[v3 00/39] faster tree-based sysctl implementation

From: Lucian Adrian Grijincu
Date: Sun May 22 2011 - 21:56:39 EST

Hi

This is version 3 of a patch series that introduces a faster/leaner
sysctl internal implementation.

Due to high number of patches and low general interest I'll just point
you to the tree/branch:

git://github.com/luciang/linux-2.6-new-sysctl.git v3-new-sysctl-alg


Patches are on top of v2.6.39. I did not pick a more recent (random)
point in Linus' tree to rebase these onto to not mess up testing.



Changes since v2
(http://thread.gmane.org/gmane.linux.kernel/1137032/focus=194748):
- added a compatibility layer to support old registering complex
sysctl trees. This layer will be deleted once all users of the old
are changed.
- subdirectories and netns correspondent dirs are now held in rbtrees
- split of from the patches that make changes in the rest of the tree
- rebased on top of 2.6.39




Changes since v1 (http://thread.gmane.org/gmane.linux.kernel/1133667):
- rebased on top of 2.6.39-rc6
- split the patch that adds the new algorithm and data structures.
- fixed a few bugs lingering in the old code
- shrinked a reference counter
- added a new reference counter to maintain ownership information
- added method to register an empty sysctl dir and converted some users
- added checks enforcing the rule that a non-netns specific directory may
not be registered after a netns specific one has already been registered.
- added cookie support: register a piece of data with the header to be
used to make simple conversions on the ctl_table. This saves memory where
we need to register sysctl tables with the same content affecting
different pieces of data.
- enforced sysctl checks



$ time modprobe dummy numdummies=N


NOTE: these stats are from v2. v3 should be a bit slower due to:
- the compatibility layer
- the old stats used cookies to prevent kmemdups() on ctl_table arrays
- the old patches had an optimisation for directories with many
subdirs that was replaced (in v3) with rbtrees

Without this patch series :(
- ipv4 only
- N=1000 time= 0m 06s
- N=2000 time= 0m 30s
- N=4000 time= 2m 35s
- ipv4 and ipv6
- N=1000 time= 0m 24s
- N=2000 time= 2m 14s
- N=4000 time=10m 16s
- N=5000 time=16m 3s

With this patch series :)
- ipv4 only
- N=1000 time= 0m 0.33s
- N=2000 time= 0m 1.25s
- N=4000 time= 0m 5.31s
- ipv4 and ipv6
- N=1000 time= 0m 0.41s
- N=2000 time= 0m 1.62s
- N=4000 time= 0m 7.64s
- N=5000 time= 0m 12.35s
- N=8000 time= 0m 36.95s




Patches marked with RFC: are patches where reviewers should pay more
attention as I may have missed something.


Part 1: introduce compatibility layer:
sysctl: introduce temporary sysctl wrappers
sysctl: register only tables of sysctl files


Part 2: minimal changes to sysctl users:
sysctl: call sysctl_init before the first sysctl registration
sysctl: no-child: manually register kernel/random
sysctl: no-child: manually register kernel/keys
sysctl: no-child: manually register fs/inotify
sysctl: no-child: manually register fs/epoll
sysctl: no-child: manually register root tables


Part 3: cleanups simplifying the new algorithm (created when asked to
break up the new algorithm patch:
sysctl: faster reimplementation of sysctl_check_table
sysctl: remove useless ctl_table->parent field
sysctl: simplify find_in_table
sysctl: sysctl_head_grab defaults to root header on NULL
sysctl: delete useless grab_header function
sysctl: rename ->used to ->ctl_use_refs
sysctl: rename sysctl_head_grab/finish to sysctl_use_header/unuse
sysctl: rename sysctl_head_next to sysctl_use_next_header
sysctl: split ->count into ctl_procfs_refs and ctl_header_refs
sysctl: rename sysctl_head_get/put to sysctl_proc_inode_get/put
sysctl: rename (un)use_table to __sysctl_(un)use_header
sysctl: simplify ->permissions hook
sysctl: group root-specific operations
sysctl: introduce ctl_table_group
sysctl: move removal from list out of start_unregistering


Part 4: new algorithm/data structures:
sysctl: faster tree-based sysctl implementation


Part 5: checks/warns requested during review:
sysctl: add duplicate entry and sanity ctl_table checks
sysctl: alloc ctl_table_header with kmem_cache
RFC: sysctl: change type of ctl_procfs_refs to u8
sysctl: check netns-specific registration order respected
sysctl: warn if registration/unregistration order is not respected
RFC: sysctl: always perform sysctl checks


Part 6: Eric requested rbtrees for subdirs. I also used rbtrees for
netns correspondent dirs. Hope that adding rbtrees after using the old
list-based implementation is good enough. The rbtree code complicates
things a bit and would uglify the patch adding the new algorithm.
sysctl: reorder members of ctl_table_header (cleanup)
sysctl: add ctl_type member
RFC: sysctl: replace subdirectory list with rbtree
RFC: sysctl: replace netns corresp list with rbtree
sysctl: union-ize some ctl_table_header fields


Part 7: Eric requested ability to register an empty dir:
sysctl: add register_sysctl_dir: register an empty sysctl directory


Part 8: unrequested feature I'd like to piggy back :)
sysctl: add ctl_cookie and ctl_cookie_handler
sysctl: add cookie to __register_sysctl_paths
sysctl: add register_net_sysctl_table_net_cookie


drivers/char/random.c | 27 +-
fs/eventpoll.c | 22 +-
fs/notify/inotify/inotify_user.c | 22 +-
fs/proc/inode.c | 2 +-
fs/proc/proc_sysctl.c | 233 +++++---
include/linux/inotify.h | 2 -
include/linux/key.h | 3 -
include/linux/poll.h | 2 -
include/linux/sysctl.h | 221 +++++---
include/net/net_namespace.h | 4 +-
init/main.c | 1 +
kernel/Makefile | 5 +-
kernel/sysctl.c | 1161 ++++++++++++++++++++++++++++----------
kernel/sysctl_check.c | 325 +++++++----
lib/Kconfig.debug | 8 -
net/sysctl_net.c | 86 ++--
security/keys/key.c | 7 +
security/keys/sysctl.c | 18 +-
18 files changed, 1495 insertions(+), 654 deletions(-)


--
Â.
..: Lucian
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/