Commit Graph

110 Commits

Author SHA1 Message Date
NeilBrown
1f1e030bf7 [PATCH] knfsd: fix hash function for IP addresses on 64bit little-endian machines.
The hash.h hash_long function, when used on a 64 bit machine, ignores many
of the middle-order bits.  (The prime chosen it too bit-sparse).

IP addresses for clients of an NFS server are very likely to differ only in
the low-order bits.  As addresses are stored in network-byte-order, these
bits become middle-order bits in a little-endian 64bit 'long', and so do
not contribute to the hash.  Thus you can have the situation where all
clients appear on one hash chain.

So, until hash_long is fixed (or maybe forever), us a hash function that
works well on IP addresses - xor the bytes together.

Thanks to "Iozone" <capps@iozone.org> for identifying this problem.

Cc: "Iozone" <capps@iozone.org>

Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-06 08:33:21 -08:00
Eric Dumazet
90ddc4f047 [NET]: move struct proto_ops to const
I noticed that some of 'struct proto_ops' used in the kernel may share
a cache line used by locks or other heavily modified data. (default
linker alignement is 32 bytes, and L1_CACHE_LINE is 64 or 128 at
least)

This patch makes sure a 'struct proto_ops' can be declared as const,
so that all cpus can share all parts of it without false sharing.

This is not mandatory : a driver can still use a read/write structure
if it needs to (and eventually a __read_mostly)

I made a global stubstitute to change all existing occurences to make
them const.

This should reduce the possibility of false sharing on SMP, and
speedup some socket system calls.

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2006-01-03 13:11:15 -08:00
Trond Myklebust
48e4918775 SUNRPC: Fix "EPIPE" error on mount of rpcsec_gss-protected partitions
gss_create_upcall() should not error just because rpc.gssd closed the
 pipe on its end. Instead, it should requeue the pending requests and then
 retry.

 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-12-19 23:12:21 -05:00
Trond Myklebust
b079fa7baa RPC: Do not block on skb allocation
If we get something like the following,
 [  125.300636]  [<c04086e1>] schedule_timeout+0x54/0xa5
 [  125.305931]  [<c040866e>] io_schedule_timeout+0x29/0x33
 [  125.311495]  [<c02880c4>] blk_congestion_wait+0x70/0x85
 [  125.317058]  [<c014136b>] throttle_vm_writeout+0x69/0x7d
 [  125.322720]  [<c014714d>] shrink_zone+0xe0/0xfa
 [  125.327560]  [<c01471d4>] shrink_caches+0x6d/0x6f
 [  125.332581]  [<c01472a6>] try_to_free_pages+0xd0/0x1b5
 [  125.338056]  [<c013fa4b>] __alloc_pages+0x135/0x2e8
 [  125.343258]  [<c03b74ad>] tcp_sendmsg+0xaa0/0xb78
 [  125.348281]  [<c03d4666>] inet_sendmsg+0x48/0x53
 [  125.353212]  [<c0388716>] sock_sendmsg+0xb8/0xd3
 [  125.358147]  [<c0388773>] kernel_sendmsg+0x42/0x4f
 [  125.363259]  [<c038bc00>] sock_no_sendpage+0x5e/0x77
 [  125.368556]  [<c03ee7af>] xs_tcp_send_request+0x2af/0x375
 then the socket is blocked until memory is reclaimed, and no
 progress can ever be made.

 Try to access the emergency pools by using GFP_ATOMIC.

 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-12-19 23:11:54 -05:00
Trond Myklebust
bb184f3356 SUNRPC: Fix Oopsable condition in rpc_pipefs
The elements on rpci->in_upcall are tracked by the filp->private_data,
 which will ensure that they get released when the file is closed.

 The exception is if rpc_close_pipes() gets called first, since that
 sets rpci->ops to NULL.

 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-12-03 15:20:10 -05:00
Trond Myklebust
b3eb67a2ab SUNRPC: Funny looking code in __rpc_purge_upcall
In __rpc_purge_upcall (net/sunrpc/rpc_pipe.c), the newer code to clean up
 the in_upcall list has a typo.
 Thanks to Vince Busam <vbusam@google.com> for spotting this!

 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-11-25 17:11:30 -05:00
NeilBrown
1887b93529 [PATCH] knfsd: make sure nfsd doesn't hog a cpu forever
Being kernel-threads, nfsd servers don't get pre-empted (depending on
CONFIG).  If there is a steady stream of NFS requests that can be served
from cache, an nfsd thread may hold on to a cpu indefinitely, which isn't
very friendly.

So it is good to have a cond_resched in there (just before looking for a
new request to serve), to make sure we play nice.

Signed-off-by: Neil Brown <neilb@suse.de>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-11-15 08:59:19 -08:00
Herbert Xu
fb286bb299 [NET]: Detect hardware rx checksum faults correctly
Here is the patch that introduces the generic skb_checksum_complete
which also checks for hardware RX checksum faults.  If that happens,
it'll call netdev_rx_csum_fault which currently prints out a stack
trace with the device name.  In future it can turn off RX checksum.

I've converted every spot under net/ that does RX checksum checks to
use skb_checksum_complete or __skb_checksum_complete with the
exceptions of:

* Those places where checksums are done bit by bit.  These will call
netdev_rx_csum_fault directly.

* The following have not been completely checked/converted:

ipmr
ip_vs
netfilter
dccp

This patch is based on patches and suggestions from Stephen Hemminger
and David S. Miller.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-11-10 13:01:24 -08:00
Trond Myklebust
940e3318c3 [PATCH] SUNRPC: don't reencode when looping in call transmit.
If the call to xprt_transmit() fails due to socket buffer space
exhaustion, we do not need to re-encode the RPC message when we
loop back through call_transmit.

Re-encoding can actually end up triggering the WARN_ON() in
call_decode() if we re-encode something like a read() request and
auth->au_rslack has changed.
It can also cause us to increment the RPCSEC_GSS sequence number
beyond the limits of the allowed window.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-11-09 19:31:33 -08:00
Christoph Hellwig
49705b7743 [PATCH] sanitize lookup_hash prototype
->permission and ->lookup have a struct nameidata * argument these days to
pass down lookup intents.  Unfortunately some callers of lookup_hash don't
actually pass this one down.  For lookup_one_len() we don't have a struct
nameidata to pass down, but as this function is a library function only
used by filesystem code this is an acceptable limitation.  All other
callers should pass down the nameidata, so this patch changes the
lookup_hash interface to only take a struct nameidata argument and derives
the other two arguments to __lookup_hash from it.  All callers already have
the nameidata argument available so this is not a problem.

At the same time I'd like to deprecate the lookup_hash interface as there
are better exported interfaces for filesystem usage.  Before it can
actually be removed I need to fix up rpc_pipefs.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Ram Pai <linuxram@us.ibm.com>
Cc: Jeff Mahoney <jeffm@suse.com>
Cc: Al Viro <viro@ftp.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-11-09 07:56:00 -08:00
Jesper Juhl
a51482bde2 [NET]: kfree cleanup
From: Jesper Juhl <jesper.juhl@gmail.com>

This is the net/ part of the big kfree cleanup patch.

Remove pointless checks for NULL prior to calling kfree() in net/.

Signed-off-by: Jesper Juhl <jesper.juhl@gmail.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Arnaldo Carvalho de Melo <acme@conectiva.com.br>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Acked-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
2005-11-08 09:41:34 -08:00
NeilBrown
80d188a643 [PATCH] knfsd: make sure svc_process call the correct pg_authenticate for multi-service port
If an RPC socket is serving multiple programs, then the pg_authenticate of
the first program in the list is called, instead of pg_authenticate for the
program to be run.

This does not cause a problem with any programs in the current kernel, but
could confuse future code.

Also set pg_authenticate for nfsd_acl_program incase it ever gets used.

Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-11-07 07:53:49 -08:00
Chuck Lever
0bbacc402e NFS,SUNRPC,NLM: fix unused variable warnings when CONFIG_SYSCTL is disabled
Fix some dprintk's so that NLM, NFS client, and RPC client compile
 cleanly if CONFIG_SYSCTL is disabled.

 Test plan:
 Compile kernel with CONFIG_NFS enabled and CONFIG_SYSCTL disabled.

 Signed-off-by: Chuck Lever <cel@netapp.com>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-11-04 15:39:48 -05:00
Chuck Lever
c556b75496 SUNRPC: allow sunrpc.o to link when CONFIG_SYSCTL is disabled
The sunrpc module should build properly even when CONFIG_SYSCTL is
 disabled.

 Reported by Jan-Benedict Glaw.

 Test plan:
 Compile kernel with CONFIG_NFS as a module and built-in, and CONFIG_SYSCTL
 enabled and disabled.

 Signed-off-by: Chuck Lever <cel@netapp.com>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-11-04 15:39:45 -05:00
Herbert Xu
6df5b9f48d [CRYPTO] Simplify one-member scatterlist expressions
This patch rewrites various occurences of &sg[0] where sg is an array
of length one to simply sg.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2005-10-30 11:19:43 +11:00
David Hardeman
378f058cc4 [PATCH] Use sg_set_buf/sg_init_one where applicable
This patch uses sg_set_buf/sg_init_one in some places where it was
duplicated.

Signed-off-by: David Hardeman <david@2gen.com>
Cc: James Bottomley <James.Bottomley@steeleye.com>
Cc: Greg KH <greg@kroah.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jeff Garzik <jgarzik@pobox.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2005-10-30 11:19:43 +11:00
Trond Myklebust
6070fe6f82 RPC: Ensure that nobody can queue up new upcalls after rpc_close_pipes()
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-10-27 22:12:46 -04:00
Trond Myklebust
4c2cb58c55 Merge /home/trondmy/scm/kernel/git/torvalds/linux-2.6 2005-10-27 19:12:49 -04:00
Trond Myklebust
6fa05b1736 Revert "RPC: stops the release_pipe() funtion from being called twice"
This reverts 747c5534c9 commit.
2005-10-27 19:08:18 -04:00
Andrew Morton
4bcde03d41 [PATCH] svcsock timestamp fix
Convert nanoseconds to microseconds correctly.

Spotted by Steve Dickson <SteveD@redhat.com>

Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-26 10:39:43 -07:00
J. Bruce Fields
a0857d03b2 RPCSEC_GSS: krb5 cleanup
Remove some senseless wrappers.

 Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-10-18 23:19:47 -07:00
J. Bruce Fields
00fd6e1425 RPCSEC_GSS remove all qop parameters
Not only are the qop parameters that are passed around throughout the gssapi
 unused by any currently implemented mechanism, but there appears to be some
 doubt as to whether they will ever be used.  Let's just kill them off for now.

 Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-10-18 23:19:47 -07:00
J. Bruce Fields
14ae162c24 RPCSEC_GSS: Add support for privacy to krb5 rpcsec_gss mechanism.
Add support for privacy to the krb5 rpcsec_gss mechanism.

 Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-10-18 23:19:46 -07:00
J. Bruce Fields
bfa91516b5 RPCSEC_GSS: krb5 pre-privacy cleanup
The code this was originally derived from processed wrap and mic tokens using
 the same functions.  This required some contortions, and more would be required
 with the addition of xdr_buf's, so it's better to separate out the two code
 paths.

 In preparation for adding privacy support, remove the last vestiges of the
 old wrap token code.

 Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-10-18 23:19:45 -07:00
J. Bruce Fields
f7b3af64c6 RPCSEC_GSS: Simplify rpcsec_gss crypto code
Factor out some code that will be shared by privacy crypto routines

 Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-10-18 23:19:45 -07:00
J. Bruce Fields
2d2da60c63 RPCSEC_GSS: client-side privacy support
Add the code to the client side to handle privacy.  This is dead code until
 we actually add privacy support to krb5.

 Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-10-18 23:19:44 -07:00
J. Bruce Fields
24b2605bec RPCSEC_GSS: cleanup au_rslack calculation
Various xdr encode routines use au_rslack to guess where the reply argument
 will end up, so we can set up the xdr_buf to recieve data into the right place
 for zero copy.

 Currently we calculate the au_rslack estimate when we check the verifier.
 Normally this only depends on the verifier size.  In the integrity case we add
 a few bytes to allow for a length and sequence number.

 It's a bit simpler to calculate only the verifier size when we check the
 verifier, and delay the full calculation till we unwrap.

 Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-10-18 23:19:44 -07:00
J. Bruce Fields
f3680312a7 SUNRPC: Retry wrap in case of memory allocation failure.
For privacy we need to allocate extra pages to hold encrypted page data when
 wrapping requests.  This allocation may fail, and we handle that case by
 waiting and retrying.

 Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-10-18 23:19:43 -07:00
J. Bruce Fields
ead5e1c26f SUNRPC: Provide a callback to allow free pages allocated during xdr encoding
For privacy, we need to allocate pages to store the encrypted data (passed
 in pages can't be used without the risk of corrupting data in the page cache).
 So we need a way to free that memory after the request has been transmitted.

 Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-10-18 23:19:43 -07:00
J. Bruce Fields
293f1eb551 SUNRPC: Add support for privacy to generic gss-api code.
Add support for privacy to generic gss-api code.  This is dead code until we
 have both a mechanism that supports privacy and code in the client or server
 that uses it.

 Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-10-18 23:19:42 -07:00
Steve Dickson
747c5534c9 RPC: stops the release_pipe() funtion from being called twice
This patch stops the release_pipe() funtion from being called
 twice by invalidating the ops pointer in the rpc_inode
 when rpc_pipe_release() is called.

 Signed-off-by: Steve Dickson <steved@redhat.com>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-10-18 23:19:40 -07:00
Trond Myklebust
5e5ce5be6f RPC: allow call_encode() to delay transmission of an RPC call.
Currently, call_encode will cause the entire RPC call to abort if it returns
 an error. This is unnecessarily rigid, and gets in the way of attempts
 to allow the NFSv4 layer to order RPC calls that carry sequence ids.

 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-10-18 14:20:11 -07:00
Chuck Lever
ea635a517e SUNRPC: Retry rpcbind requests if the server's portmapper isn't up
After a server crash/reboot, rebinding should always retry, otherwise
 requests on "hard" mounts will fail when they shouldn't.

 Test plan:
 Run a lock-intensive workload against a server while rebooting the server
 repeatedly.

 Signed-off-by: Chuck Lever <cel@netapp.com>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-10-18 14:20:10 -07:00
Trond Myklebust
cff6bf9709 Merge /home/trondmy/scm/kernel/git/torvalds/linux-2.6 2005-10-18 13:50:52 -07:00
Al Viro
dd0fc66fb3 [PATCH] gfp flags annotations - part 1
- added typedef unsigned int __nocast gfp_t;

 - replaced __nocast uses for gfp flags with gfp_t - it gives exactly
   the same warnings as far as sparse is concerned, doesn't change
   generated code (from gcc point of view we replaced unsigned int with
   typedef) and documents what's going on far better.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-08 15:00:57 -07:00
Randy Dunlap
dd13a285b7 [RPC]: fix sparse gfp nocast warnings
Fix nocast sparse warnings:
net/rxrpc/call.c:2013:25: warning: implicit cast to nocast type
net/rxrpc/connection.c:538:46: warning: implicit cast to nocast type
net/sunrpc/sched.c:730:36: warning: implicit cast to nocast type
net/sunrpc/sched.c:734:56: warning: implicit cast to nocast type

Signed-off-by: Randy Dunlap <rdunlap@xenotime.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2005-10-04 22:44:45 -07:00
Chuck Lever
6cd7525a00 SUNRPC: fix bug in patch "portmapper doesn't need a reserved port"
The in-kernel portmapper does in fact need a reserved port when registering
 new services, but not when performing bind queries.

 Ensure that we distinguish between the two cases.

 Signed-off-by: Chuck Lever <cel@netapp.com>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-09-23 13:54:10 -04:00
Trond Myklebust
f134585a73 Revert "[PATCH] RPC,NFS: new rpc_pipefs patch"
This reverts 17f4e6febca160a9f9dd4bdece9784577a2f4524 commit.
2005-09-23 12:39:00 -04:00
Christoph Hellwig
278c995c8a [PATCH] RPC,NFS: new rpc_pipefs patch
Currently rpc_mkdir/rpc_rmdir and rpc_mkpipe/mk_unlink have an API that's
 a little unfortunate.  They take a path relative to the rpc_pipefs root and
 thus need to perform a full lookup.  If you look at debugfs or usbfs they
 always store the dentry for directories they created and thus can pass in
 a dentry + single pathname component pair into their equivalents of the
 above functions.

 And in fact rpc_pipefs actually stores a dentry for all but one component so
 this change not only simplifies the core rpc_pipe code but also the callers.

 Unfortuntately this code path is only used by the NFS4 idmapper and
 AUTH_GSSAPI for which I don't have a test enviroment.  Could someone give
 it a spin?  It's the last bit needed before we can rework the
 lookup_hash API

 Signed-off-by: Christoph Hellwig <hch@lst.de>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-09-23 12:38:57 -04:00
Chuck Lever
470056c288 [PATCH] RPC: rationalize set_buffer_size
In fact, ->set_buffer_size should be completely functionless for non-UDP.

 Test-plan:
 Check socket buffer size on UDP sockets over time.

 Signed-off-by: Chuck Lever <cel@netapp.com>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-09-23 12:38:55 -04:00
Chuck Lever
03bf4b707e [PATCH] RPC: parametrize various transport connect timeouts
Each transport implementation can now set unique bind, connect,
 reestablishment, and idle timeout values.  These are variables,
 allowing the values to be modified dynamically.  This permits
 exponential backoff of any of these values, for instance.

 As an example, we implement exponential backoff for the connection
 reestablishment timeout.

 Test-plan:
 Destructive testing (unplugging the network temporarily).  Connectathon
 with UDP and TCP.

 Signed-off-by: Chuck Lever <cel@netapp.com>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-09-23 12:38:53 -04:00
Chuck Lever
3167e12c0c [PATCH] RPC: make sure to get the same local port number when reconnecting
Implement a best practice: if the remote end drops our connection, try to
 reconnect using the same port number.  This is important because the NFS
 server's Duplicate Reply Cache often hashes on the source port number.
 If the client reuses the port number when it reconnects, the server's DRC
 will be more effective.

 Based on suggestions by Mike Eisler, Olaf Kirch, and Alexey Kuznetsky.

 Test-plan:
 Destructive testing.

 Signed-off-by: Chuck Lever <cel@netapp.com>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-09-23 12:38:52 -04:00
Chuck Lever
529b33c6db [PATCH] RPC: allow RPC client's port range to be adjustable
Select an RPC client source port between 650 and 1023 instead of between
 1 and 800.  The old range conflicts with a number of network services.
 Provide sysctls to allow admins to select a different port range.

 Note that this doesn't affect user-level RPC library behavior, which
 still uses 1 to 800.

 Based on a suggestion by Olaf Kirch <okir@suse.de>.

 Test-plan:
 Repeated mount and unmount.  Destructive testing.  Idle timeouts.

 Signed-off-by: Chuck Lever <cel@netapp.com>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-09-23 12:38:50 -04:00
Chuck Lever
555ee3af16 [PATCH] RPC: clean up after nocong was removed
Clean-up:  Move some macros that are specific to the Van Jacobson
 implementation into xprt.c.  Get rid of the cong_wait field in
 rpc_xprt, which is no longer used.  Get rid of xprt_clear_backlog.

 Test-plan:
 Compile with CONFIG_NFS enabled.

 Signed-off-by: Chuck Lever <cel@netapp.com>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-09-23 12:38:48 -04:00
Chuck Lever
ed63c00370 [PATCH] RPC: remove xprt->nocong
Get rid of the "xprt->nocong" variable.

 Test-plan:
 Use WAN simulation to cause sporadic bursty packet loss with UDP mounts.
 Look for significant regression in performance or client stability.

 Signed-off-by: Chuck Lever <cel@netapp.com>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-09-23 12:38:47 -04:00
Chuck Lever
a58dd398f5 [PATCH] RPC: add a release_rqst callout to the RPC transport switch
The final place where congestion control state is adjusted is in
 xprt_release, where each request is finally released.  Add a callout
 there to allow transports to perform additional processing when a
 request is about to be released.

 Test-plan:
 Use WAN simulation to cause sporadic bursty packet loss.  Look for significant
 regression in performance or client stability.

 Signed-off-by: Chuck Lever <cel@netapp.com>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-09-23 12:38:45 -04:00
Chuck Lever
1570c1e41e [PATCH] RPC: add generic interface for adjusting the congestion window
A new interface that allows transports to adjust their congestion window
 using the Van Jacobson implementation in xprt.c is provided.

 Test-plan:
 Use WAN simulation to cause sporadic bursty packet loss.  Look for
 significant regression in performance or client stability.

 Signed-off-by: Chuck Lever <cel@netapp.com>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-09-23 12:38:43 -04:00
Chuck Lever
46c0ee8bc4 [PATCH] RPC: separate xprt_timer implementations
Allow transports to hook the retransmit timer interrupt.  Some transports
 calculate their congestion window here so that a retransmit timeout has
 immediate effect on the congestion window.

 Test-plan:
 Use WAN simulation to cause sporadic bursty packet loss.  Look for significant
 regression in performance or client stability.

 Signed-off-by: Chuck Lever <cel@netapp.com>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-09-23 12:38:41 -04:00
Chuck Lever
49e9a89086 [PATCH] RPC: expose API for serializing access to RPC transports
The next method we abstract is the one that releases a transport,
 allowing another task to have access to the transport.

 Again, one generic version of this is provided for transports that
 don't need the RPC client to perform congestion control, and one
 version is for transports that can use the original Van Jacobson
 implementation in xprt.c.

 Test-plan:
 Use WAN simulation to cause sporadic bursty packet loss.  Look for
 significant regression in performance or client stability.

 Signed-off-by: Chuck Lever <cel@netapp.com>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-09-23 12:38:40 -04:00
Chuck Lever
12a804698b [PATCH] RPC: expose API for serializing access to RPC transports
The next several patches introduce an API that allows transports to
 choose whether the RPC client provides congestion control or whether
 the transport itself provides it.

 The first method we abstract is the one that serializes access to the
 RPC transport to prevent the bytes from different requests from mingling
 together.  This method provides proper request serialization and the
 opportunity to prevent new requests from being started because the
 transport is congested.

 The normal situation is for the transport to handle congestion control
 itself.  Although NFS over UDP was first, it has been recognized after
 years of experience that having the transport provide congestion control
 is much better than doing it in the RPC client.  Thus TCP, and probably
 every future transport implementation, will use the default method,
 xprt_lock_write, provided in xprt.c, which does not provide any kind
 of congestion control.  UDP can continue using the xprt.c-provided
 Van Jacobson congestion avoidance implementation.

 Test-plan:
 Use WAN simulation to cause sporadic bursty packet loss.  Look for significant
 regression in performance or client stability.

 Signed-off-by: Chuck Lever <cel@netapp.com>
 Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
2005-09-23 12:38:38 -04:00