linux_dsm_epyc7002/Documentation
David Ahern 9ab948a91b ipv4: Allow amount of dirty memory from fib resizing to be controllable
fib_trie implementation calls synchronize_rcu when a certain amount of
pages are dirty from freed entries. The number of pages was determined
experimentally in 2009 (commit c3059477fc).

At the current setting, synchronize_rcu is called often -- 51 times in a
second in one test with an average of an 8 msec delay adding a fib entry.
The total impact is a lot of slow down modifying the fib. This is seen
in the output of 'time' - the difference between real time and sys+user.
For example, using 720,022 single path routes and 'ip -batch'[1]:

    $ time ./ip -batch ipv4/routes-1-hops
    real    0m14.214s
    user    0m2.513s
    sys     0m6.783s

So roughly 35% of the actual time to install the routes is from the ip
command getting scheduled out, most notably due to synchronize_rcu (this
is observed using 'perf sched timehist').

This patch makes the amount of dirty memory configurable between 64k where
the synchronize_rcu is called often (small, low end systems that are memory
sensitive) to 64M where synchronize_rcu is called rarely during a large
FIB change (for high end systems with lots of memory). The default is 512kB
which corresponds to the current setting of 128 pages with a 4kB page size.

As an example, at 16MB the worst interval shows 4 calls to synchronize_rcu
in a second blocking for up to 30 msec in a single instance, and a total
of almost 100 msec across the 4 calls in the second. The trade off is
allowing FIB entries to consume more memory in a given time window but
but with much better fib insertion rates (~30% increase in prefixes/sec).
With this patch and net.ipv4.fib_sync_mem set to 16MB, the same batch
file runs in:

    $ time ./ip -batch ipv4/routes-1-hops
    real    0m9.692s
    user    0m2.491s
    sys     0m6.769s

So the dead time is reduced to about 1/2 second or <5% of the real time.

[1] 'ip' modified to not request ACK messages which improves route
    insertion times by about 20%

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-21 13:29:53 -07:00
..
ABI A large number of bug fixes and cleanups. One new feature to allow 2019-03-12 15:03:21 -07:00
accelerators ocxl: Document new OCXL IOCTLs 2018-06-03 20:40:33 +10:00
accounting psi: cgroup support 2018-10-26 16:26:32 -07:00
acpi ACPI: Documentation: Fix path for acpidbg tool 2019-03-07 11:28:33 +01:00
admin-guide Merge branch 'core-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2019-03-10 13:46:08 -07:00
aoe
arm Documentation: Use "while" instead of "whilst" 2018-11-20 09:30:43 -07:00
arm64 arm64 updates for 5.1: 2019-03-10 10:17:23 -07:00
auxdisplay Doc: misc-devices: move lcd-panel-cgram.txt to auxdisplay/ 2018-04-12 16:08:02 +02:00
backlight
block block: document usage of bio iterator helpers 2019-02-15 08:40:12 -07:00
blockdev zram: idle writeback fixes and cleanup 2019-01-08 17:15:10 -08:00
bpf docs/bpf: minor casing/punctuation fixes 2019-03-02 00:40:04 +01:00
bus-devices
cdrom Drop all 00-INDEX files from Documentation/ 2018-09-09 15:08:58 -06:00
cgroup-v1 A fairly routine cycle for docs - lots of typo fixes, some new documents, 2019-03-09 09:56:17 -08:00
cma
connector
console Documentation: corrections to console/console.txt 2018-08-10 16:09:40 -06:00
core-api Merge branch 'akpm' (patches from Andrew) 2019-03-12 10:39:53 -07:00
cpu-freq Documentation: cpu-freq: Frequencies aren't always sorted 2018-11-07 13:29:04 +01:00
crypto crypto: skcipher - remove remnants of internal IV generators 2018-12-23 11:52:45 +08:00
dev-tools Documentation/dev-tools: Use gcc version number instead svn revision number 2019-01-14 17:25:41 -07:00
device-mapper dm cache: add support for discard passdown to the origin device 2019-03-05 14:53:52 -05:00
devicetree Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net 2019-03-14 09:28:12 -07:00
doc-guide docs: kernel-doc: typo "if ... if" -> "if ... is" 2019-02-17 15:38:47 -07:00
driver-api dmaengine updates for v5.1-rc1 2019-03-14 09:11:54 -07:00
driver-model Merge branches 'clk-optional', 'clk-devm-clkdev-register', 'clk-allwinner', 'clk-meson' and 'clk-renesas' into clk-next 2019-03-08 10:27:21 -08:00
early-userspace Correct gen_init_cpio tool's documentation 2018-11-25 12:25:53 -07:00
EDID Docs/EDID: Calculate CRC while building the code 2018-11-06 07:36:22 -07:00
extcon
fault-injection doc: fault-injection: fix macro name in example 2019-01-07 15:36:11 -07:00
fb fbdev: fbmem: convert CONFIG_FB_LOGO_CENTER into a cmd line option 2019-01-16 17:42:35 +01:00
features Documentation/features: Add csky kernel features 2019-01-07 22:22:16 +08:00
filesystems The highlights are: 2019-03-12 14:58:35 -07:00
firmware_class
fmc Drop all 00-INDEX files from Documentation/ 2018-09-09 15:08:58 -06:00
fpga docs: fpga: add a document for FPGA Device Feature List (DFL) Framework Overview 2018-07-15 13:55:44 +02:00
gpio Drop all 00-INDEX files from Documentation/ 2018-09-09 15:08:58 -06:00
gpu Merge drm/drm-next into drm-misc-next 2019-02-11 10:35:35 +01:00
hid HID: doc: fix wrong data structure reference for UHID_OUTPUT 2018-12-18 14:55:22 +01:00
hwmon A fairly routine cycle for docs - lots of typo fixes, some new documents, 2019-03-09 09:56:17 -08:00
i2c i2c: gpio: fault-injector: add 'inject_panic' injector 2019-02-23 10:34:08 +01:00
ia64
ide Drop all 00-INDEX files from Documentation/ 2018-09-09 15:08:58 -06:00
iio
infiniband Documentation/infiniband: update from locked to pinned_vm 2019-02-07 12:56:23 -07:00
input doc: Change LXR references to elixir.bootlin.com 2019-02-01 16:05:03 -07:00
interconnect interconnect: Add generic on-chip interconnect API 2019-01-22 13:37:25 +01:00
ioctl seccomp: add a return code to trap to userspace 2018-12-11 16:28:41 -08:00
isdn Drop all 00-INDEX files from Documentation/ 2018-09-09 15:08:58 -06:00
kbuild kbuild: remove cc-version macro 2019-03-04 22:34:59 +09:00
kdump kdump: Document kernel data exported in the vmcoreinfo note 2019-01-15 11:05:28 +01:00
kernel-hacking doc:it_IT: translation for kernel-hacking 2018-07-26 16:21:09 -06:00
laptops Documentation: fix lg-laptop.rst warnings 2019-02-11 08:27:47 -07:00
leds Documentation: Use "while" instead of "whilst" 2018-11-20 09:30:43 -07:00
lightnvm
livepatch livepatch: Remove signal sysfs attribute 2019-01-16 22:09:33 +01:00
locking Documentation/locking/lockdep: Drop last two chars of sample states 2019-03-04 12:55:18 -07:00
m68k Drop all 00-INDEX files from Documentation/ 2018-09-09 15:08:58 -06:00
maintainer docs: Fix more broken references 2018-06-15 18:11:26 -03:00
md
media media: Documentation: fix several typos 2019-03-01 09:54:06 -05:00
memory-devices
mic
mips Drop all 00-INDEX files from Documentation/ 2018-09-09 15:08:58 -06:00
misc-devices Documentation: add ibmvmc to toctree(index) and fix warnings 2019-01-14 08:37:17 -07:00
mmc Drop all 00-INDEX files from Documentation/ 2018-09-09 15:08:58 -06:00
mtd Documentation: mtd: remove stale pxa3xx NAND controller documentation 2018-09-04 23:37:38 +02:00
namespaces
netlabel Drop all 00-INDEX files from Documentation/ 2018-09-09 15:08:58 -06:00
networking ipv4: Allow amount of dirty memory from fib resizing to be controllable 2019-03-21 13:29:53 -07:00
nfc
nios2
nvdimm libnvdimm/security: Add documentation for nvdimm security support 2018-12-21 12:44:41 -08:00
nvmem Documentation: nvmem: document cell tables and lookup entries 2018-09-28 15:14:54 +02:00
openrisc
parisc Drop all 00-INDEX files from Documentation/ 2018-09-09 15:08:58 -06:00
PCI pci-v4.20-changes 2018-10-25 06:50:48 -07:00
pcmcia pcmcia: remove long deprecated pcmcia_request_exclusive_irq() function 2018-08-18 12:30:42 -07:00
perf Documentation: perf: Add documentation for ThunderX2 PMU uncore driver 2018-12-06 12:29:47 +00:00
phy
platform
power PM/EM: Document the Energy Model framework 2019-01-27 12:29:37 +01:00
powerpc powerpc/fadump: Reservationless firmware assisted dump 2018-12-21 11:32:49 +11:00
pps
process A fairly routine cycle for docs - lots of typo fixes, some new documents, 2019-03-09 09:56:17 -08:00
pti
ptp ptp: Fix documentation to match code. 2018-03-26 12:13:21 -04:00
rapidio
RCU A fairly routine cycle for docs - lots of typo fixes, some new documents, 2019-03-09 09:56:17 -08:00
riscv perf: riscv: Add Document for Future Porting Guide 2018-06-04 14:02:11 -07:00
s390 Documentation: Use "while" instead of "whilst" 2018-11-20 09:30:43 -07:00
scheduler sched/doc: Document Energy Aware Scheduling 2019-01-27 12:29:37 +01:00
scsi scsi: ufs-bsg: Allow reading descriptors 2019-02-27 09:00:02 -05:00
security doc: security: Add kern-doc for lsm_hooks.h 2019-02-22 08:54:09 -07:00
serial Documentation: Use "while" instead of "whilst" 2018-11-20 09:30:43 -07:00
sh sh: remove board_time_init() callback 2018-12-18 16:13:04 +01:00
sound ASoC: More changes for v5.1 2019-02-28 13:30:55 +01:00
sparc
sphinx Documentation/sphinx: allow "functions" with no parameters 2018-06-30 07:52:42 -06:00
sphinx-static docs: improve readability for people with poorer eyesight 2018-10-07 09:16:50 -06:00
spi pxa2xx: replace spi_master with spi_controller 2019-01-23 10:59:56 +00:00
sysctl A fairly routine cycle for docs - lots of typo fixes, some new documents, 2019-03-09 09:56:17 -08:00
target scsi: target/core: Remove the write_pending_status() callback function 2019-02-04 21:23:59 -05:00
thermal Documentation: Use "while" instead of "whilst" 2018-11-20 09:30:43 -07:00
timers Docs: Correct /proc/stat path 2019-02-22 08:50:17 -07:00
trace doc: trace: Fix documentation for uprobe_profile 2019-02-21 10:28:55 -05:00
translations A fairly routine cycle for docs - lots of typo fixes, some new documents, 2019-03-09 09:56:17 -08:00
usb usb: core: add option of only authorizing internal devices 2019-02-22 09:27:55 +01:00
userspace-api x86/speculation: Add PR_SPEC_DISABLE_NOEXEC 2019-01-29 22:11:49 +01:00
virtual virtio-ccw: diag 500 may return a negative cookie 2019-03-06 11:19:33 -05:00
vm docs: Use underscore not hyphen in label 2019-02-01 16:04:01 -07:00
w1 Drop all 00-INDEX files from Documentation/ 2018-09-09 15:08:58 -06:00
watchdog Documentation/watchdog: Add documentation mlx-wdt driver 2019-03-02 15:28:20 +01:00
wimax
x86 x86/resctrl: Avoid confusion over the new X86_RESCTRL config 2019-02-02 10:34:52 +01:00
xilinx Documentation: xilinx: Add documentation for eemi APIs 2018-10-09 13:26:05 +02:00
xtensa xtensa: document boot parameter passing 2019-02-03 18:06:19 -08:00
.gitignore
atomic_bitops.txt
atomic_t.txt
bt8xxgpio.txt
btmrvl.txt
bus-virt-phys-mapping.txt
Changes
clearing-warn-once.txt
CodingStyle
conf.py This is a fairly typical cycle for documentation. There's some welcome 2018-10-24 18:01:11 +01:00
cpu-load.txt
cputopology.txt
crc32.txt
dcdbas.txt
debugging-modules.txt
debugging-via-ohci1394.txt
dell_rbu.txt Documentation: remove stale firmware API reference 2018-05-14 16:44:41 +02:00
digsig.txt
DMA-API-HOWTO.txt Documentation/DMA-API-HOWTO: update dma_mask sections 2019-02-20 07:29:47 -07:00
DMA-API.txt virtio: fixes, cleanups 2019-03-10 12:47:57 -07:00
DMA-attributes.txt
DMA-ISA-LPC.txt Documentation/DMA-ISA-LPC: fix an incorrect reference 2019-02-11 08:23:07 -07:00
docutils.conf
dontdiff kernel/configs: use .incbin directive to embed config_data.gz 2019-03-07 18:32:02 -08:00
efi-stub.txt efi_stub: update documentation on dtb= parameter 2018-09-09 14:46:44 -06:00
eisa.txt
futex-requeue-pi.txt
gcc-plugins.txt
highuid.txt
hw_random.txt
hwspinlock.txt
index.rst Documentation: add ibmvmc to toctree(index) and fix warnings 2019-01-14 08:37:17 -07:00
intel_txt.txt
Intel-IOMMU.txt
io_ordering.txt
io-mapping.txt
iostats.txt block: Track DISCARD statistics and output them in stat and diskstat 2018-07-18 08:44:22 -06:00
IPMI.txt
IRQ-affinity.txt
IRQ-domain.txt
IRQ.txt
irqflags-tracing.txt
isa.txt
isapnp.txt
kernel-per-CPU-kthreads.txt doc: Update removal of RCU-bh/sched update machinery 2018-08-30 10:59:48 -07:00
kobject.txt kref/kobject: Improve documentation 2018-12-06 13:57:03 +01:00
kprobes.txt kprobes/Documentation: Fix various typos 2018-06-22 11:10:55 +02:00
kref.txt
ldm.txt
lockup-watchdogs.txt
logo.gif
logo.txt
lsm.txt
lzo.txt lib/lzo: separate lzo-rle from lzo 2019-03-07 18:32:03 -08:00
mailbox.txt
Makefile kbuild: Add support for DT binding schema checks 2018-12-13 09:41:32 -06:00
memory-barriers.txt Documentation: Use "while" instead of "whilst" 2018-11-20 09:30:43 -07:00
men-chameleon-bus.txt
nommu-mmap.txt Documentation: nommu-map: Fix duplicate word typo 2018-06-26 09:01:27 -06:00
ntb.txt
numastat.txt
padata.txt
parport-lowlevel.txt
percpu-rw-semaphore.txt
phy.txt
pi-futex.txt
pnp.txt
preempt-locking.txt Documentation: preempt-locking: Use better example 2018-10-12 11:35:47 -06:00
pwm.txt
rbtree.txt
remoteproc.txt
rfkill.txt rfkill: Fix several typos in documentation 2018-06-15 13:36:08 +02:00
robust-futex-ABI.txt
robust-futexes.txt
rpmsg.txt
rtc.txt
SAK.txt
sgi-ioc4.txt
siphash.txt
SM501.txt
smsc_ece1099.txt
speculation.txt
static-keys.txt static_keys.txt: Fix trivial spelling mistake 2019-02-06 16:44:16 -07:00
SubmittingPatches
svga.txt
switchtec.txt NTB: switchtec_ntb: Update switchtec documentation with prerequisites for NTB 2018-10-11 11:28:53 -05:00
sync_file.txt
tee.txt
this_cpu_ops.txt
unaligned-memory-access.txt
vfio-mediated-device.txt vfio/mdev: Check globally for duplicate devices 2018-06-08 10:24:27 -06:00
vfio.txt vfio: fix documentation 2018-05-08 09:16:41 -06:00
video-output.txt
xillybus.txt
xz.txt
zorro.txt