FreeBSD src
Go to file
Garrett Wollman 3c42b5bf28 Fix overflow bugs in and remove obsolete limit from kernel RPC
implementation.

The kernel RPC code, which is responsible for the low-level scheduling
of incoming NFS requests, contains a throttling mechanism that
prevents too much kernel memory from being tied up by NFS requests
that are being serviced.  When the throttle is engaged, the RPC layer
stops servicing incoming NFS sockets, resulting ultimately in
backpressure on the clients (if they're using TCP).  However, this is
a very heavy-handed mechanism as it prevents all clients from making
any requests, regardless of how heavy or light they are.  (Thus, when
engaged, the throttle often prevents clients from even mounting the
filesystem.)  The throttle mechanism applies specifically to requests
that have been received by the RPC layer (from a TCP or UDP socket)
and are queued waiting to be serviced by one of the nfsd threads; it
does not limit the amount of backlog in the socket buffers.

The original implementation limited the total bytes of queued requests
to the minimum of a quarter of (nmbclusters * MCLBYTES) and 45 MiB.
The former limit seems reasonable, since requests queued in the socket
buffers and replies being constructed to the requests in progress will
all require some amount of network memory, but the 45 MiB limit is
plainly ridiculous for modern memory sizes: when running 256 service
threads on a busy server, 45 MiB would result in just a single
maximum-sized NFS3PROC_WRITE queued per thread before throttling.

Removing this limit exposed integer-overflow bugs in the original
computation, and related bugs in the routines that actually account
for the amount of traffic enqueued for service threads.  The old
implementation also attempted to reduce accounting overhead by
batching updates until each queue is fully drained, but this is prone
to livelock, resulting in repeated accumulate-throttle-drain cycles on
a busy server.  Various data types are changed to long or unsigned
long; explicit 64-bit types are not used due to the unavailability of
64-bit atomics on many 32-bit platforms, but those platforms also
cannot support nmbclusters large enough to cause overflow.

This code (in a 10.1 kernel) is presently running on production NFS
servers at CSAIL.

Summary of this revision:
* Removes 45 MiB limit on requests queued for nfsd service threads
* Fixes integer-overflow and signedness bugs
* Avoids unnecessary throttling by not deferring accounting for
  completed requests

Differential Revision:	https://reviews.freebsd.org/D2165
Reviewed by:	rmacklem, mav
MFC after:	30 days
Relnotes:	yes
Sponsored by:	MIT Computer Science & Artificial Intelligence Laboratory
2015-04-01 00:45:47 +00:00
bin sh: Add more tests for exotic IFS splitting. 2015-03-31 20:59:37 +00:00
cddl Fix a misparenthesization that could cause a crash if TERM is not set. 2015-03-31 02:49:05 +00:00
contrib Fix build. 2015-03-31 19:35:32 +00:00
crypto Document "none" for VersionAddendum. 2015-03-23 02:45:12 +00:00
etc Add limited to the default restrictions. 2015-03-31 19:56:46 +00:00
games Step 2 of eliminating the "games" distribution: Remove punch card 2015-02-22 08:50:05 +00:00
gnu Switch to ELF toolchain readelf(1) 2015-03-30 17:38:25 +00:00
include Clean some spaces vs tabs. 2015-03-29 20:20:45 +00:00
kerberos5 Add a ${CP} alias for copying files in the build. 2015-01-16 21:39:08 +00:00
lib Fix "MOVS" instruction memory to MMIO emulation. Currently updates to 2015-04-01 00:15:31 +00:00
libexec Correct copyright typo 2015-03-31 12:53:07 +00:00
release Add code for creating an EC2 AMI. 2015-04-01 00:00:17 +00:00
rescue Significant upgrades to sa(4) and mt(1). 2015-02-23 21:59:30 +00:00
sbin Constify. 2015-03-31 19:12:13 +00:00
secure Add the openssl header for arm64. As it is based on MACHINE_CPUARCH it 2015-03-24 14:16:14 +00:00
share MFV ntp 4.2.8p1 (r258945, r275970, r276091, r276092, r276093, r278284) 2015-03-30 13:30:15 +00:00
sys Fix overflow bugs in and remove obsolete limit from kernel RPC 2015-04-01 00:45:47 +00:00
tests Add some new modes to OpenCrypto. These modes are AES-ICM (can be used 2014-12-12 19:56:36 +00:00
tools - Fix -Wsign issue 2015-03-31 06:51:13 +00:00
usr.bin Remove bogus cast. 2015-03-31 15:03:58 +00:00
usr.sbin Fix typo in a comment. 2015-03-31 21:34:42 +00:00
.arcconfig
.arclint
COPYRIGHT Bump copyright year. 2014-12-31 10:00:43 +00:00
LOCKS
MAINTAINERS Remove cokane@ from MAINTAINERS for 3dfx(4)/tdfx(4) because their email 2014-11-25 05:25:12 +00:00
Makefile Make TARGET_ARCH=powerpc64 work without TARGET=powerpc. 2015-03-21 16:54:01 +00:00
Makefile.inc1 Add --sysroot to the compiler flags for clang or gcc external toolchains 2015-03-26 23:37:03 +00:00
ObsoleteFiles.inc Remove the bootconfig parsing. We never used it and always passed either an 2015-03-29 20:37:28 +00:00
README Import OpenSSL 1.0.1m. 2015-03-20 15:28:40 +00:00
UPDATING Remove from legacy ata(4) driver support for hardware, supported by newer 2015-03-24 18:09:07 +00:00

This is the top level of the FreeBSD source directory.  This file
was last revised on:
$FreeBSD$

For copyright information, please see the file COPYRIGHT in this
directory (additional copyright information also exists for some
sources in this tree - please see the specific source directories for
more information).

The Makefile in this directory supports a number of targets for
building components (or all) of the FreeBSD source tree, the most
commonly used one being ``world'', which rebuilds and installs
everything in the FreeBSD system from the source tree except the
kernel, the kernel-modules and the contents of /etc.  The ``world''
target should only be used in cases where the source tree has not
changed from the currently running version.  See:
http://www.freebsd.org/doc/en_US.ISO8859-1/books/handbook/makeworld.html
for more information, including setting make(1) variables.

The ``buildkernel'' and ``installkernel'' targets build and install
the kernel and the modules (see below).  Please see the top of
the Makefile in this directory for more information on the
standard build targets and compile-time flags.

Building a kernel is a somewhat more involved process, documentation
for which can be found at:
   http://www.freebsd.org/doc/en_US.ISO8859-1/books/handbook/kernelconfig.html
And in the config(8) man page.
Note: If you want to build and install the kernel with the
``buildkernel'' and ``installkernel'' targets, you might need to build
world before.  More information is available in the handbook.

The sample kernel configuration files reside in the sys/<arch>/conf
sub-directory (assuming that you've installed the kernel sources), the
file named GENERIC being the one used to build your initial installation
kernel.  The file NOTES contains entries and documentation for all possible
devices, not just those commonly used.  It is the successor of the ancient
LINT file, but in contrast to LINT, it is not buildable as a kernel but a
pure reference and documentation file.


Source Roadmap:
---------------
bin		System/user commands.

cddl		Various commands and libraries under the Common Development
		and Distribution License.

contrib		Packages contributed by 3rd parties.

crypto		Cryptography stuff (see crypto/README).

etc		Template files for /etc.

games		Amusements.

gnu		Various commands and libraries under the GNU Public License.
		Please see gnu/COPYING* for more information.

include		System include files.

kerberos5	Kerberos5 (Heimdal) package.

lib		System libraries.

libexec		System daemons.

release		Release building Makefile & associated tools.

rescue		Build system for statically linked /rescue utilities.

sbin		System commands.

secure		Cryptographic libraries and commands.

share		Shared resources.

sys		Kernel sources.

tools		Utilities for regression testing and miscellaneous tasks.

usr.bin		User commands.

usr.sbin	System administration commands.


For information on synchronizing your source tree with one or more of
the FreeBSD Project's development branches, please see:

  http://www.freebsd.org/doc/en_US.ISO8859-1/books/handbook/synching.html