linux-toradex.git/include/linux/sunrpc/cache.h, branch v2.6.26-rc5

svcrpc: move unused field from cache_deferred_req

2008-04-23T20:13:37+00:00

This field is set once and never used; probably some artifact of an
earlier implementation idea.

Signed-off-by: J. Bruce Fields

knfsd: allow cache_register to return error on failure

2008-02-01T21:42:05+00:00

Newer server features such as nfsv4 and gss depend on proc to work, so a
failure to initialize the proc files they need should be treated as
fatal.

Thanks to Andrew Morton for style fix and compile fix in case where
CONFIG_NFSD_V4 is undefined.

Cc: Andrew Morton 
Acked-by: NeilBrown 
Signed-off-by: J. Bruce Fields

knfsd: cache unregistration needn't return error

2008-02-01T21:42:04+00:00

There's really nothing much the caller can do if cache unregistration
fails.  And indeed, all any caller does in this case is print an error
and continue.  So just return void and move the printk's inside
cache_unregister.

Acked-by: NeilBrown 
Signed-off-by: J. Bruce Fields

nfsd: remove unused cache_for_each macro

2007-10-09T22:31:55+00:00

This macro is unused.

Signed-off-by: "J. Bruce Fields" 
Acked-by:  Neil Brown

[PATCH] knfsd: knfsd: cache ipmap per TCP socket

2006-10-04T14:55:16+00:00

Speed up high call-rate workloads by caching the struct ip_map for the peer on
the connected struct svc_sock instead of looking it up in the ip_map cache
hashtable on every call.  This helps workloads using AUTH_SYS authentication
over TCP.

Testing was on a 4 CPU 4 NIC Altix using 4 IRIX clients, each with 16
synthetic client threads simulating an rsync (i.e.  recursive directory
listing) workload reading from an i386 RH9 install image (161480 regular files
in 10841 directories) on the server.  That tree is small enough to fill in the
server's RAM so no disk traffic was involved.  This setup gives a sustained
call rate in excess of 60000 calls/sec before being CPU-bound on the server.

Profiling showed strcmp(), called from ip_map_match(), was taking 4.8% of each
CPU, and ip_map_lookup() was taking 2.9%.  This patch drops both contribution
into the profile noise.

Note that the above result overstates this value of this patch for most
workloads.  The synthetic clients are all using separate IP addresses, so
there are 64 entries in the ip_map cache hash.  Because the kernel measured
contained the bug fixed in commit

commit 1f1e030bf75774b6a283518e1534d598e14147d4

and was running on 64bit little-endian machine, probably all of those 64
entries were on a single chain, thus increasing the cost of ip_map_lookup().

With a modern kernel you would need more clients to see the same amount of
performance improvement.  This patch has helped to scale knfsd to handle a
deployment with 2000 NFS clients.

Signed-off-by: Greg Banks 
Signed-off-by: Neil Brown 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

[PATCH] fs/nfsd/export.c,net/sunrpc/cache.c: make needlessly global code static

2006-03-27T16:44:43+00:00

We can now make some code static.

Signed-off-by: Adrian Bunk 
Cc: Neil Brown 
Cc: Trond Myklebust 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

[PATCH] knfsd: Convert sunrpc_cache to use krefs

2006-03-27T16:44:43+00:00

.. it makes some of the code nicer.

Signed-off-by: Neil Brown 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

[PATCH] knfsd: Unexport cache_fresh and fix a small race

2006-03-27T16:44:43+00:00

Cache_fresh is now only used in cache.c, so unexport it.

Part of cache_fresh (setting CACHE_VALID) should really be done under the
lock, while part (calling cache_revisit_request etc) must be done outside the
lock.  So we split it up appropriately.

Signed-off-by: Neil Brown 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

[PATCH] knfsd: Remove DefineCacheLookup

2006-03-27T16:44:42+00:00

This has been replaced by more traditional code.

Signed-off-by: Neil Brown 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

[PATCH] knfsd: Create cache_lookup function instead of using a macro to declare one

2006-03-27T16:44:41+00:00

The C++-like 'template' approach proves to be too ugly and hard to work with.

The old 'template' won't go away until all users are updated.

Signed-off-by: Neil Brown 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds