_level_irq+0x22)
> :| + func -85! 30.267 __ipipe_spin_lock_irqsave+0x9
> (mask_and_ack_8259A+0x29)
I suspect the tracer to induce massive cache misses on your setup, which
limits the interpretation we can have of this log. Could you apply the
following patch, and post back the frozen log for the very same test?
TIA,
--- 2.6.20-ipipe-1.8-08/kernel/ipipe/core.c~ 2007-09-16 16:54:34.000000000 +0200
+++ 2.6.20-ipipe-1.8-08/kernel/ipipe/core.c 2007-10-10 13:05:28.000000000 +0200
@@ -283,7 +283,7 @@
unsigned long flags;
int s;
- local_irq_save_hw(flags);
+ local_irq_save_hw_notrace(flags);
__raw_spin_lock(lock);
ipipe_load_cpuid();
ipd = per_cpu(ipipe_percpu_domain, cpuid);
@@ -302,7 +302,7 @@
ipd = per_cpu(ipipe_percpu_domain, cpuid);
if (!raw_demangle_irq_bits(&x))
__clear_bit(IPIPE_STALL_FLAG, &ipd->cpudata[cpuid].status);
- local_irq_restore_hw(x);
+ local_irq_restore_hw_notrace(x);
}
/*
> :| # func -55 0.385
> __ipipe_spin_unlock_irqrestore+0x9 (mask_and_ack_8259A+0x73)
> :| + func -54 0.349 __ipipe_walk_pipeline+0xe
> (__ipipe_handle_irq+0x81)
> :| + end 0xfffffffa -54+ 2.204 common_interrupt+0x38
> (__ipipe_restore_pipeline_head+0x60)
Another NIC interrupt, still not running the task...
> :| + begin 0xfffffff1 -52 0.331 common_interrupt+0x29
> (__ipipe_restore_pipeline_head+0x60)
> :| + func -52 0.804 __ipipe_handle_irq+0x14
> (common_interrupt+0x2e)
> :| + func -51 0.371 __ipipe_ack_irq+0x8
> (__ipipe_handle_irq+0x151)
> :| + func -50 0.321 __ipipe_ack_level_irq+0x12
> (__ipipe_ack_irq+0x19)
> :| + func -50 0.252 mask_and_ack_8259A+0x14
> (__ipipe_ack_level_irq+0x22)
> :| + func -50! 38.784 __ipipe_spin_lock_irqsave+0x9
> (mask_and_ack_8259A+0x29)
> :| # func -11 0.367
> __ipipe_spin_unlock_irqrestore+0x9 (mask_and_ack_8259A+0x73)
> :| + func -11 0.346 __ipipe_walk_pipeline+0xe
> (__ipipe_handle_irq+0x81)
> :| + end 0xfffffff1 -10 0.715 common_interrupt+0x38
> (__ipipe_restore_pipeline_head+0x60)
Then an IDE interrupt.
> :| + begin 0x80000001 -10 0.351 __ipipe_dispatch_event+0x180
> (__ipipe_syscall_root+0x44)
> :| + end 0x80000001 -9+ 3.002 __ipipe_dispatch_event+0x154
> (__ipipe_syscall_root+0x44)
Your task is back, way too late obviously. Still, the additional
interrupts do not cause the massive jitter, even if they increase the
worst-case. The next frozen log may tell us more.
--
Philippe.
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-10 11:30 ` Philippe Gerum
@ 2007-10-12 14:05 ` CHABAL David
2007-10-12 14:21 ` Jan Kiszka
0 siblings, 1 reply; 30+ messages in thread
From: CHABAL David @ 2007-10-12 14:05 UTC (permalink / raw)
To: rpm; +Cc: xenomai
[-- Attachment #1: Type: text/plain, Size: 1370 bytes --]
Philippe Gerum a écrit :
>
> I suspect the tracer to induce massive cache misses on your setup, which
> limits the interpretation we can have of this log. Could you apply the
> following patch, and post back the frozen log for the very same test?
> TIA,
>
> --- 2.6.20-ipipe-1.8-08/kernel/ipipe/core.c~ 2007-09-16 16:54:34.000000000 +0200
> +++ 2.6.20-ipipe-1.8-08/kernel/ipipe/core.c 2007-10-10 13:05:28.000000000 +0200
> @@ -283,7 +283,7 @@
> unsigned long flags;
> int s;
>
> - local_irq_save_hw(flags);
> + local_irq_save_hw_notrace(flags);
> __raw_spin_lock(lock);
> ipipe_load_cpuid();
> ipd = per_cpu(ipipe_percpu_domain, cpuid);
> @@ -302,7 +302,7 @@
> ipd = per_cpu(ipipe_percpu_domain, cpuid);
> if (!raw_demangle_irq_bits(&x))
> __clear_bit(IPIPE_STALL_FLAG, &ipd->cpudata[cpuid].status);
> - local_irq_restore_hw(x);
> + local_irq_restore_hw_notrace(x);
> }
>
> /*
>
The freeze file enclosed is generated with this patch and the i8259.c patch.
---|------------|------------|------------|--------|-------------------------
RTS| 5.570| 9.400| 85.356| 0| 00:08:55/00:08:55
Should I try without the I-pipe debugger ?
Thank you for your help,
David
PS: I don't know if it's relevant but sometimes I get "eth0: Too much
work in interrupt, status 8401." in my logs.
[-- Attachment #2: freeze.txt --]
[-- Type: text/plain, Size: 13150 bytes --]
I-pipe frozen back-tracing service on 2.6.20/ipipe-1.8-08
------------------------------------------------------------
******** WARNING ********
The following debugging options will increase the observed latencies:
o CONFIG_XENO_OPT_DEBUG
Freeze: 976382813724 cycles, Trace Points: 128 (+10)
Calibrated minimum trace-point overhead: 0.248 us
+----- Hard IRQs ('|': locked)
|+---- <unused>
||+--- Xenomai
|||+-- IShield
||||+- Linux ('*': domain stalled, '+': current, '#': current+stalled)
||||| +---------- Delay flag ('+': > 1 us, '!': > 10 us)
||||| | +- NMI noise ('N')
||||| | |
Type User Val. Time Delay Function (Parent)
: +func -132 0.274 ipipe_check_context+0xc (boomerang_start_xmit+0x123)
: #func -132 0.303 ipipe_check_context+0xc (boomerang_start_xmit+0x163)
: #func -132 0.299 issue_and_wait+0xe (boomerang_start_xmit+0x170)
: #func -132 0.348 iowrite16+0x8 (issue_and_wait+0x2a)
: #func -131+ 3.124 ioread16+0x8 (issue_and_wait+0x45)
: #func -128+ 7.336 ioread32+0x8 (boomerang_start_xmit+0x188)
: #func -121 0.355 iowrite16+0x8 (boomerang_start_xmit+0x1c9)
: #func -120 0.336 __ipipe_restore_root+0x8 (boomerang_start_xmit+0x1d0)
: #func -120 0.316 __ipipe_unstall_root+0x8 (__ipipe_restore_root+0x1b)
:| #begin 0x80000000 -120 0.322 __ipipe_unstall_root+0x4b (__ipipe_restore_root+0x1b)
:| +end 0x80000000 -119 0.330 __ipipe_unstall_root+0x3a (__ipipe_restore_root+0x1b)
: +func -119 0.310 ipipe_check_context+0xc (boomerang_start_xmit+0x1da)
: +func -119 0.267 ipipe_check_context+0xc (__qdisc_run+0x134)
: +func -119 0.314 ipipe_check_context+0xc (__qdisc_run+0x7a)
: +func -118 0.311 pfifo_fast_dequeue+0x9 (__qdisc_run+0x99)
: +func -118 0.265 ipipe_check_context+0xc (dev_queue_xmit+0x93)
: +func -118 0.271 local_bh_enable+0xb (dev_queue_xmit+0xa1)
: +func -117 0.321 ipipe_check_context+0xc (local_bh_enable+0x49)
: +func -117 0.304 update_send_head+0xa (__tcp_push_pending_frames+0x122)
: +func -117 0.431 tcp_init_tso_segs+0x16 (__tcp_push_pending_frames+0x154)
: +func -116 0.599 tcp_set_skb_tso_segs+0x16 (tcp_init_tso_segs+0x46)
: +func -116 0.606 tcp_cwnd_validate+0x8 (__tcp_push_pending_frames+0x2d3)
: +func -115 0.685 tcp_check_space+0x9 (tcp_rcv_established+0x410)
: +func -114 0.310 cond_resched_softirq+0x8 (release_sock+0x69)
: +func -114 0.286 tcp_v4_do_rcv+0x14 (release_sock+0x64)
: +func -114 0.505 tcp_rcv_established+0x14 (tcp_v4_do_rcv+0xb3)
: +func -113 0.938 tcp_ack+0x11 (tcp_rcv_established+0x3e1)
: +func -112 0.262 __kfree_skb+0x11 (tcp_ack+0x46a)
: +func -112 0.259 kfree_skbmem+0x9 (__kfree_skb+0x47)
: +func -112 0.737 skb_release_data+0xa (kfree_skbmem+0x10)
: +func -111 0.260 __kfree_skb+0x11 (tcp_ack+0x46a)
: +func -111 0.250 kfree_skbmem+0x9 (__kfree_skb+0x47)
: +func -111 0.442 skb_release_data+0xa (kfree_skbmem+0x10)
: +func -110 0.282 tcp_ack_saw_tstamp+0x9 (tcp_ack+0x672)
: +func -110 0.480 tcp_rtt_estimator+0xa (tcp_ack_saw_tstamp+0x1c)
: +func -109 0.270 sk_reset_timer+0x9 (tcp_ack+0xd92)
: +func -109 0.307 mod_timer+0x8 (sk_reset_timer+0x14)
: +func -109 0.277 __mod_timer+0xe (mod_timer+0x19)
: +func -109 0.260 lock_timer_base+0x16 (__mod_timer+0x27)
: +func -108 0.285 ipipe_check_context+0xc (lock_timer_base+0x2b)
: #func -108 0.386 ipipe_check_context+0xc (lock_timer_base+0x4b)
: #func -108 0.331 internal_add_timer+0x12 (__mod_timer+0x88)
: #func -107 0.284 __ipipe_restore_root+0x8 (__mod_timer+0xb4)
: #func -107 0.327 __ipipe_unstall_root+0x8 (__ipipe_restore_root+0x1b)
:| #begin 0x80000000 -107 0.327 __ipipe_unstall_root+0x4b (__ipipe_restore_root+0x1b)
:| +end 0x80000000 -106 0.363 __ipipe_unstall_root+0x3a (__ipipe_restore_root+0x1b)
: +func -106 0.368 ipipe_check_context+0xc (__mod_timer+0xa2)
: +func -106 0.465 bictcp_acked+0x9 (tcp_ack+0x6ac)
: +func -105 0.296 tcp_cong_avoid+0x11 (tcp_ack+0xd48)
: +func -105 0.517 bictcp_cong_avoid+0xe (tcp_cong_avoid+0x2b)
: +func -104 0.300 __kfree_skb+0x11 (tcp_rcv_established+0x3e8)
: +func -104 0.259 kfree_skbmem+0x9 (__kfree_skb+0x47)
: +func -104 0.349 skb_release_data+0xa (kfree_skbmem+0x10)
: +func -103 0.262 kfree+0xb (skb_release_data+0x5d)
: +func -103 0.487 ipipe_check_context+0xc (kfree+0x1b)
: #func -103 0.352 __ipipe_restore_root+0x8 (kfree+0x73)
: #func -102 0.316 __ipipe_unstall_root+0x8 (__ipipe_restore_root+0x1b)
:| #begin 0x80000000 -102 0.322 __ipipe_unstall_root+0x4b (__ipipe_restore_root+0x1b)
:| +end 0x80000000 -102 0.400 __ipipe_unstall_root+0x3a (__ipipe_restore_root+0x1b)
: +func -101 0.273 kmem_cache_free+0xe (kfree_skbmem+0x3d)
: +func -101 0.275 ipipe_check_context+0xc (kmem_cache_free+0x40)
: #func -101 0.286 __ipipe_restore_root+0x8 (kmem_cache_free+0x84)
: #func -100 0.306 __ipipe_unstall_root+0x8 (__ipipe_restore_root+0x1b)
:| #begin 0x80000000 -100 0.382 __ipipe_unstall_root+0x4b (__ipipe_restore_root+0x1b)
:| +end 0x80000000 -100 0.374 __ipipe_unstall_root+0x3a (__ipipe_restore_root+0x1b)
: +func -99 0.404 tcp_current_mss+0x14 (tcp_rcv_established+0x3fb)
: +func -99 0.307 __tcp_push_pending_frames+0xe (tcp_rcv_established+0x409)
: +func -99 0.442 tcp_init_tso_segs+0x16 (__tcp_push_pending_frames+0x154)
: +func -98 0.285 tcp_transmit_skb+0xe (__tcp_push_pending_frames+0x10f)
: +func -98 0.769 skb_clone+0xe (tcp_transmit_skb+0x6d)
: +func -97 0.486 __tcp_select_window+0xe (tcp_transmit_skb+0x19b)
: +func -97 0.497 tcp_v4_send_check+0x14 (tcp_transmit_skb+0x45a)
: +func -96 0.297 ip_queue_xmit+0xe (tcp_transmit_skb+0x3b0)
: +func -96 0.586 __sk_dst_check+0x11 (ip_queue_xmit+0x29e)
: +func -95 0.490 ip_output+0xe (ip_queue_xmit+0x1ac)
: +func -95 0.355 dev_queue_xmit+0xe (ip_output+0x10b)
: +func -94 0.269 local_bh_disable+0x8 (dev_queue_xmit+0x43)
: +func -94 0.271 ipipe_check_context+0xc (dev_queue_xmit+0x5d)
: +func -94 0.579 pfifo_fast_enqueue+0xa (dev_queue_xmit+0x71)
:| +begin 0xffffff16 -93 0.327 ipipe_ipi3+0x2e (dev_queue_xmit+0x83)
:| +func -93 0.356 __ipipe_handle_irq+0x14 (ipipe_ipi3+0x33)
:| +func -93 0.312 __ipipe_ack_apic+0x8 (__ipipe_handle_irq+0xaf)
:| +func -92 0.333 __ipipe_dispatch_wired+0x16 (__ipipe_handle_irq+0x68)
:| # func -92 0.319 xnintr_clock_handler+0x8 (__ipipe_dispatch_wired+0x9f)
:| # func -92 0.374 xnintr_irq_handler+0xe (xnintr_clock_handler+0x17)
:| # func -91 0.314 xnpod_announce_tick+0x8 (xnintr_irq_handler+0x3b)
:| # func -91 0.484 xntimer_do_tick_aperiodic+0xe (xnpod_announce_tick+0xf)
:| # func -91 0.301 xnthread_periodic_handler+0x8 (xntimer_do_tick_aperiodic+0x217)
:| # func -90 0.314 xnpod_resume_thread+0xe (xnthread_periodic_handler+0x2c)
:| # [ 3945] samplin 99 -90+ 1.008 xnpod_resume_thread+0x56 (xnthread_periodic_handler+0x2c)
:| # func -89 0.330 xnpod_schedule+0xe (xnintr_irq_handler+0x135)
:| # [ 3596] konsole -1 -89+ 1.073 xnpod_schedule+0x90 (xnintr_irq_handler+0x135)
:| # func -87 0.621 __switch_to+0xe (xnpod_schedule+0x493)
:| # [ 3945] samplin 99 -87 0.743 xnpod_schedule+0x56b (xnpod_suspend_thread+0x18b)
:| # func -86 0.346 __ipipe_restore_pipeline_head+0x12 (xnpod_wait_thread_period+0x12b)
:| + end 0x80000000 -86+ 1.346 __ipipe_restore_pipeline_head+0x5c (xnpod_wait_thread_period+0x12b)
:| + begin 0xfffffffa -84 0.407 common_interrupt+0x29 (__ipipe_restore_pipeline_head+0x60)
:| + func -84 0.415 __ipipe_handle_irq+0x14 (common_interrupt+0x2e)
:| + func -84 0.306 __ipipe_ack_irq+0x8 (__ipipe_handle_irq+0x151)
:| + func -83 0.295 __ipipe_ack_level_irq+0x12 (__ipipe_ack_irq+0x19)
:| + func -83 0.278 mask_and_ack_8259A+0x14 (__ipipe_ack_level_irq+0x22)
:| + func -83! 31.046 __ipipe_spin_lock_irqsave+0x8 (mask_and_ack_8259A+0x29)
:| # func -52 0.400 __ipipe_spin_unlock_irqrestore+0x8 (mask_and_ack_8259A+0x73)
:| + func -51 0.355 __ipipe_walk_pipeline+0xe (__ipipe_handle_irq+0x81)
:| + end 0xfffffffa -51! 10.159 common_interrupt+0x38 (__ipipe_restore_pipeline_head+0x60)
:| + begin 0xfffffff0 -41 0.355 common_interrupt+0x29 (__ipipe_restore_pipeline_head+0x60)
:| + func -40 0.642 __ipipe_handle_irq+0x14 (common_interrupt+0x2e)
:| + func -40 0.394 __ipipe_ack_irq+0x8 (__ipipe_handle_irq+0x151)
:| + func -39 0.255 __ipipe_ack_level_irq+0x12 (__ipipe_ack_irq+0x19)
:| + func -39 0.247 mask_and_ack_8259A+0x14 (__ipipe_ack_level_irq+0x22)
:| + func -39! 28.454 __ipipe_spin_lock_irqsave+0x8 (mask_and_ack_8259A+0x29)
:| # func -10 0.351 __ipipe_spin_unlock_irqrestore+0x8 (mask_and_ack_8259A+0x73)
:| + func -10 0.292 __ipipe_walk_pipeline+0xe (__ipipe_handle_irq+0x81)
:| + end 0xfffffff0 -10 0.743 common_interrupt+0x38 (__ipipe_restore_pipeline_head+0x60)
:| + begin 0x80000001 -9 0.381 __ipipe_dispatch_event+0x180 (__ipipe_syscall_root+0x44)
:| + end 0x80000001 -9+ 3.306 __ipipe_dispatch_event+0x154 (__ipipe_syscall_root+0x44)
: + func -5 0.325 __ipipe_syscall_root+0xa (system_call+0x29)
: + func -5 0.326 __ipipe_dispatch_event+0xe (__ipipe_syscall_root+0x44)
:| + begin 0x80000001 -5 0.383 __ipipe_dispatch_event+0x1a0 (__ipipe_syscall_root+0x44)
:| + end 0x80000001 -4 0.321 __ipipe_dispatch_event+0x18f (__ipipe_syscall_root+0x44)
: + func -4+ 1.012 hisyscall_event+0x14 (__ipipe_dispatch_event+0xb5)
: + func -3+ 1.019 xnshadow_sys_trace+0x16 (hisyscall_event+0x189)
: + func -2 0.404 ipipe_trace_frozen_reset+0x9 (xnshadow_sys_trace+0xd7)
: + func -2 0.259 __ipipe_global_path_lock+0x8 (ipipe_trace_frozen_reset+0x13)
: + func -1+ 1.135 __ipipe_spin_lock_irqsave+0x8 (__ipipe_global_path_lock+0x12)
:| # func 0 0.289 __ipipe_spin_unlock_irqcomplete+0x9 (__ipipe_global_path_unlock+0x63)
:| + end 0x80000001 0 0.366 __ipipe_spin_unlock_irqcomplete+0x2e (__ipipe_global_path_unlock+0x63)
< + freeze 0x00014d6c 0 0.571 xnshadow_sys_trace+0xa0 (hisyscall_event+0x189)
| + begin 0x80000001 0 0.316 __ipipe_dispatch_event+0x180 (__ipipe_syscall_root+0x44)
| + end 0x80000001 0 0.826 __ipipe_dispatch_event+0x154 (__ipipe_syscall_root+0x44)
+ func 1 0.286 __ipipe_syscall_root+0xa (system_call+0x29)
+ func 2 0.297 __ipipe_dispatch_event+0xe (__ipipe_syscall_root+0x44)
| + begin 0x80000001 2 0.306 __ipipe_dispatch_event+0x1a0 (__ipipe_syscall_root+0x44)
| + end 0x80000001 2 0.318 __ipipe_dispatch_event+0x18f (__ipipe_syscall_root+0x44)
+ func 2 0.392 hisyscall_event+0x14 (__ipipe_dispatch_event+0xb5)
+ func 3 0.296 __rt_task_wait_period+0x11 (hisyscall_event+0x189)
+ func 3 0.326 rt_task_wait_period+0x8 (__rt_task_wait_period+0x21)
+ func 3 0.000 xnpod_wait_thread_period+0xe (rt_task_wait_period+0x38)
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-12 14:05 ` CHABAL David
@ 2007-10-12 14:21 ` Jan Kiszka
2007-10-12 14:26 ` CHABAL David
2007-10-12 15:34 ` Philippe Gerum
0 siblings, 2 replies; 30+ messages in thread
From: Jan Kiszka @ 2007-10-12 14:21 UTC (permalink / raw)
To: CHABAL David; +Cc: xenomai
CHABAL David wrote:
> Philippe Gerum a écrit :
>>
>> I suspect the tracer to induce massive cache misses on your setup, which
>> limits the interpretation we can have of this log. Could you apply the
>> following patch, and post back the frozen log for the very same test?
>> TIA,
>>
>> --- 2.6.20-ipipe-1.8-08/kernel/ipipe/core.c~ 2007-09-16
>> 16:54:34.000000000 +0200
>> +++ 2.6.20-ipipe-1.8-08/kernel/ipipe/core.c 2007-10-10
>> 13:05:28.000000000 +0200
>> @@ -283,7 +283,7 @@
>> unsigned long flags;
>> int s;
>>
>> - local_irq_save_hw(flags);
>> + local_irq_save_hw_notrace(flags);
>> __raw_spin_lock(lock);
>> ipipe_load_cpuid();
>> ipd = per_cpu(ipipe_percpu_domain, cpuid);
>> @@ -302,7 +302,7 @@
>> ipd = per_cpu(ipipe_percpu_domain, cpuid);
>> if (!raw_demangle_irq_bits(&x))
>> __clear_bit(IPIPE_STALL_FLAG, &ipd->cpudata[cpuid].status);
>> - local_irq_restore_hw(x);
>> + local_irq_restore_hw_notrace(x);
>> }
>>
>> /*
>>
> The freeze file enclosed is generated with this patch and the i8259.c
> patch.
>
> ---|------------|------------|------------|--------|-------------------------
>
> RTS| 5.570| 9.400| 85.356| 0| 00:08:55/00:08:55
>
> Should I try without the I-pipe debugger ?
Never say never, but the tracer most probably not causing these
latencies. Currently, all points to the good-old programmable interrupt
controller.
Do you have CONFIG_X86_UP_IOAPIC enabled? If no, please try to do so.
Jan
--
Siemens AG, Corporate Technology, CT SE 2
Corporate Competence Center Embedded Linux
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-12 14:21 ` Jan Kiszka
@ 2007-10-12 14:26 ` CHABAL David
2007-10-12 15:34 ` Philippe Gerum
1 sibling, 0 replies; 30+ messages in thread
From: CHABAL David @ 2007-10-12 14:26 UTC (permalink / raw)
To: Jan Kiszka; +Cc: xenomai
Jan Kiszka a écrit :
> CHABAL David wrote:
>> Philippe Gerum a écrit :
>>> I suspect the tracer to induce massive cache misses on your setup, which
>>> limits the interpretation we can have of this log. Could you apply the
>>> following patch, and post back the frozen log for the very same test?
>>> TIA,
>>>
>>> --- 2.6.20-ipipe-1.8-08/kernel/ipipe/core.c~ 2007-09-16
>>> 16:54:34.000000000 +0200
>>> +++ 2.6.20-ipipe-1.8-08/kernel/ipipe/core.c 2007-10-10
>>> 13:05:28.000000000 +0200
>>> @@ -283,7 +283,7 @@
>>> unsigned long flags;
>>> int s;
>>>
>>> - local_irq_save_hw(flags);
>>> + local_irq_save_hw_notrace(flags);
>>> __raw_spin_lock(lock);
>>> ipipe_load_cpuid();
>>> ipd = per_cpu(ipipe_percpu_domain, cpuid);
>>> @@ -302,7 +302,7 @@
>>> ipd = per_cpu(ipipe_percpu_domain, cpuid);
>>> if (!raw_demangle_irq_bits(&x))
>>> __clear_bit(IPIPE_STALL_FLAG, &ipd->cpudata[cpuid].status);
>>> - local_irq_restore_hw(x);
>>> + local_irq_restore_hw_notrace(x);
>>> }
>>>
>>> /*
>>>
>> The freeze file enclosed is generated with this patch and the i8259.c
>> patch.
>>
>> ---|------------|------------|------------|--------|-------------------------
>>
>> RTS| 5.570| 9.400| 85.356| 0| 00:08:55/00:08:55
>>
>> Should I try without the I-pipe debugger ?
>
> Never say never, but the tracer most probably not causing these
> latencies. Currently, all points to the good-old programmable interrupt
> controller.
>
> Do you have CONFIG_X86_UP_IOAPIC enabled? If no, please try to do so.
>
> Jan
>
Yes, I did it.
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-12 14:21 ` Jan Kiszka
2007-10-12 14:26 ` CHABAL David
@ 2007-10-12 15:34 ` Philippe Gerum
2007-10-12 15:49 ` Jan Kiszka
1 sibling, 1 reply; 30+ messages in thread
From: Philippe Gerum @ 2007-10-12 15:34 UTC (permalink / raw)
To: Jan Kiszka; +Cc: xenomai
On Fri, 2007-10-12 at 16:21 +0200, Jan Kiszka wrote:
> CHABAL David wrote:
> > Philippe Gerum a écrit :
> >>
> >> I suspect the tracer to induce massive cache misses on your setup, which
> >> limits the interpretation we can have of this log. Could you apply the
> >> following patch, and post back the frozen log for the very same test?
> >> TIA,
> >>
> >> --- 2.6.20-ipipe-1.8-08/kernel/ipipe/core.c~ 2007-09-16
> >> 16:54:34.000000000 +0200
> >> +++ 2.6.20-ipipe-1.8-08/kernel/ipipe/core.c 2007-10-10
> >> 13:05:28.000000000 +0200
> >> @@ -283,7 +283,7 @@
> >> unsigned long flags;
> >> int s;
> >>
> >> - local_irq_save_hw(flags);
> >> + local_irq_save_hw_notrace(flags);
> >> __raw_spin_lock(lock);
> >> ipipe_load_cpuid();
> >> ipd = per_cpu(ipipe_percpu_domain, cpuid);
> >> @@ -302,7 +302,7 @@
> >> ipd = per_cpu(ipipe_percpu_domain, cpuid);
> >> if (!raw_demangle_irq_bits(&x))
> >> __clear_bit(IPIPE_STALL_FLAG, &ipd->cpudata[cpuid].status);
> >> - local_irq_restore_hw(x);
> >> + local_irq_restore_hw_notrace(x);
> >> }
> >>
> >> /*
> >>
> > The freeze file enclosed is generated with this patch and the i8259.c
> > patch.
> >
> > ---|------------|------------|------------|--------|-------------------------
> >
> > RTS| 5.570| 9.400| 85.356| 0| 00:08:55/00:08:55
> >
> > Should I try without the I-pipe debugger ?
>
> Never say never, but the tracer most probably not causing these
> latencies. Currently, all points to the good-old programmable interrupt
> controller.
>
> Do you have CONFIG_X86_UP_IOAPIC enabled? If no, please try to do so.
>
Large spots are seen in the __ipipe_spin_lock_irqsave() routine, so we
are not running the XT-PIC mask/ack code proper. I just can't figure out
right now why the hardened spinlocking routine would cause such jitter
in UP mode, aside of a massive cache miss accessing the root stall bit.
David, I've just released the following Adeos patch, it is aimed at
improving the cache footprints of the I-pipe -- this is a backport of
what we now have in the 2.6.22/1.10 series. Please use this instead of
1.8-08, and try another set of traces.
http://download.gna.org/adeos/patches/v2.6/i386/adeos-ipipe-2.6.20-i386-1.10-06.patch
--
Philippe.
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-12 15:34 ` Philippe Gerum
@ 2007-10-12 15:49 ` Jan Kiszka
2007-10-12 16:43 ` Philippe Gerum
0 siblings, 1 reply; 30+ messages in thread
From: Jan Kiszka @ 2007-10-12 15:49 UTC (permalink / raw)
To: rpm; +Cc: xenomai
Philippe Gerum wrote:
> On Fri, 2007-10-12 at 16:21 +0200, Jan Kiszka wrote:
>> CHABAL David wrote:
>>> Philippe Gerum a écrit :
>>>> I suspect the tracer to induce massive cache misses on your setup, which
>>>> limits the interpretation we can have of this log. Could you apply the
>>>> following patch, and post back the frozen log for the very same test?
>>>> TIA,
>>>>
>>>> --- 2.6.20-ipipe-1.8-08/kernel/ipipe/core.c~ 2007-09-16
>>>> 16:54:34.000000000 +0200
>>>> +++ 2.6.20-ipipe-1.8-08/kernel/ipipe/core.c 2007-10-10
>>>> 13:05:28.000000000 +0200
>>>> @@ -283,7 +283,7 @@
>>>> unsigned long flags;
>>>> int s;
>>>>
>>>> - local_irq_save_hw(flags);
>>>> + local_irq_save_hw_notrace(flags);
>>>> __raw_spin_lock(lock);
>>>> ipipe_load_cpuid();
>>>> ipd = per_cpu(ipipe_percpu_domain, cpuid);
>>>> @@ -302,7 +302,7 @@
>>>> ipd = per_cpu(ipipe_percpu_domain, cpuid);
>>>> if (!raw_demangle_irq_bits(&x))
>>>> __clear_bit(IPIPE_STALL_FLAG, &ipd->cpudata[cpuid].status);
>>>> - local_irq_restore_hw(x);
>>>> + local_irq_restore_hw_notrace(x);
>>>> }
>>>>
>>>> /*
>>>>
>>> The freeze file enclosed is generated with this patch and the i8259.c
>>> patch.
>>>
>>> ---|------------|------------|------------|--------|-------------------------
>>>
>>> RTS| 5.570| 9.400| 85.356| 0| 00:08:55/00:08:55
>>>
>>> Should I try without the I-pipe debugger ?
>> Never say never, but the tracer most probably not causing these
>> latencies. Currently, all points to the good-old programmable interrupt
>> controller.
>>
>> Do you have CONFIG_X86_UP_IOAPIC enabled? If no, please try to do so.
>>
>
> Large spots are seen in the __ipipe_spin_lock_irqsave() routine, so we
> are not running the XT-PIC mask/ack code proper. I just can't figure out
As there are no function calls between spin_lock and unlock, the passed
time is accounted to the spin_lock function by the tracer. Thus, the
delay could perfectly include potential I/O stalls as well.
> right now why the hardened spinlocking routine would cause such jitter
> in UP mode, aside of a massive cache miss accessing the root stall bit.
>
> David, I've just released the following Adeos patch, it is aimed at
> improving the cache footprints of the I-pipe -- this is a backport of
> what we now have in the 2.6.22/1.10 series. Please use this instead of
> 1.8-08, and try another set of traces.
> http://download.gna.org/adeos/patches/v2.6/i386/adeos-ipipe-2.6.20-i386-1.10-06.patch
>
At this chance, what about instrumenting mask_and_ack_8259A with
ipipe_trace_special() calls to get a more fine-grained picture of what
is going on there? Remember, we are calling about ~30 us here, so
caching effects - given the involved code size - are not really that likely.
Jan
--
Siemens AG, Corporate Technology, CT SE 2
Corporate Competence Center Embedded Linux
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-12 15:49 ` Jan Kiszka
@ 2007-10-12 16:43 ` Philippe Gerum
2007-10-17 8:25 ` CHABAL David
0 siblings, 1 reply; 30+ messages in thread
From: Philippe Gerum @ 2007-10-12 16:43 UTC (permalink / raw)
To: Jan Kiszka; +Cc: xenomai
On Fri, 2007-10-12 at 17:49 +0200, Jan Kiszka wrote:
> Philippe Gerum wrote:
> > On Fri, 2007-10-12 at 16:21 +0200, Jan Kiszka wrote:
> >> CHABAL David wrote:
> >>> Philippe Gerum a écrit :
> >>>> I suspect the tracer to induce massive cache misses on your setup, which
> >>>> limits the interpretation we can have of this log. Could you apply the
> >>>> following patch, and post back the frozen log for the very same test?
> >>>> TIA,
> >>>>
> >>>> --- 2.6.20-ipipe-1.8-08/kernel/ipipe/core.c~ 2007-09-16
> >>>> 16:54:34.000000000 +0200
> >>>> +++ 2.6.20-ipipe-1.8-08/kernel/ipipe/core.c 2007-10-10
> >>>> 13:05:28.000000000 +0200
> >>>> @@ -283,7 +283,7 @@
> >>>> unsigned long flags;
> >>>> int s;
> >>>>
> >>>> - local_irq_save_hw(flags);
> >>>> + local_irq_save_hw_notrace(flags);
> >>>> __raw_spin_lock(lock);
> >>>> ipipe_load_cpuid();
> >>>> ipd = per_cpu(ipipe_percpu_domain, cpuid);
> >>>> @@ -302,7 +302,7 @@
> >>>> ipd = per_cpu(ipipe_percpu_domain, cpuid);
> >>>> if (!raw_demangle_irq_bits(&x))
> >>>> __clear_bit(IPIPE_STALL_FLAG, &ipd->cpudata[cpuid].status);
> >>>> - local_irq_restore_hw(x);
> >>>> + local_irq_restore_hw_notrace(x);
> >>>> }
> >>>>
> >>>> /*
> >>>>
> >>> The freeze file enclosed is generated with this patch and the i8259.c
> >>> patch.
> >>>
> >>> ---|------------|------------|------------|--------|-------------------------
> >>>
> >>> RTS| 5.570| 9.400| 85.356| 0| 00:08:55/00:08:55
> >>>
> >>> Should I try without the I-pipe debugger ?
> >> Never say never, but the tracer most probably not causing these
> >> latencies. Currently, all points to the good-old programmable interrupt
> >> controller.
> >>
> >> Do you have CONFIG_X86_UP_IOAPIC enabled? If no, please try to do so.
> >>
> >
> > Large spots are seen in the __ipipe_spin_lock_irqsave() routine, so we
> > are not running the XT-PIC mask/ack code proper. I just can't figure out
>
> As there are no function calls between spin_lock and unlock, the passed
> time is accounted to the spin_lock function by the tracer. Thus, the
> delay could perfectly include potential I/O stalls as well.
>
Indeed, that's true. Too bad we can only rely on mcount() style
instrumentation, this is deceptive here.
> > right now why the hardened spinlocking routine would cause such jitter
> > in UP mode, aside of a massive cache miss accessing the root stall bit.
> >
> > David, I've just released the following Adeos patch, it is aimed at
> > improving the cache footprints of the I-pipe -- this is a backport of
> > what we now have in the 2.6.22/1.10 series. Please use this instead of
> > 1.8-08, and try another set of traces.
> > http://download.gna.org/adeos/patches/v2.6/i386/adeos-ipipe-2.6.20-i386-1.10-06.patch
> >
>
> At this chance, what about instrumenting mask_and_ack_8259A with
> ipipe_trace_special() calls to get a more fine-grained picture of what
> is going on there?
Yes, good idea. Too many crappy hardwares need many tracepoints...
For now, I really wonder which part of the slave ack causes such delay.
David, please apply this, this should send some more traces enclosing
the execution of the suspected code:
--- 2.6.20-ipipe-1.8-08/arch/i386/kernel/i8259.c~ 2007-10-05 15:47:41.000000000 +0200
+++ 2.6.20-ipipe-1.8-08/arch/i386/kernel/i8259.c 2007-10-12 18:19:31.000000000 +0200
@@ -185,10 +185,13 @@
handle_real_irq:
if (irq & 8) {
+ ipipe_trace_special(0x11, irq);
inb(PIC_SLAVE_IMR); /* DUMMY - (do we need this?) */
+ ipipe_trace_special(0x22, irq);
outb(cached_slave_mask, PIC_SLAVE_IMR);
outb(0x60+(irq&7),PIC_SLAVE_CMD);/* 'Specific EOI' to slave */
outb(0x60+PIC_CASCADE_IR,PIC_MASTER_CMD); /* 'Specific EOI' to master-IRQ2 */
+ ipipe_trace_special(0x33, irq);
} else {
inb(PIC_MASTER_IMR); /* DUMMY - (do we need this?) */
outb(cached_master_mask, PIC_MASTER_IMR);
> Remember, we are calling about ~30 us here, so
> caching effects - given the involved code size - are not really that likely.
Not on this code size, I agree.
> Jan
>
--
Philippe.
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-12 16:43 ` Philippe Gerum
@ 2007-10-17 8:25 ` CHABAL David
2007-10-17 8:41 ` Philippe Gerum
2007-10-17 8:43 ` Philippe Gerum
0 siblings, 2 replies; 30+ messages in thread
From: CHABAL David @ 2007-10-17 8:25 UTC (permalink / raw)
To: rpm; +Cc: xenomai
Philippe Gerum a écrit :
> On Fri, 2007-10-12 at 17:49 +0200, Jan Kiszka wrote:
>> Philippe Gerum wrote:
>>> On Fri, 2007-10-12 at 16:21 +0200, Jan Kiszka wrote:
>>>> CHABAL David wrote:
>>>>> Philippe Gerum a écrit :
>>>>>> I suspect the tracer to induce massive cache misses on your setup, which
>>>>>> limits the interpretation we can have of this log. Could you apply the
>>>>>> following patch, and post back the frozen log for the very same test?
>>>>>> TIA,
>>>>>>
>>>>>> --- 2.6.20-ipipe-1.8-08/kernel/ipipe/core.c~ 2007-09-16
>>>>>> 16:54:34.000000000 +0200
>>>>>> +++ 2.6.20-ipipe-1.8-08/kernel/ipipe/core.c 2007-10-10
>>>>>> 13:05:28.000000000 +0200
>>>>>> @@ -283,7 +283,7 @@
>>>>>> unsigned long flags;
>>>>>> int s;
>>>>>>
>>>>>> - local_irq_save_hw(flags);
>>>>>> + local_irq_save_hw_notrace(flags);
>>>>>> __raw_spin_lock(lock);
>>>>>> ipipe_load_cpuid();
>>>>>> ipd = per_cpu(ipipe_percpu_domain, cpuid);
>>>>>> @@ -302,7 +302,7 @@
>>>>>> ipd = per_cpu(ipipe_percpu_domain, cpuid);
>>>>>> if (!raw_demangle_irq_bits(&x))
>>>>>> __clear_bit(IPIPE_STALL_FLAG, &ipd->cpudata[cpuid].status);
>>>>>> - local_irq_restore_hw(x);
>>>>>> + local_irq_restore_hw_notrace(x);
>>>>>> }
>>>>>>
>>>>>> /*
>>>>>>
>>>>> The freeze file enclosed is generated with this patch and the i8259.c
>>>>> patch.
>>>>>
>>>>> ---|------------|------------|------------|--------|-------------------------
>>>>>
>>>>> RTS| 5.570| 9.400| 85.356| 0| 00:08:55/00:08:55
>>>>>
>>>>> Should I try without the I-pipe debugger ?
>>>> Never say never, but the tracer most probably not causing these
>>>> latencies. Currently, all points to the good-old programmable interrupt
>>>> controller.
>>>>
>>>> Do you have CONFIG_X86_UP_IOAPIC enabled? If no, please try to do so.
>>>>
>>> Large spots are seen in the __ipipe_spin_lock_irqsave() routine, so we
>>> are not running the XT-PIC mask/ack code proper. I just can't figure out
>> As there are no function calls between spin_lock and unlock, the passed
>> time is accounted to the spin_lock function by the tracer. Thus, the
>> delay could perfectly include potential I/O stalls as well.
>>
>
> Indeed, that's true. Too bad we can only rely on mcount() style
> instrumentation, this is deceptive here.
>
>>> right now why the hardened spinlocking routine would cause such jitter
>>> in UP mode, aside of a massive cache miss accessing the root stall bit.
>>>
>>> David, I've just released the following Adeos patch, it is aimed at
>>> improving the cache footprints of the I-pipe -- this is a backport of
>>> what we now have in the 2.6.22/1.10 series. Please use this instead of
>>> 1.8-08, and try another set of traces.
>>> http://download.gna.org/adeos/patches/v2.6/i386/adeos-ipipe-2.6.20-i386-1.10-06.patch
>>>
>> At this chance, what about instrumenting mask_and_ack_8259A with
>> ipipe_trace_special() calls to get a more fine-grained picture of what
>> is going on there?
>
> Yes, good idea. Too many crappy hardwares need many tracepoints...
>
> For now, I really wonder which part of the slave ack causes such delay.
> David, please apply this, this should send some more traces enclosing
> the execution of the suspected code:
>
> --- 2.6.20-ipipe-1.8-08/arch/i386/kernel/i8259.c~ 2007-10-05 15:47:41.000000000 +0200
> +++ 2.6.20-ipipe-1.8-08/arch/i386/kernel/i8259.c 2007-10-12 18:19:31.000000000 +0200
> @@ -185,10 +185,13 @@
>
> handle_real_irq:
> if (irq & 8) {
> + ipipe_trace_special(0x11, irq);
> inb(PIC_SLAVE_IMR); /* DUMMY - (do we need this?) */
> + ipipe_trace_special(0x22, irq);
> outb(cached_slave_mask, PIC_SLAVE_IMR);
> outb(0x60+(irq&7),PIC_SLAVE_CMD);/* 'Specific EOI' to slave */
> outb(0x60+PIC_CASCADE_IR,PIC_MASTER_CMD); /* 'Specific EOI' to master-IRQ2 */
> + ipipe_trace_special(0x33, irq);
> } else {
> inb(PIC_MASTER_IMR); /* DUMMY - (do we need this?) */
> outb(cached_master_mask, PIC_MASTER_IMR);
>
>> Remember, we are calling about ~30 us here, so
>> caching effects - given the involved code size - are not really that likely.
>
> Not on this code size, I agree.
>
>> Jan
>>
I met some problems after applying adeos-ipipe-2.6.20-i386-1.10-06.patch
(sorry, if I post on the wrong mailing-list)
1. entry.S
==========
[root@domain.hid linux-2.6.20]# make
CHK include/linux/version.h
CHK include/linux/utsrelease.h
CHK include/linux/compile.h
dnsdomainname: Unknown host
AS arch/i386/kernel/entry.o
arch/i386/kernel/entry.S: Assembler messages:
arch/i386/kernel/entry.S:307: Error: invalid character '_' in mnemonic
arch/i386/kernel/entry.S:398: Error: invalid character '_' in mnemonic
arch/i386/kernel/entry.S:444: Error: invalid character '_' in mnemonic
arch/i386/kernel/entry.S:536: Error: invalid character '_' in mnemonic
make[1]: *** [arch/i386/kernel/entry.o] Error 1
make: *** [arch/i386/kernel] Error 2
Analysis:
Located in the DISABLE_INTERRUPTS macro, __load_cpu_number is undefined.
Solution:
File linux-2.6.20/include/asm-i386/irqflags.h, l.128, comment
#undef __load_cpu_number
2.KSYM_SYMBOL_LEN
==================
CC kernel/ipipe/tracer.o
kernel/ipipe/tracer.c: In function ?__ipipe_rd_trigger?:
kernel/ipipe/tracer.c:1209: warning: implicit declaration of function
?sprint_symbol?
kernel/ipipe/tracer.c: In function ?__ipipe_wr_trigger?:
kernel/ipipe/tracer.c:1227: error: ?KSYM_SYMBOL_LEN? undeclared (first
use in this function)
kernel/ipipe/tracer.c:1227: error: (Each undeclared identifier is
reported only once
kernel/ipipe/tracer.c:1227: error: for each function it appears in.)
kernel/ipipe/tracer.c:1227: warning: unused variable ?buf?
make[2]: *** [kernel/ipipe/tracer.o] Error 1
Analysis:
KSYM_SYMBOL_LEN only defined on 2.6.22 ?
Solution:
I replace it by 128 (don't ask me why...).
I post my new results as soon as the kernel is built.
David
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-17 8:25 ` CHABAL David
@ 2007-10-17 8:41 ` Philippe Gerum
2007-10-17 8:55 ` CHABAL David
2007-10-17 8:56 ` Philippe Gerum
2007-10-17 8:43 ` Philippe Gerum
1 sibling, 2 replies; 30+ messages in thread
From: Philippe Gerum @ 2007-10-17 8:41 UTC (permalink / raw)
To: CHABAL David; +Cc: xenomai
On Wed, 2007-10-17 at 10:25 +0200, CHABAL David wrote:
> I met some problems after applying adeos-ipipe-2.6.20-i386-1.10-06.patch
> (sorry, if I post on the wrong mailing-list)
>
The most recent patch for the 2.6.20 series is 1.10-08.
> 1. entry.S
> ==========
> [root@domain.hid linux-2.6.20]# make
> CHK include/linux/version.h
> CHK include/linux/utsrelease.h
> CHK include/linux/compile.h
> dnsdomainname: Unknown host
> AS arch/i386/kernel/entry.o
> arch/i386/kernel/entry.S: Assembler messages:
> arch/i386/kernel/entry.S:307: Error: invalid character '_' in mnemonic
> arch/i386/kernel/entry.S:398: Error: invalid character '_' in mnemonic
> arch/i386/kernel/entry.S:444: Error: invalid character '_' in mnemonic
> arch/i386/kernel/entry.S:536: Error: invalid character '_' in mnemonic
> make[1]: *** [arch/i386/kernel/entry.o] Error 1
> make: *** [arch/i386/kernel] Error 2
>
Make sure to disable CONFIG_PARAVIRT.
--
Philippe.
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-17 8:25 ` CHABAL David
2007-10-17 8:41 ` Philippe Gerum
@ 2007-10-17 8:43 ` Philippe Gerum
1 sibling, 0 replies; 30+ messages in thread
From: Philippe Gerum @ 2007-10-17 8:43 UTC (permalink / raw)
To: CHABAL David; +Cc: xenomai
On Wed, 2007-10-17 at 10:25 +0200, CHABAL David wrote:
> 2.KSYM_SYMBOL_LEN
> ==================
> CC kernel/ipipe/tracer.o
> kernel/ipipe/tracer.c: In function ?__ipipe_rd_trigger?:
> kernel/ipipe/tracer.c:1209: warning: implicit declaration of function
> ?sprint_symbol?
> kernel/ipipe/tracer.c: In function ?__ipipe_wr_trigger?:
> kernel/ipipe/tracer.c:1227: error: ?KSYM_SYMBOL_LEN? undeclared (first
> use in this function)
> kernel/ipipe/tracer.c:1227: error: (Each undeclared identifier is
> reported only once
> kernel/ipipe/tracer.c:1227: error: for each function it appears in.)
> kernel/ipipe/tracer.c:1227: warning: unused variable ?buf?
> make[2]: *** [kernel/ipipe/tracer.o] Error 1
>
This one is a tracer issue. Will fix.
> Analysis:
> KSYM_SYMBOL_LEN only defined on 2.6.22 ?
>
> Solution:
> I replace it by 128 (don't ask me why...).
>
>
> I post my new results as soon as the kernel is built.
>
> David
>
>
--
Philippe.
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-17 8:41 ` Philippe Gerum
@ 2007-10-17 8:55 ` CHABAL David
2007-10-17 9:17 ` Philippe Gerum
2007-10-17 8:56 ` Philippe Gerum
1 sibling, 1 reply; 30+ messages in thread
From: CHABAL David @ 2007-10-17 8:55 UTC (permalink / raw)
To: rpm; +Cc: xenomai
Philippe Gerum a écrit :
> On Wed, 2007-10-17 at 10:25 +0200, CHABAL David wrote:
>
>> I met some problems after applying adeos-ipipe-2.6.20-i386-1.10-06.patch
>> (sorry, if I post on the wrong mailing-list)
>>
>
> The most recent patch for the 2.6.20 series is 1.10-08.
OK. But the line "#undef..." is also present in 1.10-08.
>
>> 1. entry.S
>> ==========
>> [root@domain.hid linux-2.6.20]# make
>> CHK include/linux/version.h
>> CHK include/linux/utsrelease.h
>> CHK include/linux/compile.h
>> dnsdomainname: Unknown host
>> AS arch/i386/kernel/entry.o
>> arch/i386/kernel/entry.S: Assembler messages:
>> arch/i386/kernel/entry.S:307: Error: invalid character '_' in mnemonic
>> arch/i386/kernel/entry.S:398: Error: invalid character '_' in mnemonic
>> arch/i386/kernel/entry.S:444: Error: invalid character '_' in mnemonic
>> arch/i386/kernel/entry.S:536: Error: invalid character '_' in mnemonic
>> make[1]: *** [arch/i386/kernel/entry.o] Error 1
>> make: *** [arch/i386/kernel] Error 2
>>
>
> Make sure to disable CONFIG_PARAVIRT.
>
I don't have any CONFIG_PARAVIRT in my .config.
The linker claims a function, so I can't continue the test:
..
UPD include/linux/compile.h
CC init/version.o
LD init/built-in.o
LD .tmp_vmlinux1
kernel/built-in.o: In function `__ipipe_rd_trigger':
tracer.c:(.text+0x330a1): undefined reference to `sprint_symbol'
make: *** [.tmp_vmlinux1] Error 1
[root@domain.hid linux-2.6.20]#
David
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-17 8:41 ` Philippe Gerum
2007-10-17 8:55 ` CHABAL David
@ 2007-10-17 8:56 ` Philippe Gerum
1 sibling, 0 replies; 30+ messages in thread
From: Philippe Gerum @ 2007-10-17 8:56 UTC (permalink / raw)
To: CHABAL David; +Cc: xenomai
On Wed, 2007-10-17 at 10:41 +0200, Philippe Gerum wrote:
> On Wed, 2007-10-17 at 10:25 +0200, CHABAL David wrote:
>
> > I met some problems after applying adeos-ipipe-2.6.20-i386-1.10-06.patch
> > (sorry, if I post on the wrong mailing-list)
> >
>
> The most recent patch for the 2.6.20 series is 1.10-08.
>
> > 1. entry.S
> > ==========
> > [root@domain.hid linux-2.6.20]# make
> > CHK include/linux/version.h
> > CHK include/linux/utsrelease.h
> > CHK include/linux/compile.h
> > dnsdomainname: Unknown host
> > AS arch/i386/kernel/entry.o
> > arch/i386/kernel/entry.S: Assembler messages:
> > arch/i386/kernel/entry.S:307: Error: invalid character '_' in mnemonic
> > arch/i386/kernel/entry.S:398: Error: invalid character '_' in mnemonic
> > arch/i386/kernel/entry.S:444: Error: invalid character '_' in mnemonic
> > arch/i386/kernel/entry.S:536: Error: invalid character '_' in mnemonic
> > make[1]: *** [arch/i386/kernel/entry.o] Error 1
> > make: *** [arch/i386/kernel] Error 2
> >
>
> Make sure to disable CONFIG_PARAVIRT.
>
Yeah, right. Forget about this, the code is utterly wrong, and we should
not undef the macro, indeed. Let's try differently to avoid name
clashes. 1.10-09 is on its way.
--
Philippe.
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-17 8:55 ` CHABAL David
@ 2007-10-17 9:17 ` Philippe Gerum
2007-10-17 13:14 ` CHABAL David
0 siblings, 1 reply; 30+ messages in thread
From: Philippe Gerum @ 2007-10-17 9:17 UTC (permalink / raw)
To: CHABAL David; +Cc: xenomai
On Wed, 2007-10-17 at 10:55 +0200, CHABAL David wrote:
> Philippe Gerum a écrit :
> > On Wed, 2007-10-17 at 10:25 +0200, CHABAL David wrote:
> >
> >> I met some problems after applying adeos-ipipe-2.6.20-i386-1.10-06.patch
> >> (sorry, if I post on the wrong mailing-list)
> >>
> >
> > The most recent patch for the 2.6.20 series is 1.10-08.
>
> OK. But the line "#undef..." is also present in 1.10-08.
>
> >
> >> 1. entry.S
> >> ==========
> >> [root@domain.hid linux-2.6.20]# make
> >> CHK include/linux/version.h
> >> CHK include/linux/utsrelease.h
> >> CHK include/linux/compile.h
> >> dnsdomainname: Unknown host
> >> AS arch/i386/kernel/entry.o
> >> arch/i386/kernel/entry.S: Assembler messages:
> >> arch/i386/kernel/entry.S:307: Error: invalid character '_' in mnemonic
> >> arch/i386/kernel/entry.S:398: Error: invalid character '_' in mnemonic
> >> arch/i386/kernel/entry.S:444: Error: invalid character '_' in mnemonic
> >> arch/i386/kernel/entry.S:536: Error: invalid character '_' in mnemonic
> >> make[1]: *** [arch/i386/kernel/entry.o] Error 1
> >> make: *** [arch/i386/kernel] Error 2
> >>
> >
> > Make sure to disable CONFIG_PARAVIRT.
> >
>
> I don't have any CONFIG_PARAVIRT in my .config.
>
>
> The linker claims a function, so I can't continue the test:
> ..
> UPD include/linux/compile.h
> CC init/version.o
> LD init/built-in.o
> LD .tmp_vmlinux1
> kernel/built-in.o: In function `__ipipe_rd_trigger':
> tracer.c:(.text+0x330a1): undefined reference to `sprint_symbol'
> make: *** [.tmp_vmlinux1] Error 1
> [root@domain.hid linux-2.6.20]#
>
This one should fix the pending issues:
http://download.gna.org/adeos/patches/v2.6/i386/adeos-ipipe-2.6.20-i386-1.10-09.patch
> David
--
Philippe.
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-17 9:17 ` Philippe Gerum
@ 2007-10-17 13:14 ` CHABAL David
2007-10-17 13:46 ` Philippe Gerum
0 siblings, 1 reply; 30+ messages in thread
From: CHABAL David @ 2007-10-17 13:14 UTC (permalink / raw)
To: rpm; +Cc: xenomai
>
> This one should fix the pending issues:
> http://download.gna.org/adeos/patches/v2.6/i386/adeos-ipipe-2.6.20-i386-1.10-09.patch
>
>> David
The latest patch works fine, here the new results with :
- vanillia 2.6.20 patched with Xenomai 2.3.3
- added debug info according your last post
---|------------|------------|------------|--------|-------------------------
RTS| 5.975| 10.136| 98.264| 0| 00:09:40/00:09:40
(the header shows rev.08 but this is really 1.10-09).
I-pipe frozen back-tracing service on 2.6.20/ipipe-1.10-08
------------------------------------------------------------
CPU: 0, Freeze: 1765415011903 cycles, Trace Points: 128 (+10)
Calibrated minimum trace-point overhead: 0.258 us
+----- Hard IRQs ('|': locked)
|+---- <unused>
||+--- Xenomai
|||+-- IShield
||||+- Linux ('*': domain stalled, '+': current, '#': current+stalled)
||||| +---------- Delay flag ('+': > 1 us, '!':
> 10 us)
||||| | +- NMI noise ('N')
||||| | |
Type User Val. Time Delay Function (Parent)
: #func -139 0.422 __ipipe_restore_root+0x8
(boomerang_start_xmit+0x1d0)
: #func -138 0.349 __ipipe_unstall_root+0x8
(__ipipe_restore_root+0x27)
:| #begin 0x80000000 -138 0.356 __ipipe_unstall_root+0x4d
(__ipipe_restore_root+0x27)
:| +end 0x80000000 -138 0.355 __ipipe_unstall_root+0x3f
(__ipipe_restore_root+0x27)
: +func -137 0.430 ipipe_check_context+0xc
(boomerang_start_xmit+0x1da)
: +func -137 0.281 ipipe_check_context+0xc
(__qdisc_run+0x134)
: +func -137 0.308 ipipe_check_context+0xc
(__qdisc_run+0x7a)
: +func -136 0.338 pfifo_fast_dequeue+0x9
(__qdisc_run+0x99)
: +func -136 0.340 ipipe_check_context+0xc
(dev_queue_xmit+0x93)
: +func -136 0.286 local_bh_enable+0xb
(dev_queue_xmit+0xa1)
: +func -135 0.344 ipipe_check_context+0xc
(local_bh_enable+0x52)
: +func -135 0.311 update_send_head+0xa
(__tcp_push_pending_frames+0x122)
: +func -135 0.427 tcp_init_tso_segs+0x16
(__tcp_push_pending_frames+0x154)
: +func -134 0.683 tcp_set_skb_tso_segs+0x16
(tcp_init_tso_segs+0x46)
: +func -133 0.308 tcp_transmit_skb+0xe
(__tcp_push_pending_frames+0x10f)
: +func -133 0.862 skb_clone+0xe
(tcp_transmit_skb+0x6d)
: +func -132 0.468 __tcp_select_window+0xe
(tcp_transmit_skb+0x19b)
: +func -132 0.416 tcp_v4_send_check+0x14
(tcp_transmit_skb+0x45a)
: +func -131 0.297 ip_queue_xmit+0xe
(tcp_transmit_skb+0x3b0)
: +func -131 0.564 __sk_dst_check+0x11
(ip_queue_xmit+0x29e)
: +func -131 0.616 ip_output+0xe (ip_queue_xmit+0x1ac)
: +func -130 0.310 dev_queue_xmit+0xe
(ip_output+0x10b)
: +func -130 0.296 local_bh_disable+0x8
(dev_queue_xmit+0x43)
: +func -129 0.284 ipipe_check_context+0xc
(dev_queue_xmit+0x5d)
: +func -129 0.422 pfifo_fast_enqueue+0xa
(dev_queue_xmit+0x71)
: +func -129 0.282 __qdisc_run+0xe
(dev_queue_xmit+0x1df)
: +func -128 0.352 pfifo_fast_dequeue+0x9
(__qdisc_run+0x99)
: +func -128 0.274 ipipe_check_context+0xc
(__qdisc_run+0x10a)
: +func -128 0.330 ipipe_check_context+0xc
(__qdisc_run+0x54)
: +func -127 0.277 dev_hard_start_xmit+0xe
(__qdisc_run+0x64)
: +func -127 0.310 ipipe_check_context+0xc
(dev_hard_start_xmit+0x4f)
: +func -127 0.304 skb_clone+0xe
(dev_hard_start_xmit+0xa9)
: +func -126 0.366 kmem_cache_alloc+0x14
(skb_clone+0x3c)
: +func -126 0.290 ipipe_check_context+0xc
(kmem_cache_alloc+0x27)
: #func -126 0.345 __ipipe_restore_root+0x8
(kmem_cache_alloc+0x68)
: #func -125 0.363 __ipipe_unstall_root+0x8
(__ipipe_restore_root+0x27)
:| #begin 0x80000000 -125 0.471 __ipipe_unstall_root+0x4d
(__ipipe_restore_root+0x27)
:| +end 0x80000000 -125 0.586 __ipipe_unstall_root+0x3f
(__ipipe_restore_root+0x27)
: +func -124 0.322 packet_rcv_spkt+0x14
(dev_hard_start_xmit+0xfe)
: +func -124 0.396 strlcpy+0x14 (packet_rcv_spkt+0x8e)
: +func -123 0.284 sock_queue_rcv_skb+0x14
(packet_rcv_spkt+0xa0)
: +func -123 0.284 local_bh_disable+0x8
(sock_queue_rcv_skb+0x45)
: +func -123 0.575 sk_run_filter+0x14
(sock_queue_rcv_skb+0x5c)
: +func -122 0.281 local_bh_enable+0xb
(sock_queue_rcv_skb+0xd5)
: +func -122 0.413 ipipe_check_context+0xc
(local_bh_enable+0x52)
: +func -122 0.415 kfree_skb+0x8
(packet_rcv_spkt+0xab)
: +func -121 0.286 __kfree_skb+0x11 (kfree_skb+0x1e)
: +func -121 0.362 kfree_skbmem+0x9 (__kfree_skb+0x47)
: +func -120 0.594 skb_release_data+0xa
(kfree_skbmem+0x10)
: +func -120 0.271 kmem_cache_free+0xe
(kfree_skbmem+0x3d)
: +func -120 0.321 ipipe_check_context+0xc
(kmem_cache_free+0x40)
: #func -119 0.334 __ipipe_restore_root+0x8
(kmem_cache_free+0x84)
: #func -119 0.382 __ipipe_unstall_root+0x8
(__ipipe_restore_root+0x27)
:| #begin 0x80000000 -119 0.377 __ipipe_unstall_root+0x4d
(__ipipe_restore_root+0x27)
:| +end 0x80000000 -118 0.420 __ipipe_unstall_root+0x3f
(__ipipe_restore_root+0x27)
: +func -118 0.307 ipipe_check_context+0xc
(dev_hard_start_xmit+0x10d)
: +func -117 0.437 boomerang_start_xmit+0xe
(dev_hard_start_xmit+0x1cb)
: +func -117 0.286 ipipe_check_context+0xc
(boomerang_start_xmit+0x123)
: #func -117 0.353 ipipe_check_context+0xc
(boomerang_start_xmit+0x163)
: #func -116 0.282 issue_and_wait+0xe
(boomerang_start_xmit+0x170)
: #func -116 0.474 iowrite16+0x8 (issue_and_wait+0x2a)
: #func -116+ 5.673 ioread16+0x8 (issue_and_wait+0x45)
:| #begin 0xffffff16 -110 0.439 ipipe_ipi3+0x2e (ioread16+0x14)
:| #func -109 0.431 __ipipe_handle_irq+0x14
(ipipe_ipi3+0x33)
:| #func -109 0.435 __ipipe_ack_apic+0x8
(__ipipe_handle_irq+0x8f)
:| #func -109 0.390 __ipipe_dispatch_wired+0x16
(__ipipe_handle_irq+0x4f)
:| # *func -108 0.513 xnintr_clock_handler+0x8
(__ipipe_dispatch_wired+0xaa)
:| # *func -108 0.446 xnintr_irq_handler+0xe
(xnintr_clock_handler+0x17)
:| # *func -107 0.467 xnpod_announce_tick+0x8
(xnintr_irq_handler+0x3b)
:| # *func -107 0.520 xntimer_do_tick_aperiodic+0xe
(xnpod_announce_tick+0xf)
:| # *func -106 0.334 xnthread_periodic_handler+0x8
(xntimer_do_tick_aperiodic+0x217)
:| # *func -106 0.329 xnpod_resume_thread+0xe
(xnthread_periodic_handler+0x2c)
:| # *[ 3912] samplin 99 -106+ 1.099 xnpod_resume_thread+0x5d
(xnthread_periodic_handler+0x2c)
:| # *func -105 0.390 xnpod_schedule+0xe
(xnintr_irq_handler+0x135)
:| # *[ 3487] konsole -1 -104+ 1.191 xnpod_schedule+0x97
(xnintr_irq_handler+0x135)
:| # *func -103 0.576 __switch_to+0xe
(xnpod_schedule+0x498)
:| # *[ 3912] samplin 99 -102 0.752 xnpod_schedule+0x570
(xnpod_suspend_thread+0x19b)
:| # *func -102 0.366
__ipipe_restore_pipeline_head+0x12 (xnpod_wait_thread_period+0x138)
:| + *end 0x80000000 -101! 14.474
__ipipe_restore_pipeline_head+0x7e (xnpod_wait_thread_period+0x138)
:| + *begin 0xfffffff1 -87 0.385 common_interrupt+0x29
(__ipipe_restore_pipeline_head+0x82)
:| + *func -86 0.923 __ipipe_handle_irq+0x14
(common_interrupt+0x2e)
:| + *func -85 0.561 __ipipe_set_irq_pending+0x16
(__ipipe_handle_irq+0x124)
:| + *func -85 0.463 __ipipe_ack_irq+0x8
(__ipipe_handle_irq+0x13d)
:| + *func -84 0.319 __ipipe_ack_level_irq+0x12
(__ipipe_ack_irq+0x19)
:| + *func -84 0.389 mask_and_ack_8259A+0x14
(__ipipe_ack_level_irq+0x22)
:| + *func -84 0.397 __ipipe_spin_lock_irqsave+0x9
(mask_and_ack_8259A+0x29)
:| # *(0x11) 0x0000000e -83! 17.062 mask_and_ack_8259A+0xbc
(__ipipe_ack_level_irq+0x22)
:| # *(0x22) 0x0000000e -66! 23.096 mask_and_ack_8259A+0xca
(__ipipe_ack_level_irq+0x22)
:| # *(0x33) 0x0000000e -43 0.415 mask_and_ack_8259A+0xf3
(__ipipe_ack_level_irq+0x22)
:| # *func -43 0.418
__ipipe_spin_unlock_irqrestore+0x9 (mask_and_ack_8259A+0x67)
:| + *func -42 0.397 __ipipe_walk_pipeline+0xa
(__ipipe_handle_irq+0x62)
:| + *end 0xfffffff1 -42+ 6.601 common_interrupt+0x38
(__ipipe_restore_pipeline_head+0x82)
:| + *begin 0xfffffffa -35 0.523 common_interrupt+0x29
(__ipipe_restore_pipeline_head+0x82)
:| + *func -35 0.435 __ipipe_handle_irq+0x14
(common_interrupt+0x2e)
:| + *func -34 0.342 __ipipe_set_irq_pending+0x16
(__ipipe_handle_irq+0x124)
:| + *func -34 0.304 __ipipe_ack_irq+0x8
(__ipipe_handle_irq+0x13d)
:| + *func -34 0.378 __ipipe_ack_level_irq+0x12
(__ipipe_ack_irq+0x19)
:| + *func -33 0.301 mask_and_ack_8259A+0x14
(__ipipe_ack_level_irq+0x22)
:| + *func -33! 15.117 __ipipe_spin_lock_irqsave+0x9
(mask_and_ack_8259A+0x29)
:| # *func -18 0.430
__ipipe_spin_unlock_irqrestore+0x9 (mask_and_ack_8259A+0x67)
:| + *func -18 0.475 __ipipe_walk_pipeline+0xa
(__ipipe_handle_irq+0x62)
:| + *end 0xfffffffa -17 0.796 common_interrupt+0x38
(__ipipe_restore_pipeline_head+0x82)
:| + *begin 0x80000001 -16 0.478 __ipipe_dispatch_event+0x1b1
(__ipipe_syscall_root+0x44)
:| + *end 0x80000001 -16+ 2.710 __ipipe_dispatch_event+0x17e
(__ipipe_syscall_root+0x44)
:| + *begin 0xffffff16 -13 0.433 ipipe_ipi3+0x2e (<b7f40dba>)
:| + *func -13 0.345 __ipipe_handle_irq+0x14
(ipipe_ipi3+0x33)
:| + *func -12 0.360 __ipipe_ack_apic+0x8
(__ipipe_handle_irq+0x8f)
:| + *func -12 0.345 __ipipe_dispatch_wired+0x16
(__ipipe_handle_irq+0x4f)
:| # *func -12 0.370 xnintr_clock_handler+0x8
(__ipipe_dispatch_wired+0xaa)
:| # *func -11 0.418 xnintr_irq_handler+0xe
(xnintr_clock_handler+0x17)
:| # *func -11 0.306 xnpod_announce_tick+0x8
(xnintr_irq_handler+0x3b)
:| # *func -10 0.415 xntimer_do_tick_aperiodic+0xe
(xnpod_announce_tick+0xf)
:| # *func -10+ 1.198 xnthread_periodic_handler+0x8
(xntimer_do_tick_aperiodic+0x217)
:| + *func -9 0.382 __ipipe_walk_pipeline+0xa
(__ipipe_handle_irq+0x62)
:| + *end 0xffffff16 -8+ 1.598 ipipe_ipi3+0x3d (<b7f40dba>)
: + *func -7 0.364 __ipipe_syscall_root+0xa
(system_call+0x29)
: + *func -7 0.409 __ipipe_dispatch_event+0xe
(__ipipe_syscall_root+0x44)
:| + *begin 0x80000001 -6 0.424 __ipipe_dispatch_event+0x1d0
(__ipipe_syscall_root+0x44)
:| + *end 0x80000001 -6 0.409 __ipipe_dispatch_event+0x1c0
(__ipipe_syscall_root+0x44)
: + *func -5+ 1.158 hisyscall_event+0x14
(__ipipe_dispatch_event+0xc0)
: + *func -4+ 1.166 xnshadow_sys_trace+0x16
(hisyscall_event+0x189)
: + *func -3 0.502 ipipe_trace_frozen_reset+0x9
(xnshadow_sys_trace+0xd7)
: + *func -2 0.307 __ipipe_global_path_lock+0x8
(ipipe_trace_frozen_reset+0x13)
: + *func -2 0.340 __ipipe_spin_lock_irqsave+0x9
(__ipipe_global_path_lock+0x12)
:| + *begin 0x80000001 -2+ 1.322 __ipipe_spin_lock_irqsave+0x4b
(__ipipe_global_path_lock+0x12)
:| # *func 0 0.516
__ipipe_spin_unlock_irqcomplete+0x9 (__ipipe_global_path_unlock+0x63)
:| + *end 0x80000001 0 0.446
__ipipe_spin_unlock_irqcomplete+0x38 (__ipipe_global_path_unlock+0x63)
< + *freeze 0x00017fd8 0 0.513 xnshadow_sys_trace+0xa0
(hisyscall_event+0x189)
| + *begin 0x80000001 0 0.426 __ipipe_dispatch_event+0x1b1
(__ipipe_syscall_root+0x44)
| + *end 0x80000001 0 0.942 __ipipe_dispatch_event+0x17e
(__ipipe_syscall_root+0x44)
+ *func 1 0.311 __ipipe_syscall_root+0xa
(system_call+0x29)
+ *func 2 0.329 __ipipe_dispatch_event+0xe
(__ipipe_syscall_root+0x44)
| + *begin 0x80000001 2 0.422 __ipipe_dispatch_event+0x1d0
(__ipipe_syscall_root+0x44)
| + *end 0x80000001 2 0.351 __ipipe_dispatch_event+0x1c0
(__ipipe_syscall_root+0x44)
+ *func 3 0.433 hisyscall_event+0x14
(__ipipe_dispatch_event+0xc0)
+ *func 3 0.333 __rt_task_wait_period+0x11
(hisyscall_event+0x189)
+ *func 4 0.472 rt_task_wait_period+0x8
(__rt_task_wait_period+0x21)
+ *func 4 0.000 xnpod_wait_thread_period+0xe
(rt_task_wait_period+0x38)
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-17 13:14 ` CHABAL David
@ 2007-10-17 13:46 ` Philippe Gerum
2007-10-17 14:52 ` CHABAL David
0 siblings, 1 reply; 30+ messages in thread
From: Philippe Gerum @ 2007-10-17 13:46 UTC (permalink / raw)
To: CHABAL David; +Cc: xenomai
On Wed, 2007-10-17 at 15:14 +0200, CHABAL David wrote:
> :| + *func -84 0.389 mask_and_ack_8259A+0x14
> (__ipipe_ack_level_irq+0x22)
> :| + *func -84 0.397 __ipipe_spin_lock_irqsave+0x9
> (mask_and_ack_8259A+0x29)
> :| # *(0x11) 0x0000000e -83! 17.062 mask_and_ack_8259A+0xbc
> (__ipipe_ack_level_irq+0x22)
> :| # *(0x22) 0x0000000e -66! 23.096 mask_and_ack_8259A+0xca
> (__ipipe_ack_level_irq+0x22)
> :| # *(0x33) 0x0000000e -43 0.415 mask_and_ack_8259A+0xf3
> (__ipipe_ack_level_irq+0x22)
> :| # *func -43 0.418
> __ipipe_spin_unlock_irqrestore+0x9 (mask_and_ack_8259A+0x67)
> :| + *func -42 0.397 __ipipe_walk_pipeline+0xa
Grmmff... I think the PIC on this box has some deep troubles; please try
this patch, in replacement of the previous ipipe_trace_special
instrumentation:
--- 2.6.20-ipipe-1.8-08/arch/i386/kernel/i8259.c~ 2007-10-12
18:19:31.000000000 +0200
+++ 2.6.20-ipipe-1.8-08/arch/i386/kernel/i8259.c 2007-10-17
15:42:35.000000000 +0200
@@ -128,7 +128,7 @@
* This has to be protected by the irq controller spinlock
* before being called.
*/
-static inline int i8259A_irq_real(unsigned int irq)
+int i8259A_irq_real(unsigned int irq)
{
int value;
int irqmask = 1<<irq;
@@ -174,6 +174,8 @@
*/
if (cached_irq_mask & irqmask)
goto spurious_8259A_irq;
+
+ ipipe_trace_special(0x77, irq);
#ifdef CONFIG_IPIPE
if (irq == 0) {
outb(0x60,PIC_MASTER_CMD); /* 'Specific EOI to master */
@@ -185,18 +187,14 @@
handle_real_irq:
if (irq & 8) {
- ipipe_trace_special(0x10, irq);
- inb(PIC_SLAVE_IMR); /* DUMMY - (do we need this?) */
- ipipe_trace_special(0x11, irq);
outb(cached_slave_mask, PIC_SLAVE_IMR);
outb(0x60+(irq&7),PIC_SLAVE_CMD);/* 'Specific EOI' to slave */
outb(0x60+PIC_CASCADE_IR,PIC_MASTER_CMD); /* 'Specific EOI' to
master-IRQ2 */
- ipipe_trace_special(0x12, irq);
} else {
- inb(PIC_MASTER_IMR); /* DUMMY - (do we need this?) */
outb(cached_master_mask, PIC_MASTER_IMR);
outb(0x60+irq,PIC_MASTER_CMD); /* 'Specific EOI to master */
}
+ ipipe_trace_special(0x99, irq);
spin_unlock_irqrestore(&i8259A_lock, flags);
return;
--
Philippe.
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-17 13:46 ` Philippe Gerum
@ 2007-10-17 14:52 ` CHABAL David
2007-10-17 15:24 ` Philippe Gerum
0 siblings, 1 reply; 30+ messages in thread
From: CHABAL David @ 2007-10-17 14:52 UTC (permalink / raw)
To: rpm; +Cc: xenomai
[-- Attachment #1: Type: text/plain, Size: 597 bytes --]
>
> Grmmff... I think the PIC on this box has some deep troubles; please try
> this patch, in replacement of the previous ipipe_trace_special
> instrumentation:
>
RTD| 8.348| 10.387| 43.647| 0| 6.098|
80.440
---|------------|------------|------------|--------|-------------------------
RTS| 6.098| 10.020| 80.440| 0| 00:17:20/00:17:20
[root@domain.hid bin]#
IRQ handling takes 17µs in the worst case.
It takes a long time to write 3 poor bytes...
May be is it a SMI problem ??? (Globally disable SMI is on)
David
[-- Attachment #2: freeze.txt --]
[-- Type: text/plain, Size: 13185 bytes --]
I-pipe frozen back-tracing service on 2.6.20/ipipe-1.10-08
------------------------------------------------------------
CPU: 0, Freeze: 1199670455059 cycles, Trace Points: 128 (+10)
Calibrated minimum trace-point overhead: 0.258 us
+----- Hard IRQs ('|': locked)
|+---- <unused>
||+--- Xenomai
|||+-- IShield
||||+- Linux ('*': domain stalled, '+': current, '#': current+stalled)
||||| +---------- Delay flag ('+': > 1 us, '!': > 10 us)
||||| | +- NMI noise ('N')
||||| | |
Type User Val. Time Delay Function (Parent)
: +func -127 0.340 skb_release_data+0xa (kfree_skbmem+0x10)
: +func -127 0.271 kmem_cache_free+0xe (kfree_skbmem+0x3d)
: +func -126 0.315 ipipe_check_context+0xc (kmem_cache_free+0x40)
: #func -126 0.334 __ipipe_restore_root+0x8 (kmem_cache_free+0x84)
: #func -126 0.300 __ipipe_unstall_root+0x8 (__ipipe_restore_root+0x27)
:| #begin 0x80000000 -126 0.377 __ipipe_unstall_root+0x4d (__ipipe_restore_root+0x27)
:| +end 0x80000000 -125 0.420 __ipipe_unstall_root+0x3f (__ipipe_restore_root+0x27)
: +func -125 0.307 ipipe_check_context+0xc (dev_hard_start_xmit+0x10d)
: +func -124 0.345 boomerang_start_xmit+0xe (dev_hard_start_xmit+0x1cb)
: +func -124 0.285 ipipe_check_context+0xc (boomerang_start_xmit+0x123)
: #func -124 0.353 ipipe_check_context+0xc (boomerang_start_xmit+0x163)
: #func -123 0.275 issue_and_wait+0xe (boomerang_start_xmit+0x170)
: #func -123 0.403 iowrite16+0x8 (issue_and_wait+0x2a)
: #func -123+ 5.960 ioread16+0x8 (issue_and_wait+0x45)
: #func -117+ 7.038 ioread32+0x8 (boomerang_start_xmit+0x188)
: #func -110 0.459 iowrite16+0x8 (boomerang_start_xmit+0x1c9)
: #func -109 0.352 __ipipe_restore_root+0x8 (boomerang_start_xmit+0x1d0)
: #func -109 0.385 __ipipe_unstall_root+0x8 (__ipipe_restore_root+0x27)
:| #begin 0x80000000 -109 0.341 __ipipe_unstall_root+0x4d (__ipipe_restore_root+0x27)
:| +end 0x80000000 -108 0.353 __ipipe_unstall_root+0x3f (__ipipe_restore_root+0x27)
: +func -108 0.346 ipipe_check_context+0xc (boomerang_start_xmit+0x1da)
: +func -108 0.274 ipipe_check_context+0xc (__qdisc_run+0x134)
: +func -107 0.285 ipipe_check_context+0xc (__qdisc_run+0x7a)
: +func -107 0.300 pfifo_fast_dequeue+0x9 (__qdisc_run+0x99)
: +func -107 0.271 ipipe_check_context+0xc (dev_queue_xmit+0x93)
: +func -106 0.281 local_bh_enable+0xb (dev_queue_xmit+0xa1)
: +func -106 0.338 ipipe_check_context+0xc (local_bh_enable+0x52)
: +func -106 0.390 update_send_head+0xa (__tcp_push_pending_frames+0x122)
: +func -105 0.381 tcp_cwnd_validate+0x8 (__tcp_push_pending_frames+0x2d3)
: +func -105 0.554 tcp_check_space+0x9 (tcp_rcv_established+0x410)
: +func -104 0.378 ipipe_check_context+0xc (tcp_v4_rcv+0x58a)
: +func -104 0.379 ipipe_check_context+0xc (ip_local_deliver+0xe7)
: +func -104 0.334 ipipe_check_context+0xc (netif_receive_skb+0x172)
: +func -103 0.331 ipipe_check_context+0xc (process_backlog+0x4a)
: #func -103 0.371 __ipipe_unstall_root+0x8 (process_backlog+0x84)
:| #begin 0x80000000 -103 0.322 __ipipe_unstall_root+0x4d (process_backlog+0x84)
:| +end 0x80000000 -102 0.371 __ipipe_unstall_root+0x3f (process_backlog+0x84)
: +func -102 0.341 netif_receive_skb+0xe (process_backlog+0x8e)
: +func -102 0.418 ipipe_check_context+0xc (netif_receive_skb+0x7f)
: +func -101 0.295 packet_rcv_spkt+0x14 (netif_receive_skb+0x14a)
: +func -101 0.269 skb_clone+0xe (packet_rcv_spkt+0xcc)
: +func -101 0.269 kmem_cache_alloc+0x14 (skb_clone+0x3c)
: +func -100 0.307 ipipe_check_context+0xc (kmem_cache_alloc+0x27)
: #func -100 0.355 __ipipe_restore_root+0x8 (kmem_cache_alloc+0x68)
: #func -100 0.375 __ipipe_unstall_root+0x8 (__ipipe_restore_root+0x27)
:| #begin 0x80000000 -99 0.448 __ipipe_unstall_root+0x4d (__ipipe_restore_root+0x27)
:| +end 0x80000000 -99 0.509 __ipipe_unstall_root+0x3f (__ipipe_restore_root+0x27)
: +func -98 0.356 kfree_skb+0x8 (packet_rcv_spkt+0xd5)
: +func -98 0.396 strlcpy+0x14 (packet_rcv_spkt+0x8e)
: +func -98 0.265 sock_queue_rcv_skb+0x14 (packet_rcv_spkt+0xa0)
: +func -97 0.285 local_bh_disable+0x8 (sock_queue_rcv_skb+0x45)
: +func -97 0.540 sk_run_filter+0x14 (sock_queue_rcv_skb+0x5c)
: +func -97 0.281 local_bh_enable+0xb (sock_queue_rcv_skb+0xd5)
: +func -96 0.289 ipipe_check_context+0xc (local_bh_enable+0x52)
: +func -96 0.295 kfree_skb+0x8 (packet_rcv_spkt+0xab)
: +func -96 0.269 __kfree_skb+0x11 (kfree_skb+0x1e)
: +func -95 0.336 kfree_skbmem+0x9 (__kfree_skb+0x47)
: +func -95 0.362 skb_release_data+0xa (kfree_skbmem+0x10)
: +func -95 0.327 kmem_cache_free+0xe (kfree_skbmem+0x3d)
: +func -94 0.278 ipipe_check_context+0xc (kmem_cache_free+0x40)
: #func -94 0.334 __ipipe_restore_root+0x8 (kmem_cache_free+0x84)
: #func -94 0.371 __ipipe_unstall_root+0x8 (__ipipe_restore_root+0x27)
:| #begin 0x80000000 -93 0.344 __ipipe_unstall_root+0x4d (__ipipe_restore_root+0x27)
:| +end 0x80000000 -93 0.445 __ipipe_unstall_root+0x3f (__ipipe_restore_root+0x27)
: +func -93 0.493 ip_rcv+0x14 (netif_receive_skb+0x166)
: +func -92 0.306 ip_route_input+0x11 (ip_rcv+0x338)
: +func -92 0.321 rt_hash_code+0x9 (ip_route_input+0x3d)
: +func -91 0.403 ipipe_check_context+0xc (ip_route_input+0x49)
: +func -91 0.385 ipipe_check_context+0xc (ip_route_input+0xd2)
: +func -91 0.311 ip_local_deliver+0xe (ip_rcv+0x226)
: +func -90 0.374 ipipe_check_context+0xc (ip_local_deliver+0x6d)
: +func -90 0.614 tcp_v4_rcv+0xe (ip_local_deliver+0xa8)
:| +begin 0xffffff16 -89 0.375 ipipe_ipi3+0x2e (tcp_v4_rcv+0xfa)
:| +func -89 0.368 __ipipe_handle_irq+0x14 (ipipe_ipi3+0x33)
:| +func -89 0.337 __ipipe_ack_apic+0x8 (__ipipe_handle_irq+0x8f)
:| +func -88 0.382 __ipipe_dispatch_wired+0x16 (__ipipe_handle_irq+0x4f)
:| # func -88 0.370 xnintr_clock_handler+0x8 (__ipipe_dispatch_wired+0xaa)
:| # func -88 0.353 xnintr_irq_handler+0xe (xnintr_clock_handler+0x17)
:| # func -87 0.353 xnpod_announce_tick+0x8 (xnintr_irq_handler+0x3b)
:| # func -87 0.500 xntimer_do_tick_aperiodic+0xe (xnpod_announce_tick+0xf)
:| # func -86 0.301 xnthread_periodic_handler+0x8 (xntimer_do_tick_aperiodic+0x217)
:| # func -86 0.322 xnpod_resume_thread+0xe (xnthread_periodic_handler+0x2c)
:| # [ 3875] samplin 99 -86+ 1.013 xnpod_resume_thread+0x5d (xnthread_periodic_handler+0x2c)
:| # func -85 0.404 xnpod_schedule+0xe (xnintr_irq_handler+0x135)
:| # [ 3463] konsole -1 -84+ 1.075 xnpod_schedule+0x97 (xnintr_irq_handler+0x135)
:| # func -83 0.647 __switch_to+0xe (xnpod_schedule+0x498)
:| # [ 3875] samplin 99 -83 0.629 xnpod_schedule+0x570 (xnpod_suspend_thread+0x19b)
:| # func -82 0.327 __ipipe_restore_pipeline_head+0x12 (xnpod_wait_thread_period+0x138)
:| + end 0x80000000 -82! 26.569 __ipipe_restore_pipeline_head+0x7e (xnpod_wait_thread_period+0x138)
:| + begin 0xfffffff1 -55 0.371 common_interrupt+0x29 (__ipipe_restore_pipeline_head+0x82)
:| + func -55 0.886 __ipipe_handle_irq+0x14 (common_interrupt+0x2e)
:| + func -54 0.540 __ipipe_set_irq_pending+0x16 (__ipipe_handle_irq+0x124)
:| + func -53 0.457 __ipipe_ack_irq+0x8 (__ipipe_handle_irq+0x13d)
:| + func -53 0.323 __ipipe_ack_level_irq+0x12 (__ipipe_ack_irq+0x19)
:| + func -52 0.303 mask_and_ack_8259A+0x14 (__ipipe_ack_level_irq+0x22)
:| + func -52 0.308 __ipipe_spin_lock_irqsave+0x9 (mask_and_ack_8259A+0x29)
:| # (0x77) 0x0000000e -52! 16.894 mask_and_ack_8259A+0x3f (__ipipe_ack_level_irq+0x22)
:| # (0x99) 0x0000000e -35 0.310 mask_and_ack_8259A+0x7b (__ipipe_ack_level_irq+0x22)
:| # func -35 0.386 __ipipe_spin_unlock_irqrestore+0x9 (mask_and_ack_8259A+0x87)
:| + func -34 0.370 __ipipe_walk_pipeline+0xa (__ipipe_handle_irq+0x62)
:| + end 0xfffffff1 -34+ 6.810 common_interrupt+0x38 (__ipipe_restore_pipeline_head+0x82)
:| + begin 0xfffffffa -27 0.379 common_interrupt+0x29 (__ipipe_restore_pipeline_head+0x82)
:| + func -27 0.364 __ipipe_handle_irq+0x14 (common_interrupt+0x2e)
:| + func -26 0.307 __ipipe_set_irq_pending+0x16 (__ipipe_handle_irq+0x124)
:| + func -26 0.285 __ipipe_ack_irq+0x8 (__ipipe_handle_irq+0x13d)
:| + func -26 0.278 __ipipe_ack_level_irq+0x12 (__ipipe_ack_irq+0x19)
:| + func -25 0.284 mask_and_ack_8259A+0x14 (__ipipe_ack_level_irq+0x22)
:| + func -25 0.290 __ipipe_spin_lock_irqsave+0x9 (mask_and_ack_8259A+0x29)
:| # (0x77) 0x00000005 -25! 12.952 mask_and_ack_8259A+0x3f (__ipipe_ack_level_irq+0x22)
:| # (0x99) 0x00000005 -12 0.288 mask_and_ack_8259A+0x7b (__ipipe_ack_level_irq+0x22)
:| # func -12 0.355 __ipipe_spin_unlock_irqrestore+0x9 (mask_and_ack_8259A+0x87)
:| + func -11 0.327 __ipipe_walk_pipeline+0xa (__ipipe_handle_irq+0x62)
:| + end 0xfffffffa -11 0.760 common_interrupt+0x38 (__ipipe_restore_pipeline_head+0x82)
:| + begin 0x80000001 -10 0.463 __ipipe_dispatch_event+0x1b1 (__ipipe_syscall_root+0x44)
:| + end 0x80000001 -10+ 3.172 __ipipe_dispatch_event+0x17e (__ipipe_syscall_root+0x44)
: + func -7 0.314 __ipipe_syscall_root+0xa (system_call+0x29)
: + func -6 0.326 __ipipe_dispatch_event+0xe (__ipipe_syscall_root+0x44)
:| + begin 0x80000001 -6 0.407 __ipipe_dispatch_event+0x1d0 (__ipipe_syscall_root+0x44)
:| + end 0x80000001 -6 0.356 __ipipe_dispatch_event+0x1c0 (__ipipe_syscall_root+0x44)
: + func -5+ 1.032 hisyscall_event+0x14 (__ipipe_dispatch_event+0xc0)
: + func -4+ 1.234 xnshadow_sys_trace+0x16 (hisyscall_event+0x189)
: + func -3 0.442 ipipe_trace_frozen_reset+0x9 (xnshadow_sys_trace+0xd7)
: + func -2 0.271 __ipipe_global_path_lock+0x8 (ipipe_trace_frozen_reset+0x13)
: + func -2 0.303 __ipipe_spin_lock_irqsave+0x9 (__ipipe_global_path_lock+0x12)
:| + begin 0x80000001 -2+ 1.545 __ipipe_spin_lock_irqsave+0x4b (__ipipe_global_path_lock+0x12)
:| # func 0 0.413 __ipipe_spin_unlock_irqcomplete+0x9 (__ipipe_global_path_unlock+0x63)
:| + end 0x80000001 0 0.422 __ipipe_spin_unlock_irqcomplete+0x38 (__ipipe_global_path_unlock+0x63)
< + freeze 0x00013a38 0 0.454 xnshadow_sys_trace+0xa0 (hisyscall_event+0x189)
| + begin 0x80000001 0 0.363 __ipipe_dispatch_event+0x1b1 (__ipipe_syscall_root+0x44)
| + end 0x80000001 0 0.886 __ipipe_dispatch_event+0x17e (__ipipe_syscall_root+0x44)
+ func 1 0.292 __ipipe_syscall_root+0xa (system_call+0x29)
+ func 1 0.293 __ipipe_dispatch_event+0xe (__ipipe_syscall_root+0x44)
| + begin 0x80000001 2 0.322 __ipipe_dispatch_event+0x1d0 (__ipipe_syscall_root+0x44)
| + end 0x80000001 2 0.329 __ipipe_dispatch_event+0x1c0 (__ipipe_syscall_root+0x44)
+ func 2 0.412 hisyscall_event+0x14 (__ipipe_dispatch_event+0xc0)
+ func 3 0.315 __rt_task_wait_period+0x11 (hisyscall_event+0x189)
+ func 3 0.364 rt_task_wait_period+0x8 (__rt_task_wait_period+0x21)
+ func 4 0.000 xnpod_wait_thread_period+0xe (rt_task_wait_period+0x38)
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-17 14:52 ` CHABAL David
@ 2007-10-17 15:24 ` Philippe Gerum
2007-10-17 15:46 ` CHABAL David
0 siblings, 1 reply; 30+ messages in thread
From: Philippe Gerum @ 2007-10-17 15:24 UTC (permalink / raw)
To: CHABAL David; +Cc: xenomai
On Wed, 2007-10-17 at 16:52 +0200, CHABAL David wrote:
> >
> > Grmmff... I think the PIC on this box has some deep troubles; please try
> > this patch, in replacement of the previous ipipe_trace_special
> > instrumentation:
> >
>
>
> RTD| 8.348| 10.387| 43.647| 0| 6.098|
> 80.440
> ---|------------|------------|------------|--------|-------------------------
> RTS| 6.098| 10.020| 80.440| 0| 00:17:20/00:17:20
> [root@domain.hid bin]#
>
>
> IRQ handling takes 17µs in the worst case.
>
> It takes a long time to write 3 poor bytes...
>
Indeed. Each outb to the ISA bus should be somewhere in the 1-2.5 us
range depending on the hw, maybe a bit higher in case of contention, but
not that much.
> May be is it a SMI problem ??? (Globally disable SMI is on)
>
It's less likely with an ICH-2 chipset.
I see that CONFIG_IDEDMA_PCI_AUTO is disabled. Any reason not to use PCI
DMA when available for IDE drives with your hw?
--
Philippe.
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-17 15:24 ` Philippe Gerum
@ 2007-10-17 15:46 ` CHABAL David
2007-10-17 16:05 ` Philippe Gerum
0 siblings, 1 reply; 30+ messages in thread
From: CHABAL David @ 2007-10-17 15:46 UTC (permalink / raw)
To: rpm; +Cc: xenomai
Philippe Gerum a écrit :
> On Wed, 2007-10-17 at 16:52 +0200, CHABAL David wrote:
>>> Grmmff... I think the PIC on this box has some deep troubles; please try
>>> this patch, in replacement of the previous ipipe_trace_special
>>> instrumentation:
>>>
>>
>> RTD| 8.348| 10.387| 43.647| 0| 6.098|
>> 80.440
>> ---|------------|------------|------------|--------|-------------------------
>> RTS| 6.098| 10.020| 80.440| 0| 00:17:20/00:17:20
>> [root@domain.hid bin]#
>>
>>
>> IRQ handling takes 17µs in the worst case.
>>
>> It takes a long time to write 3 poor bytes...
>>
>
> Indeed. Each outb to the ISA bus should be somewhere in the 1-2.5 us
> range depending on the hw, maybe a bit higher in case of contention, but
> not that much.
>
>> May be is it a SMI problem ??? (Globally disable SMI is on)
>>
>
> It's less likely with an ICH-2 chipset.
>
> I see that CONFIG_IDEDMA_PCI_AUTO is disabled. Any reason not to use PCI
> DMA when available for IDE drives with your hw?
>
I read this about DMA:
http://www.rtai.dk/cgi-bin/gratiswiki.pl?DMA_And_Jitter
but I'm not sure if I understood well.
David
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-17 15:46 ` CHABAL David
@ 2007-10-17 16:05 ` Philippe Gerum
2007-10-18 12:38 ` CHABAL David
0 siblings, 1 reply; 30+ messages in thread
From: Philippe Gerum @ 2007-10-17 16:05 UTC (permalink / raw)
To: CHABAL David; +Cc: xenomai
On Wed, 2007-10-17 at 17:46 +0200, CHABAL David wrote:
> Philippe Gerum a écrit :
> > On Wed, 2007-10-17 at 16:52 +0200, CHABAL David wrote:
> >>> Grmmff... I think the PIC on this box has some deep troubles; please try
> >>> this patch, in replacement of the previous ipipe_trace_special
> >>> instrumentation:
> >>>
> >>
> >> RTD| 8.348| 10.387| 43.647| 0| 6.098|
> >> 80.440
> >> ---|------------|------------|------------|--------|-------------------------
> >> RTS| 6.098| 10.020| 80.440| 0| 00:17:20/00:17:20
> >> [root@domain.hid bin]#
> >>
> >>
> >> IRQ handling takes 17µs in the worst case.
> >>
> >> It takes a long time to write 3 poor bytes...
> >>
> >
> > Indeed. Each outb to the ISA bus should be somewhere in the 1-2.5 us
> > range depending on the hw, maybe a bit higher in case of contention, but
> > not that much.
> >
> >> May be is it a SMI problem ??? (Globally disable SMI is on)
> >>
> >
> > It's less likely with an ICH-2 chipset.
> >
> > I see that CONFIG_IDEDMA_PCI_AUTO is disabled. Any reason not to use PCI
> > DMA when available for IDE drives with your hw?
> >
>
> I read this about DMA:
> http://www.rtai.dk/cgi-bin/gratiswiki.pl?DMA_And_Jitter
>
As usual, usage of DMA in real-time situations is a trade-off, and
should be evaluated within the context of the hw at hand. DMA does bus
mastering, but OTOH, forcing PIO raises native Linux latencies, which
also has some drawbacks for real-time kernels implementing RT/non-RT
mode transitions for tasks like Xenomai and RTAI do. For this reason,
you may want to try switching PCI DMA on for your platform, until it
does prove bad latency-wise.
--
Philippe.
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-17 16:05 ` Philippe Gerum
@ 2007-10-18 12:38 ` CHABAL David
2007-10-18 13:18 ` Philippe Gerum
0 siblings, 1 reply; 30+ messages in thread
From: CHABAL David @ 2007-10-18 12:38 UTC (permalink / raw)
To: rpm; +Cc: xenomai
Philippe Gerum a écrit :
> On Wed, 2007-10-17 at 17:46 +0200, CHABAL David wrote:
>> Philippe Gerum a écrit :
>>> On Wed, 2007-10-17 at 16:52 +0200, CHABAL David wrote:
>>>>> Grmmff... I think the PIC on this box has some deep troubles; please try
>>>>> this patch, in replacement of the previous ipipe_trace_special
>>>>> instrumentation:
>>>>>
>>>> RTD| 8.348| 10.387| 43.647| 0| 6.098|
>>>> 80.440
>>>> ---|------------|------------|------------|--------|-------------------------
>>>> RTS| 6.098| 10.020| 80.440| 0| 00:17:20/00:17:20
>>>> [root@domain.hid bin]#
>>>>
>>>>
>>>> IRQ handling takes 17µs in the worst case.
>>>>
>>>> It takes a long time to write 3 poor bytes...
>>>>
>>> Indeed. Each outb to the ISA bus should be somewhere in the 1-2.5 us
>>> range depending on the hw, maybe a bit higher in case of contention, but
>>> not that much.
>>>
>>>> May be is it a SMI problem ??? (Globally disable SMI is on)
>>>>
>>> It's less likely with an ICH-2 chipset.
>>>
>>> I see that CONFIG_IDEDMA_PCI_AUTO is disabled. Any reason not to use PCI
>>> DMA when available for IDE drives with your hw?
>>>
>> I read this about DMA:
>> http://www.rtai.dk/cgi-bin/gratiswiki.pl?DMA_And_Jitter
>>
>
> As usual, usage of DMA in real-time situations is a trade-off, and
> should be evaluated within the context of the hw at hand. DMA does bus
> mastering, but OTOH, forcing PIO raises native Linux latencies, which
> also has some drawbacks for real-time kernels implementing RT/non-RT
> mode transitions for tasks like Xenomai and RTAI do. For this reason,
> you may want to try switching PCI DMA on for your platform, until it
> does prove bad latency-wise.
>
I tested it but the results are almost the same.
I will try to upgrade my kernel to the 2.6.22 and to test again.
David
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-18 12:38 ` CHABAL David
@ 2007-10-18 13:18 ` Philippe Gerum
2007-10-22 14:28 ` CHABAL David
0 siblings, 1 reply; 30+ messages in thread
From: Philippe Gerum @ 2007-10-18 13:18 UTC (permalink / raw)
To: CHABAL David; +Cc: xenomai
On Thu, 2007-10-18 at 14:38 +0200, CHABAL David wrote:
> Philippe Gerum a écrit :
> > On Wed, 2007-10-17 at 17:46 +0200, CHABAL David wrote:
> >> Philippe Gerum a écrit :
> >>> On Wed, 2007-10-17 at 16:52 +0200, CHABAL David wrote:
> >>>>> Grmmff... I think the PIC on this box has some deep troubles; please try
> >>>>> this patch, in replacement of the previous ipipe_trace_special
> >>>>> instrumentation:
> >>>>>
> >>>> RTD| 8.348| 10.387| 43.647| 0| 6.098|
> >>>> 80.440
> >>>> ---|------------|------------|------------|--------|-------------------------
> >>>> RTS| 6.098| 10.020| 80.440| 0| 00:17:20/00:17:20
> >>>> [root@domain.hid bin]#
> >>>>
> >>>>
> >>>> IRQ handling takes 17µs in the worst case.
> >>>>
> >>>> It takes a long time to write 3 poor bytes...
> >>>>
> >>> Indeed. Each outb to the ISA bus should be somewhere in the 1-2.5 us
> >>> range depending on the hw, maybe a bit higher in case of contention, but
> >>> not that much.
> >>>
> >>>> May be is it a SMI problem ??? (Globally disable SMI is on)
> >>>>
> >>> It's less likely with an ICH-2 chipset.
> >>>
> >>> I see that CONFIG_IDEDMA_PCI_AUTO is disabled. Any reason not to use PCI
> >>> DMA when available for IDE drives with your hw?
> >>>
> >> I read this about DMA:
> >> http://www.rtai.dk/cgi-bin/gratiswiki.pl?DMA_And_Jitter
> >>
> >
> > As usual, usage of DMA in real-time situations is a trade-off, and
> > should be evaluated within the context of the hw at hand. DMA does bus
> > mastering, but OTOH, forcing PIO raises native Linux latencies, which
> > also has some drawbacks for real-time kernels implementing RT/non-RT
> > mode transitions for tasks like Xenomai and RTAI do. For this reason,
> > you may want to try switching PCI DMA on for your platform, until it
> > does prove bad latency-wise.
> >
> I tested it but the results are almost the same.
>
Good, at least you get PCI DMA back.
> I will try to upgrade my kernel to the 2.6.22 and to test again.
>
At this point, it seems reasonable to think that your hw has some
problems. You may want to confirm this by measuring the time spent in
acknowledging interrupts on the slave i8259A in mask_and_ack_8259A(), on
an unpatched 2.6.20 kernel (e.g. using a couple of rdtscll() within a
single interrupt-free section). If you still reach peaks beyond 20us,
then the odds of having the very same issue with newer kernels are high.
> David
--
Philippe.
^ permalink raw reply [flat|nested] 30+ messages in thread
* Re: [Xenomai-help] awful latencies (~110us)
2007-10-18 13:18 ` Philippe Gerum
@ 2007-10-22 14:28 ` CHABAL David
0 siblings, 0 replies; 30+ messages in thread
From: CHABAL David @ 2007-10-22 14:28 UTC (permalink / raw)
To: rpm; +Cc: xenomai
Philippe Gerum a écrit :
> On Thu, 2007-10-18 at 14:38 +0200, CHABAL David wrote:
>> Philippe Gerum a écrit :
>>> On Wed, 2007-10-17 at 17:46 +0200, CHABAL David wrote:
>>>> Philippe Gerum a écrit :
>>>>> On Wed, 2007-10-17 at 16:52 +0200, CHABAL David wrote:
>>>>>>> Grmmff... I think the PIC on this box has some deep troubles; please try
>>>>>>> this patch, in replacement of the previous ipipe_trace_special
>>>>>>> instrumentation:
>>>>>>>
>>>>>> RTD| 8.348| 10.387| 43.647| 0| 6.098|
>>>>>> 80.440
>>>>>> ---|------------|------------|------------|--------|-------------------------
>>>>>> RTS| 6.098| 10.020| 80.440| 0| 00:17:20/00:17:20
>>>>>> [root@domain.hid bin]#
>>>>>>
>>>>>>
>>>>>> IRQ handling takes 17µs in the worst case.
>>>>>>
>>>>>> It takes a long time to write 3 poor bytes...
>>>>>>
>>>>> Indeed. Each outb to the ISA bus should be somewhere in the 1-2.5 us
>>>>> range depending on the hw, maybe a bit higher in case of contention, but
>>>>> not that much.
>>>>>
>>>>>> May be is it a SMI problem ??? (Globally disable SMI is on)
>>>>>>
>>>>> It's less likely with an ICH-2 chipset.
>>>>>
>>>>> I see that CONFIG_IDEDMA_PCI_AUTO is disabled. Any reason not to use PCI
>>>>> DMA when available for IDE drives with your hw?
>>>>>
>>>> I read this about DMA:
>>>> http://www.rtai.dk/cgi-bin/gratiswiki.pl?DMA_And_Jitter
>>>>
>>> As usual, usage of DMA in real-time situations is a trade-off, and
>>> should be evaluated within the context of the hw at hand. DMA does bus
>>> mastering, but OTOH, forcing PIO raises native Linux latencies, which
>>> also has some drawbacks for real-time kernels implementing RT/non-RT
>>> mode transitions for tasks like Xenomai and RTAI do. For this reason,
>>> you may want to try switching PCI DMA on for your platform, until it
>>> does prove bad latency-wise.
>>>
>> I tested it but the results are almost the same.
>>
>
> Good, at least you get PCI DMA back.
>
>> I will try to upgrade my kernel to the 2.6.22 and to test again.
>>
>
> At this point, it seems reasonable to think that your hw has some
> problems. You may want to confirm this by measuring the time spent in
> acknowledging interrupts on the slave i8259A in mask_and_ack_8259A(), on
> an unpatched 2.6.20 kernel (e.g. using a couple of rdtscll() within a
> single interrupt-free section). If you still reach peaks beyond 20us,
> then the odds of having the very same issue with newer kernels are high.
>
>> David
Right. Adeos and Xenomai are innocents. Without then and with rdtscll, I get until 35 µs for
an IRQ handling (!).
So, I will change my HW.
Thanks for your help.
David
^ permalink raw reply [flat|nested] 30+ messages in thread
end of thread, other threads:[~2007-10-22 14:28 UTC | newest]
Thread overview: 30+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2007-10-05 7:52 [Xenomai-help] awful latencies (~110us) CHABAL David
2007-10-05 8:30 ` Gilles Chanteperdrix
2007-10-05 9:04 ` CHABAL David
2007-10-05 9:20 ` Philippe Gerum
2007-10-05 10:29 ` CHABAL David
2007-10-05 12:35 ` Jan Kiszka
2007-10-05 14:02 ` Philippe Gerum
2007-10-08 12:46 ` CHABAL David
2007-10-10 11:30 ` Philippe Gerum
2007-10-12 14:05 ` CHABAL David
2007-10-12 14:21 ` Jan Kiszka
2007-10-12 14:26 ` CHABAL David
2007-10-12 15:34 ` Philippe Gerum
2007-10-12 15:49 ` Jan Kiszka
2007-10-12 16:43 ` Philippe Gerum
2007-10-17 8:25 ` CHABAL David
2007-10-17 8:41 ` Philippe Gerum
2007-10-17 8:55 ` CHABAL David
2007-10-17 9:17 ` Philippe Gerum
2007-10-17 13:14 ` CHABAL David
2007-10-17 13:46 ` Philippe Gerum
2007-10-17 14:52 ` CHABAL David
2007-10-17 15:24 ` Philippe Gerum
2007-10-17 15:46 ` CHABAL David
2007-10-17 16:05 ` Philippe Gerum
2007-10-18 12:38 ` CHABAL David
2007-10-18 13:18 ` Philippe Gerum
2007-10-22 14:28 ` CHABAL David
2007-10-17 8:56 ` Philippe Gerum
2007-10-17 8:43 ` Philippe Gerum
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.