2.6.15-rc5-rt2 slowness

Hi!

Thanks to Steven's Kconfig fixes I was able to compile 2.6.15-rc5 with Ingo's rt2-patch just fine.

I have two small problem with it, however. One is the Oops just posted, the other is a high system load and bad responsiveness of the system as a whole. I didn't even bother to measure timer/sleep jitters as the system was dog slow and the fans started to run a full speed nearly immediately.

We observed this on two different systems, one with the config attached to my mail with the Oops/backtrace.

I'll try to recompile the kernel with some debug options, if anyone knows if there's something I should specifically look for this may be helpful.

Greetings,

Gunter

Ok, I recompiled the kernel with some debug options and attached a /proc/latency_trace output, hoping it will be helpful to track down the problem...

Please tell me if there's anything else I should do.

Greetings,

Gunter

preemption latency trace v1.1.5 on 2.6.15-rc5-rt2.zb.20051216.1
--------------------------------------------------------------------
latency: 45 us, #94/94, CPU#0 | (M:rt VP:0, KP:0, SP:1 HP:1)

    -----------------
    | task: IRQ 12-733 (uid:0 nice:-5 policy:1 rt_prio:47)
    -----------------

                 _------=> CPU#            
                / _-----=> irqs-off        
               | / _----=> need-resched    
               || / _---=> hardirq/softirq 
               ||| / _--=> preempt-depth   
               |||| /                      
               |||||     delay             
   cmd     pid ||||| time  |   caller      
      \   /    |||||   \   |   /           
konquero-4635  0D.h3    0us : __trace_start_sched_wakeup (try_to_wake_up)
konquero-4635  0D.h3    1us : __trace_start_sched_wakeup <<...>-733> (34 0)
konquero-4635  0Dnh2    1us : try_to_wake_up <<...>-733> (34 74)
konquero-4635  0Dnh2    1us : check_raw_flags (try_to_wake_up)
konquero-4635  0Dnh1    1us : preempt_schedule (try_to_wake_up)
konquero-4635  0Dnh1    1us : wake_up_process (redirect_hardirq)
konquero-4635  0Dnh.    2us : preempt_schedule (__do_IRQ)
konquero-4635  0Dnh.    2us : irq_exit (do_IRQ)
konquero-4635  0Dn..    2us : __schedule (work_resched)
konquero-4635  0Dn..    3us : profile_hit (__schedule)
konquero-4635  0Dn.1    3us : sched_clock (__schedule)
konquero-4635  0D..2    5us : trace_array (__schedule)
konquero-4635  0D..2    6us : trace_array <<...>-733> (34 34)
konquero-4635  0D..2    6us : trace_array <konquero-4635> (74 78)
konquero-4635  0D..2    7us : trace_array <<...>-4458> (74 78)
konquero-4635  0D..2    7us : trace_array <<...>-4621> (75 78)
konquero-4635  0D..2    7us : trace_array <<...>-5894> (76 78)
konquero-4635  0D..2    8us : trace_array <<...>-5892> (77 78)
konquero-4635  0D..2    8us+: trace_array (__schedule)
   <...>-733   0D..2   11us : __switch_to (__schedule)
   <...>-733   0D..2   11us : __schedule <konquero-4635> (74 34)
   <...>-733   0D.h2   13us : do_IRQ (c030af09 0 0)
   <...>-733   0D.h3   13us+: mask_and_ack_8259A (__do_IRQ)
   <...>-733   0D.h4   16us : check_raw_flags (mask_and_ack_8259A)
   <...>-733   0D.h3   16us : redirect_hardirq (__do_IRQ)
   <...>-733   0D.h2   16us : handle_IRQ_event (__do_IRQ)
   <...>-733   0D.h2   17us : timer_interrupt (handle_IRQ_event)
   <...>-733   0D.h2   18us : handle_nextevent_tick_update (timer_interrupt)
   <...>-733   0D.h2   18us : hrtimer_interrupt (handle_nextevent_tick_update)
   <...>-733   0D.h2   19us : get_monotonic_clock (hrtimer_interrupt)
   <...>-733   0D.h2   19us : acpi_pm_read (get_monotonic_clock)
   <...>-733   0D.h2   20us : get_check_value (get_monotonic_clock)
   <...>-733   0D.h3   21us : check_raw_flags (get_check_value)
   <...>-733   0D.h2   21us : check_monotonic_clock (get_monotonic_clock)
   <...>-733   0D.h3   21us : check_raw_flags (check_monotonic_clock)
   <...>-733   0D.h2   22us : clockevents_set_next_event (hrtimer_interrupt)
   <...>-733   0D.h2   22us : get_monotonic_clock (clockevents_set_next_event)
   <...>-733   0D.h2   23us : acpi_pm_read (get_monotonic_clock)
   <...>-733   0D.h2   23us : get_check_value (get_monotonic_clock)
   <...>-733   0D.h3   24us : check_raw_flags (get_check_value)
   <...>-733   0D.h2   24us : check_monotonic_clock (get_monotonic_clock)
   <...>-733   0D.h3   24us : check_raw_flags (check_monotonic_clock)
   <...>-733   0D.h2   25us+: pit_next_event (clockevents_set_next_event)
   <...>-733   0D.h3   29us : check_raw_flags (pit_next_event)
   <...>-733   0D.h2   29us : handle_tick (handle_nextevent_tick_update)
   <...>-733   0D.h3   29us : do_timer (handle_tick)
   <...>-733   0D.h2   30us : handle_update (handle_nextevent_tick_update)
   <...>-733   0D.h2   30us : update_process_times (handle_update)
   <...>-733   0D.h2   31us : account_system_time (update_process_times)
   <...>-733   0D.h2   31us : run_local_timers (update_process_times)
   <...>-733   0D.h2   31us : raise_softirq (run_local_timers)
   <...>-733   0D.h2   32us : wakeup_softirqd (raise_softirq)
   <...>-733   0D.h2   32us : wake_up_process (wakeup_softirqd)
   <...>-733   0D.h2   32us : check_preempt_wakeup (wake_up_process)
   <...>-733   0D.h2   33us : try_to_wake_up (wake_up_process)
   <...>-733   0D.h3   33us : activate_task (try_to_wake_up)
   <...>-733   0D.h3   33us : sched_clock (activate_task)
   <...>-733   0D.h3   33us : activate_task <<...>-3> (62 6)
   <...>-733   0D.h3   33us : enqueue_task (activate_task)
   <...>-733   0D.h3   34us : check_raw_flags (try_to_wake_up)
   <...>-733   0D.h2   34us : wake_up_process (wakeup_softirqd)
   <...>-733   0D.h2   34us : check_raw_flags (raise_softirq)
   <...>-733   0D.h2   34us : rcu_pending (update_process_times)
   <...>-733   0D.h2   35us : rcu_check_callbacks (update_process_times)
   <...>-733   0D.h2   35us : rcu_try_flip (rcu_check_callbacks)
   <...>-733   0D.h3   36us : check_raw_flags (rcu_try_flip)
   <...>-733   0D.h3   36us : __rcu_advance_callbacks (rcu_check_callbacks)
   <...>-733   0D.h3   36us : check_raw_flags (rcu_check_callbacks)
   <...>-733   0D.h2   36us : __tasklet_schedule (rcu_check_callbacks)
   <...>-733   0D.h2   37us : wakeup_softirqd (__tasklet_schedule)
   <...>-733   0D.h2   37us : wake_up_process (wakeup_softirqd)
   <...>-733   0D.h2   37us : check_preempt_wakeup (wake_up_process)
   <...>-733   0D.h2   38us : try_to_wake_up (wake_up_process)
   <...>-733   0D.h3   38us : activate_task (try_to_wake_up)
   <...>-733   0D.h3   38us : sched_clock (activate_task)
   <...>-733   0D.h3   38us : activate_task <<...>-7> (62 7)
   <...>-733   0D.h3   38us : enqueue_task (activate_task)
   <...>-733   0D.h3   39us : check_raw_flags (try_to_wake_up)
   <...>-733   0D.h2   39us : wake_up_process (wakeup_softirqd)
   <...>-733   0D.h2   39us : check_raw_flags (__tasklet_schedule)
   <...>-733   0D.h2   39us : scheduler_tick (update_process_times)
   <...>-733   0D.h2   39us : sched_clock (scheduler_tick)
   <...>-733   0D.h2   40us : softlockup_tick (update_process_times)
   <...>-733   0D.h2   40us : touch_light_softlockup_watchdog (softlockup_tick)
   <...>-733   0D.h3   41us : note_interrupt (__do_IRQ)
   <...>-733   0D.h3   41us : enable_8259A_irq (__do_IRQ)
   <...>-733   0D.h4   42us : check_raw_flags (enable_8259A_irq)
   <...>-733   0D.h2   43us : irq_exit (do_IRQ)
   <...>-733   0D..2   43us < (608)
   <...>-733   0...1   43us : trace_stop_sched_switched (__schedule)
   <...>-733   0D..2   44us : trace_stop_sched_switched <<...>-733> (34 0)
   <...>-733   0D..2   45us : trace_stop_sched_switched (__schedule)

vim:ft=help

Hi!

Some further info:

,----[ cat rcuctrs rcugp rcuptrs rcustats schedstat ]

| CPU last cur
|   0    0   0
| ggp = 36340
| oldggp=36343  newggp=36354
| nl=c07fd218/c96abee8 nt=c94eae1c
|  wl=c07fd220/00000000 wt=c07fd220 dl=c07fd228/00000000 dt=c07fd228
| ggp=36368 lgp=36368 rcc=36368
| na=135275 nl=3 wa=135272 wl=0 da=135272 dl=0 dr=135272 di=135272
| rtf1=36624 rtf2=36624 rtf3=36368 rtfe1=0 rtfe2=0 rtfe3=256
| version 12
| timestamp 80698
| cpu0 0 0 4 4 736 1123111 85725 0 0 92271 332649 1037386

`----

.config of the currently running kernel is attached.

The system I'm trying this on is a Celeron-M 1,5 GHz Notebook with an i865 chipset. The CPU was forced to ACPI C0 state:

# cat /sys/module/processor/parameters/max_cstate
0

cpufreq scaling governor is set to "performance".

Greetings,

Gunter

#
# Automatically generated make config: don't edit # Linux kernel version: 2.6.15-rc5-rt2.zb.20051216.2 # Fri Dec 16 12:16:58 2005
#
CONFIG_X86_32=y
CONFIG_GENERIC_TIME=y CONFIG_SEMAPHORE_SLEEPERS=y
CONFIG_X86=y
CONFIG_MMU=y
CONFIG_UID16=y
CONFIG_GENERIC_ISA_DMA=y CONFIG_GENERIC_IOMAP=y CONFIG_ARCH_MAY_HAVE_PC_FDC=y

#
# Code maturity level options
#
CONFIG_EXPERIMENTAL=y
CONFIG_CLEAN_COMPILE=y
CONFIG_BROKEN_ON_SMP=y
CONFIG_LOCK_KERNEL=y
CONFIG_INIT_ENV_ARG_LIMIT=32

#
# General setup
#
CONFIG_LOCALVERSION=""
CONFIG_LOCALVERSION_AUTO=y
CONFIG_SWAP=y
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
# CONFIG_BSD_PROCESS_ACCT is not set
CONFIG_SYSCTL=y
# CONFIG_AUDIT is not set
CONFIG_HOTPLUG=y
CONFIG_KOBJECT_UEVENT=y
CONFIG_IKCONFIG=y
CONFIG_IKCONFIG_PROC=y
CONFIG_INITRAMFS_SOURCE=""
# CONFIG_EMBEDDED is not set
CONFIG_KALLSYMS=y
# CONFIG_KALLSYMS_ALL is not set
# CONFIG_KALLSYMS_EXTRA_PASS is not set
CONFIG_PRINTK=y
CONFIG_BUG=y
CONFIG_BASE_FULL=y
CONFIG_FUTEX=y
CONFIG_EPOLL=y
CONFIG_SHMEM=y
CONFIG_CC_ALIGN_FUNCTIONS=0
CONFIG_CC_ALIGN_LABELS=0
CONFIG_CC_ALIGN_LOOPS=0
CONFIG_CC_ALIGN_JUMPS=0
# CONFIG_TINY_SHMEM is not set
CONFIG_BASE_SMALL=0
CONFIG_SLOB=y

#
# Loadable module support
#
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
# CONFIG_MODULE_FORCE_UNLOAD is not set
CONFIG_OBSOLETE_MODPARM=y
# CONFIG_MODVERSIONS is not set
# CONFIG_MODULE_SRCVERSION_ALL is not set
CONFIG_KMOD=y

#
# Block layer
#
# CONFIG_LBD is not set

#
# IO Schedulers
#
CONFIG_IOSCHED_NOOP=y
CONFIG_IOSCHED_AS=y
CONFIG_IOSCHED_DEADLINE=y
CONFIG_IOSCHED_CFQ=y
# CONFIG_DEFAULT_AS is not set
# CONFIG_DEFAULT_DEADLINE is not set
CONFIG_DEFAULT_CFQ=y
# CONFIG_DEFAULT_NOOP is not set
CONFIG_DEFAULT_IOSCHED="cfq"

#
# Processor type and features
#
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_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_MCYRIXIII is not set
# CONFIG_MVIAC3_2 is not set
# CONFIG_X86_GENERIC is not set
CONFIG_X86_CMPXCHG=y
CONFIG_X86_XADD=y
CONFIG_X86_L1_CACHE_SHIFT=5
CONFIG_RWSEM_GENERIC_SPINLOCK=y
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_HIGH_RES_TIMERS=y
CONFIG_HIGH_RES_RESOLUTION=1000
# CONFIG_SMP is not set
# CONFIG_PREEMPT_NONE is not set
# CONFIG_PREEMPT_VOLUNTARY is not set
# CONFIG_PREEMPT_DESKTOP is not set
CONFIG_PREEMPT_RT=y
CONFIG_PREEMPT=y
CONFIG_PREEMPT_SOFTIRQS=y
CONFIG_PREEMPT_HARDIRQS=y
CONFIG_PREEMPT_BKL=y
CONFIG_PREEMPT_RCU=y
CONFIG_RCU_STATS=y
CONFIG_ASM_SEMAPHORES=y
CONFIG_X86_UP_APIC=y
CONFIG_X86_UP_IOAPIC=y
CONFIG_X86_LOCAL_APIC=y
CONFIG_X86_IO_APIC=y
CONFIG_X86_MCE=y
CONFIG_X86_MCE_NONFATAL=y
# CONFIG_X86_MCE_P4THERMAL is not set
# CONFIG_TOSHIBA is not set
# CONFIG_I8K is not set
# CONFIG_X86_REBOOTFIXUPS is not set
CONFIG_MICROCODE=m
CONFIG_X86_MSR=m
CONFIG_X86_CPUID=m

#
# Firmware Drivers
#
# CONFIG_EDD is not set
# 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_SELECT_MEMORY_MODEL=y
CONFIG_FLATMEM_MANUAL=y
# CONFIG_DISCONTIGMEM_MANUAL is not set
# CONFIG_SPARSEMEM_MANUAL is not set
CONFIG_FLATMEM=y
CONFIG_FLAT_NODE_MEM_MAP=y
# CONFIG_SPARSEMEM_STATIC is not set
CONFIG_SPLIT_PTLOCK_CPUS=4
# CONFIG_MATH_EMULATION is not set
CONFIG_MTRR=y
# CONFIG_EFI is not set
CONFIG_SECCOMP=y
# CONFIG_HZ_100 is not set
CONFIG_HZ_250=y
# CONFIG_HZ_1000 is not set
CONFIG_HZ=250
CONFIG_PHYSICAL_START=0x100000
# CONFIG_KEXEC is not set

#
# Power management options (ACPI, APM)
#
CONFIG_PM=y
# CONFIG_PM_LEGACY is not set
# CONFIG_PM_DEBUG 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=y
# CONFIG_ACPI_HOTKEY is not set
CONFIG_ACPI_FAN=y
CONFIG_ACPI_PROCESSOR=y
CONFIG_ACPI_THERMAL=y
# CONFIG_ACPI_ASUS is not set
# CONFIG_ACPI_IBM is not set
# CONFIG_ACPI_TOSHIBA is not set
# CONFIG_ACPI_CUSTOM_DSDT 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
CONFIG_ACPI_CONTAINER=y

#
# APM (Advanced Power Management) BIOS Support
#

#
# CPU Frequency scaling
#
CONFIG_CPU_FREQ=y
CONFIG_CPU_FREQ_TABLE=y
# CONFIG_CPU_FREQ_DEBUG is not set CONFIG_CPU_FREQ_STAT=y
# CONFIG_CPU_FREQ_STAT_DETAILS is not set
# CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE is not set CONFIG_CPU_FREQ_DEFAULT_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_PERFORMANCE=y CONFIG_CPU_FREQ_GOV_POWERSAVE=y CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_ONDEMAND=y CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y

#
# CPUFreq processor drivers
#
# CONFIG_X86_ACPI_CPUFREQ is not set
# CONFIG_X86_POWERNOW_K6 is not set
# CONFIG_X86_POWERNOW_K7 is not set
# CONFIG_X86_POWERNOW_K8 is not set
# CONFIG_X86_GX_SUSPMOD is not set
# CONFIG_X86_SPEEDSTEP_CENTRINO is not set
CONFIG_X86_SPEEDSTEP_ICH=y
# CONFIG_X86_SPEEDSTEP_SMI is not set
CONFIG_X86_P4_CLOCKMOD=y
# CONFIG_X86_CPUFREQ_NFORCE2 is not set
# CONFIG_X86_LONGRUN is not set
# CONFIG_X86_LONGHAUL is not set

#

# shared options
#
CONFIG_X86_SPEEDSTEP_LIB=y
CONFIG_X86_SPEEDSTEP_RELAXED_CAP_CHECK=y

#
# 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_PCI_MSI is not set
# CONFIG_PCI_LEGACY_PROC is not set
# CONFIG_PCI_DEBUG 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=m
# CONFIG_PCMCIA_DEBUG is not set
CONFIG_PCMCIA=m
CONFIG_PCMCIA_LOAD_CIS=y
CONFIG_PCMCIA_IOCTL=y
CONFIG_CARDBUS=y

#
# PC-card bridges
#
CONFIG_YENTA=m
# CONFIG_PD6729 is not set
# CONFIG_I82092 is not set
# CONFIG_I82365 is not set
# CONFIG_TCIC is not set
CONFIG_PCMCIA_PROBE=y
CONFIG_PCCARD_NONSTATIC=m

#
# PCI Hotplug Support
#
# CONFIG_HOTPLUG_PCI is not set

#
# Executable file formats
#
CONFIG_BINFMT_ELF=y
# CONFIG_BINFMT_AOUT is not set
CONFIG_BINFMT_MISC=y

#
# Networking
#
CONFIG_NET=y

#
# Networking options
#
CONFIG_PACKET=y
CONFIG_PACKET_MMAP=y
CONFIG_UNIX=y
CONFIG_XFRM=y
CONFIG_XFRM_USER=y
CONFIG_NET_KEY=y
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=y
CONFIG_NET_IPGRE=y
# CONFIG_ARPD is not set
CONFIG_SYN_COOKIES=y
CONFIG_INET_AH=y
CONFIG_INET_ESP=y
CONFIG_INET_IPCOMP=y
CONFIG_INET_TUNNEL=y
CONFIG_INET_DIAG=m
CONFIG_INET_TCP_DIAG=m
# CONFIG_TCP_CONG_ADVANCED is not set
CONFIG_TCP_CONG_BIC=y

#
# IP: Virtual Server Configuration
#
# CONFIG_IP_VS is not set
# CONFIG_IPV6 is not set
CONFIG_NETFILTER=y
# CONFIG_NETFILTER_DEBUG is not set

#
# Core Netfilter Configuration
#
CONFIG_NETFILTER_NETLINK=m
CONFIG_NETFILTER_NETLINK_QUEUE=m
CONFIG_NETFILTER_NETLINK_LOG=m

#
# IP: Netfilter Configuration
#
CONFIG_IP_NF_CONNTRACK=m
CONFIG_IP_NF_CT_ACCT=y
CONFIG_IP_NF_CONNTRACK_MARK=y
# CONFIG_IP_NF_CONNTRACK_EVENTS is not set
CONFIG_IP_NF_CONNTRACK_NETLINK=m
CONFIG_IP_NF_CT_PROTO_SCTP=m
CONFIG_IP_NF_FTP=m
CONFIG_IP_NF_IRC=m
CONFIG_IP_NF_NETBIOS_NS=m
CONFIG_IP_NF_TFTP=m
CONFIG_IP_NF_AMANDA=m
CONFIG_IP_NF_PPTP=m
CONFIG_IP_NF_QUEUE=m
CONFIG_IP_NF_IPTABLES=y
CONFIG_IP_NF_MATCH_LIMIT=m
CONFIG_IP_NF_MATCH_IPRANGE=m
CONFIG_IP_NF_MATCH_MAC=m
CONFIG_IP_NF_MATCH_PKTTYPE=m
CONFIG_IP_NF_MATCH_MARK=m
CONFIG_IP_NF_MATCH_MULTIPORT=m
CONFIG_IP_NF_MATCH_TOS=m
CONFIG_IP_NF_MATCH_RECENT=m
CONFIG_IP_NF_MATCH_ECN=m
CONFIG_IP_NF_MATCH_DSCP=m
CONFIG_IP_NF_MATCH_AH_ESP=m
CONFIG_IP_NF_MATCH_LENGTH=m
CONFIG_IP_NF_MATCH_TTL=m
CONFIG_IP_NF_MATCH_TCPMSS=m
CONFIG_IP_NF_MATCH_HELPER=m
CONFIG_IP_NF_MATCH_STATE=m
CONFIG_IP_NF_MATCH_CONNTRACK=m
CONFIG_IP_NF_MATCH_OWNER=m
CONFIG_IP_NF_MATCH_ADDRTYPE=m
CONFIG_IP_NF_MATCH_REALM=m
CONFIG_IP_NF_MATCH_SCTP=m
CONFIG_IP_NF_MATCH_DCCP=m
CONFIG_IP_NF_MATCH_COMMENT=m
CONFIG_IP_NF_MATCH_CONNMARK=m
CONFIG_IP_NF_MATCH_CONNBYTES=m
CONFIG_IP_NF_MATCH_HASHLIMIT=m
CONFIG_IP_NF_MATCH_STRING=m
CONFIG_IP_NF_FILTER=m
CONFIG_IP_NF_TARGET_REJECT=m
CONFIG_IP_NF_TARGET_LOG=m
CONFIG_IP_NF_TARGET_ULOG=m
CONFIG_IP_NF_TARGET_TCPMSS=m
CONFIG_IP_NF_TARGET_NFQUEUE=m
CONFIG_IP_NF_NAT=m
CONFIG_IP_NF_NAT_NEEDED=y
CONFIG_IP_NF_TARGET_MASQUERADE=m
CONFIG_IP_NF_TARGET_REDIRECT=m
CONFIG_IP_NF_TARGET_NETMAP=m
CONFIG_IP_NF_TARGET_SAME=m
CONFIG_IP_NF_NAT_SNMP_BASIC=m
CONFIG_IP_NF_NAT_IRC=m
CONFIG_IP_NF_NAT_FTP=m
CONFIG_IP_NF_NAT_TFTP=m
CONFIG_IP_NF_NAT_AMANDA=m
CONFIG_IP_NF_NAT_PPTP=m
CONFIG_IP_NF_MANGLE=m
CONFIG_IP_NF_TARGET_TOS=m
CONFIG_IP_NF_TARGET_ECN=m
CONFIG_IP_NF_TARGET_DSCP=m
CONFIG_IP_NF_TARGET_MARK=m
CONFIG_IP_NF_TARGET_CLASSIFY=m
CONFIG_IP_NF_TARGET_TTL=m
CONFIG_IP_NF_TARGET_CONNMARK=m
CONFIG_IP_NF_TARGET_CLUSTERIP=m
CONFIG_IP_NF_RAW=m
CONFIG_IP_NF_TARGET_NOTRACK=m
CONFIG_IP_NF_ARPTABLES=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m

#
# DCCP Configuration (EXPERIMENTAL)
#
CONFIG_IP_DCCP=m
CONFIG_INET_DCCP_DIAG=m

#
# DCCP CCIDs Configuration (EXPERIMENTAL)
#
CONFIG_IP_DCCP_CCID3=m
CONFIG_IP_DCCP_TFRC_LIB=m

#
# DCCP Kernel Hacking
#
# CONFIG_IP_DCCP_DEBUG is not set
# CONFIG_IP_DCCP_UNLOAD_HACK is not set

#
# SCTP Configuration (EXPERIMENTAL)
#
# CONFIG_IP_SCTP is not set
# CONFIG_ATM 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
# CONFIG_X25 is not set
# CONFIG_LAPB is not set
# CONFIG_NET_DIVERT is not set
# CONFIG_ECONET is not set
# CONFIG_WAN_ROUTER is not set

#
# QoS and/or fair queueing
#
CONFIG_NET_SCHED=y
# CONFIG_NET_SCH_CLK_JIFFIES is not set
# CONFIG_NET_SCH_CLK_GETTIMEOFDAY is not set
CONFIG_NET_SCH_CLK_CPU=y

#
# Queueing/Scheduling
#
# CONFIG_NET_SCH_CBQ is not set
CONFIG_NET_SCH_HTB=m
# CONFIG_NET_SCH_HFSC is not set
# CONFIG_NET_SCH_PRIO is not set
# CONFIG_NET_SCH_RED is not set
CONFIG_NET_SCH_SFQ=m
# CONFIG_NET_SCH_TEQL is not set
# CONFIG_NET_SCH_TBF is not set
# CONFIG_NET_SCH_GRED is not set
# CONFIG_NET_SCH_DSMARK is not set
# CONFIG_NET_SCH_NETEM is not set
# CONFIG_NET_SCH_INGRESS is not set

#
# Classification
#
CONFIG_NET_CLS=y
CONFIG_NET_CLS_BASIC=m
# CONFIG_NET_CLS_TCINDEX is not set
# CONFIG_NET_CLS_ROUTE4 is not set
CONFIG_NET_CLS_ROUTE=y
CONFIG_NET_CLS_FW=m
CONFIG_NET_CLS_U32=m
CONFIG_CLS_U32_PERF=y
CONFIG_CLS_U32_MARK=y
CONFIG_NET_CLS_RSVP=m
CONFIG_NET_CLS_RSVP6=m
CONFIG_NET_EMATCH=y
CONFIG_NET_EMATCH_STACK=32
CONFIG_NET_EMATCH_CMP=m
CONFIG_NET_EMATCH_NBYTE=m
CONFIG_NET_EMATCH_U32=m
CONFIG_NET_EMATCH_META=m
CONFIG_NET_EMATCH_TEXT=m
CONFIG_NET_CLS_ACT=y
CONFIG_NET_ACT_POLICE=m
CONFIG_NET_ACT_GACT=m
CONFIG_GACT_PROB=y
CONFIG_NET_ACT_MIRRED=m
CONFIG_NET_ACT_IPT=m
CONFIG_NET_ACT_PEDIT=m
CONFIG_NET_ACT_SIMP=m
# CONFIG_NET_CLS_IND is not set
CONFIG_NET_ESTIMATOR=y

#
# Network testing
#
# CONFIG_NET_PKTGEN is not set
# CONFIG_HAMRADIO is not set
# CONFIG_IRDA is not set
CONFIG_BT=m
CONFIG_BT_L2CAP=m
CONFIG_BT_SCO=m
CONFIG_BT_RFCOMM=m
CONFIG_BT_RFCOMM_TTY=y
CONFIG_BT_BNEP=m
# CONFIG_BT_BNEP_MC_FILTER is not set
# CONFIG_BT_BNEP_PROTO_FILTER is not set
CONFIG_BT_HIDP=m

#
# Bluetooth device drivers
#
CONFIG_BT_HCIUSB=m
CONFIG_BT_HCIUSB_SCO=y
# CONFIG_BT_HCIUART is not set
# CONFIG_BT_HCIBCM203X is not set
# CONFIG_BT_HCIBPA10X is not set
# CONFIG_BT_HCIBFUSB is not set
# CONFIG_BT_HCIDTL1 is not set
# CONFIG_BT_HCIBT3C is not set
# CONFIG_BT_HCIBLUECARD is not set
# CONFIG_BT_HCIBTUART is not set
# CONFIG_BT_HCIVHCI is not set
CONFIG_IEEE80211=m
# CONFIG_IEEE80211_DEBUG is not set
CONFIG_IEEE80211_CRYPT_WEP=m
CONFIG_IEEE80211_CRYPT_CCMP=m
CONFIG_IEEE80211_CRYPT_TKIP=m

#
# Device Drivers
#

#
# Generic Driver Options
#
# CONFIG_STANDALONE is not set
# CONFIG_PREVENT_FIRMWARE_BUILD is not set
CONFIG_FW_LOADER=y
# CONFIG_DEBUG_DRIVER 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
# CONFIG_PNPBIOS is not set
CONFIG_PNPACPI=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_UMEM is not set
# CONFIG_BLK_DEV_COW_COMMON is not set
CONFIG_BLK_DEV_LOOP=m
CONFIG_BLK_DEV_CRYPTOLOOP=m
CONFIG_BLK_DEV_NBD=m
# CONFIG_BLK_DEV_SX8 is not set
# CONFIG_BLK_DEV_UB is not set
# CONFIG_BLK_DEV_RAM is not set
CONFIG_BLK_DEV_RAM_COUNT=16
CONFIG_CDROM_PKTCDVD=m
CONFIG_CDROM_PKTCDVD_BUFFERS=8
# CONFIG_CDROM_PKTCDVD_WCACHE is not set
# CONFIG_ATA_OVER_ETH 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 is not set
# CONFIG_BLK_DEV_IDECS is not set CONFIG_BLK_DEV_IDECD=m
# CONFIG_BLK_DEV_IDETAPE is not set
# CONFIG_BLK_DEV_IDEFLOPPY is not set
# CONFIG_BLK_DEV_IDESCSI is not set
# CONFIG_IDE_TASK_IOCTL is not set

#
# IDE chipset support/bugfixes
#
CONFIG_IDE_GENERIC=y
# CONFIG_BLK_DEV_CMD640 is not set
# CONFIG_BLK_DEV_IDEPNP is not set
CONFIG_BLK_DEV_IDEPCI=y
# CONFIG_IDEPCI_SHARE_IRQ is not set
# CONFIG_BLK_DEV_OFFBOARD is not set
CONFIG_BLK_DEV_GENERIC=y
# CONFIG_BLK_DEV_OPTI621 is not set
# 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=y
# CONFIG_IDEDMA_ONLYDISK 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_CS5520 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_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=y
# CONFIG_BLK_DEV_HD is not set

#
# SCSI device support
#
# CONFIG_RAID_ATTRS is not set
CONFIG_SCSI=m
CONFIG_SCSI_PROC_FS=y

#
# SCSI support type (disk, tape, CD-ROM)
#
CONFIG_BLK_DEV_SD=m
# CONFIG_CHR_DEV_ST is not set
# CONFIG_CHR_DEV_OSST is not set
# CONFIG_BLK_DEV_SR is not set
# CONFIG_CHR_DEV_SG is not set
# CONFIG_CHR_DEV_SCH is not set

#
# Some SCSI devices (e.g. CD jukebox) support multiple LUNs #
# CONFIG_SCSI_MULTI_LUN is not set
# CONFIG_SCSI_CONSTANTS is not set
# CONFIG_SCSI_LOGGING is not set

#
# SCSI Transport Attributes
#
# CONFIG_SCSI_SPI_ATTRS is not set
# CONFIG_SCSI_FC_ATTRS is not set
# CONFIG_SCSI_ISCSI_ATTRS is not set
# CONFIG_SCSI_SAS_ATTRS is not set

#
# SCSI low-level drivers
#
# CONFIG_ISCSI_TCP is not set
# CONFIG_BLK_DEV_3W_XXXX_RAID is not set
# CONFIG_SCSI_3W_9XXX is not set
# CONFIG_SCSI_7000FASST is not set
# CONFIG_SCSI_ACARD is not set
# CONFIG_SCSI_AHA152X is not set
# CONFIG_SCSI_AHA1542 is not set
# CONFIG_SCSI_AACRAID is not set
# CONFIG_SCSI_AIC7XXX is not set
# CONFIG_SCSI_AIC7XXX_OLD is not set
# CONFIG_SCSI_AIC79XX is not set
# CONFIG_SCSI_DPT_I2O is not set
# CONFIG_SCSI_IN2000 is not set
# CONFIG_MEGARAID_NEWGEN is not set
# CONFIG_MEGARAID_LEGACY is not set
# CONFIG_MEGARAID_SAS is not set
# CONFIG_SCSI_SATA is not set
# CONFIG_SCSI_BUSLOGIC is not set
# CONFIG_SCSI_DMX3191D is not set
# CONFIG_SCSI_DTC3280 is not set
# CONFIG_SCSI_EATA is not set
# CONFIG_SCSI_FUTURE_DOMAIN is not set
# CONFIG_SCSI_GDTH is not set
# CONFIG_SCSI_GENERIC_NCR5380 is not set
# CONFIG_SCSI_GENERIC_NCR5380_MMIO is not set
# CONFIG_SCSI_IPS is not set
# CONFIG_SCSI_INITIO is not set
# CONFIG_SCSI_INIA100 is not set
# CONFIG_SCSI_NCR53C406A is not set
# CONFIG_SCSI_SYM53C8XX_2 is not set
# CONFIG_SCSI_IPR is not set
# CONFIG_SCSI_PAS16 is not set
# CONFIG_SCSI_PSI240I is not set
# CONFIG_SCSI_QLOGIC_FAS is not set
# CONFIG_SCSI_QLOGIC_FC is not set
# CONFIG_SCSI_QLOGIC_1280 is not set
CONFIG_SCSI_QLA2XXX=m
# CONFIG_SCSI_QLA21XX is not set
# CONFIG_SCSI_QLA22XX is not set
# CONFIG_SCSI_QLA2300 is not set
# CONFIG_SCSI_QLA2322 is not set
# CONFIG_SCSI_QLA6312 is not set
# CONFIG_SCSI_QLA24XX is not set
# CONFIG_SCSI_LPFC is not set
# CONFIG_SCSI_SYM53C416 is not set
# CONFIG_SCSI_DC395x is not set
# CONFIG_SCSI_DC390T is not set
# CONFIG_SCSI_T128 is not set
# CONFIG_SCSI_U14_34F is not set
# CONFIG_SCSI_ULTRASTOR is not set
# CONFIG_SCSI_NSP32 is not set
# CONFIG_SCSI_DEBUG is not set

#
# PCMCIA SCSI adapter support
#
# CONFIG_PCMCIA_AHA152X is not set
# CONFIG_PCMCIA_FDOMAIN is not set
# CONFIG_PCMCIA_NINJA_SCSI is not set
# CONFIG_PCMCIA_QLOGIC is not set
# CONFIG_PCMCIA_SYM53C500 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
# CONFIG_FUSION_SPI is not set
# CONFIG_FUSION_FC is not set
# CONFIG_FUSION_SAS is not set

#
# IEEE 1394 (FireWire) support
#
CONFIG_IEEE1394=y

#
# Subsystem Options
#
# CONFIG_IEEE1394_VERBOSEDEBUG is not set
# CONFIG_IEEE1394_OUI_DB is not set
CONFIG_IEEE1394_EXTRA_CONFIG_ROMS=y
CONFIG_IEEE1394_CONFIG_ROM_IP1394=y
# CONFIG_IEEE1394_EXPORT_FULL_API is not set

#
# Device Drivers
#

#
# Texas Instruments PCILynx requires I2C
#
CONFIG_IEEE1394_OHCI1394=m

#
# Protocol Drivers
#
CONFIG_IEEE1394_VIDEO1394=m
CONFIG_IEEE1394_SBP2=m
# CONFIG_IEEE1394_SBP2_PHYS_DMA is not set
CONFIG_IEEE1394_ETH1394=m
CONFIG_IEEE1394_DV1394=m
CONFIG_IEEE1394_RAWIO=m
CONFIG_IEEE1394_CMP=m
CONFIG_IEEE1394_AMDTP=m

#
# I2O device support
#
# CONFIG_I2O is not set

#
# Network device support
#
CONFIG_NETDEVICES=y
CONFIG_DUMMY=y
# CONFIG_BONDING is not set
# CONFIG_EQUALIZER is not set
CONFIG_TUN=y
# 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 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_AT1700 is not set
# CONFIG_DEPCA is not set
# CONFIG_HP100 is not set
# CONFIG_NET_ISA is not set
CONFIG_NET_PCI=y
# CONFIG_PCNET32 is not set
# CONFIG_AMD8111_ETH is not set
# CONFIG_ADAPTEC_STARFIRE is not set
# CONFIG_AC3200 is not set
# CONFIG_APRICOT is not set
# CONFIG_B44 is not set
# CONFIG_FORCEDETH is not set
# CONFIG_CS89x0 is not set
# CONFIG_DGRS is not set
CONFIG_EEPRO100=m
CONFIG_E100=m
# CONFIG_FEALNX is not set
# CONFIG_NATSEMI is not set
# CONFIG_NE2K_PCI is not set
# CONFIG_8139CP is not set
CONFIG_8139TOO=y
CONFIG_8139TOO_PIO=y
# CONFIG_8139TOO_TUNE_TWISTER is not set
# CONFIG_8139TOO_8129 is not set
# CONFIG_8139_OLD_RX_RESET is not set
# CONFIG_SIS900 is not set
# CONFIG_EPIC100 is not set
# CONFIG_SUNDANCE is not set
# CONFIG_TLAN is not set
# CONFIG_VIA_RHINE 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_YELLOWFIN is not set
# CONFIG_R8169 is not set
# CONFIG_SIS190 is not set
# CONFIG_SKGE is not set
# CONFIG_SK98LIN is not set
# CONFIG_VIA_VELOCITY is not set
# CONFIG_TIGON3 is not set
# CONFIG_BNX2 is not set

#
# Ethernet (10000 Mbit)
#
# CONFIG_CHELSIO_T1 is not set
# CONFIG_IXGB is not set
# CONFIG_S2IO is not set

#
# Token Ring devices
#
# CONFIG_TR is not set

#
# Wireless LAN (non-hamradio)
#
CONFIG_NET_RADIO=y

#
# Obsolete Wireless cards support (pre-802.11)
#
# CONFIG_STRIP is not set
# CONFIG_ARLAN is not set
# CONFIG_WAVELAN is not set
# CONFIG_PCMCIA_WAVELAN is not set
# CONFIG_PCMCIA_NETWAVE is not set

#
# Wireless 802.11 Frequency Hopping cards support
#
# CONFIG_PCMCIA_RAYCS is not set

#
# Wireless 802.11b ISA/PCI cards support
#
# CONFIG_IPW2100 is not set
# CONFIG_IPW2200 is not set
# CONFIG_AIRO is not set
# CONFIG_HERMES is not set
# CONFIG_ATMEL is not set

#
# Wireless 802.11b Pcmcia/Cardbus cards support
#
# CONFIG_AIRO_CS is not set
# CONFIG_PCMCIA_WL3501 is not set

#
# Prism GT/Duette 802.11(a/b/g) PCI/Cardbus support #
CONFIG_PRISM54=m
# CONFIG_HOSTAP is not set CONFIG_NET_WIRELESS=y

#
# PCMCIA network device support
#
# CONFIG_NET_PCMCIA is not set

#
# Wan interfaces
#
# CONFIG_WAN is not set
# CONFIG_FDDI is not set
# CONFIG_HIPPI is not set
CONFIG_PPP=m
# CONFIG_PPP_MULTILINK is not set
CONFIG_PPP_FILTER=y
CONFIG_PPP_ASYNC=m
CONFIG_PPP_SYNC_TTY=m
CONFIG_PPP_DEFLATE=m
CONFIG_PPP_BSDCOMP=m
# CONFIG_PPP_MPPE is not set
CONFIG_PPPOE=m
# CONFIG_SLIP is not set
# CONFIG_NET_FC is not set
# CONFIG_SHAPER is not set
# CONFIG_NETCONSOLE 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

#
# Userland interfaces
#
CONFIG_INPUT_MOUSEDEV=y
CONFIG_INPUT_MOUSEDEV_PSAUX=y
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=y
# 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_INPUT_MOUSE=y
CONFIG_MOUSE_PS2=y
CONFIG_MOUSE_SERIAL=m
# 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=y
CONFIG_INPUT_PCSPKR=y
# CONFIG_INPUT_WISTRON_BTNS is not set
CONFIG_INPUT_UINPUT=m

#
# Hardware I/O ports
#
CONFIG_SERIO=y
CONFIG_SERIO_I8042=y
CONFIG_SERIO_SERPORT=m
# CONFIG_SERIO_CT82C710 is not set
# CONFIG_SERIO_PCIPS2 is not set
CONFIG_SERIO_LIBPS2=y
# CONFIG_SERIO_RAW is not set
# CONFIG_GAMEPORT is not set

#
# Character devices
#
CONFIG_VT=y
CONFIG_VT_CONSOLE=y
CONFIG_HW_CONSOLE=y
# CONFIG_SERIAL_NONSTANDARD is not set

#
# Serial drivers
#
# CONFIG_SERIAL_8250 is not set

#
# Non-8250 serial port support
#
# 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 is not set
CONFIG_NVRAM=m
CONFIG_RTC=y
# CONFIG_RTC_HISTOGRAM is not set
# CONFIG_BLOCKER is not set
# CONFIG_LPPTEST is not set
# CONFIG_DTLK is not set
# CONFIG_R3964 is not set
# CONFIG_APPLICOM is not set
# CONFIG_SONYPI is not set

#
# Ftape, the floppy tape device driver
#
# CONFIG_FTAPE 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=y
# 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=y
# CONFIG_DRM_TDFX is not set
# CONFIG_DRM_R128 is not set
# CONFIG_DRM_RADEON is not set
# CONFIG_DRM_I810 is not set
CONFIG_DRM_I830=m
# CONFIG_DRM_I915 is not set
# CONFIG_DRM_MGA is not set
# CONFIG_DRM_SIS is not set
# CONFIG_DRM_VIA is not set
# CONFIG_DRM_SAVAGE is not set

#
# PCMCIA character devices
#
# CONFIG_SYNCLINK_CS is not set
# CONFIG_CARDMAN_4000 is not set
# CONFIG_CARDMAN_4040 is not set
# CONFIG_MWAVE is not set
# CONFIG_RAW_DRIVER is not set
CONFIG_HPET=y
# CONFIG_HPET_RTC_IRQ is not set
CONFIG_HPET_MMAP=y
# CONFIG_HANGCHECK_TIMER is not set

#
# TPM devices
#
# CONFIG_TCG_TPM is not set
# CONFIG_TELCLOCK is not set

#
# I2C support
#
# CONFIG_I2C is not set

#
# Dallas's 1-wire bus
#
# CONFIG_W1 is not set

#
# Hardware Monitoring support
#
CONFIG_HWMON=y
# CONFIG_HWMON_VID is not set
# CONFIG_SENSORS_HDAPS is not set
# CONFIG_HWMON_DEBUG_CHIP is not set

#
# Misc devices
#
# CONFIG_IBM_ASM is not set

#
# Multimedia Capabilities Port drivers
#

#
# Multimedia devices
#
# CONFIG_VIDEO_DEV is not set

#
# Digital Video Broadcasting Devices
#
# CONFIG_DVB is not set

#
# Graphics support
#
# CONFIG_FB is not set
CONFIG_VIDEO_SELECT=y

#
# Console display driver support
#
CONFIG_VGA_CONSOLE=y
# CONFIG_MDA_CONSOLE is not set
CONFIG_DUMMY_CONSOLE=y

#
# Sound
#
CONFIG_SOUND=y

#
# Advanced Linux Sound Architecture
#
CONFIG_SND=m
CONFIG_SND_AC97_CODEC=m
CONFIG_SND_AC97_BUS=m
CONFIG_SND_TIMER=m
CONFIG_SND_PCM=m
CONFIG_SND_SEQUENCER=m
# CONFIG_SND_SEQ_DUMMY is not set
CONFIG_SND_OSSEMUL=y
CONFIG_SND_MIXER_OSS=m
CONFIG_SND_PCM_OSS=m
CONFIG_SND_SEQUENCER_OSS=y
CONFIG_SND_RTCTIMER=m
CONFIG_SND_SEQ_RTCTIMER_DEFAULT=y
# CONFIG_SND_VERBOSE_PRINTK is not set
# CONFIG_SND_DEBUG is not set

#
# Generic devices
#
# CONFIG_SND_DUMMY is not set
# CONFIG_SND_VIRMIDI is not set
# CONFIG_SND_MTPAV is not set
# CONFIG_SND_SERIAL_U16550 is not set
# CONFIG_SND_MPU401 is not set

#
# ISA devices
#
# CONFIG_SND_AD1816A is not set
# CONFIG_SND_AD1848 is not set
# CONFIG_SND_CS4231 is not set
# CONFIG_SND_CS4232 is not set
# CONFIG_SND_CS4236 is not set
# CONFIG_SND_ES968 is not set
# CONFIG_SND_ES1688 is not set
# CONFIG_SND_ES18XX is not set
# CONFIG_SND_GUSCLASSIC is not set
# CONFIG_SND_GUSEXTREME is not set
# CONFIG_SND_GUSMAX is not set
# CONFIG_SND_INTERWAVE is not set
# CONFIG_SND_INTERWAVE_STB is not set
# CONFIG_SND_OPTI92X_AD1848 is not set
# CONFIG_SND_OPTI92X_CS4231 is not set
# CONFIG_SND_OPTI93X is not set
# CONFIG_SND_SB8 is not set
# CONFIG_SND_SB16 is not set
# CONFIG_SND_SBAWE is not set
# CONFIG_SND_WAVEFRONT is not set
# CONFIG_SND_ALS100 is not set
# CONFIG_SND_AZT2320 is not set
# CONFIG_SND_CMI8330 is not set
# CONFIG_SND_DT019X is not set
# CONFIG_SND_OPL3SA2 is not set
# CONFIG_SND_SGALAXY is not set
# CONFIG_SND_SSCAPE is not set

#
# PCI devices
#
# CONFIG_SND_ALI5451 is not set
# CONFIG_SND_ATIIXP is not set
# CONFIG_SND_ATIIXP_MODEM is not set
# CONFIG_SND_AU8810 is not set
# CONFIG_SND_AU8820 is not set
# CONFIG_SND_AU8830 is not set
# CONFIG_SND_AZT3328 is not set
# CONFIG_SND_BT87X is not set
# CONFIG_SND_CS46XX is not set
# CONFIG_SND_CS4281 is not set
# CONFIG_SND_EMU10K1 is not set
# CONFIG_SND_EMU10K1X is not set
# CONFIG_SND_CA0106 is not set
# CONFIG_SND_KORG1212 is not set
# CONFIG_SND_MIXART is not set
# CONFIG_SND_NM256 is not set
# CONFIG_SND_RME32 is not set
# CONFIG_SND_RME96 is not set
# CONFIG_SND_RME9652 is not set
# CONFIG_SND_HDSP is not set
# CONFIG_SND_HDSPM is not set
# CONFIG_SND_TRIDENT is not set
# CONFIG_SND_YMFPCI is not set
# CONFIG_SND_AD1889 is not set
# CONFIG_SND_ALS4000 is not set
# CONFIG_SND_CMIPCI is not set
# CONFIG_SND_ENS1370 is not set
# CONFIG_SND_ENS1371 is not set
# CONFIG_SND_ES1938 is not set
# CONFIG_SND_ES1968 is not set
# CONFIG_SND_MAESTRO3 is not set
# CONFIG_SND_FM801 is not set
# CONFIG_SND_ICE1712 is not set
# CONFIG_SND_ICE1724 is not set
CONFIG_SND_INTEL8X0=m
CONFIG_SND_INTEL8X0M=m
# CONFIG_SND_SONICVIBES is not set
# CONFIG_SND_VIA82XX is not set
# CONFIG_SND_VIA82XX_MODEM is not set
# CONFIG_SND_VX222 is not set
# CONFIG_SND_HDA_INTEL is not set

#
# USB devices
#
# CONFIG_SND_USB_AUDIO is not set
# CONFIG_SND_USB_USX2Y is not set

#
# PCMCIA devices
#
# CONFIG_SND_VXPOCKET is not set
# CONFIG_SND_PDAUDIOCF is not set

#
# Open Sound System
#
# CONFIG_SOUND_PRIME is not set

#
# USB support
#
CONFIG_USB_ARCH_HAS_HCD=y
CONFIG_USB_ARCH_HAS_OHCI=y
CONFIG_USB=m
# CONFIG_USB_DEBUG is not set

#
# Miscellaneous USB options
#
CONFIG_USB_DEVICEFS=y
CONFIG_USB_BANDWIDTH=y
# CONFIG_USB_DYNAMIC_MINORS is not set
# CONFIG_USB_SUSPEND is not set
# CONFIG_USB_OTG is not set

#
# USB Host Controller Drivers
#
CONFIG_USB_EHCI_HCD=m
# CONFIG_USB_EHCI_SPLIT_ISO is not set
# CONFIG_USB_EHCI_ROOT_HUB_TT is not set
# CONFIG_USB_ISP116X_HCD is not set
# CONFIG_USB_OHCI_HCD is not set
CONFIG_USB_UHCI_HCD=m
# CONFIG_USB_SL811_HCD is not set

#
# USB Device Class drivers
#
# CONFIG_OBSOLETE_OSS_USB_DRIVER is not set
# CONFIG_USB_ACM is not set
CONFIG_USB_PRINTER=m

#
# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support' #

#

# may also be needed; see USB_STORAGE Help for more information
#
CONFIG_USB_STORAGE=m
# CONFIG_USB_STORAGE_DEBUG is not set
# CONFIG_USB_STORAGE_DATAFAB is not set
# CONFIG_USB_STORAGE_FREECOM is not set
# CONFIG_USB_STORAGE_ISD200 is not set
# CONFIG_USB_STORAGE_DPCM is not set
# CONFIG_USB_STORAGE_USBAT is not set
# CONFIG_USB_STORAGE_SDDR09 is not set
# CONFIG_USB_STORAGE_SDDR55 is not set
# CONFIG_USB_STORAGE_JUMPSHOT is not set

#
# USB Input Devices
#
CONFIG_USB_HID=m
CONFIG_USB_HIDINPUT=y
# CONFIG_HID_FF is not set
CONFIG_USB_HIDDEV=y

#
# USB HID Boot Protocol drivers
#
# CONFIG_USB_KBD is not set
# CONFIG_USB_MOUSE 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_MTOUCH is not set
# CONFIG_USB_ITMTOUCH is not set
# CONFIG_USB_EGALAX is not set
# CONFIG_USB_YEALINK is not set
# CONFIG_USB_XPAD is not set
# CONFIG_USB_ATI_REMOTE is not set
# CONFIG_USB_KEYSPAN_REMOTE is not set
# CONFIG_USB_APPLETOUCH is not set

#
# USB Imaging devices
#
# CONFIG_USB_MDC800 is not set
# CONFIG_USB_MICROTEK is not set

#
# USB Multimedia devices
#
# CONFIG_USB_DABUSB is not set

#
# Video4Linux support is needed for USB Multimedia device support #

#
# USB Network Adapters
#
# CONFIG_USB_CATC is not set
# CONFIG_USB_KAWETH is not set
# CONFIG_USB_PEGASUS is not set
# CONFIG_USB_RTL8150 is not set
# CONFIG_USB_USBNET is not set
# CONFIG_USB_ZD1201 is not set
# CONFIG_USB_MON is not set

#
# USB port drivers
#

#
# USB Serial Converter support
#
CONFIG_USB_SERIAL=m
# CONFIG_USB_SERIAL_GENERIC is not set
# CONFIG_USB_SERIAL_AIRPRIME is not set
# CONFIG_USB_SERIAL_ANYDATA is not set
# CONFIG_USB_SERIAL_BELKIN is not set
# CONFIG_USB_SERIAL_WHITEHEAT is not set
# CONFIG_USB_SERIAL_DIGI_ACCELEPORT is not set
# CONFIG_USB_SERIAL_CP2101 is not set
# CONFIG_USB_SERIAL_CYPRESS_M8 is not set
# CONFIG_USB_SERIAL_EMPEG is not set
# CONFIG_USB_SERIAL_FTDI_SIO is not set
CONFIG_USB_SERIAL_VISOR=m
# CONFIG_USB_SERIAL_IPAQ is not set
# CONFIG_USB_SERIAL_IR is not set
# CONFIG_USB_SERIAL_EDGEPORT is not set
# CONFIG_USB_SERIAL_EDGEPORT_TI is not set
# CONFIG_USB_SERIAL_GARMIN is not set
# CONFIG_USB_SERIAL_IPW is not set
# CONFIG_USB_SERIAL_KEYSPAN_PDA is not set
# CONFIG_USB_SERIAL_KEYSPAN is not set
# CONFIG_USB_SERIAL_KLSI is not set
# CONFIG_USB_SERIAL_KOBIL_SCT is not set
# CONFIG_USB_SERIAL_MCT_U232 is not set
# CONFIG_USB_SERIAL_PL2303 is not set
# CONFIG_USB_SERIAL_HP4X is not set
# CONFIG_USB_SERIAL_SAFE is not set
# CONFIG_USB_SERIAL_TI is not set
# CONFIG_USB_SERIAL_CYBERJACK is not set
# CONFIG_USB_SERIAL_XIRCOM is not set
# CONFIG_USB_SERIAL_OMNINET is not set

#
# USB Miscellaneous drivers
#
# CONFIG_USB_EMI62 is not set
# CONFIG_USB_EMI26 is not set
# CONFIG_USB_AUERSWALD is not set
# CONFIG_USB_RIO500 is not set
# CONFIG_USB_LEGOTOWER is not set
# CONFIG_USB_LCD is not set
# CONFIG_USB_LED is not set
# CONFIG_USB_CYTHERM is not set
# CONFIG_USB_PHIDGETKIT is not set
# CONFIG_USB_PHIDGETSERVO is not set
# CONFIG_USB_IDMOUSE is not set
# CONFIG_USB_SISUSBVGA is not set
# CONFIG_USB_LD is not set
# CONFIG_USB_TEST is not set

#
# USB DSL modem support
#

#
# USB Gadget Support
#
# CONFIG_USB_GADGET is not set

#
# MMC/SD Card support
#
CONFIG_MMC=m
# CONFIG_MMC_DEBUG is not set
CONFIG_MMC_BLOCK=m
CONFIG_MMC_WBSD=m

#
# InfiniBand support
#
# CONFIG_INFINIBAND is not set

#
# SN Devices
#

#
# File systems
#
CONFIG_EXT2_FS=y
# CONFIG_EXT2_FS_XATTR is not set
# CONFIG_EXT2_FS_XIP is not set
# CONFIG_EXT3_FS is not set
# CONFIG_JBD is not set
CONFIG_REISERFS_FS=m
# CONFIG_REISERFS_CHECK is not set
# CONFIG_REISERFS_PROC_INFO is not set
# CONFIG_REISERFS_FS_XATTR is not set
# CONFIG_JFS_FS is not set
CONFIG_FS_POSIX_ACL=y
# CONFIG_XFS_FS is not set
# CONFIG_MINIX_FS is not set
# CONFIG_ROMFS_FS is not set
CONFIG_INOTIFY=y
# CONFIG_QUOTA is not set
CONFIG_DNOTIFY=y
# CONFIG_AUTOFS_FS is not set
CONFIG_AUTOFS4_FS=m
CONFIG_FUSE_FS=m

#
# CD-ROM/DVD Filesystems
#
CONFIG_ISO9660_FS=m
CONFIG_JOLIET=y
CONFIG_ZISOFS=y
CONFIG_ZISOFS_FS=m
CONFIG_UDF_FS=m
CONFIG_UDF_NLS=y

#
# DOS/FAT/NT Filesystems
#
CONFIG_FAT_FS=m
# CONFIG_MSDOS_FS is not set
CONFIG_VFAT_FS=m
CONFIG_FAT_DEFAULT_CODEPAGE=437
CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-15"
CONFIG_NTFS_FS=m
# CONFIG_NTFS_DEBUG is not set
# CONFIG_NTFS_RW is not set

#
# Pseudo filesystems
#
CONFIG_PROC_FS=y
CONFIG_PROC_KCORE=y
CONFIG_SYSFS=y
CONFIG_TMPFS=y
# CONFIG_HUGETLBFS is not set
# CONFIG_HUGETLB_PAGE is not set
CONFIG_RAMFS=y
CONFIG_RELAYFS_FS=m

#
# Miscellaneous filesystems
#
# CONFIG_ADFS_FS is not set
# CONFIG_AFFS_FS is not set
# CONFIG_HFS_FS is not set
# CONFIG_HFSPLUS_FS is not set
# CONFIG_BEFS_FS is not set
# CONFIG_BFS_FS is not set
# CONFIG_EFS_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=m
CONFIG_NFS_V3=y
# CONFIG_NFS_V3_ACL is not set
CONFIG_NFS_V4=y
# CONFIG_NFS_DIRECTIO is not set
CONFIG_NFSD=m
CONFIG_NFSD_V3=y
# CONFIG_NFSD_V3_ACL is not set
CONFIG_NFSD_V4=y
CONFIG_NFSD_TCP=y
CONFIG_LOCKD=m
CONFIG_LOCKD_V4=y
CONFIG_EXPORTFS=m
CONFIG_NFS_COMMON=y
CONFIG_SUNRPC=m
CONFIG_SUNRPC_GSS=m
CONFIG_RPCSEC_GSS_KRB5=m
# CONFIG_RPCSEC_GSS_SPKM3 is not set
CONFIG_SMB_FS=m
CONFIG_SMB_NLS_DEFAULT=y
CONFIG_SMB_NLS_REMOTE="iso8859-15"
CONFIG_CIFS=m
# CONFIG_CIFS_STATS is not set
# CONFIG_CIFS_XATTR is not set
# CONFIG_CIFS_EXPERIMENTAL is not set
# CONFIG_NCP_FS is not set
# CONFIG_CODA_FS is not set
# CONFIG_AFS_FS is not set
# CONFIG_9P_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="iso8859-15"
CONFIG_NLS_CODEPAGE_437=m
# CONFIG_NLS_CODEPAGE_737 is not set
# CONFIG_NLS_CODEPAGE_775 is not set
CONFIG_NLS_CODEPAGE_850=m
# CONFIG_NLS_CODEPAGE_852 is not set
# 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 is not set
# CONFIG_NLS_ASCII is not set
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=y
# CONFIG_NLS_KOI8_R is not set
# CONFIG_NLS_KOI8_U is not set
CONFIG_NLS_UTF8=m

#
# Instrumentation Support
#
# CONFIG_PROFILING is not set
CONFIG_PROFILE_NMI=y
# CONFIG_KPROBES is not set

#
# Kernel hacking
#
# CONFIG_PRINTK_TIME is not set
# CONFIG_PRINTK_IGNORE_LOGLEVEL is not set
CONFIG_DEBUG_KERNEL=y
# CONFIG_MAGIC_SYSRQ is not set
CONFIG_LOG_BUF_SHIFT=14
CONFIG_PARANOID_GENERIC_TIME=y
CONFIG_DETECT_SOFTLOCKUP=y
CONFIG_SCHEDSTATS=y
CONFIG_DEBUG_PREEMPT=y
CONFIG_DEBUG_IRQ_FLAGS=y
CONFIG_WAKEUP_TIMING=y
# CONFIG_WAKEUP_LATENCY_HIST is not set
CONFIG_PREEMPT_TRACE=y
CONFIG_CRITICAL_PREEMPT_TIMING=y
# CONFIG_PREEMPT_OFF_HIST is not set
CONFIG_CRITICAL_IRQSOFF_TIMING=y
# CONFIG_INTERRUPT_OFF_HIST is not set
CONFIG_CRITICAL_TIMING=y
CONFIG_LATENCY_TIMING=y
CONFIG_LATENCY_TRACE=y
CONFIG_MCOUNT=y
CONFIG_DEBUG_DEADLOCKS=y
# CONFIG_DEBUG_RT_LOCKING_MODE is not set
# CONFIG_DEBUG_KOBJECT is not set
CONFIG_DEBUG_BUGVERBOSE=y
# CONFIG_DEBUG_INFO is not set
# CONFIG_DEBUG_FS is not set
# CONFIG_DEBUG_VM is not set
CONFIG_FRAME_POINTER=y
# CONFIG_RCU_TORTURE_TEST is not set
CONFIG_EARLY_PRINTK=y
CONFIG_DEBUG_STACKOVERFLOW=y
CONFIG_DEBUG_STACK_USAGE=y
# CONFIG_DEBUG_PAGEALLOC is not set
# CONFIG_4KSTACKS is not set
CONFIG_X86_FIND_SMP_CONFIG=y
CONFIG_X86_MPPARSE=y

#
# Security options
#
# CONFIG_KEYS is not set
# CONFIG_SECURITY is not set

#
# Cryptographic options
#
CONFIG_CRYPTO=y
CONFIG_CRYPTO_HMAC=y
# CONFIG_CRYPTO_NULL is not set
# CONFIG_CRYPTO_MD4 is not set
CONFIG_CRYPTO_MD5=y
CONFIG_CRYPTO_SHA1=y
CONFIG_CRYPTO_SHA256=y
CONFIG_CRYPTO_SHA512=y
# CONFIG_CRYPTO_WP512 is not set
# CONFIG_CRYPTO_TGR192 is not set
CONFIG_CRYPTO_DES=y
# CONFIG_CRYPTO_BLOWFISH is not set
# CONFIG_CRYPTO_TWOFISH is not set
# CONFIG_CRYPTO_SERPENT is not set
CONFIG_CRYPTO_AES=m
CONFIG_CRYPTO_AES_586=y
# CONFIG_CRYPTO_CAST5 is not set
# CONFIG_CRYPTO_CAST6 is not set
# CONFIG_CRYPTO_TEA is not set
CONFIG_CRYPTO_ARC4=m
# CONFIG_CRYPTO_KHAZAD is not set
# CONFIG_CRYPTO_ANUBIS is not set
CONFIG_CRYPTO_DEFLATE=y
CONFIG_CRYPTO_MICHAEL_MIC=m
# CONFIG_CRYPTO_CRC32C is not set
# CONFIG_CRYPTO_TEST is not set

#
# Hardware crypto devices
#
# CONFIG_CRYPTO_DEV_PADLOCK is not set

#
# Library routines
#
CONFIG_CRC_CCITT=y
# CONFIG_CRC16 is not set
CONFIG_CRC32=y
# CONFIG_LIBCRC32C is not set
CONFIG_ZLIB_INFLATE=y
CONFIG_ZLIB_DEFLATE=y
CONFIG_TEXTSEARCH=y
CONFIG_TEXTSEARCH_KMP=m
CONFIG_TEXTSEARCH_BM=m
CONFIG_TEXTSEARCH_FSM=m
CONFIG_GENERIC_HARDIRQS=y
CONFIG_GENERIC_IRQ_PROBE=y
CONFIG_X86_BIOS_REBOOT=y
CONFIG_KTIME_SCALAR=y

Sorry, your latency trace doesn't help. The 45usec is not really a latency (well not a bad one).

-- Steve

I'll look into your oops later (or maybe Ingo has some time), but I've also notice the slowness of 2.6.15-rc5-rt2, and I'm investigating it now.

Thanks,

-- Steve

Hey Steven,
Do check that the slowness you're seeing isn't related to the
CONFIG_PARANIOD_GENERIC_TIME option being enabled. It is expected that the extra checks made by that config option would slow things down a bit.

thanks
-john

The first kernel I built which showed this behaviour had no debugging options enabled.

It happens if the system is mostly idle, in this state "top" will show a kernel usage of 20%-50%, and as soon as something cpu intensive is started, the whole system becomes extremely unresponsive.

Greetings,

Gunter

Hi John,

Thanks for the suggestion, but I've been running my tests with that turned off. Actually, I've turned off pretty much all debugging, and added my own logdev device. As mentioned in my previous email, that I CC you on, I found the culprit.

Seems, the SLOB is not as fast as the SLAB. I'll look more into this tomorrow. (My wife is taking by daughter out of town for gymnastics, so I get to stay home and work :-/ )

-- Steve

Ingo,

After searching all over to find out where the slowness is, I finally discovered it. It's the SLOB!

I noticed a that a make install of the kernel over NFS took on 2.6.15-rc5 ~26 seconds to complete, and on 2.6.15-rc5-rt2 it took almost 2 minutes for the same operation on the same machine.

I added my logdev device to record lots of output, and it found the place that is taking the longest:

In 2.6.15-rc5-rt2:

[  789.171773] cpu:0 kfree_skbmem:291 in
[  789.171873] cpu:0 kfree_skbmem:295 1
[  789.172357] cpu:0 kfree_skbmem:320 out

in 2.6.15-rc5:

[  343.253988] cpu:0 kfree_skbmem:291 in
[  343.253990] cpu:0 kfree_skbmem:295 1
[  343.253991] cpu:0 kfree_skbmem:320 out

Here's the code for both systems (they are identical here):

void kfree_skbmem(struct sk_buff *skb)

{
	struct sk_buff *other;
	atomic_t *fclone_ref;

	edprint("in");
	skb_release_data(skb);
	switch (skb->fclone) {
	case SKB_FCLONE_UNAVAILABLE:
	edprint("1");
		kmem_cache_free(skbuff_head_cache, skb);
		break;

	case SKB_FCLONE_ORIG:
	edprint("2");
		fclone_ref = (atomic_t *) (skb + 2);
		if (atomic_dec_and_test(fclone_ref))
			kmem_cache_free(skbuff_fclone_cache, skb);
		break;

	case SKB_FCLONE_CLONE:
	edprint("3");
		fclone_ref = (atomic_t *) (skb + 1);
		other = skb - 1;

		/* The clone portion is available for
		 * fast-cloning again.
		 */
		skb->fclone = SKB_FCLONE_UNAVAILABLE;

		if (atomic_dec_and_test(fclone_ref))
			kmem_cache_free(skbuff_fclone_cache, other);
		break;
	};
	edprint("out");
}

My edprint records in a ring buffer (much like relayfs), and produces the above output. The time in brackets is in seconds. We see the difference between "1" and "out" is greatly different. (Note, I have a edprint in all interrupts, so I would know if one was taken, and these times are not a one time deal, but show up like this every time).

So for 2.6.15-rc5 the time difference is 343.253991 - 343.253990 or 1 usec, where as the time for 2.6.15-rc5-rt2 is 789.172357 - 789.171873 or 484 usecs! We're talking about a 48,400% increase here!

The difference here is that the kmem_cache_free in rt is a SLOB where as the vanilla kernel still uses SLABs, What's the rational for SLOB now?

The patches used are here:

For the logdev device:
http://www.kihontech.com/logdev/logdev-2.6.15-rc5-rt2.patch
http://www.kihontech.com/logdev/logdev-2.6.15-rc5.patch

For debugging (on top of logdev):
http://www.kihontech.com/logdev/debug-2.6.15-rc5-rt2.patch
http://www.kihontech.com/logdev/debug-2.6.15-rc5.patch

(I also added my patches previously posted to get it to compile and handle the softirq hrtimer problems).

Thanks,

-- Steve

Ingo,

I ported your old changes of 2.6.14-rt22 of mm/slab.c to 2.6.15-rc5-rt2 and tried it out. I believe that this confirms that the SLOB _is_ the problem in the slowness. Booting with this slab patch, gives the old speeds that we use to have.

Now, is the solution to bring the SLOB up to par with the SLAB, or to make the SLAB as close to possible to the mainline (why remove NUMA?) and keep it for PREEMPT_RT?

Below is the port of the slab changes if anyone else would like to see if this speeds things up for them.

-- Steve

Index: linux-2.6.15-rc5-rt2/init/Kconfig
===================================================================
@@ -402,7 +402,7 @@
 	default y
 	bool "Use full SLAB allocator" if EMBEDDED
 	# we switch to the SLOB on PREEMPT_RT
-	depends on !PREEMPT_RT
+#	depends on !PREEMPT_RT
 	help
 	  Disabling this replaces the advanced SLAB allocator and
 	  kmalloc support with the drastically simpler SLOB allocator.

This drastically improves performance on my slower uniprocessor system. 2.6.15-rc5-rt2 still doesn't boot on my dual 933 box, with or without this patch. I will try to dig into that a bit more today.

   kr

ok, i've added this back in - but we really need a cleaner port of SLAB
...

Ingo

Actually, how much do you want that SLOB code? For the last couple of days I've been working on different approaches that can speed it up. Right now I have one that takes advantage of the different caches. But unfortunately, I'm dealing with a bad pointer some where that keeps making it bug. Argh!

-- Steve

well, the SLOB is mainly about being simple and small. So as long as those speedups are SMP-only, they ought to be fine. The problems are mainly SMP related, correct?

Ingo

Actually, no. My test is to do a make install over NFS of a kernel that has already been built.

The times I'm getting for the SLAB is ~26 seconds, the time for the SLOB is 1 minute 32 seconds. So your looking at >300% slowness here. The test bed is a UP. (I do that first before looking into SMP).

I'm still trying to keep the SLOB simple. It's the lack of sleep that is making it hard ;)

-- Steve

Amazing what you see after a few hours of sleep. My bug that I was looking for all yesterday happened to be a < when it should have been a <=.

OK, it boots and runs. Now I just need to clean it up and prepare to ship! My test which is simply to run make install on a prebuilt kernel over NFS. The test box is:

bert:/home/rostedt/work/ernie/linux-2.6.15-rc5-rt2# cat /proc/cpuinfo
processor       : 0
vendor_id       : GenuineIntel
cpu family      : 6
model           : 8
model name      : Pentium III (Coppermine)
stepping        : 3
cpu MHz         : 736.045
cache size      : 256 KB
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 2
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge
mca cmov pat pse36 mmx fxsr sse
bogomips        : 1472.74

The box where the kernel is NFS mounted is running the 2.6.15-rc4:

rostedt@gandalf:~/work/ernie/linux-2.6.15-rc5-rt2$ cat /proc/cpuinfo
processor       : 0
vendor_id       : AuthenticAMD
cpu family      : 15
model           : 43
model name      : AMD Athlon(tm) 64 X2 Dual Core Processor 4200+
stepping        : 1
cpu MHz         : 2210.221
cache size      : 512 KB
physical id     : 0
siblings        : 2
core id         : 0
cpu cores       : 2
fpu             : yes
fpu_exception   : yes
cpuid level     : 1
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge
mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext
fxsr_opt lm 3dnowext 3dnow pni lahf_lm cmp_legacy
bogomips        : 4424.61
TLB size        : 1024 4K pages
clflush size    : 64
cache_alignment : 64
address sizes   : 40 bits physical, 48 bits virtual
power management: ts fid vid ttp

processor : 1
vendor_id : AuthenticAMD
cpu family : 15
model : 43
model name : AMD Athlon(tm) 64 X2 Dual Core Processor 4200+
stepping : 1
cpu MHz : 2210.221
cache size : 512 KB
physical id : 0
siblings : 2
core id : 1
cpu cores : 2
fpu : yes
fpu_exception : yes
cpuid level : 1
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge
mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt lm 3dnowext 3dnow pni lahf_lm cmp_legacy
bogomips : 4419.74
TLB size : 1024 4K pages
clflush size : 64
cache_alignment : 64
address sizes : 40 bits physical, 48 bits virtual
power management: ts fid vid ttp

Here's the times for "time make install": Three runs for each.

rt with slab:

run 1:

  real    0m27.327s
  user    0m15.151s
  sys     0m3.149s

run 2:

  real    0m26.952s
  user    0m15.171s
  sys     0m3.178s

run 3:

  real    0m27.269s
  user    0m15.175s
  sys     0m3.226s

rt with slob (plain):

run 1:

  real    1m26.845s
  user    0m16.173s
  sys     0m29.558s

run 2:

  real    1m27.895s
  user    0m16.532s
  sys     0m30.460s

run 3:

  real    1m25.645s
  user    0m16.468s
  sys     0m30.973s

rt with slob (new):

run 1:

  real    0m28.740s
  user    0m15.364s
  sys     0m3.866s

run 2:

  real    0m27.782s
  user    0m15.409s
  sys     0m3.885s

run 3:

  real    0m27.576s
  user    0m15.193s
  sys     0m3.933s

As you see, the new SLOB code runs almost as fast as the SLAB code. With some more improvements, I'm sure it can get even faster.

I'll send out the patch real soon (after I wash and dry it).

Note: After I send out the patch, I'll give it a try on SMP.

-- Steve

cool, the numbers are really impressive! I'm wondering where the biggest hit comes from - perhaps the SLOB does linear list walking when allocating?

Ingo

Yeah, I think that is the biggest hit. The SLOB does the old K&R memory management. Basically, right from the book. But it is slow and can fragment very easily.

I have a little more to do on this patch, (I don't perform the correct cleanup on kmem_cache_destroy), but I'll send it to you anyway within the next couple of minutes. Just so you can take a look and try it out.

-- Steve

This patch uses the mem_map pages to find the bigblock descriptor for large allocations.

-- Steve

Index: linux-2.6.15-rc5-rt2/mm/slob.c
===================================================================
@@ -50,15 +50,42 @@
 struct bigblock {
 	int order;
 	void *pages;
-	struct bigblock *next;
 };
 typedef struct bigblock bigblock_t;
 
 static slob_t arena = { .next = &arena, .units = 1 };
 static slob_t *slobfree = &arena;
-static bigblock_t *bigblocks;
 static DEFINE_SPINLOCK(slob_lock);
-static DEFINE_SPINLOCK(block_lock);
+
+#define __get_slob_block(b) ((unsigned long)(b) & ~(PAGE_SIZE-1))
+
+static inline struct page *get_slob_page(const void *mem)
+{
+	void *virt = (void*)__get_slob_block(mem);
+
+	return virt_to_page(virt);
+}
+
+static inline void zero_slob_block(const void *b)
+{
+	struct page *page;
+	page = get_slob_page(b);
+	memset(&page->lru, 0, sizeof(page->lru));
+}
+
+static inline void *get_slob_block(const void *b)
+{
+	struct page *page;
+	page = get_slob_page(b);
+	return page->lru.next;
+}
+
+static inline void set_slob_block(const void *b, void *data)
+{
+	struct page *page;
+	page = get_slob_page(b);
+	page->lru.next = data;
+}
 
 static void slob_free(void *b, int size);
 

@@ -108,6 +135,7 @@
 			if (!cur)
 				return 0;
 
+			zero_slob_block(cur);
 			slob_free(cur, PAGE_SIZE);
 			spin_lock_irqsave(&slob_lock, flags);
 			cur = slobfree;

@@ -162,7 +190,6 @@
 {
 	slob_t *m;
 	bigblock_t *bb;
-	unsigned long flags;
 
 	if (size < PAGE_SIZE - SLOB_UNIT) {
 		m = slob_alloc(size + SLOB_UNIT, gfp, 0);

@@ -177,10 +204,7 @@
 	bb->pages = (void *)__get_free_pages(gfp, bb->order);
 
 	if (bb->pages) {
-		spin_lock_irqsave(&block_lock, flags);
-		bb->next = bigblocks;
-		bigblocks = bb;
-		spin_unlock_irqrestore(&block_lock, flags);
+		set_slob_block(bb->pages, bb);
 		return bb->pages;
 	}
 

@@ -192,25 +216,16 @@
 
 void kfree(const void *block)
 {
-	bigblock_t *bb, **last = &bigblocks;
-	unsigned long flags;
+	bigblock_t *bb;
 
 	if (!block)
 		return;
 
-	if (!((unsigned long)block & (PAGE_SIZE-1))) {
-		/* might be on the big block list */
-		spin_lock_irqsave(&block_lock, flags);
-		for (bb = bigblocks; bb; last = &bb->next, bb = bb->next) {
-			if (bb->pages == block) {
-				*last = bb->next;
-				spin_unlock_irqrestore(&block_lock, flags);
-				free_pages((unsigned long)block, bb->order);
-				slob_free(bb, sizeof(bigblock_t));
-				return;
-			}
-		}
-		spin_unlock_irqrestore(&block_lock, flags);
+	bb = get_slob_block(block);
+	if (bb) {
+		free_pages((unsigned long)block, bb->order);
+		slob_free(bb, sizeof(bigblock_t));
+		return;
 	}
 
 	slob_free((slob_t *)block - 1, 0);

@@ -222,20 +237,13 @@
 unsigned int ksize(const void *block)
 {
 	bigblock_t *bb;
-	unsigned long flags;
 
 	if (!block)
 		return 0;
 
-	if (!((unsigned long)block & (PAGE_SIZE-1))) {
-		spin_lock_irqsave(&block_lock, flags);
-		for (bb = bigblocks; bb; bb = bb->next)
-			if (bb->pages == block) {
-				spin_unlock_irqrestore(&slob_lock, flags);
-				return PAGE_SIZE << bb->order;
-			}
-		spin_unlock_irqrestore(&block_lock, flags);
-	}
+	bb = get_slob_block(block);
+	if (bb)
+		return PAGE_SIZE << bb->order;
 
 	return ((slob_t *)block - 1)->units * SLOB_UNIT;
 }

(Andrew, I'm CC'ing you and Matt to see if you would like this in -mm)

OK Ingo, here it is.

The old SLOB did the old K&R memory allocations.

It had a global link list "slobfree". When it needed memory it would search this list linearly to find the first spot that fit and then return it. It was broken up into SLOB_UNITS which was the number of bytes to hold slob_t.

Since the sizes of the allocations would greatly fluctuate, the chances for fragmentation was very high. This would also cause the looking for free locations to increase, since the number of free blocks would also increase due to the fragmentation.

It also had one global spinlock for ALL allocations. This would obviously kill SMP performance.

For large blocks greater than PAGE_SIZE it would just use the buddy system. This I didn't change, in fact, I made it use the buddy system for blocks greater than PAGE_SIZE >> 1, but I'll explain that below.

The problem that this system had, was it made another global link list to hold all of these large blocks, which means it needed another global spinlock to manage this list.

When any block was freed via kfree, it would first search all the big blocks to see if it was a large allocation, and if not, then it would search the slobfree list to find where it goes. Both taking two global spinlocks!

Here's what I've done to solve this.

First things first, the first patch was to get rid of the bigblock list. I'm simple used the method of SLAB to use the lru list field of the corresponding page to store the pointer to the bigblock descriptor which has the information to free it. This got rid of the bigblock link list and global spinlock.

The next patch was the big improvement, with the largest changes. I took advantage of how the kmem_cache usage that SLAB also takes advantage of. I created a memory pool like the global one, but for every cache with a size less then PAGE_SIZE >> 1.

[ Note: I picked PAGE_SIZE >> 1, since it didn't seem to make much difference when there were greater, since it would use a full page for just one allocation. I can play with this more, but it still seems to be a waste ].

I used lru.next of the page that the pages are allocated for, for the bigblock descriptors (as described above), and now I use lru.prev to point to the cache that the items belong to in the pool. So I removed the need for the descriptor being held in the pool.

I also created the general caches like SLAB for kmalloc and kfree, for sizes 32 through PAGE_SIZE >> 1. All greater allocations will use the backend buddy system.

Tests:
=====

To test this, I used what showed the problem the greatest. Doing a make install over NFS. So on my 733MHz UP machine, I ran "time make install" on the -rt kernel with the old SLAB, as well as -rt kernel with the default (old) SLOB, and then with the SLOB with these patches (three tests each). Here's the results:

rt with slab:

run 1:

  real    0m27.327s
  user    0m15.151s
  sys     0m3.149s

run 2:

  real    0m26.952s
  user    0m15.171s
  sys     0m3.178s

run 3:

  real    0m27.269s
  user    0m15.175s
  sys     0m3.226s

rt with slob (plain):

run 1:

  real    1m26.845s
  user    0m16.173s
  sys     0m29.558s

run 2:

  real    1m27.895s
  user    0m16.532s
  sys     0m30.460s

run 3:

  real    1m25.645s
  user    0m16.468s
  sys     0m30.973s

rt with slob (new):

run 1:

  real    0m28.740s
  user    0m15.364s
  sys     0m3.866s

run 2:

  real    0m27.782s
  user    0m15.409s
  sys     0m3.885s

run 3:

  real    0m27.576s
  user    0m15.193s
  sys     0m3.933s

So I have improved the speed of SLOB to almost that of SLAB!

TODO: IMPORTANT!!!

1) I haven't cleaned up the kmem_cache_destroy yet, so every time that happens, there's a memory leak.

2) I need to test on SMP.

-- Steve

I just tested it out on SMP (2x), and it boots. Ingo, do you have a good memory test that I can do benchmarks with? Something better that my "make install" test.

Thanks,

-- Steve

networking is the most SLAB-intensive, so your test over NFS ought to be pretty good already.

Ingo

could you also post the output of 'size mm/slob.o', with and without these patches, with CONFIG_EMBEDDED and CONFIG_CC_OPTIMIZE_FOR_SIZE enabled? (and with all debugging options disabled) Both the UP and the SMP overhead would be interesting to see.

Ingo

Well, there is definitely a hit there:

rt (slob new):
size mm/slob.o

   text    data     bss     dec     hex filename
   2051     112     233    2396     95c mm/slob.o

without
size mm/slob.o
text data bss dec hex filename
1331 120 8 1459 5b3 mm/slob.o

rt smp (slob new)
size mm/slob.o

   text    data     bss     dec     hex filename
   2297     120     233    2650     a5a mm/slob.o

without
size mm/slob.o
text data bss dec hex filename
1573 140 8 1721 6b9 mm/slob.o

So, should this be a third memory managment system? A fast_slob?

Just for kicks here's slab.o:

rt:
size mm/slab.o
text data bss dec hex filename
8896 556 144 9596 257c mm/slab.o

rt smp:
size mm/slab.o
text data bss dec hex filename
9679 640 84 10403 28a3 mm/slab.o

So there's still a great improvement on that (maybe not the bss though).

-- Steve

There's also crap that can be removed in my patch. Like I started a cache_chain algorithm. For example by adding just:

#if 0
static void test_slob(slob_t *s)
{

[...]

}

void print_slobs(void)
{

[...]

}
#endif

I get:
rt:
size mm/slob.o

   text    data     bss     dec     hex filename
   1889     112     233    2234     8ba mm/slob.o

rt smp:
size mm/slob.o

   text    data     bss     dec     hex filename
   2135     120     233    2488     9b8 mm/slob.o

So, I probably need to add stuff for CONFIG_OPTIMIZE_FOR_SIZE.

-- Steve

Steven Rostedt
Senior Programmer
Kihon Technologies
(607)786-4830

On the target systems for the original SLOB design, we have less than 16MB of memory, so the linked list walking is pretty well bounded.

And again, the locking primarily exists for PREEMPT and small dual-core. So I'm still a bit amused that you guys are using it for -RT.

I don't think this is correct, or else indicates a bug. We should only scan the big block list when the freed block was page-aligned.

This I like a lot. I'd like to see a size/performance measurement of this by itself. I suspect it's an unambiguous win in both categories.

Hmm. By every size, I assume you mean powers of two. Which negates some of the fine-grained allocation savings that current SLOB provides.

[...]

Nice.

For what it's worth, I think we really ought to consider a generalized allocator approach like Sun's VMEM, with various removable pieces.

Currently we've got something like this:

get_free_pages boot_mem idr resource_* vmalloc ...

        |
      slab
        |
  per_cpu/node
        |
  kmem_cache_alloc
        |
     kmalloc

We could take it in a direction like this:

generic range allocator (completely agnostic)

          |
  optional size buckets           (reduced fragmentation, O(1))
          |    
    optional slab                 (cache-friendly, pre-initialized)
          |
 optional per cpu/node caches     (cache-hot and lockless)
          |

kmalloc / kmem_cache_alloc / boot_mem / idr / resource_* / vmalloc / ...

(You read that right, the top level allocator can replace all the different allocators that hand back integers or non-overlapping ranges.)

Each user of, say, kmem_create() could then pass in flags to specify which caching layers ought to be bypassed. IDR, for example, would probably disable all the layers and specify a first-fit policy.

And then depending on our global size and performance requirements, we could globally disable some layers like SLAB, buckets, or per_cpu caches. With all the optional layers disabled, we'd end up with something much like SLOB (but underneath get_free_page!).

Mathematics is the supreme nostalgia of our time.

I bet after a while of running, your performance will still suffer due to fragmentation. The more fragmented it is, the more space you lose and the more steps you need to walk.

Remember, because of the small stack, kmalloc and kfree are used an awful lot. And if you slow those down, you will start to take a big hit in performance.

I think this is due to the complexity of the current SLAB. With slab.c unmodified, the RT kernel doesn't boot. And it's getting more complex, so to make the proper changes to have it run under a fully preemptible kernel, takes knowing all the details of the SLAB.

Ingo can answer this better himself, but I have a feeling he jumped to your SLOB system just because of the simplicity.

Yep, you're right here. I forgot about that since updating the bigblock list was the first thing I did, and I didn't need that check anymore. So, I was wrong here, yours does _only_ scan the bigblock list if the block is page aligned.

Actually the performance gain was disappointingly small. As it was a separate patch and I though it would gain a lot. But if IIRC, it only increased the speed by a second or two (of the 1 minute 27 seconds). That's why I spent so much time in the next approach.

Yeah its the same as what the slabs use. But I would like to take measurements of a running system between the two approaches. After a day of heavy network traffic, see what the fragmentation is like and how much is wasted. This would require me finishing my cache_chain work, and adding something similar to your SLOB.

But the powers of two is only for the kmalloc, which this is a know behavior of the current system. So it <should> only be used for things that would alloc and free within a quick time (like for things you would like to put on a stack but cant), or the size is close to (less than or equal) a power of two. Otherwise a kmem_cache is made which is the size of expected object (off by UNIT_SIZE).

Oh, this reminds me, I probably still need to add a shrink cache algorithm. Which would be very hard to do in the current SLOB.

Also note, I don't need to save the descriptor in with each kmalloc as the current SLOB does. Since each memory pool is of a fixed size, I again use the mem_map pages to store the location of the descriptor. So I save on memory that way.

Interesting, I don't know how Sun's VMEM works. Do you have links to some documentation?

That looks like quite an undertaking, but may be well worth it. I think Linux's memory management is starting to show it's age. It's been through a few transformations, and maybe it's time to go through another. The work being done by the NUMA folks, should be taking into account, and maybe we can come up with a way that can make things easier and less complex without losing performance.

BTW, the NUMA code in the slabs was the main killer for the RT conversion.

Thanks for the input,

-- Steve

True, with the exception that the improved packing may be the difference between fitting the working set in memory and thrashing/OOMing for some applications. Not running at all = infinitely bad performance.

And the fragmentation is really not all that bad. Remember, Linux and other legacy systems used similar allocators for ages.

And only a config switch away..

Still, if it's a size win, it definitely makes sense to merge. Removing the big block list lock is also a good thing and might make a bigger difference on SMP.

There are a fair number of long-lived kmalloc objects. You might try playing with the kmalloc accounting patch in -tiny to see what's out there.

http://www.selenic.com/repo/tiny?f=bbcd48f1d9c1;file=kmalloc-accounting.patch;style=raw

Hmmm? It already has one.

http://citeseer.ist.psu.edu/bonwick01magazines.html

Fortunately, it can be done completely piecemeal.

I think the VMEM scheme avoids that problem to some degree, but I might be wrong.

Mathematics is the supreme nostalgia of our time.

Well the best way to see, is to try it out with real applications on small machines. I guess I need to pull out my IBM Thinkpad 75c (32 megs, I'll need to only allocate half) and try out the two and see how far I can push it. Unfortunately, this test may need to wait, since I have a ton of other things to push out first.

If someone else (perhaps yourself) would like to give my patches a try, I would be really appreciate it. :)

But the performance, was greatly reduced, and the system just booted up.

Well, I guess I can check out the -mm branch and at least port the first patch over.

I'll have to try this out too. Thanks for the link.

The current version in Ingo's 2.6.15-rc5-rt2 didn't have one.

Thanks, I'll read up on this.

If you would like me to test any code, I'd be happy to when I have time. And maybe even add a few patches myself.

-- Steve

Hi Steve and Matt,

The slab allocator is indeed complex, messy, and hard to understand. In case you're interested, I have included a replacement I started out a while a go. It follows the design of a magazine allocator described by Bonwick. It's not a complete replacement but should boot (well, did anyway at some point). I have also included a user space test harness I am using to smoke it.

If there's enough interest, I would be more than glad to help write a replacement for mm/slab.c :-)

Pekka

Index: 2.6/mm/kmalloc.c
===================================================================
@@ -0,0 +1,170 @@
+/*
+ * mm/kmalloc.c - A general purpose memory allocator.
+ *
+ * Copyright (C) 1996, 1997 Mark Hemment
+ * Copyright (C) 1999 Andrea Arcangeli
+ * Copyright (C) 2000, 2002 Manfred Spraul
+ * Copyright (C) 2005 Shai Fultheim
+ * Copyright (C) 2005 Shobhit Dayal
+ * Copyright (C) 2005 Alok N Kataria
+ * Copyright (C) 2005 Christoph Lameter
+ * Copyright (C) 2005 Pekka Enberg
+ *
+ * This file is released under the GPLv2.
+ */
+
+#include <linux/kernel.h>
+#include <linux/kmem.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/string.h>
+
+struct cache_sizes malloc_sizes[] = {
+#define CACHE(x) { .cs_size = (x) },
+#include <linux/kmalloc_sizes.h>
+	{ .cs_size = ULONG_MAX }
+#undef CACHE
+};
+EXPORT_SYMBOL(malloc_sizes);
+
+struct cache_names {
+	char *name;
+	char *name_dma;
+};
+
+static struct cache_names cache_names[] = {
+#define CACHE(x) { .name = "size-" #x, .name_dma = "size-" #x "(DMA" },
+#include <linux/kmalloc_sizes.h>
+	{ NULL, }
+#undef CACHE
+};
+
+void kmalloc_init(void)
+{
+	struct cache_sizes *sizes = malloc_sizes;
+	struct cache_names *names = cache_names;
+
+	while (sizes->cs_size != ULONG_MAX) {
+		sizes->cs_cache = kmem_cache_create(names->name,
+						    sizes->cs_size, 0, 0,
+						    NULL, NULL);
+		sizes->cs_dma_cache = kmem_cache_create(names->name_dma,
+							sizes->cs_size, 0, 0,
+							NULL, NULL);
+		sizes++;
+		names++;
+	}
+}
+
+static struct kmem_cache *find_general_cache(size_t size, gfp_t flags)
+{
+	struct cache_sizes *sizes = malloc_sizes;
+
+	while (size > sizes->cs_size)
+		sizes++;
+
+	if (unlikely(flags & GFP_DMA))
+		return sizes->cs_dma_cache;
+	return sizes->cs_cache;
+}
+
+/**
+ * kmalloc - allocate memory
+ * @size: how many bytes of memory are required.
+ * @flags: the type of memory to allocate.
+ *
+ * kmalloc is the normal method of allocating memory
+ * in the kernel.
+ *
+ * The @flags argument may be one of:
+ *
+ * %GFP_USER - Allocate memory on behalf of user.  May sleep.
+ *
+ * %GFP_KERNEL - Allocate normal kernel ram.  May sleep.
+ *
+ * %GFP_ATOMIC - Allocation will not sleep.  Use inside interrupt handlers.
+ *
+ * Additionally, the %GFP_DMA flag may be set to indicate the memory
+ * must be suitable for DMA.  This can mean different things on different
+ * platforms.  For example, on i386, it means that the memory must come
+ * from the first 16MB.
+ */
+void *__kmalloc(size_t size, gfp_t flags)
+{
+	struct kmem_cache *cache = find_general_cache(size, flags);
+	if (unlikely(cache == NULL))
+		return NULL;
+	return kmem_cache_alloc(cache, flags);
+}
+EXPORT_SYMBOL(__kmalloc);
+
+void *kmalloc_node(size_t size, unsigned int __nocast flags, int node)
+{
+	return __kmalloc(size, flags);
+}
+EXPORT_SYMBOL(kmalloc_node);
+
+/**
+ * kzalloc - allocate memory. The memory is set to zero.
+ * @size: how many bytes of memory are required.
+ * @flags: the type of memory to allocate.
+ */
+void *kzalloc(size_t size, gfp_t flags)
+{
+        void *ret = kmalloc(size, flags);
+        if (ret)
+                memset(ret, 0, size);
+        return ret;
+}
+EXPORT_SYMBOL(kzalloc);
+
+/*
+ * kstrdup - allocate space for and copy an existing string
+ *
+ * @s: the string to duplicate
+ * @gfp: the GFP mask used in the kmalloc() call when allocating memory
+ */
+char *kstrdup(const char *s, gfp_t gfp)
+{
+	size_t len;
+	char *buf;
+
+	if (!s)
+		return NULL;
+
+	len = strlen(s) + 1;
+	buf = kmalloc(len, gfp);
+	if (buf)
+		memcpy(buf, s, len);
+	return buf;
+}
+EXPORT_SYMBOL(kstrdup);
+
+// FÌXME: duplicate!
+static struct kmem_cache *page_get_cache(struct page *page)
+{
+	return (struct kmem_cache *)page->lru.next;
+}
+
+/**
+ * kfree - free previously allocated memory
+ * @objp: pointer returned by kmalloc.
+ *
+ * If @objp is NULL, no operation is performed.
+ *
+ * Don't free memory not originally allocated by kmalloc()
+ * or you will run into trouble.
+ */
+void kfree(const void *obj)
+{
+	struct page *page;
+	struct kmem_cache *cache;
+
+	if (unlikely(!obj))
+		return;
+
+	page = virt_to_page(obj);
+	cache = page_get_cache(page);
+	kmem_cache_free(cache, (void *)obj);
+}
+EXPORT_SYMBOL(kfree);

Index: 2.6/test/Makefile
===================================================================
@@ -0,0 +1,18 @@
+all: test
+
+gen:
+	sh make-tests.sh mm/*.c > test-runner.c
+
+compile:
+	gcc -O2 -g -Wall -Iinclude -I../include -D__KERNEL__=1 ../mm/kmalloc.c mm/kmalloc-test.c ../mm/kmem.c mm/kmem-test.c mm/page_alloc.c kernel/panic.c kernel/workqueue.c kernel/timer.c CuTest.c test-runner.c -o test-runner
+
+run:
+	./test-runner
+
+test: gen compile run
+
+valgrind: gen compile
+	valgrind --leak-check=full test-runner
+
+clean:
+	rm -f *.o tags test-runner test-runner.c

Index: 2.6/test/mm/kmalloc-test.c
===================================================================
@@ -0,0 +1,21 @@
+#include <CuTest.h>
+#include <linux/kmem.h>
+
+void test_kmalloc_returns_from_slab(CuTest *ct)
+{
+	kmem_cache_init();
+	void *obj1 = kmalloc(10, GFP_KERNEL);
+	void *obj2 = kmalloc(10, GFP_KERNEL);
+	CuAssertIntEquals(ct, (unsigned long)obj1+32, (unsigned long)obj2);
+	kmem_cache_release();
+}
+
+void test_kzalloc_zeros_memory(CuTest *ct)
+{
+	int i;
+	kmem_cache_init();
+	char *obj = kzalloc(10, GFP_KERNEL);
+	for (i = 0; i < 10; i++)
+		CuAssertIntEquals(ct, 0, obj[i]);
+	kmem_cache_release();
+}

Index: 2.6/test/include/asm/processor.h
===================================================================
@@ -0,0 +1,4 @@
+#ifndef __LINUX_PROCESSOR_H
+#define __LINUX_PROCESSOR_H
+
+#endif

Index: 2.6/test/include/linux/compiler-gcc3.h
===================================================================
@@ -0,0 +1,30 @@
+/* Never include this file directly.  Include <linux/compiler.h> instead.  */
+
+/* These definitions are for GCC v3.x.  */
+#include <linux/compiler-gcc.h>
+
+#if __GNUC_MINOR__ >= 1
+# define inline		inline		__attribute__((always_inline))
+# define __inline__	__inline__	__attribute__((always_inline))
+# define __inline	__inline	__attribute__((always_inline))
+#endif
+
+#if __GNUC_MINOR__ > 0
+# define __deprecated		__attribute__((deprecated))
+#endif
+
+#if __GNUC_MINOR__ >= 3
+#else
+# define __attribute_used__	__attribute__((__unused__))
+#endif
+
+#define __attribute_const__	__attribute__((__const__))
+
+#if __GNUC_MINOR__ >= 1
+#define  noinline		__attribute__((noinline))
+#endif
+
+#if __GNUC_MINOR__ >= 4
+#define __must_check		__attribute__((warn_unused_result))
+#endif
+

Index: 2.6/test/include/asm/system.h
===================================================================
@@ -0,0 +1,7 @@
+#ifndef __LINUX_SYSTEM_H
+#define __LINUX_SYSTEM_H
+
+#define smp_wmb(x) x
+#define cmpxchg(ptr,o,n)
+
+#endif

Index: 2.6/test/include/asm/bug.h
===================================================================
@@ -0,0 +1,13 @@
+#ifndef _I386_BUG_H
+#define _I386_BUG_H
+
+#include <linux/config.h>
+#include <assert.h>
+
+#define HAVE_ARCH_BUG
+#define BUG() assert(!"bug")
+#define HAVE_ARCH_BUG_ON
+#define BUG_ON(cond) assert(!cond)
+
+#include <asm-generic/bug.h>
+#endif

Index: 2.6/mm/Makefile
===================================================================
@@ -9,7 +9,7 @@ mmu-$(CONFIG_MMU)	:= fremap.o highmem.o 
 
 obj-y			:= bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
 			   page_alloc.o page-writeback.o pdflush.o \
-			   readahead.o slab.o swap.o truncate.o vmscan.o \
+			   readahead.o kmem.o kmalloc.o swap.o truncate.o vmscan.o \
 			   prio_tree.o $(mmu-y)
 
 obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o thrash.o

Index: 2.6/test/include/stdlib.h
===================================================================
@@ -0,0 +1,11 @@
+#ifndef __STDLIB_H
+#define __STDLIB_H
+
+#include <stddef.h>
+
+extern void *malloc(size_t);
+extern void *calloc(size_t, size_t);
+extern void free(void *);
+extern void *realloc(void *, size_t);
+
+#endif

Index: 2.6/test/include/asm/page.h
===================================================================
@@ -0,0 +1,15 @@
+#ifndef __LINUX_PAGE_H
+#define __LINUX_PAGE_H
+
+#include <linux/mm.h>
+
+#define PAGE_OFFSET 0
+#define PAGE_SHIFT 12
+#define PAGE_SIZE 4096
+#define PAGE_MASK    (~(PAGE_SIZE-1))
+
+#define virt_to_page(addr) __virt_to_page((unsigned long) addr)
+
+extern struct page *__virt_to_page(unsigned long);
+
+#endif

Index: 2.6/test/include/linux/spinlock.h
===================================================================
@@ -0,0 +1,14 @@
+#ifndef __LINUX_SPINLOCK_H
+#define __LINUX_SPINLOCK_H
+
+#include <asm/atomic.h>
+
+typedef int spinlock_t;
+
+#define spin_lock_init(x)
+#define spin_lock_irqsave(x, y) (y = 1)
+#define spin_unlock_irqrestore(x, y) (y = 0)
+#define spin_lock(x)
+#define spin_unlock(x)
+
+#endif

Index: 2.6/test/include/linux/mmzone.h
===================================================================
@@ -0,0 +1,8 @@
+#ifndef __LINUX_MMZONE_H
+#define __LINUX_MMZONE_H
+
+#include <linux/threads.h>
+
+#define MAX_ORDER 11
+
+#endif

Index: 2.6/test/include/linux/threads.h
===================================================================
@@ -0,0 +1,6 @@
+#ifndef __LINUX_THREADS_H
+#define __LINUX_THREADS_H
+
+#define NR_CPUS 1
+
+#endif

Index: 2.6/test/include/linux/module.h
===================================================================
@@ -0,0 +1,7 @@
+#ifndef __LINUX_MODULE_H
+#define __LINUX_MODULE_H
+
+#define EXPORT_SYMBOL(x)
+#define EXPORT_SYMBOL_GPL(x)
+
+#endif

Index: 2.6/test/kernel/panic.c
===================================================================
@@ -0,0 +1,6 @@
+extern void abort(void);
+
+void panic(const char * fmt, ...)
+{
+	abort();
+}

Index: 2.6/test/include/asm/pgtable.h
===================================================================
@@ -0,0 +1,6 @@
+#ifndef __ASM_PGTABLE_H
+#define __ASM_PGTABLE_H
+
+#define kern_addr_valid(addr)    (1)
+
+#endif

Index: 2.6/test/include/asm/semaphore.h
===================================================================
@@ -0,0 +1,24 @@
+#ifndef __ASM_SEMAPHORE_H
+#define __ASM_SEMAPHORE_H
+
+struct semaphore {
+};
+
+static inline void init_MUTEX(struct semaphore *sem)
+{
+}
+
+static inline void up(struct semaphore *sem)
+{
+}
+
+static inline void down(struct semaphore *sem)
+{
+}
+
+static inline int down_trylock(struct semaphore *sem)
+{
+	return 1;
+}
+
+#endif

Index: 2.6/test/include/asm/uaccess.h
===================================================================
@@ -0,0 +1,4 @@
+#ifndef __ASM_UACCESS_H
+#define __ASM_UACCESS_H
+
+#endif

Index: 2.6/test/include/linux/config.h
===================================================================
@@ -0,0 +1,8 @@
+#ifndef __LINUX_CONFIG_H
+#define __LINUX_CONFIG_H
+
+#include <linux/autoconf.h>
+
+#undef CONFIG_PROC_FS
+
+#endif

Index: 2.6/test/include/linux/seq_file.h
===================================================================
@@ -0,0 +1,4 @@
+#ifndef __LINUX_SEQFILE_H
+#define __LINUX_SEQFILE_H
+
+#endif

Index: 2.6/test/include/asm/param.h
===================================================================
@@ -0,0 +1,6 @@
+#ifndef __ASM_PARAM_H
+#define __ASM_PARAM_H
+
+#define HZ 100
+
+#endif

Index: 2.6/test/include/asm/percpu.h
===================================================================
@@ -0,0 +1,6 @@
+#ifndef __ARCH_I386_PERCPU__
+#define __ARCH_I386_PERCPU__
+
+#include <asm-generic/percpu.h>
+
+#endif /* __ARCH_I386_PERCPU__ */

Index: 2.6/test/include/linux/sched.h
===================================================================
@@ -0,0 +1,7 @@
+#ifndef __LINUX_SCHED_H
+#define __LINUX_SCHED_H
+
+#include <linux/cpumask.h>
+#include <asm/param.h>
+
+#endif

Index: 2.6/test/kernel/timer.c
===================================================================
@@ -0,0 +1,5 @@
+#include <linux/timer.h>
+
+void fastcall init_timer(struct timer_list *timer)
+{
+}

Index: 2.6/test/kernel/workqueue.c
===================================================================
@@ -0,0 +1,17 @@
+#include <linux/workqueue.h>
+
+int keventd_up(void)
+{
+	return 1;
+}
+
+int fastcall schedule_delayed_work(struct work_struct *work, unsigned long delay)
+{
+	return 1;
+}
+
+int schedule_delayed_work_on(int cpu,
+			struct work_struct *work, unsigned long delay)
+{
+	return 1;
+}

Index: 2.6/test/include/asm/thread_info.h
===================================================================
@@ -0,0 +1,13 @@
+#ifndef __ASM_THREADINFO_H
+#define __ASM_THREADINFO_H
+
+#include <linux/config.h>
+#include <linux/compiler.h>
+#include <asm/page.h>
+#include <asm/processor.h>
+
+struct thread_info {
+	unsigned long flags;
+};
+
+#endif

Hi Pekka,

What other interest have you pulled up on this? I mean, have others shown interest in pushing something like this. Today's slab system is starting to become like the IDE where nobody, but a select few sado-masochis, dare to venture in. (I've CC'd them ;) Perhaps it would make the addition of NUMA easier.

Maybe, putting this into RT might be a way to get it tested, and help us with the memory management and a fully preemptible kernel.

-- Steve

For those just coming in, Pekka posted this:

http://marc.theaimsgroup.com/?l=linux-kernel&m=113510997009883&w=2

Hmm. The basics of the SLAB allocator are rather simple.

I'd be interested in seeing an alternate approach. There is the danger that you will end up end up with the same complexity as before.

Quite a long list of unsupported features. These academic papers usually only focus on one thing. The SLAB allocator has to work for a variety of situations though.

It would help to explain what ultimately will be better in the new slab allocator. The complexity could be taken care of by reorganizing the code.

True. I understand the basics of the SLAB allocator very well, but I stumble over the slab.c code quite a bit. This topic came up when Ingo replaced slab with slob in the rt patch and it killed the performance. I introduced a cross between the slab and the slob that sped up the system almost to that of the current slab.

Matt Mackall needs a memory management that uses the smallest amount of memory to handle embedded systems, and brought up the approach referenced in the paper by Bonwick.

Honestly, what I would like is a simpler solution, whether we go with a new approach or reorganize the current slab. I need to get -rt working, and the code in slab is pulling my resources more than they can extend. I'm capable to convert slab today as it is for RT but it will probably take longer than I can afford.

Yes, if we go with a new system, it would not have all the features that the slab has today, but I can live with that, and if I'm involved in the work as it grows, I'll understand it better. The problem is, I wasn't involved in the evolution of slab, and I have to deal with what it grew into, without being there to see why it does what it does today.

-- Steve

please, lets let the -rt tree out of the equation. The SLAB code is fine on upstream, and it was a pure practical maintainance decision to go for SLOB in the -rt tree. Yes, the SLAB code is complex, but i could hardly list any complexity in it tht isnt justified with a performance argument. _Maybe_ the SLAB code could be further cleaned up, maybe it could even be replaced, but we'd have to see the patches first. In any case, the -rt tree is not an argument that matters.

Ingo

You're right about the -rt tree not being an argument for upstream. I used it as an example of the complexities. This is not limited to -rt, but for any other changes as well. Years ago I tried changing the slab to run on a small embedded device with very little memory, and I was pretty much overwhelmed.

Now I see that people are converting it for NUMA. I give them a lot of credit, since they must be smarter than I ;)

-- Steve

while it could possibly be cleaned up a bit, it's one of the best-optimized subsystems Linux has. Most of the "unnecessary complexity" in SLAB is related to a performance or a debugging feature. Many times i have looked at the SLAB code in a disassembler, right next to profile output from some hot workload, and have concluded: 'I couldnt do this any better even with hand-coded assembly'.

SLAB-bashing has become somewhat fashionable, but i really challenge everyone to improve the SLAB code first (to make it more modular, easier to read, etc.), before suggesting replacements.

the SLOB is nice because it gives us a simple option at the other end of the complexity spectrum. The SLOB should remain there. (but it certainly makes sense to make it faster, within certain limits, so i'm not opposing your SLOB patches per se.)

Ingo

Hi Ingo,

I dropped working on the replacement because I wanted to do just that. I sent my patch only because Matt and Steve talked about writing a replacement and thought they would be interested to see it.

I am all for gradual improvements but after taking a stab at it, I starting to think rewriting would be easier, simply because the slab allocator has been clean-up resistant for so long.

Pekka

i'd suggest to try harder, unless you think the _fundamentals_ of the SLAB allocator are wrong. (which you are entitled to believe, but we also have to admit that the SLAB has been around for many years, and works pretty well)

most of the ugliness in slab.c comes from:

1) debugging. There's no easy solutions here, but it could be improved.

2) bootstrapping. Bootstrapping an allocator in a generic way is hard. E.g. what if cache_cache gets larger than 1 page?

3) cache-footprint tricks and lockless fastpath. SLAB does things all the right way, even that ugly memmove is the right thing. Maybe it could be cleaned up, but the fundamental complexity will likely remain.

Ingo

And I think that what was done to SLAB is excellent. But like code I've written, I've often thought, if I rewrote it again, I would do it cleaner since I learned so much in doing it.

So the only way that I can feel that I can actually improve the current system, is to write one from scratch (or start with one that is simple) and try to make it as good as the current system. But by the time I got it there, it would be just as complex as it is today. So only then, I could rewrite it to be better, since I learned why things were done the way they were, and can have that in my mind as I rewrite. So that means writing it twice!

Unfortunately, it is probably the case that those that wrote slab.c are too busy doing other things (or probably just don't want to), to rewite the slab.c with the prior knowledge of what they wrote.

For the short time, I could just force myself to study the code and play with it to see what I break, and figure out "Oh, that's whay that was done!".

-- Steve

Hi, after all the talk over SLAB and SLOBs I decided to make myself useful, and I'm trying very hard to understand the Linux implementation of SLAB. So I'm going through ever line of code and examining it thoroughly, when I find something that could be improved, either performance wise (highly doubtful), clean up wise, documentation wise, enhancement wise, or just have a question, I'll make myself known.

This email is enhancement wise. ;)

I noticed the code for index_of is a creative way of finding the cache index using the compiler to optimize to a single hard coded number. But I couldn't help noticing that it uses two methods to let you know that someone used it wrong. One is at compile time (the correct way), and the other is at run time (not good).

OK, this isn't really an enhancement since the code already works. But this change can help those later who do real enhancements to SLAB.

-- Steve

Index: linux-2.6.15-rc6/mm/slab.c
===================================================================
@@ -315,6 +315,8 @@
  */
 static __always_inline int index_of(const size_t size)
 {
+	extern void __bad_size(void);
+
 	if (__builtin_constant_p(size)) {
 		int i = 0;
 

@@ -325,12 +327,9 @@
 		i++;
 #include "linux/kmalloc_sizes.h"
 #undef CACHE
-		{
-			extern void __bad_size(void);
-			__bad_size();
-		}
+		__bad_size();
 	} else
-		BUG();
+		__bad_size();
 	return 0;
 }
 

Well, I miss a version of kmem_cache_alloc()/kmem_cache_free() that wont play with IRQ masking.

The local_irq_save()/local_irq_restore() pair is quite expensive and could be avoided for several caches that are exclusively used in process context.

(Not speaking of general caches of course, but caches like dentry_cache, filp, ...)

Eric

sure, but adding this sure wont reduce complexity ;)

in any case, on sane platforms (i386, x86_64) an irq-disable is well-optimized in hardware, and is just as fast as a preempt_disable().

Combined with the fact that CLI/STI has no register side-effects, it can even be faster/cheaper, on x86 at least.

Ingo

I'm afraid its not the case on current hardware.

The irq enable/disable pair count for more than 50% the cpu time spent in kmem_cache_alloc()/kmem_cache_free()/kfree()

oprofile results on a dual Opteron 246 :

You can see the high profile numbers right after cli and popf(sti) instructions, popf being VERY expensive.

CPU: Hammer, speed 1993.39 MHz (estimated)
Counted CPU_CLK_UNHALTED events (Cycles outside of halt state) with a unit mask of 0x00 (No unit mask) count 50000

29993     1.9317  kfree
18654     1.2014  kmem_cache_alloc
12962     0.8348  kmem_cache_free

ffffffff8015c370 <kfree>: /* kfree total: 30334 1.9335 */

   770  0.0491 :ffffffff8015c370:       push   %rbp
  2477  0.1579 :ffffffff8015c371:       mov    %rdi,%rbp
               :ffffffff8015c374:       push   %rbx
               :ffffffff8015c375:       sub    $0x8,%rsp
  1792  0.1142 :ffffffff8015c379:       test   %rdi,%rdi
               :ffffffff8015c37c:       je     ffffffff8015c452 <kfree+0xe2>
   122  0.0078 :ffffffff8015c382:       pushfq
  1001  0.0638 :ffffffff8015c383:       popq   (%rsp)
  1456  0.0928 :ffffffff8015c386:       cli
  2489  0.1586 :ffffffff8015c387:       mov    $0xffffffff7fffffff,%rax    <<

...

    72  0.0046 :ffffffff8015c44e:       pushq  (%rsp)
  1080  0.0688 :ffffffff8015c451:       popfq
 13934  0.8882 :ffffffff8015c452:       add    $0x8,%rsp      << HERE >>
   290  0.0185 :ffffffff8015c456:       pop    %rbx
               :ffffffff8015c457:       pop    %rbp
   124  0.0079 :ffffffff8015c458:       retq

ffffffff8015c460 <kmem_cache_free>: /* kmem_cache_free total: 13084 0.8340 */

   388  0.0247 :ffffffff8015c460:       sub    $0x18,%rsp
   365  0.0233 :ffffffff8015c464:       mov    %rbp,0x10(%rsp)
               :ffffffff8015c469:       mov    %rbx,0x8(%rsp)
   121  0.0077 :ffffffff8015c46e:       mov    %rsi,%rbp
   262  0.0167 :ffffffff8015c471:       pushfq
   549  0.0350 :ffffffff8015c472:       popq   (%rsp)
   351  0.0224 :ffffffff8015c475:       cli
  2478  0.1579 :ffffffff8015c476:       mov    %gs:0x34,%eax
   592  0.0377 :ffffffff8015c47e:       cltq
               :ffffffff8015c480:       mov    (%rdi,%rax,8),%rbx
     7 4.5e-04 :ffffffff8015c484:       mov    (%rbx),%eax
   200  0.0127 :ffffffff8015c486:       cmp    0x4(%rbx),%eax
               :ffffffff8015c489:       jae    ffffffff8015c48f 
<kmem_cache_free+0x2f>
               :ffffffff8015c48b:       mov    %eax,%eax
   766  0.0488 :ffffffff8015c48d:       jmp    ffffffff8015c4a0 
<kmem_cache_free+0x40>
               :ffffffff8015c48f:       mov    %rbx,%rsi
    71  0.0045 :ffffffff8015c492:       callq  ffffffff8015c810 
<cache_flusharray>
               :ffffffff8015c497:       mov    (%rbx),%eax
     1 6.4e-05 :ffffffff8015c499:       data16
               :ffffffff8015c49a:       data16
               :ffffffff8015c49b:       data16
               :ffffffff8015c49c:       nop
               :ffffffff8015c49d:       data16
               :ffffffff8015c49e:       data16
               :ffffffff8015c49f:       nop
               :ffffffff8015c4a0:       mov    %rbp,0x10(%rbx,%rax,8)
    20  0.0013 :ffffffff8015c4a5:       incl   (%rbx)
   176  0.0112 :ffffffff8015c4a7:       pushq  (%rsp)
     7 4.5e-04 :ffffffff8015c4aa:       popfq
  6187  0.3944 :ffffffff8015c4ab:       mov    0x8(%rsp),%rbx << HERE>>
   543  0.0346 :ffffffff8015c4b0:       mov    0x10(%rsp),%rbp
               :ffffffff8015c4b5:       add    $0x18,%rsp
               :ffffffff8015c4b9:       retq

ffffffff8015bd70 <kmem_cache_alloc>: /* kmem_cache_alloc total: 18803 1.1985 */

   549  0.0350 :ffffffff8015bd70:       sub    $0x8,%rsp
   700  0.0446 :ffffffff8015bd74:       pushfq
  1427  0.0910 :ffffffff8015bd75:       popq   (%rsp)
   226  0.0144 :ffffffff8015bd78:       cli
  2399  0.1529 :ffffffff8015bd79:       mov    %gs:0x34,%eax  <<HERE>>
   416  0.0265 :ffffffff8015bd81:       cltq
               :ffffffff8015bd83:       mov    (%rdi,%rax,8),%rdx
    21  0.0013 :ffffffff8015bd87:       mov    (%rdx),%eax
   172  0.0110 :ffffffff8015bd89:       test   %eax,%eax
               :ffffffff8015bd8b:       je     ffffffff8015bda1 
<kmem_cache_alloc+0x31>
     8 5.1e-04 :ffffffff8015bd8d:       dec    %eax
  1338  0.0853 :ffffffff8015bd8f:       movl   $0x1,0xc(%rdx)
     9 5.7e-04 :ffffffff8015bd96:       mov    %eax,(%rdx)
     9 5.7e-04 :ffffffff8015bd98:       mov    %eax,%eax
  1146  0.0730 :ffffffff8015bd9a:       mov    0x10(%rdx,%rax,8),%rax
     4 2.5e-04 :ffffffff8015bd9f:       jmp    ffffffff8015bda6 
<kmem_cache_alloc+0x36>
               :ffffffff8015bda1:       callq  ffffffff8015c160 
<cache_alloc_refill>
   154  0.0098 :ffffffff8015bda6:       pushq  (%rsp)
   241  0.0154 :ffffffff8015bda9:       popfq
  9222  0.5878 :ffffffff8015bdaa:       prefetchw (%rax) <<HERE>>
   758  0.0483 :ffffffff8015bdad:       add    $0x8,%rsp
     4 2.5e-04 :ffffffff8015bdb1:       retq

Eric

Isn't that due to taking an interrupt?

because you are not using NMI based profiling?

that's just the profiling interrupt hitting them. You should not analyze irq-safe code with a non-NMI profiling interrupt.

CLI/STI is extremely fast. (In fact in the -rt tree i'm using them within mutexes instead of preempt_enable()/preempt_disable(), because they are faster and generate less register side-effect.)

Ingo

I'm using oprofile on Opteron, and AFAIK it's NMI based.

# grep NMI /proc/interrupts ; sleep 1 ; grep NMI /proc/interrupts
NMI:  391352095 2867983903
NMI:  391359678 2867998498

thats 7583 and 14595 NMI / second on cpu0 and cpu1 respectivly in this sample.

Hm... I rather thought that the cli would cause a rather large hit on the pipeline and certainly on OOE. Is your observation based on any particular instruction stream? Sti, on the otherhand should be fast...

George Anzinger   [email protected]
HRT (High-res-timers):  http://sourceforge.net/projects/high-res-timers/

Just to be exact, the 'cli' is coded as 3 instruction :

pushfq
popq (%rsp)
cli

and the 'sti' is coded as 2 instructions :
pushq (%rsp)
popfq

And 'popfq' seems to be expensive, at least on Opteron machines and if oprofile is not completely wrong...

Eric

Yes, but most of my machines have a ! CONFIG_PREEMPT kernel, so preempt_enable()/preempt_disable() are empty, thus faster than CLI/STI for sure :)

Then, maybe the patch that moves 'current' in a dedicated x86_64 register may help to lower the cost of preempt_enable()/preempt_disable() on a CONFIG_PREEMPT kernel ?

Eric

I'm not sure if it'll make much of a difference over;

mov %gs:offset,%reg

So 'current' already is fairly fast on x86_64.

Exactly my point! The complexity of SLAB keeps it at the "I could not do it better myself" catagory. This wasn't suppose to be a bash, it was actually a complement. But things in the "I could not do it better myself" catagory are usually very hard to modify. Because, unless you are at the level of genius of those that wrote it, you may easily break it. Or put it to a level of "Ha, I can do this better".

I perfectly agree with this statement. As I mentioned earlier, it may have been different if I was a part of the changes that were made. But I wasn't, and that leaves me the task to figure out why things were done the way they were done. Before changes can be made, one must have a full understanding of why things exist as it does.

Don't get me wrong, my comments are more of a frustration with myself that I'm having trouble understanding all that's in SLAB. I understand the SLAB concept, but I'm having trouble with understanding the current implementation. That's _my_ problem. But I will continue to work at it, and maybe I will be able to produce some clean up patches once I do understand.

I like the SLOB code, because it was simple enough for my mortal mind. I actually started to play with it to get a better understanding of the way the SLAB works. It has actually helped in that catagory.

-- Steve

What do you mean by this? ie. what parts of it are a problem, and why?

I think that replacing the buddy allocator probably wouldn't be a good idea because it is really fast and simple for page sized allocations which are the most common, and it is good at naturally avoiding external fragmentation. Internal fragmentation is not much of a problem because it is handled by slab.

I can't see how replacing the buddy allocator with a completely agnostic range allocator could be a win at all.

Perhaps it would make more sense for bootmem, resources, vmalloc, etc. and I guess that is what Matt is suggesting.

SUSE Labs, Novell Inc.

Send instant messages to your online friends http://au.messenger.yahoo.com 

Actually, I wasn't talking about the buddy allocator, since it is probably the best backend allocator to have. I actually like it alot and it doesn't seem to have a problem.

But the slab code has gotten more complex, and probably too feature full. And I'm afraid that Christoph Lameter may be right, in that we could go to another allocation scheme and after adding all the features that the slab has, we would be just as complex.

That part I didn't agree with (replacing the buddy system I mean).

I'd still add slab there, but as I said above, anything else may become too complex. Although, playing with this Magazine thingy is starting to look interesting!

-- Steve

This patch breaks up the SLOBs by caches, and also uses the mem_map pages to find the cache descriptor.

Once again:

TODO: IMPORTANT!!!

1) I haven't cleaned up the kmem_cache_destroy yet, so every time that happens, there's a memory leak.

2) I need to test on SMP.

-- Steve

Index: linux-2.6.15-rc5-rt2/mm/slob.c
===================================================================
@@ -27,6 +27,20 @@
  * are allocated by calling __get_free_pages. As SLAB objects know
  * their size, no separate size bookkeeping is necessary and there is
  * essentially no allocation space overhead.
+ *
+ * Modified by: Steven Rostedt <[email protected]> 12/20/05
+ *
+ * Now we take advantage of the kmem_cache usage.  I've removed
+ * the global slobfree, and created one for every cache.
+ *
+ * For kmalloc/kfree I've reintroduced the usage of cache_sizes,
+ * but only for sizes 32 through PAGE_SIZE >> 1 by order of 2.
+ *
+ * Having the SLOB alloc per size of the cache should speed things up
+ * greatly, not only by making the search paths smaller, but also by
+ * keeping all the caches of similar units.  This way the fragmentation
+ * should not be as big of a problem.
+ *
  */
 
 #include <linux/config.h>

@@ -37,6 +51,8 @@
 #include <linux/module.h>
 #include <linux/timer.h>
 
+#undef DEBUG_CACHE
+
 struct slob_block {
 	int units;
 	struct slob_block *next;

@@ -53,17 +69,66 @@
 };
 typedef struct bigblock bigblock_t;
 
-static slob_t arena = { .next = &arena, .units = 1 };
-static slob_t *slobfree = &arena;
-static DEFINE_SPINLOCK(slob_lock);
+struct kmem_cache {
+	unsigned int size, align;
+	const char *name;
+	slob_t *slobfree;
+	slob_t arena;
+	spinlock_t lock;
+	void (*ctor)(void *, struct kmem_cache *, unsigned long);
+	void (*dtor)(void *, struct kmem_cache *, unsigned long);
+	atomic_t items;
+	unsigned int free;
+	struct list_head list;
+};
 
-#define __get_slob_block(b) ((unsigned long)(b) & ~(PAGE_SIZE-1))
+#define NR_SLOB_CACHES ((PAGE_SHIFT) - 5) /* 32 to PAGE_SIZE-1 by order of 2 */
+#define MAX_SLOB_CACHE_SIZE (PAGE_SIZE >> 1)
 
-static inline struct page *get_slob_page(const void *mem)
+static struct kmem_cache *cache_sizes[NR_SLOB_CACHES];
+static struct kmem_cache *bb_cache;
+
+static struct semaphore	cache_chain_sem;
+static struct list_head cache_chain;
+
+#ifdef DEBUG_CACHE
+static void test_cache(kmem_cache_t *c)
 {
-	void *virt = (void*)__get_slob_block(mem);
+	slob_t *cur = c->slobfree;
+	unsigned int x = -1 >> 2;
 
-	return virt_to_page(virt);
+	do {
+		BUG_ON(!cur->next);
+		cur = cur->next;
+	} while (cur != c->slobfree && --x);
+	BUG_ON(!x);
+}
+#else
+#define test_cache(x) do {} while(0)
+#endif
+
+/*
+ * Here we take advantage of the lru field of the pages that
+ * map to the pages we use in the SLOB.  This is done similar
+ * to what is done with SLAB.
+ *
+ * The lru.next field is used to get the bigblock descriptor
+ *    for large blocks larger than PAGE_SIZE >> 1.
+ *
+ * Set and retrieved by set_slob_block and get_slob_block
+ * respectively.
+ *
+ * The lru.prev field is used to find the cache descriptor
+ *   for small blocks smaller than or equal to PAGE_SIZE >> 1.
+ *
+ * Set and retrieved by set_slob_ptr and get_slob_ptr
+ * respectively.
+ *
+ * The use of lru.next tells us in kmalloc that the page is large.
+ */
+static inline struct page *get_slob_page(const void *mem)
+{
+	return virt_to_page(mem);
 }
 
 static inline void zero_slob_block(const void *b)

@@ -87,18 +152,39 @@
 	page->lru.next = data;
 }
 
-static void slob_free(void *b, int size);
+static inline void *get_slob_ptr(const void *b)
+{
+	struct page *page;
+	page = get_slob_page(b);
+	return page->lru.prev;
+}
+
+static inline void set_slob_ptr(const void *b, void *data)
+{
+	struct page *page;
+	page = get_slob_page(b);
+	page->lru.prev = data;
+}
+
+static void slob_free(kmem_cache_t *cachep, void *b, int size);
 
-static void *slob_alloc(size_t size, gfp_t gfp, int align)
+static void *slob_alloc(kmem_cache_t *cachep, gfp_t gfp, int align)
 {
+	size_t size;
 	slob_t *prev, *cur, *aligned = 0;
-	int delta = 0, units = SLOB_UNITS(size);
+	int delta = 0, units;
 	unsigned long flags;
 
-	spin_lock_irqsave(&slob_lock, flags);
-	prev = slobfree;
+	size = cachep->size;
+	units = SLOB_UNITS(size);
+	BUG_ON(!units);
+
+	spin_lock_irqsave(&cachep->lock, flags);
+	prev = cachep->slobfree;
 	for (cur = prev->next; ; prev = cur, cur = cur->next) {
 		if (align) {
+			while (align < SLOB_UNIT)
+				align <<= 1;
 			aligned = (slob_t *)ALIGN((unsigned long)cur, align);
 			delta = aligned - cur;
 		}

@@ -121,12 +207,16 @@
 				cur->units = units;
 			}
 
-			slobfree = prev;
-			spin_unlock_irqrestore(&slob_lock, flags);
+			cachep->slobfree = prev;
+			test_cache(cachep);
+			if (prev < prev->next)
+				BUG_ON(cur + cur->units > prev->next);
+			spin_unlock_irqrestore(&cachep->lock, flags);
 			return cur;
 		}
-		if (cur == slobfree) {
-			spin_unlock_irqrestore(&slob_lock, flags);
+		if (cur == cachep->slobfree) {
+			test_cache(cachep);
+			spin_unlock_irqrestore(&cachep->lock, flags);
 
 			if (size == PAGE_SIZE) /* trying to shrink arena? */
 				return 0;

@@ -136,14 +226,15 @@
 				return 0;
 
 			zero_slob_block(cur);
-			slob_free(cur, PAGE_SIZE);
-			spin_lock_irqsave(&slob_lock, flags);
-			cur = slobfree;
+			set_slob_ptr(cur, cachep);
+			slob_free(cachep, cur, PAGE_SIZE);
+			spin_lock_irqsave(&cachep->lock, flags);
+			cur = cachep->slobfree;
 		}
 	}
 }
 
-static void slob_free(void *block, int size)
+static void slob_free(kmem_cache_t *cachep, void *block, int size)
 {
 	slob_t *cur, *b = (slob_t *)block;
 	unsigned long flags;

@@ -155,26 +246,29 @@
 		b->units = SLOB_UNITS(size);
 
 	/* Find reinsertion point */
-	spin_lock_irqsave(&slob_lock, flags);
-	for (cur = slobfree; !(b > cur && b < cur->next); cur = cur->next)
+	spin_lock_irqsave(&cachep->lock, flags);
+	for (cur = cachep->slobfree; !(b > cur && b < cur->next); cur = cur->next)
 		if (cur >= cur->next && (b > cur || b < cur->next))
 			break;
 
 	if (b + b->units == cur->next) {
 		b->units += cur->next->units;
 		b->next = cur->next->next;
+		BUG_ON(cur->next == &cachep->arena);
 	} else
 		b->next = cur->next;
 
 	if (cur + cur->units == b) {
 		cur->units += b->units;
 		cur->next = b->next;
+		BUG_ON(b == &cachep->arena);
 	} else
 		cur->next = b;
 
-	slobfree = cur;
+	cachep->slobfree = cur;
 
-	spin_unlock_irqrestore(&slob_lock, flags);
+	test_cache(cachep);
+	spin_unlock_irqrestore(&cachep->lock, flags);
 }
 
 static int FASTCALL(find_order(int size));

@@ -188,15 +282,24 @@
 
 void *kmalloc(size_t size, gfp_t gfp)
 {
-	slob_t *m;
 	bigblock_t *bb;
 
-	if (size < PAGE_SIZE - SLOB_UNIT) {
-		m = slob_alloc(size + SLOB_UNIT, gfp, 0);
-		return m ? (void *)(m + 1) : 0;
+	/*
+	 * If the size is less than PAGE_SIZE >> 1 then
+	 * we use the generic caches.  Otherwise, we
+	 * just allocate the necessary pages.
+	 */
+	if (size <= MAX_SLOB_CACHE_SIZE) {
+		int i;
+		int order;
+		for (i=0, order=32; i < NR_SLOB_CACHES; i++, order <<= 1)
+			if (size <= order)
+				break;
+		BUG_ON(i == NR_SLOB_CACHES);
+		return kmem_cache_alloc(cache_sizes[i], gfp);
 	}
 
-	bb = slob_alloc(sizeof(bigblock_t), gfp, 0);
+	bb = slob_alloc(bb_cache, gfp, 0);
 	if (!bb)
 		return 0;
 

@@ -208,7 +311,7 @@
 		return bb->pages;
 	}
 
-	slob_free(bb, sizeof(bigblock_t));
+	slob_free(bb_cache, bb, sizeof(bigblock_t));
 	return 0;
 }
 

@@ -216,19 +319,26 @@
 
 void kfree(const void *block)
 {
+	kmem_cache_t *c;
 	bigblock_t *bb;
 
 	if (!block)
 		return;
 
+	/*
+	 * look into the page of the allocated block to
+	 * see if this is a big allocation or not.
+	 */
 	bb = get_slob_block(block);
 	if (bb) {
 		free_pages((unsigned long)block, bb->order);
-		slob_free(bb, sizeof(bigblock_t));
+		slob_free(bb_cache, bb, sizeof(bigblock_t));
 		return;
 	}
 
-	slob_free((slob_t *)block - 1, 0);
+	c = get_slob_ptr(block);
+	kmem_cache_free(c, (void *)block);
+
 	return;
 }
 

@@ -237,6 +347,7 @@
 unsigned int ksize(const void *block)
 {
 	bigblock_t *bb;
+	kmem_cache_t *c;
 
 	if (!block)
 		return 0;

@@ -245,14 +356,16 @@
 	if (bb)
 		return PAGE_SIZE << bb->order;
 
-	return ((slob_t *)block - 1)->units * SLOB_UNIT;
+	c = get_slob_ptr(block);
+	return c->size;
 }
 
-struct kmem_cache {
-	unsigned int size, align;
-	const char *name;
-	void (*ctor)(void *, struct kmem_cache *, unsigned long);
-	void (*dtor)(void *, struct kmem_cache *, unsigned long);
+static slob_t cache_arena = { .next = &cache_arena, .units = 0 };
+struct kmem_cache cache_cache = {
+	.name = "cache",
+	.slobfree = &cache_cache.arena,
+	.arena = { .next = &cache_cache.arena, .units = 0 },
+	.lock = SPIN_LOCK_UNLOCKED(cache_cache.lock)
 };
 
 struct kmem_cache *kmem_cache_create(const char *name, size_t size,

@@ -261,8 +374,22 @@
 	void (*dtor)(void*, struct kmem_cache *, unsigned long))
 {
 	struct kmem_cache *c;
+	void *p;
+
+	c = slob_alloc(&cache_cache, flags, 0);
+
+	memset(c, 0, sizeof(*c));
 
-	c = slob_alloc(sizeof(struct kmem_cache), flags, 0);
+	c->size = PAGE_SIZE;
+	c->arena.next = &c->arena;
+	c->arena.units = 0;
+	c->slobfree = &c->arena;
+	atomic_set(&c->items, 0);
+	spin_lock_init(&c->lock);
+
+	p = slob_alloc(c, 0, PAGE_SIZE-1);
+	if (p)
+		free_page((unsigned long)p);
 
 	if (c) {
 		c->name = name;

@@ -274,6 +401,9 @@
 		if (c->align < align)
 			c->align = align;
 	}
+	down(&cache_chain_sem);
+	list_add_tail(&c->list, &cache_chain);
+	up(&cache_chain_sem);
 
 	return c;
 }

@@ -281,7 +411,17 @@
 
 int kmem_cache_destroy(struct kmem_cache *c)
 {
-	slob_free(c, sizeof(struct kmem_cache));
+	down(&cache_chain_sem);
+	list_del(&c->list);
+	up(&cache_chain_sem);
+
+	BUG_ON(atomic_read(&c->items));
+
+	/*
+	 * WARNING!!! Memory leak!
+	 */
+	printk("FIX ME: need to free memory\n");
+	slob_free(&cache_cache, c, sizeof(struct kmem_cache));
 	return 0;
 }
 EXPORT_SYMBOL(kmem_cache_destroy);

@@ -290,11 +430,16 @@
 {
 	void *b;
 
-	if (c->size < PAGE_SIZE)
-		b = slob_alloc(c->size, flags, c->align);
+	atomic_inc(&c->items);
+
+	if (c->size <= MAX_SLOB_CACHE_SIZE)
+		b = slob_alloc(c, flags, c->align);
 	else
 		b = (void *)__get_free_pages(flags, find_order(c->size));
 
+	if (!b)
+		return 0;
+
 	if (c->ctor)
 		c->ctor(b, c, SLAB_CTOR_CONSTRUCTOR);
 

@@ -304,11 +449,13 @@
 
 void kmem_cache_free(struct kmem_cache *c, void *b)
 {
+	atomic_dec(&c->items);
+
 	if (c->dtor)
 		c->dtor(b, c, 0);
 
-	if (c->size < PAGE_SIZE)
-		slob_free(b, c->size);
+	if (c->size <= MAX_SLOB_CACHE_SIZE)
+		slob_free(c, b, c->size);
 	else
 		free_pages((unsigned long)b, find_order(c->size));
 }

@@ -326,22 +473,62 @@
 }
 EXPORT_SYMBOL(kmem_cache_name);
 
-static struct timer_list slob_timer = TIMER_INITIALIZER(
-	(void (*)(unsigned long))kmem_cache_init, 0, 0);
+static char cache_names[NR_SLOB_CACHES][15];
 
 void kmem_cache_init(void)
 {
-	void *p = slob_alloc(PAGE_SIZE, 0, PAGE_SIZE-1);
+	static int done;
+	void *p;
 
-	if (p)
-		free_page((unsigned long)p);
-
-	mod_timer(&slob_timer, jiffies + HZ);
+	if (!done) {
+		int i;
+		int size = 32;
+		done = 1;
+
+		init_MUTEX(&cache_chain_sem);
+		INIT_LIST_HEAD(&cache_chain);
+
+		cache_cache.size = PAGE_SIZE;
+		p = slob_alloc(&cache_cache, 0, PAGE_SIZE-1);
+		if (p)
+			free_page((unsigned long)p);
+		cache_cache.size = sizeof(struct kmem_cache);
+
+		bb_cache = kmem_cache_create("bb_cache",sizeof(bigblock_t), 0,
+					     GFP_KERNEL, NULL, NULL);
+		for (i=0; i < NR_SLOB_CACHES; i++, size <<= 1)
+			cache_sizes[i] = kmem_cache_create(cache_names[i], size, 0,
+							   GFP_KERNEL, NULL, NULL);
+	}
 }
 
 atomic_t slab_reclaim_pages = ATOMIC_INIT(0);
 EXPORT_SYMBOL(slab_reclaim_pages);
 
+static void test_slob(slob_t *s)
+{
+	slob_t *p;
+	long x = 0;
+
+	for (p=s->next; p != s && x < 10000; p = p->next, x++)
+		printk(".");
+}
+
+void print_slobs(void)
+{
+	struct list_head *curr;
+
+	list_for_each(curr, &cache_chain) {
+		kmem_cache_t *c = list_entry(curr, struct kmem_cache, list);
+
+		printk("%s items:%d",
+		       c->name?:"<none>",
+		       atomic_read(&c->items));
+		test_slob(&c->arena);
+		printk("\n");
+	}
+}
+
 #ifdef CONFIG_SMP
 
 void *__alloc_percpu(size_t size, size_t align)

Oh, but if this does work out, it _will_ improve SMP performance greatly!

-- Steve

No. I experienced horrible performance running the original patch with the SLOB on my uniprocessor system vs. the patch with Steven's SLAB patch applied on the same system. In fact I am currently running the latter on that system now. With the original patch the system is really unusable.

   kr