2.6.4-rc1-mm2

2.6.4-rc1-mm2

[Andrew Morton]

ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.4-rc1/2.6.4-rc1-mm2/

- More VM tweaks and tuneups

- Added a 4k kernel- and irq-stack option for x86

- Largeish NFS client update




Changes since 2.6.4-rc1-mm1:


 linus.patch
 bk-acpi.patch
 bk-alsa.patch
 bk-driver-core.patch
 bk-input.patch
 bk-netdev.patch
 bk-pci.patch
 bk-scsi.patch
 bk-usb.patch

 Latest versions of external bug^Wtrees

-umount-dataloss-fix.patch
-ppc64-iseries-mmu-hashtable-fix.patch
-ppc64-export-numa-symbols.patch
-ppc64-cpu_vm_mask-fix.patch
-doc-index-updates.patch
-poweroff-atomicity-fix.patch
-bio-highmem-fix.patch
-ini9100u-build-fix.patch
-move-scatterwalk-functions-to-own-file.patch
-in-place-encryption-fix.patch
-dm-crypt-cleanups.patch
-dm-crypt-end_io-bv_offset-fix.patch
-proc-thread-visibility-revert.patch
-zr36067-update.patch
-keyspan-c99-fixes.patch
-hisax-c99-fixes.patch
-raid1-bio_put-oops-fix.patch
-README-update.patch
-DCSSBLK-depends-on-s390.patch
-xprt_create_socket-fix.patch
-tty-drivers-devfs-fix.patch
-vt-mode-changes-fix.patch
-sys_alarm-retval-fix.patch
-gcc-35-lec-fix.patch
-ip_rt_init-sizing-fix.patch
-buslogic-sections-fix.patch
-remove-make-dep-references.patch
-use-set_task_cpu-in-kthread_bind.patch
-tcp-oops-fix.patch
-swap-config-clarity.patch
-powernow-k8-fix.patch
-x86_64-update.patch
-libata-fix.patch
-usb-pc-watchdog-implementation.patch
-pdflush-use-kthread.patch
-firmware-pin-module.patch
-firmware-delay-hotplug.patch

 Merged

+fastcall-warning-fixes-2.patch

 Fix up fastcall-warning-fixes.patch

+ppc64-xmon-survival-fix.patch

 ppc64 debugger fix

+put_compat_timespec-prototype-fix.patch

 Fix a warning

+sparc-sys_ioperm-fix.patch

 Fix sparc build breakage

-sched-group-power-warning-fixes.patch

 Folded into sched-group-power.patch

+sched-smt-nice-handling.patch

 Improve the CPU scheduler's balancing of differently-niced tasks between
 siblings.

+nfs-improved-writeback-strategy.patch
+nfs-simplify-config-options.patch
+nfs-fix-msync.patch
+nfs-mount-return-useful-errors.patch
+nfs-misc-minor-fixes.patch
+nfs-lockd-sync-01.patch
+nfs-lockd-sync-02.patch
+nfs-lockd-sync-03.patch
+nfs-lockd-sync-04.patch
+nfs-rpc-remove-redundant-memset.patch
+nfs-tunable-rpc-slot-table.patch
+nfs-short-read-fix.patch

 NFS updates

-sleep_on-needs_lock_kernel.patch

 This broke, and seems to have served its purpose.

-apic-apic-setup-buggy.patch
-mmconfig.patch
-sal-support.patch
-expanded-pci-config-space-core.patch

 Still under development in various other trees.

+mq-update-01.patch

 Small fixes to the posix message queue code

+use-wait_task_inactive-in-kthread_bind.patch

 kthread synchronisation fix

+HPFS10-fix-RC4-rc1.patch

 Another HPFS fixup

+selinux-cleanup-binary-mount-data.patch

 Make SELinux handle binary mount data more nicely.

+udffs-update.patch

 Update to the UDF filesystem

+kbuild-redundant-CFLAGS.patch

 kbuild cleanup

+numa-aware-zonelist-builder.patch

 Optimise the memory zonelists layout for NUMA

+remove-redundant-unplug_timer-deletion.patch

 Kill unneeded del_timer()

+alpha-switch-semaphores.patch

 Reimplement alpha semaphores

+serial_core-build-fix.patch

 Compile fix

+blk-unplug-when-max-request-queued.patch

 auto-unplug a disk queue when it has assembled a full-sized request

+queue_work_on_cpu.patch

 Add queue_work_on_cpu() to the workqueue API.

+sb16-sample-size-fix.patch

 sb16 driver fix

+ext2-ext3-ENOSPC-fix.patch

 Fix bogus ENOSPC in ext3 and ext3 when using the `oldalloc' mount option.

+missing-MODULE_LICENSEs.patch

 Add some GPL tags

+v4l1-compatibility-module-fix.patch

 v4l fix

+i2o-fixes.patch

 i2o driver fixes

+m68k-rename-sys_functions.patch

 m68k sys_* namespace cleanup

+pdc_202xx_old-update.patch
+pdc202xx_new-update.patch
+siimage-update.patch
+ide-cleanups-01.patch
+ide-cleanups-02.patch
+ide-cleanups-03.patch

 IDE updates

+kswapd-avoid-higher-zones-reverse-direction.patch
+kswapd-avoid-higher-zones-reverse-direction-fix.patch
+vm-batch-inactive-scanning.patch
+vm-batch-inactive-scanning-fix.patch
+vm-balance-refill-rate.patch
+shrink-inode-cache-harder.patch

 More memory reclaim work

-ia64-lockmeter-fix.patch
-lockmeter-2.2-cruft.patch

 Folded into lockmeter.patch

+lockmeter-ia64-fix.patch

 Fix lockmeter on ia64

+ia32-4k-stacks.patch
+ia32-4k-stacks-build-fix.patch
+4k-stacks-in-modversions-magic.patch

 4k stacks for x86




All 245 patches:


linus.patch

bk-acpi.patch

bk-alsa.patch

bk-driver-core.patch

bk-input.patch

bk-netdev.patch

bk-pci.patch

bk-scsi.patch

bk-usb.patch

mm.patch
  add -mmN to EXTRAVERSION

dma_sync_for_device-cpu.patch
  dma_sync_for_{cpu,device}()

move-dma_consistent_dma_mask.patch
  move consistent_dma_mask to the generic device

move-dma_consistent_dma_mask-x86_64-fix.patch

kgdb-ga.patch
  kgdb stub for ia32 (George Anzinger's one)
  kgdbL warning fix
  kgdb buffer overflow fix
  kgdbL warning fix
  kgdb: CONFIG_DEBUG_INFO fix
  x86_64 fixes
  correct kgdb.txt Documentation link (against  2.6.1-rc1-mm2)

kgdb-ga-recent-gcc-fix.patch
  kgdb: fix for recent gcc

kgdboe-netpoll.patch
  kgdb-over-ethernet via netpoll

kgdboe-non-ia32-build-fix.patch

kgdb-warning-fixes.patch
  kgdb warning fixes

kgdb-x86_64-support.patch
  kgdb-x86_64-support.patch for 2.6.2-rc1-mm3

kgdb-THREAD_SIZE-fixes.patch
  THREAD_SIZE fixes for kgdb

must-fix.patch
  must fix lists update
  must fix list update
  mustfix update

must-fix-update-5.patch
  must-fix update

fastcall-warning-fixes.patch
  fastcall / regparm fixes

fastcall-warning-fixes-2.patch
  more fastcall fixes

ppc64-xmon-survival-fix.patch
  ppc64: Make xmon survive exit after soft reset

ppc64-reloc_hide.patch

put_compat_timespec-prototype-fix.patch
  fix put_compat_timespec prototype

compat-signal-noarch-2004-01-29.patch
  Generic 32-bit compat for copy_siginfo_to_user

compat-generic-ipc-emulation.patch
  generic 32 bit emulation for System-V IPC

sparc-sys_ioperm-fix.patch
  sparc: fix sys_ioperm

remove-sys_ioperm-stubs.patch
  Clean up sys_ioperm stubs

readdir-cleanups.patch
  readdir() cleanups

invalidate_inodes-speedup.patch
  invalidate_inodes speedup
  more invalidate_inodes speedup fixes

cfq-4.patch
  CFQ io scheduler
  CFQ fixes

config_spinline.patch
  uninline spinlocks for profiling accuracy.

pdflush-diag.patch

zap_page_range-debug.patch
  zap_page_range() debug

get_user_pages-handle-VM_IO.patch
  fix get_user_pages() against mappings of /dev/mem

support-zillions-of-scsi-disks.patch
  support many SCSI disks

pci_set_power_state-might-sleep.patch

CONFIG_STANDALONE-default-to-n.patch
  Make CONFIG_STANDALONE default to N

extra-buffer-diags.patch

CONFIG_SYSFS.patch
  From: Pat Mochel <mochel@osdl.org>
  Subject: [PATCH] Add CONFIG_SYSFS

CONFIG_SYSFS-boot-from-disk-fix.patch

slab-leak-detector.patch
  slab leak detector
  mm/slab.c warning in cache_alloc_debugcheck_after

scale-nr_requests.patch
  scale nr_requests with TCQ depth

truncate_inode_pages-check.patch

local_bh_enable-warning-fix.patch

sched-find_busiest_node-resolution-fix.patch
  sched: improved resolution in find_busiest_node

sched-domains.patch
  sched: scheduler domain support
  sched: fix for NR_CPUS > BITS_PER_LONG
  sched: clarify find_busiest_group
  sched: find_busiest_group arithmetic fix

sched-domains-improvements.patch
  sched domains kernbench improvements

sched-clock-fixes.patch
  fix sched_clock()

sched-sibling-map-to-cpumask.patch
  sched: cpu_sibling_map to cpu_mask
  p4-clockmod sibling_map fix
  p4-clockmod: handle more than two siblings

sched-domains-i386-ht.patch
  sched: implement domains for i386 HT
  sched: Fix CONFIG_SMT oops on UP
  sched: fix SMT + NUMA bug
  Change arch_init_sched_domains to use cpu_online_map
  Fix build with NR_CPUS > BITS_PER_LONG

sched-domain-tweak.patch
  i386-sched-domain code consolidation

sched-no-drop-balance.patch
  sched: handle inter-CPU jiffies skew

sched-directed-migration.patch
  sched_balance_exec(): don't fiddle with the cpus_allowed mask

sched-domain-debugging.patch
  sched_domain debugging

sched-domain-balancing-improvements.patch
  scheduler domain balancing improvements

sched-group-power.patch
  sched-group-power
  sched-group-power warning fixes

sched-domains-use-cpu_possible_map.patch
  sched_domains: use cpu_possible_map

sched-smt-nice-handling.patch
  sched: SMT niceness handling

fa311-mac-address-fix.patch
  wrong mac address with netgear FA311 ethernet card

laptop-mode-2.patch
  laptop-mode for 2.6, version 6
  Documentation/laptop-mode.txt
  laptop-mode documentation updates
  Laptop mode documentation addition
  laptop mode simplification

pid_max-fix.patch
  Bug when setting pid_max > 32k

use-soft-float.patch
  Use -msoft-float

DRM-cvs-update.patch
  DRM cvs update

drm-include-fix.patch

process-migration-speedup.patch
  Reduce TLB flushing during process migration

hotplugcpu-generalise-bogolock.patch
  Atomic Hotplug CPU: Generalize Bogolock

hotplugcpu-generalise-bogolock-fix-for-kthread-stop-using-signals.patch

hotplugcpu-use-bogolock-in-modules.patch
  Atomic Hotplug CPU: Use Bogolock in module.c

hotplugcpu-core.patch
  Atomic Hotplug CPU: Hotplug CPU Core

stop_machine-warning-fix.patch

hotplugcpu-core-sparc64-build-fix.patch
  hotplugcpu-core sparc64 build fix

hotplugcpu-core-fix-for-kthread-stop-using-signals.patch

migrate_to_cpu-dependency-fix.patch
  migrate_to_cpu() dependency fix

hotplugcpu-core-drain_local_pages-fix.patch
  split drain_local_pages

hotplugcpu-rcupdate-many-cpus-fix.patch
  CPU hotplug, rcupdate high NR_CPUS fix

nfs-31-attr.patch
  NFSv2/v3/v4: New attribute revalidation code

nfs-reconnect-fix.patch

nfs-mount-fix.patch
  Update to NFS mount....

nfs-d_drop-lowmem.patch
  NFS: handle nfs_fhget() error

nfs-avoid-i_size_write.patch
  NFS: avoid unlocked i_size_write()

nfs_unlink-oops-fix.patch
  nfs: fix "busy inodes after umount"

nfs-remove-XID-spinlock.patch
  nfs: Remove an unnecessary spinlock from XID generation...

nfs-misc-rpc-fixes.patch
  nfs: Misc RPC fixes...

nfs-improved-writeback-strategy.patch
  nfs: improve writeback caching

nfs-simplify-config-options.patch
  nfs: simplify client configuration options.

nfs-fix-msync.patch
  nfs: fix msync()

nfs-mount-return-useful-errors.patch
  nfs: make mount command return more useful errors

nfs-misc-minor-fixes.patch
  nfs: misc minor fixes

nfs-lockd-sync-01.patch
  nfs: sync lockd to 2.4.x

nfs-lockd-sync-02.patch
  nfs: sync lockd to 2.4.x

nfs-lockd-sync-03.patch
  nfs: sync lockd to 2.4.x

nfs-lockd-sync-04.patch
  nfs: sync lockd to 2.4.x

nfs-rpc-remove-redundant-memset.patch
  nfs: remove unnecessary memset() in RPC

nfs-tunable-rpc-slot-table.patch
  nfs: make the RPC slot table size a tunable value.

nfs-short-read-fix.patch
  nfs: fix an NFSv2 read bug

nfs-server-in-root_server_path.patch
  Pull NFS server address out of root_server_path

non-readable-binaries.patch
  Handle non-readable binfmt_misc executables

binfmt_misc-credentials.patch
  binfmt_misc: improve calaulation of interpreter's credentials

initramfs-search-for-init.patch
  search for /init for initramfs boots

centaur-crypto-core-support.patch
  First steps toward VIA crypto support

adaptive-lazy-readahead.patch
  adaptive lazy readahead

ext3-journalled-quotas.patch
  ext3: Journalled quotas

ext3-journalled-quotas-warning-fix.patch

ext3-journalled-quotas-cleanups.patch

sysfs_remove_dir-race-fix.patch
  sysfs_remove_dir-vs-dcache_readdir race fix

sysfs_remove_subdir-dentry-leak-fix.patch
  Fix dentry refcounting in sysfs_remove_group()

per-node-rss-tracking.patch
  Track per-node RSS for NUMA

aic7xxx-deadlock-fix.patch
  aic7xxx deadlock fix

futex_wait-debug.patch
  futex_wait debug

module_exit-deadlock-fix.patch
  module unload deadlock fix

tulip-printk-cleanup.patch
  tulip printk cleanup

parport-01-move-exports.patch
  parport: move exports

parport-02-use-module_init.patch
  parport: use module_init() for low-level driver init

parport-03-sysctls-use-module_init.patch
  parport: use module_init() for sysctl registration

parport-04-move-option-parsing.patch
  parport: move parport_pc option parsing

parport-irq-warning-fix.patch
  parport warning fixes

parport-05-parport_pc_probe_port-fixes.patch
  parport: sanitize parport_pc_probe_port()

parport-06-refcounting-fixes.patch
  parport: refcounting fixes

parport-07-unregister-fixes.patch
  parport: parport_unregister_port() splitups abd fixes

parport-08-parport_announce-cleanups.patch
  parport: parport_announce_port() cleanup

parport-09-track-used-ports.patch
  parport: parport_pc(): keep track of ports

parport-09-track-used-ports-fix.patch

parport-10-sunbpp-track-ports.patch
  parport: parport_sunbpp(): keep track of ports

parport-11-remove-parport_enumerate.patch
  parport: remove parport_enumerate()

parport-12-driver-list-cleanup.patch
  parport: use list.h for driver list

hitachi-scsi_devinfo-fix.patch
  Add Hitachi 9960 Storage on SCSI devlist as BLIST_SPARSELUN|BLIST_LARGELUN

selinux-inode-race-trap.patch
  Try to diagnose Bug 2153

ext3-dirty-debug-patch.patch
  ext3 debug patch

ufs2-01.patch
  read-only support for UFS2

ide-scsi-error-handling-fixes.patch
  ide-scsi error handling fixes

fb_console_init-fix.patch
  fb_console_init fix

poll-select-longer-timeouts.patch
  poll()/select(): support longer timeouts

poll-select-range-check-fix.patch
  poll()/select() range checking fix

poll-select-handle-large-timeouts.patch
  poll()/select(): handle long timeouts

zwane-is-floppy-maintainer-now.patch
  floppy oops fix(?)

pcmcia-debugging-rework-1.patch
  Overhaul PCMCIA debugging (1)

cs_err-compile-fix.patch
  pcmcia: workaround for gcc-2.95 bug in cs_err()

pcmcia-debugging-rework-2.patch
  Overhaul PCMCIA debugging (2)

distribute-early-allocations-across-nodes.patch
  Manfred's patch to distribute boot allocations across nodes

time-interpolator-fix.patch
  time interpolator fix

kmsg-nonblock.patch
  teach /proc/kmsg about O_NONBLOCK

mixart-build-fix.patch
  CONFIG_SND_MIXART doesn't compile

add-a-slab-for-ethernet.patch
  Add a kmalloc slab for ethernet packets

remove-__io_virt_debug.patch
  remove __io_virt_debug

rioctrl-retval-fixes.patch
  char/rio/rioctrl: fix ioctl return values

genrtc-cleanups.patch
  genrtc: cleanups

piix_ide_init-can-be-__init.patch
  piix_ide_init can be __init

fusion-use-min-max.patch
  message/fusion: use kernel min/max

doc2000-warning-fixes.patch
  mtd/doc200x: warning fixes

initrd-kconfig-dependencies.patch
  Fix initrd Kconfig dependencies

queue-congestion-callout.patch
  Add queue congestion callout

queue-congestion-dm-implementation.patch
  Implement queue congestion callout for device mapper

scsi-host-allocation-fix.patch
  SCSI host num allocation improvement

i386-early-memory-cleanup.patch
  i386 very early memory detection cleanup patch

modular-mce-handler.patch
  Allow X86_MCE_NONFATAL to be a module

LOOP_CHANGE_FD.patch
  LOOP_CHANGE_FD ioctl

cs46_xx-c99-fix.patch
  c99 initializers for cs46xx_wrapper

remove-more-KERNEL_SYSCALLS.patch
  further __KERNEL_SYSCALLS__ removal

remove-more-KERNEL_SYSCALLS-build-fix.patch
  build fix for remove-more-KERNEL_SYSCALLS.patch

remove-more-KERNEL_SYSCALLS-build-fix-2.patch
  fix the build for remove-more-KERNEL_SYSCALLS

remove-nlmclnt_grace_wait.patch
  kill a dead function in lockd

mq-01-codemove.patch
  posix message queues: code move

mq-02-syscalls.patch
  posix message queues: syscall stubs

mq-03-core.patch
  posix message queues: implementation

mq-03-core-update.patch
  posix message queues: update to core patch

mq-04-linuxext-poll.patch
  posix message queues: linux-specific poll extension

mq-05-linuxext-mount.patch
  posix message queues: made user mountable

mq-update-01.patch
  posix message queue update

use-wait_task_inactive-in-kthread_bind.patch
  use wait_task_inactive() in kthread_bind()

HPFS1-hpfs2-RC4-rc1.patch

HPFS2-hpfs_namei-RC4-rc1.patch

HPFS3-hpfs_iget-RC4-rc1.patch

HPFS4-hpfs_lock_iget-RC4-rc1.patch

HPFS5-hpfs_locking-RC4-rc1.patch

HPFS6-hpfs_cleanup-RC4-rc1.patch

HPFS7-hpfs_cleanup2-RC4-rc1.patch

HPFS8-hpfs_race2-RC4-rc1.patch

HPFS9-hpfs_deadlock-RC4-rc1.patch

HPFS10-fix-RC4-rc1.patch

selinux-cleanup-binary-mount-data.patch
  selinux: clean up binary mount data

udffs-update.patch
  UDF filesystem update

kbuild-redundant-CFLAGS.patch
  kbuild: Remove CFLAGS assignment in i386/mach-*/Makefile

numa-aware-zonelist-builder.patch
  NUMA-aware zonelist builder

remove-redundant-unplug_timer-deletion.patch
  Redundant unplug_timer deletion

alpha-switch-semaphores.patch
  Alpha: switch semaphores to PPC scheme

serial_core-build-fix.patch
  serial_core.h needs sched.h

blk-unplug-when-max-request-queued.patch
  block: unplug the queue when a single full-sized request is ready

queue_work_on_cpu.patch
  Add queue_work_on_cpu() workqueue function

sb16-sample-size-fix.patch
  sb16 sample size fix

ext2-ext3-ENOSPC-fix.patch
  ext2/ext3 -ENOSPC bug

missing-MODULE_LICENSEs.patch
  add missing MODULE_LICENSEs

v4l1-compatibility-module-fix.patch
  v4l1 compatibility module fix.

i2o-fixes.patch
  i2o subsystem minor bugfixes

m68k-rename-sys_functions.patch
  m68k: rename sys_* functions

pdc_202xx_old-update.patch
  ide: small update for pdc202xx_old driver

pdc202xx_new-update.patch
  ide: update for pdc202xx_new driver

siimage-update.patch
  ide: update for siimage driver

ide-cleanups-01.patch
  ide: IDE cleanups

ide-cleanups-02.patch
  ide: IDE cleanups

ide-cleanups-03.patch
  ide: IDE cleanups

instrument-highmem-page-reclaim.patch
  vm: per-zone vmscan instrumentation

blk_congestion_wait-return-remaining.patch
  return remaining jiffies from blk_congestion_wait()

vmscan-remove-priority.patch
  mm/vmscan.c: remove unused priority argument.

kswapd-throttling-fixes.patch
  kswapd throttling fixes

vm-refill_inactive-preserve-referenced.patch
  vmscan: preserve page referenced info in refill_inactive()

shrink_slab-precision-fix.patch
  shrink_slab: math precision fix

try_to_free_pages-shrink_slab-evenness.patch
  vm: shrink slab evenly in try_to_free_pages()

vmscan-total_scanned-fix.patch
  vmscan: fix calculation of number of pages scanned

shrink_slab-for-all-zones-2.patch
  vm: scan slab in response to highmem scanning

zone-balancing-fix-2.patch
  vmscan: zone balancing fix

vmscan-control-by-nr_to_scan-only.patch
  vmscan: drive everything via nr_to_scan

vmscan-balance-zone-scanning-rates.patch
  Balance inter-zone scan rates

vmscan-dont-throttle-if-zero-max_scan.patch
  vmscan: avoid bogus throttling

kswapd-avoid-higher-zones.patch
  kswapd: avoid unnecessary reclaiming from higher zones

kswapd-avoid-higher-zones-reverse-direction.patch
  kswapd: fix lumpy page reclaim

kswapd-avoid-higher-zones-reverse-direction-fix.patch
  fix the kswapd zone scanning algorithm

vmscan-throttle-later.patch
  vmscan: less throttling of page allocators and kswapd

vm-batch-inactive-scanning.patch
  vmscan: batch up inactive list scanning work

vm-batch-inactive-scanning-fix.patch
  fix vm-batch-inactive-scanning.patch

vm-balance-refill-rate.patch
  vm: balance inactive zone refill rates

shrink-inode-cache-harder.patch
  vm: shrink icache harder

slab-no-higher-order.patch
  slab: avoid higher-order allocations

list_del-debug.patch
  list_del debug check

oops-dump-preceding-code.patch
  i386 oops output: dump preceding code

lockmeter.patch
  lockmeter

lockmeter-ia64-fix.patch
  ia64 CONFIG_LOCKMETER fix

4g-2.6.0-test2-mm2-A5.patch
  4G/4G split patch
  4G/4G: remove debug code
  4g4g: pmd fix
  4g/4g: fixes from Bill
  4g4g: fpu emulation fix
  4g/4g usercopy atomicity fix
  4G/4G: remove debug code
  4g4g: pmd fix
  4g/4g: fixes from Bill
  4g4g: fpu emulation fix
  4g/4g usercopy atomicity fix
  4G/4G preempt on vstack
  4G/4G: even number of kmap types
  4g4g: fix __get_user in slab
  4g4g: Remove extra .data.idt section definition
  4g/4g linker error (overlapping sections)
  4G/4G: remove debug code
  4g4g: pmd fix
  4g/4g: fixes from Bill
  4g4g: fpu emulation fix
  4g4g: show_registers() fix
  4g/4g usercopy atomicity fix
  4g4g: debug flags fix
  4g4g: Fix wrong asm-offsets entry
  cyclone time fixmap fix
  4G/4G preempt on vstack
  4G/4G: even number of kmap types
  4g4g: fix __get_user in slab
  4g4g: Remove extra .data.idt section definition
  4g/4g linker error (overlapping sections)
  4G/4G: remove debug code
  4g4g: pmd fix
  4g/4g: fixes from Bill
  4g4g: fpu emulation fix
  4g4g: show_registers() fix
  4g/4g usercopy atomicity fix
  4g4g: debug flags fix
  4g4g: Fix wrong asm-offsets entry
  cyclone time fixmap fix
  use direct_copy_{to,from}_user for kernel access in mm/usercopy.c
  4G/4G might_sleep warning fix
  4g/4g pagetable accounting fix
  Fix 4G/4G and WP test lockup
  4G/4G KERNEL_DS usercopy again
  Fix 4G/4G X11/vm86 oops
  Fix 4G/4G athlon triplefault
  4g4g SEP fix
  Fix 4G/4G split fix for pre-pentiumII machines
  4g/4g PAE ACPI low mappings fix
  zap_low_mappings() cannot be __init
  4g/4g: remove printk at boot

4g4g-THREAD_SIZE-fixes.patch

4g4g-locked-userspace-copy.patch
  Do a locked user-space copy for 4g/4g

ia32-4k-stacks.patch
  ia32: 4Kb stacks (and irqstacks) patch

ia32-4k-stacks-build-fix.patch
  4k stacks build fix

4k-stacks-in-modversions-magic.patch
  Add 4k stacks to module version magic

ppc-fixes.patch
  make mm4 compile on ppc

O_DIRECT-race-fixes-rollup.patch
  O_DIRECT data exposure fixes

O_DIRECT-ll_rw_block-vs-block_write_full_page-fix.patch
  Fix race between ll_rw_block() and block_write_full_page()

blockdev-direct-io-speedup.patch
  blockdev direct-io speedups

O_DIRECT-vs-buffered-fix.patch
  Fix O_DIRECT-vs-buffered data exposure bug

O_DIRECT-vs-buffered-fix-pdflush-hang-fix.patch
  pdflush hang fix

serialise-writeback-fdatawait.patch
  serialize_writeback_fdatawait patch

dio-aio-fixes.patch
  direct-io AIO fixes

aio-fallback-bio_count-race-fix-2.patch
  AIO+DIO bio_count race fix

Re: 2.6.4-rc1-mm2

[J.A. Magallon]

On 03.03, Andrew Morton wrote:
> 
> ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.4-rc1/2.6.4-rc1-mm2/
> 
> - More VM tweaks and tuneups
> 
> - Added a 4k kernel- and irq-stack option for x86
> 
> - Largeish NFS client update
> 

I can't deselect the crypto API, with the same .config as previous kernels.
Some core driver now depends on it ?

TIA

-- 
J.A. Magallon <jamagallon()able!es>     \                 Software is like sex:
werewolf!able!es                         \           It's better when it's free
Mandrake Linux release 10.0 (RC1) for i586
Linux 2.6.4-rc1-jam1 (gcc 3.4.0 (Mandrake Linux 10.0 3.4.0-0.2mdk))

Re: 2.6.4-rc1-mm2 (compile stats)

[John Cherry]

Linux 2.6 (mm tree) Compile Statistics (gcc 3.2.2)
Warnings/Errors Summary

Kernel            bzImage   bzImage  bzImage  modules  bzImage  modules
                (defconfig) (allno) (allyes) (allyes) (allmod) (allmod)
--------------- ---------- -------- -------- -------- -------- --------
2.6.3-rc1-mm1     1w/0e     5w/0e   144w/ 5e  11w/0e   3w/0e    145w/0e
2.6.3-rc1-mm1     1w/0e     5w/0e   147w/ 5e  11w/0e   3w/0e    147w/0e
2.6.3-mm4         1w/0e     5w/0e   146w/ 0e   7w/0e   3w/0e    142w/0e
2.6.3-mm3         1w/2e     5w/2e   146w/15e   7w/0e   3w/2e    144w/5e
2.6.3-mm2         1w/8e     5w/0e   140w/ 0e   7w/0e   3w/0e    138w/0e
2.6.3-mm1         1w/0e     5w/0e   143w/ 5e   7w/0e   3w/0e    141w/0e
2.6.3-rc3-mm1     1w/0e     0w/0e   144w/13e   7w/0e   3w/0e    142w/3e
2.6.3-rc2-mm1     1w/0e     0w/265e 144w/ 5e   7w/0e   3w/0e    145w/0e
2.6.3-rc1-mm1     1w/0e     0w/265e 141w/ 5e   7w/0e   3w/0e    143w/0e
2.6.2-mm1         2w/0e     0w/264e 147w/ 5e   7w/0e   3w/0e    173w/0e
2.6.2-rc3-mm1     2w/0e     0w/265e 146w/ 5e   7w/0e   3w/0e    172w/0e
2.6.2-rc2-mm2     0w/0e     0w/264e 145w/ 5e   7w/0e   3w/0e    171w/0e
2.6.2-rc2-mm1     0w/0e     0w/264e 146w/ 5e   7w/0e   3w/0e    172w/0e
2.6.2-rc1-mm3     0w/0e     0w/265e 144w/ 8e   7w/0e   3w/0e    169w/0e
2.6.2-rc1-mm2     0w/0e     0w/264e 144w/ 5e  10w/0e   3w/0e    171w/0e
2.6.2-rc1-mm1     0w/0e     0w/264e 144w/ 5e  10w/0e   3w/0e    171w/0e
2.6.1-mm5         2w/5e     0w/264e 153w/11e  10w/0e   3w/0e    180w/0e
2.6.1-mm4         0w/821e   0w/264e 154w/ 5e   8w/1e   5w/0e    179w/0e
2.6.1-mm3         0w/0e     0w/0e   151w/ 5e  10w/0e   3w/0e    177w/0e
2.6.1-mm2         0w/0e     0w/0e   143w/ 5e  12w/0e   3w/0e    171w/0e
2.6.1-mm1         0w/0e     0w/0e   146w/ 9e  12w/0e   6w/0e    171w/0e
2.6.1-rc2-mm1     0w/0e     0w/0e   149w/ 0e  12w/0e   6w/0e    171w/4e
2.6.1-rc1-mm2     0w/0e     0w/0e   157w/15e  12w/0e   3w/0e    185w/4e
2.6.1-rc1-mm1     0w/0e     0w/0e   156w/10e  12w/0e   3w/0e    184w/2e
2.6.0-mm2         0w/0e     0w/0e   161w/ 0e  12w/0e   3w/0e    189w/0e
2.6.0-mm1         0w/0e     0w/0e   173w/ 0e  12w/0e   3w/0e    212w/0e

Web page with links to complete details:
   http://developer.osdl.org/cherry/compile/

John

Re: 2.6.4-rc1-mm2

[Adrian Bunk]

On Wed, Mar 03, 2004 at 12:32:29PM +0100, J.A. Magallon wrote:
> 
> On 03.03, Andrew Morton wrote:
> > 
> > ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.4-rc1/2.6.4-rc1-mm2/
> > 
> > - More VM tweaks and tuneups
> > 
> > - Added a 4k kernel- and irq-stack option for x86
> > 
> > - Largeish NFS client update
> > 
> 
> I can't deselect the crypto API, with the same .config as previous kernels.
> Some core driver now depends on it ?

Looking at the diff, the following options now select CRYPTO:
- Provide NFSv4 client support (EXPERIMENTAL)
- Secure RPC: Kerberos V mechanism (EXPERIMENTAL)

> TIA

cu
Adrian

-- 

       "Is there not promise of rain?" Ling Tan asked suddenly out
        of the darkness. There had been need of rain for many days.
       "Only a promise," Lao Er said.
                                       Pearl S. Buck - Dragon Seed

Re: 2.6.4-rc1-mm2

[Luiz Fernando Capitulino]

Hi Andrew,

Em Qua, 2004-03-03 às 01:15, Andrew Morton escreveu:
> ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.4-rc1/2.6.4-rc1-mm2/

I got this:

Unable to handle kernel paging request at virtual address c1d61f70
printing eip:
c0211f8f
*pde = 00006063
*pte = 01d61000
Oops: 0000 [#1]
DEBUG_PAGEALLOC
CPU:    0
EIP:    0060:[__make_request+671/1184]    Not tainted VLI
EFLAGS: 00010093
EIP is at __make_request+0x29f/0x4a0
eax: c1d61f60   ebx: c1d61f60   ecx: 00000008   edx: 00000100
esi: c79dadf8   edi: 00000000   ebp: c137dc7c   esp: c137dc4c
ds: 007b   es: 007b   ss: 0068
Process kswapd0 (pid: 7, threadinfo=c137c000 task=c1393a50)
Stack: 00000000 0000000c 0422361f 00000000 00000008 00000008 00000001 c1d61f60 
       c3e047a8 c79dadf8 00000008 c3e047a8 c137dcd0 c0212284 c012f702 00000200 
       c116bbd4 00000010 c137dcb8 c137dcf0 c012f702 03700008 00000000 c1393a50 
Call Trace:
 [generic_make_request+244/368] generic_make_request+0xf4/0x170
 [mempool_alloc+98/256] mempool_alloc+0x62/0x100
 [mempool_alloc+98/256] mempool_alloc+0x62/0x100
 [autoremove_wake_function+0/64] autoremove_wake_function+0x0/0x40
 [submit_bio+88/240] submit_bio+0x58/0xf0
 [kernel_map_pages+22/80] kernel_map_pages+0x16/0x50
 [bio_alloc+195/416] bio_alloc+0xc3/0x1a0
 [__block_write_full_page+380/880] __block_write_full_page+0x17c/0x370
 [blkdev_get_block+0/80] blkdev_get_block+0x0/0x50
 [block_write_full_page+179/192] block_write_full_page+0xb3/0xc0
 [blkdev_get_block+0/80] blkdev_get_block+0x0/0x50
 [shrink_list+949/1184] shrink_list+0x3b5/0x4a0
 [shrink_cache+334/848] shrink_cache+0x14e/0x350
 [shrink_slab+127/368] shrink_slab+0x7f/0x170
 [shrink_zone+149/160] shrink_zone+0x95/0xa0
 [balance_pgdat+430/512] balance_pgdat+0x1ae/0x200
 [kswapd+226/240] kswapd+0xe2/0xf0
 [autoremove_wake_function+0/64] autoremove_wake_function+0x0/0x40
 [autoremove_wake_function+0/64] autoremove_wake_function+0x0/0x40
 [kswapd+0/240] kswapd+0x0/0xf0
 [kernel_thread_helper+5/12] kernel_thread_helper+0x5/0xc

 Code: 01 00 00 39 86 48 01 00 00 74 25 8b 86 90 00 00 00 8b 96 8c 00 00 00 01 d0 3b 86 e8 00 00 00 74 15 0f b7 96 90 01 00 00 8b 45 ec <39> 50 10 74 06 fb e9 6c fe ff ff 8b 86 50 01 00 00 a8 04 75 f0 

 I was opening the w3m program, tried to reproduce without success.

-- 
Luiz Fernando N. Capitulino
<lcapitulino@prefeitura.sp.gov.br>
<http://www.telecentros.sp.gov.br>

Re: 2.6.4-rc1-mm2

[Andrew Morton]

Luiz Fernando Capitulino <lcapitulino@prefeitura.sp.gov.br> wrote:
>
> Em Qua, 2004-03-03 às 01:15, Andrew Morton escreveu:
> > ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.4-rc1/2.6.4-rc1-mm2/
> 
> I got this:
> 
> Unable to handle kernel paging request at virtual address c1d61f70
> printing eip:
> c0211f8f
> *pde = 00006063
> *pte = 01d61000
> Oops: 0000 [#1]
> DEBUG_PAGEALLOC
> CPU:    0
> EIP:    0060:[__make_request+671/1184]    Not tainted VLI
> EFLAGS: 00010093
> EIP is at __make_request+0x29f/0x4a0

hm, there's a possibility of indirection through an uninitialised variable
there.

--- 25/drivers/block/ll_rw_blk.c~blk-unplug-when-max-request-queued-fix	Wed Mar  3 16:03:01 2004
+++ 25-akpm/drivers/block/ll_rw_blk.c	Wed Mar  3 16:03:32 2004
@@ -2004,7 +2004,8 @@ EXPORT_SYMBOL(__blk_attempt_remerge);
 
 static int __make_request(request_queue_t *q, struct bio *bio)
 {
-	struct request *req, *freereq = NULL;
+	struct request *req = NULL;
+	struct request *freereq = NULL;
 	int el_ret, rw, nr_sectors, cur_nr_sectors, barrier, ra;
 	sector_t sector;
 
@@ -2154,7 +2155,7 @@ out:
 		int nr_queued = q->rq.count[READ] + q->rq.count[WRITE];
 
 		if (nr_queued == q->unplug_thresh ||
-				req->nr_sectors == q->max_sectors)
+				(req && req->nr_sectors == q->max_sectors))
 			__generic_unplug_device(q);
 	}
 	spin_unlock_irq(q->queue_lock);

_

VM patches in 2.6.4-rc1-mm2

[Mike Fedyk]

Andrew Morton wrote:
> ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.4-rc1/2.6.4-rc1-mm2/
> 
> - More VM tweaks and tuneups

Running 2.6.3-lofft-snsus-264rc1mm2vm (nfsd loff_t, sunrpc locking & -mm 
VM patches).  Seems to be working well.

Both servers started running this kernel on Wednesday morning, or at the 
end of week9 in the graphs.

On a 1G fileserver:
http://www.matchmail.com/stats/lrrd/matchmail.com/fileserver.matchmail.com-memory.html

Swapping has gone down to zero in this kernel also:
http://www.matchmail.com/stats/lrrd/matchmail.com/fileserver.matchmail.com-swap.html

Top users of slab:
buffer_head        71822  74382     48   77    1 : tunables  120   60
pte_chain          19557  21180    128   30    1 : tunables  120   60
dentry_cache       17771  27840    256   15    1 : tunables  120   60
radix_tree_node    13666  13680    260   15    1 : tunables   54   27
nfs_inode_cache     7870   7872    640    6    1 : tunables   54   27
ext3_inode_cache    5402   7028    512    7    1 : tunables   54   27
vm_area_struct      5385   6728     64   58    1 : tunables  120   60
size-128            2184   2310    128   30    1 : tunables  120   60
filp                2144   2670    256   15    1 : tunables  120   60
inode_cache         1117   1130    384   10    1 : tunables   54   27
size-64              896    928     64   58    1 : tunables  120   60
size-32              836    896     32  112    1 : tunables  120   60


And a 1.5G file/kde over VNC terminal server:
http://www.matchmail.com/stats/lrrd/matchmail.com/srv-lnx2600.matchmail.com-memory.html

Swapping has gone down to zero on this server also:
http://www.matchmail.com/stats/lrrd/matchmail.com/srv-lnx2600.matchmail.com-swap.html

One thing for this server.  Most of the desktops are not in use right 
now, so I'd expect the swap usage to grow, but shouldn't be swapping in 
and out a lot in this workload.

Top users of slab:
pte_chain         112097 113550    128   30    1 : tunables  120   60
buffer_head        85089 103334     48   77    1 : tunables  120   60
dentry_cache       81260 112875    256   15    1 : tunables  120   60
ext3_inode_cache   72637  84805    512    7    1 : tunables   54   27
vm_area_struct     40689  41876     64   58    1 : tunables  120   60
radix_tree_node    15603  19140    260   15    1 : tunables   54   27
filp               14536  14955    256   15    1 : tunables  120   60
size-32             3420   3472     32  112    1 : tunables  120   60
size-128            3420   3720    128   30    1 : tunables  120   60
size-64             2768   2958     64   58    1 : tunables  120   60
dnotify_cache       2364   2490     20  166    1 : tunables  120   60
sock_inode_cache    1867   1918    512    7    1 : tunables   54   27
proc_inode_cache    1650   2040    384   10    1 : tunables   54   27
unix_sock           1635   1645    512    7    1 : tunables   54   27
inode_cache         1620   1620    384   10    1 : tunables   54   27
task_struct          578    595   1584    5    2 : tunables   24   12
size-8192            574    574   8192    1    2 : tunables    8    4

Most of the previous 2.6 kernels I was running on these servers would be 
lightly hitting swap by now.  This definitely looks better to me.

I want to continue running these patches until at least Tuesday of next 
week to see how they perform over a longer period.

P.S. I've changed the color scheme in the graphs, let me know what you 
think of them.  They seem better, but there are a couple colors that 
aren't easily seen when they overlap... :-/

Mike

Re: VM patches in 2.6.4-rc1-mm2

[Andrew Morton]

Mike Fedyk <mfedyk@matchmail.com> wrote:
>
> Andrew Morton wrote:
> > ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.4-rc1/2.6.4-rc1-mm2/
> > 
> > - More VM tweaks and tuneups
> 
> Running 2.6.3-lofft-snsus-264rc1mm2vm (nfsd loff_t, sunrpc locking & -mm 
> VM patches).  Seems to be working well.

OK, good.

> Most of the previous 2.6 kernels I was running on these servers would be 
> lightly hitting swap by now.  This definitely looks better to me.

It sounds worse to me.  "Lightly hitting swap" is good.  It gets rid of stuff,
freeing up physical memory.

But I do not see a lot of difference here.  The 900MB desktop machine is
300M into swap after 24 hours.  That's usual.

Re: VM patches in 2.6.4-rc1-mm2

[Mike Fedyk]

Andrew Morton wrote:
> Mike Fedyk <mfedyk@matchmail.com> wrote:
> 
>>Andrew Morton wrote:
>>
>>>ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.4-rc1/2.6.4-rc1-mm2/
>>>
>>>- More VM tweaks and tuneups
>>
>>Running 2.6.3-lofft-snsus-264rc1mm2vm (nfsd loff_t, sunrpc locking & -mm 
>>VM patches).  Seems to be working well.
> 
> 
> OK, good.
> 
> 
>>Most of the previous 2.6 kernels I was running on these servers would be 
>>lightly hitting swap by now.  This definitely looks better to me.
> 
> 
> It sounds worse to me.  "Lightly hitting swap" is good.  It gets rid of stuff,
> freeing up physical memory.

Swapping out is good to me.  It's the swapping in, and out, and in, 
and... that's bad.

> 
> But I do not see a lot of difference here.

Let's let it run a few more days to make sure.

> The 900MB desktop machine is
> 300M into swap after 24 hours.  That's usual.

Neither of my servers have 900MB ram...

Mike

Re: 2.6.4-rc1-mm[12] - dm_any_congested issues

[Valdis.Kletnieks]

[-- Attachment #1: Type: text/plain, Size: 1776 bytes --]

On Tue, 02 Mar 2004 20:15:36 PST, Andrew Morton <akpm@osdl.org>  said:

(Added in -rc1-mm1 which I didn't try, problem noticed in -rc2-mm2)

> queue-congestion-dm-implementation.patch
>   Implement queue congestion callout for device mapper

This is causing the following trace every second or 2 on my laptop:

Mar  4 17:47:26 turing-police kernel: Debug: sleeping function called from invalid context at include/linux/rwsem.h:43
Mar  4 17:47:26 turing-police kernel: in_atomic():1, irqs_disabled():0
Mar  4 17:47:27 turing-police kernel: Call Trace:
Mar  4 17:47:27 turing-police kernel:  [__might_sleep+159/168] __might_sleep+0x9f/0xa8
Mar  4 17:47:27 turing-police kernel:  [dm_any_congested+19/67] dm_any_congested+0x13/0x43
Mar  4 17:47:27 turing-police kernel:  [sync_sb_inodes+212/592] sync_sb_inodes+0xd4/0x250
Mar  4 17:47:27 turing-police kernel:  [writeback_inodes+87/155] writeback_inodes+0x57/0x9b
Mar  4 17:47:27 turing-police kernel:  [wb_kupdate+197/311] wb_kupdate+0xc5/0x137
Mar  4 17:47:27 turing-police kernel:  [__pdflush+278/441] __pdflush+0x116/0x1b9
Mar  4 17:47:27 turing-police kernel:  [pdflush+15/17] pdflush+0xf/0x11
Mar  4 17:47:27 turing-police kernel:  [wb_kupdate+0/311] wb_kupdate+0x0/0x137
Mar  4 17:47:27 turing-police kernel:  [kthread+106/147] kthread+0x6a/0x93
Mar  4 17:47:27 turing-police kernel:  [pdflush+0/17] pdflush+0x0/0x11
Mar  4 17:47:27 turing-police kernel:  [kthread+0/147] kthread+0x0/0x93
Mar  4 17:47:27 turing-police kernel:  [kernel_thread_helper+5/11] kernel_thread_helper+0x5/0xb

Of course backing it out makes the messages go away, since dm_any_congested()
was added by that patch.  This patch just not ready for prime time, or am I (as usual)
managing to trip over some silly corner case due to odd configuration?

[-- Attachment #2: Type: application/pgp-signature, Size: 226 bytes --]

Re: 2.6.4-rc1-mm[12] - dm_any_congested issues

[Miquel van Smoorenburg]

In article <200403051754.i25Hsjg7015052@turing-police.cc.vt.edu>,
 <Valdis.Kletnieks@vt.edu> wrote:
>On Tue, 02 Mar 2004 20:15:36 PST, Andrew Morton <akpm@osdl.org>  said:
>
>(Added in -rc1-mm1 which I didn't try, problem noticed in -rc2-mm2)
>
>> queue-congestion-dm-implementation.patch
>>   Implement queue congestion callout for device mapper
>
>This is causing the following trace every second or 2 on my laptop:
>
>Mar  4 17:47:26 turing-police kernel: Debug: sleeping function called
>from invalid context at include/linux/rwsem.h:43
>Of course backing it out makes the messages go away, since dm_any_congested()
>was added by that patch.  This patch just not ready for prime time, or
>am I (as usual)
>managing to trip over some silly corner case due to odd configuration?

It's a bug. The new queue congestion function cannot sleep, yet
it calls parts of DM that can sleep (indirectly). This needs to
be fixed in DM (I think).
See https://www.redhat.com/archives/linux-lvm/2004-March/msg00033.html

Mike.

Re: VM patches in 2.6.4-rc1-mm2

[Mike Fedyk]

Andrew Morton wrote:
> Mike Fedyk <mfedyk@matchmail.com> wrote:
>>Most of the previous 2.6 kernels I was running on these servers would be 
>>lightly hitting swap by now.  This definitely looks better to me.
> 
> 
> It sounds worse to me.  "Lightly hitting swap" is good.  It gets rid of stuff,
> freeing up physical memory.

Andrew, it looks like you're right.  This[1] server doesn't seem to be 
hitting swap enough.  But my other[2] file server is doing great with it 
on the other hand (though, it hasn't swapped at all).

Maybe a little tuning is in order?

Any patches I should try?

Mike

[1]
http://www.matchmail.com/stats/lrrd/matchmail.com/srv-lnx2600.matchmail.com-memory.html

[2]
http://www.matchmail.com/stats/lrrd/matchmail.com/fileserver.matchmail.com-memory.html

Re: VM patches in 2.6.4-rc1-mm2

[Nick Piggin]

Mike Fedyk wrote:

> Andrew Morton wrote:
>
>> Mike Fedyk <mfedyk@matchmail.com> wrote:
>>
>>> Most of the previous 2.6 kernels I was running on these servers 
>>> would be lightly hitting swap by now.  This definitely looks better 
>>> to me.
>>
>>
>>
>> It sounds worse to me.  "Lightly hitting swap" is good.  It gets rid 
>> of stuff,
>> freeing up physical memory.
>
>
> Andrew, it looks like you're right.  This[1] server doesn't seem to be 
> hitting swap enough.  But my other[2] file server is doing great with 
> it on the other hand (though, it hasn't swapped at all).
>

Just curious, what makes you say [1] isn't hitting swap enough and [2]
is OK? The graphs are better now, by the way. Thank you.

> Maybe a little tuning is in order?
>
> Any patches I should try?
>

Mainline doesn't put enough pressure on slab with highmem systems. This
creates a lot more ZONE_NORMAL pressure and that causes swapping.

Now with the 2.6 VM, you don't do any mapped memory scaning at all
while you only have a small amount of memory pressure. This means that
truely inactive mapped pages never get reclaimed.

The patches you are using do not address this. My split active list
patches should do so. Alternatively you can increase
/proc/sys/vm/swappiness, but that isn't a complete solution, and might
make things too swappy. It is a difficult beast to control.

Re: VM patches in 2.6.4-rc1-mm2

[Mike Fedyk]

Nick Piggin wrote:
> 
> 
> Mike Fedyk wrote:
> 
>> Andrew Morton wrote:
>>
>>> Mike Fedyk <mfedyk@matchmail.com> wrote:
>>>
>>>> Most of the previous 2.6 kernels I was running on these servers 
>>>> would be lightly hitting swap by now.  This definitely looks better 
>>>> to me.
>>>
>>>
>>>
>>>
>>> It sounds worse to me.  "Lightly hitting swap" is good.  It gets rid 
>>> of stuff,
>>> freeing up physical memory.
>>
>>
>>
>> Andrew, it looks like you're right.  This[1] server doesn't seem to be 
>> hitting swap enough.  But my other[2] file server is doing great with 
>> it on the other hand (though, it hasn't swapped at all).
>>
> 
> Just curious, what makes you say [1] isn't hitting swap enough and [2]
> is OK? The graphs are better now, by the way. Thank you.

Well, with [1], I know most of those apps aren't being used, so I'm sure 
it should be hitting swap more.

And with [2], it isn't fair since I'm just happy it's not swapping 
throughout the day and all of userspace is in ram, but it's probably not 
good either.  And I'm sure there are some gettys and such that aren't 
being used, so they should have swapped out by now.

> 
>> Maybe a little tuning is in order?
>>
>> Any patches I should try?
>>
> 
> Mainline doesn't put enough pressure on slab with highmem systems. This
> creates a lot more ZONE_NORMAL pressure and that causes swapping.
> 

Yep, saw that.  Especially with 128MB Highmem (eg, 1G RAM)

> Now with the 2.6 VM, you don't do any mapped memory scaning at all

You mean 2.6-mm?

> while you only have a small amount of memory pressure. This means that
> truely inactive mapped pages never get reclaimed.
> 

If I have enough pressure, they will be eventually?  But my caches will 
still be smaller than optimal, right?

> The patches you are using do not address this. My split active list
> patches should do so. Alternatively you can increase
> /proc/sys/vm/swappiness, but that isn't a complete solution, and might
> make things too swappy. It is a difficult beast to control.

Has akpm said that he would be including the active split patch in -mm?

Do you have a patch against -mm (you wrote to ask for your latest...)?

Mike

Re: VM patches in 2.6.4-rc1-mm2

[Nick Piggin]

Mike Fedyk wrote:

> Nick Piggin wrote:
>
>>
>>
>> Mike Fedyk wrote:
>>
>>> Andrew Morton wrote:
>>>
>>>> Mike Fedyk <mfedyk@matchmail.com> wrote:
>>>>
>>>>> Most of the previous 2.6 kernels I was running on these servers 
>>>>> would be lightly hitting swap by now.  This definitely looks 
>>>>> better to me.
>>>>
>>>>
>>>>
>>>>
>>>>
>>>> It sounds worse to me.  "Lightly hitting swap" is good.  It gets 
>>>> rid of stuff,
>>>> freeing up physical memory.
>>>
>>>
>>>
>>>
>>> Andrew, it looks like you're right.  This[1] server doesn't seem to 
>>> be hitting swap enough.  But my other[2] file server is doing great 
>>> with it on the other hand (though, it hasn't swapped at all).
>>>
>>
>> Just curious, what makes you say [1] isn't hitting swap enough and [2]
>> is OK? The graphs are better now, by the way. Thank you.
>
>
> Well, with [1], I know most of those apps aren't being used, so I'm 
> sure it should be hitting swap more.
>
> And with [2], it isn't fair since I'm just happy it's not swapping 
> throughout the day and all of userspace is in ram, but it's probably 
> not good either.  And I'm sure there are some gettys and such that 
> aren't being used, so they should have swapped out by now.
>


Yep OK.


>>
>>> Maybe a little tuning is in order?
>>>
>>> Any patches I should try?
>>>
>>
>> Mainline doesn't put enough pressure on slab with highmem systems. This
>> creates a lot more ZONE_NORMAL pressure and that causes swapping.
>>
>
> Yep, saw that.  Especially with 128MB Highmem (eg, 1G RAM)
>
>> Now with the 2.6 VM, you don't do any mapped memory scaning at all
>
>
> You mean 2.6-mm?
>

Yes, either mm or linus.

>> while you only have a small amount of memory pressure. This means that
>> truely inactive mapped pages never get reclaimed.
>>
>
> If I have enough pressure, they will be eventually?  But my caches 
> will still be smaller than optimal, right?
>

If you get a lot of pressure at one time it should push out your
inactive mapped pages. Will get most of the really inactive ones,
but it won't help pages becoming inactive in future.

>> The patches you are using do not address this. My split active list
>> patches should do so. Alternatively you can increase
>> /proc/sys/vm/swappiness, but that isn't a complete solution, and might
>> make things too swappy. It is a difficult beast to control.
>
>
> Has akpm said that he would be including the active split patch in -mm?
>

Hasn't looked at it much. Probably not until some of the more basic
VM patches can get merged into -linus.

> Do you have a patch against -mm (you wrote to ask for your latest...)?
>

Yep...

Re: VM patches in 2.6.4-rc1-mm2

[Mike Fedyk]

Nick Piggin wrote:
> 
> 
> Mike Fedyk wrote:
> 
>> Nick Piggin wrote:
>>> Mainline doesn't put enough pressure on slab with highmem systems. This
>>> creates a lot more ZONE_NORMAL pressure and that causes swapping.
>>>
>>
>> Yep, saw that.  Especially with 128MB Highmem (eg, 1G RAM)
>>
>>> Now with the 2.6 VM, you don't do any mapped memory scaning at all
>>
>>
>>
>> You mean 2.6-mm?
>>
> 
> Yes, either mm or linus.
> 

Have there been any VM patches merged into mainline?  Or are you saying 
that the imbalance in mainline would be enough to overcome to lack of 
scanning of mapped pages?

>>> while you only have a small amount of memory pressure. This means that
>>> truely inactive mapped pages never get reclaimed.
>>>
>>
>> If I have enough pressure, they will be eventually?  But my caches 
>> will still be smaller than optimal, right?
>>
> 
> If you get a lot of pressure at one time it should push out your
> inactive mapped pages. Will get most of the really inactive ones,
> but it won't help pages becoming inactive in future.
> 

Ok, I see.  This might be happening, since it is steadily getting more 
into swap.

>>> The patches you are using do not address this. My split active list
>>> patches should do so. Alternatively you can increase
>>> /proc/sys/vm/swappiness, but that isn't a complete solution, and might
>>> make things too swappy. It is a difficult beast to control.
>>
>>
>>
>> Has akpm said that he would be including the active split patch in -mm?
>>
> 
> Hasn't looked at it much. Probably not until some of the more basic
> VM patches can get merged into -linus.

Yes, I wonder if the VM patches helped -mm in the reaim tests...

Let's get the fsfaz (free slab for all zones) into mainline asap! :-D

>> Do you have a patch against -mm (you wrote to ask for your latest...)?
>>
> 
> Yep...

Let me get back to you sometime next week.  So far, the VM is reacting 
ok with this combined workload.

Mike

Re: VM patches in 2.6.4-rc1-mm2

[Nick Piggin]

Mike Fedyk wrote:

> Nick Piggin wrote:
>
>>
>>
>> Mike Fedyk wrote:
>>
>>> Nick Piggin wrote:
>>>
>>>> Mainline doesn't put enough pressure on slab with highmem systems. 
>>>> This
>>>> creates a lot more ZONE_NORMAL pressure and that causes swapping.
>>>>
>>>
>>> Yep, saw that.  Especially with 128MB Highmem (eg, 1G RAM)
>>>
>>>> Now with the 2.6 VM, you don't do any mapped memory scaning at all
>>>
>>>
>>>
>>>
>>> You mean 2.6-mm?
>>>
>>
>> Yes, either mm or linus.
>>
>
> Have there been any VM patches merged into mainline?  Or are you 
> saying that the imbalance in mainline would be enough to overcome to 
> lack of scanning of mapped pages?
>

There have been no VM patches merged into mainline. I just mean that
neither mm or mainline does any mapped memory scanning when memory
pressure is low.

>>
>> If you get a lot of pressure at one time it should push out your
>> inactive mapped pages. Will get most of the really inactive ones,
>> but it won't help pages becoming inactive in future.
>>
>
> Ok, I see.  This might be happening, since it is steadily getting more 
> into swap.
>


For the one that is swapping, yes this would be happening.


>>
>> Hasn't looked at it much. Probably not until some of the more basic
>> VM patches can get merged into -linus.
>
>
> Yes, I wonder if the VM patches helped -mm in the reaim tests...
>
> Let's get the fsfaz (free slab for all zones) into mainline asap! :-D
>


Well all the ones in -mm now are probably right to go to 2.6.5
I hope.