- 28 Mar, 2009 11 commits
-
-
Chuck Lever authored
The kernel uses an IPv6 loopback address when registering its AF_INET6 RPC services so that it can tell whether the local portmapper is actually IPv6-enabled. Since the legacy portmapper doesn't listen on IPv6, however, this causes a long timeout on older systems if the kernel happens to try creating and registering an AF_INET6 RPC service. Originally I wanted to use a connected transport (either TCP or connected UDP) so that the upcall would fail immediately if the portmapper wasn't listening on IPv6, but we never agreed on what transport to use. In the end, it's of little consequence to the kernel whether the local portmapper is listening on IPv6. It's only important whether the portmapper supports rpcbind v4. And the kernel can't tell that at all if it is sending requests via IPv6 -- the portmapper will just ignore them. So, send both rpcbind v2 and v4 SET/UNSET requests via IPv4 loopback to maintain better backwards compatibility between new kernels and legacy user space, and prevent multi-second hangs in some cases when the kernel attempts to register RPC services. This patch is part of a series that addresses http://bugzilla.kernel.org/show_bug.cgi?id=12256Signed-off-by:
Chuck Lever <chuck.lever@oracle.com> Signed-off-by:
Trond Myklebust <Trond.Myklebust@netapp.com>
-
Chuck Lever authored
We are about to convert to using separate RPC listener sockets for PF_INET and PF_INET6. This echoes the way IPv6 is handled in user space by TI-RPC, and eliminates the need for ULPs to worry about mapped IPv4 AF_INET6 addresses when doing address comparisons. Start by setting the IPV6ONLY flag on PF_INET6 RPC listener sockets. Signed-off-by:
-
Chuck Lever authored
We're about to convert over to using separate PF_INET and PF_INET6 listeners, instead of a single PF_INET6 listener that also receives AF_INET requests and maps them to AF_INET6. Clear the way by removing the logic in lockd and the NFSv4 callback server that creates an AF_INET6 service listener. Signed-off-by:
-
Chuck Lever authored
Since an RPC service listener's protocol family is specified now via svc_create_xprt(), it no longer needs to be passed to svc_create() or svc_create_pooled(). Remove that argument from the synopsis of those functions, and remove the sv_family field from the svc_serv struct. Signed-off-by:
-
Chuck Lever authored
The sv_family field is going away. Pass a protocol family argument to svc_create_xprt() instead of extracting the family from the passed-in svc_serv struct. Again, as this is a listener socket and not an address, we make this new argument an "int" protocol family, instead of an "sa_family_t." Signed-off-by:
-
Chuck Lever authored
Since the sv_family field is going away, modify svc_setup_socket() to extract the protocol family from the passed-in socket instead of from the passed-in svc_serv struct. Signed-off-by:
-
Chuck Lever authored
The sv_family field is going away. Instead of using sv_family, have the svc_register() function take a protocol family argument. Since this argument represents a protocol family, and not an address family, this argument takes an int, as this is what is passed to sock_create_kern(). Also make sure svc_register's helpers are checking for PF_FOO instead of AF_FOO. The value of [AP]F_FOO are equivalent; this is simply a symbolic change to reflect the semantics of the value stored in that variable. sock_create_kern() should return EPFNOSUPPORT if the passed-in protocol family isn't supported, but it uses EAFNOSUPPORT for this case. We will stick with that tradition here, as svc_register() is called by the RPC server in the same path as sock_create_kern(). Signed-off-by:
-
Chuck Lever authored
Clean up: add documentating comment and use appropriate data types for svc_find_xprt()'s arguments. This also eliminates a mixed sign comparison: @port was an int, while the return value of svc_xprt_local_port() is an unsigned short. Signed-off-by:
-
Chuck Lever authored
Make sure port value read from user space by write_ports is valid before passing it to svc_find_xprt(). If it wasn't, the writer would get ENOENT instead of EINVAL. Noticed-by:
J. Bruce Fields <bfields@fieldses.org> Signed-off-by:
-
Chuck Lever authored
Clean up: Enable the use of const arguments in higher level svc_ APIs by adding const to the arguments of the helper functions in svc_xprt.h Signed-off-by:
-
Chuck Lever authored
In 2007, commit e65fe397 added additional sanity checking to rpcb_decode_getaddr() to make sure we were getting a reply that was long enough to be an actual universal address. If the uaddr string isn't long enough, the XDR decoder returns EIO. However, an empty string is a valid RPCB_GETADDR response if the requested service isn't registered. Moreover, "::.n.m" is also a valid RPCB_GETADDR response for IPv6 addresses that is shorter than rpcb_decode_getaddr()'s lower limit of 11. So this sanity check introduced a regression for rpcbind requests against IPv6 remotes. So revert the lower bound check added by commit e65fe397, and add an explicit check for an empty uaddr string, similar to libtirpc's rpcb_getaddr(3). Pointed-out-by:
Jeff Layton <jlayton@redhat.com> Signed-off-by:
-
- 19 Mar, 2009 8 commits
-
-
Trond Myklebust authored
Close-to-open cache consistency rules really only require us to flush out writes on calls to close(), and require us to revalidate attributes on the very last close of the file. Currently we appear to be doing a lot of extra attribute revalidation and cache flushes. Signed-off-by: -
Trond Myklebust authored
NFS appears to be returning an unnecessary "delete" notification when we're doing an atomic rename. See http://bugzilla.gnome.org/show_bug.cgi?id=575684 The fix is to get rid of the redundant call to d_delete(). Signed-off-by:
-
Trond Myklebust authored
Move the definition of nfs_need_commit() into the #ifdef CONFIG_NFS_V3 section as originally intended in the patch "NFS: cleanup - remove struct nfs_inode->ncommit" Signed-off-by: -
Tom Talpey authored
printk formats in prior commit were reversed/incorrect. Compiled without warning on x86 and x86_64, but detected on ppc. Signed-off-by:
Tom Talpey <tmtalpey@gmail.com> Signed-off-by:
-
Trond Myklebust authored
As long as one task is holding the socket lock, then calls to xprt_force_disconnect(xprt) will not succeed in shutting down the socket. In particular, this would mean that a server initiated shutdown will not succeed until the lock is relinquished. In order to avoid the deadlock, we should ensure that xs_tcp_send_request() closes the socket on EPIPE errors too. Signed-off-by: -
Trond Myklebust authored
Signed-off-by: -
Trond Myklebust authored
Signed-off-by: -
Trond Myklebust authored
This fixes a regression against FreeBSD servers as reported by Tomas Kasparek. Apparently when using RPC over a TCP socket, the FreeBSD servers don't ever react to the client closing the socket, and so commit e06799f9 (SUNRPC: Use shutdown() instead of close() when disconnecting a TCP socket) causes the setup to hang forever whenever the client attempts to close and then reconnect. We break the deadlock by adding a 'linger2' style timeout to the socket, after which, the client will abort the connection using a TCP 'RST'. The default timeout is set to 15 seconds. A subsequent patch will put it under user control by means of a systctl. Signed-off-by:
-
- 11 Mar, 2009 21 commits
-
-
Trond Myklebust authored
If xs_nospace() finds that the socket has disconnected, it attempts to return ENOTCONN, however that value is then squashed by the callers. Signed-off-by: -
Trond Myklebust authored
Enforce the comment in xs_tcp_connect_worker4/xs_tcp_connect_worker6 that we should delay, then retry on certain connection errors. Signed-off-by: -
Trond Myklebust authored
While we should definitely return socket errors to the task that is currently trying to send data, there is no need to propagate the same error to all the other tasks on xprt->pending. Doing so actually slows down recovery, since it causes more than one tasks to attempt socket recovery. Signed-off-by: -
Trond Myklebust authored
Ensure that we pick up and handle socket errors as they occur. Signed-off-by: -
Trond Myklebust authored
If we get an ECONNREFUSED error, we currently go to sleep on the 'xprt->sending' wait queue. The problem is that no timeout is set there, and there is nothing else that will wake the task up later. We should deal with ECONNREFUSED in call_status, given that is where we also deal with -EHOSTDOWN, and friends. Signed-off-by: -
Trond Myklebust authored
Signed-off-by: -
Trond Myklebust authored
...so that we can distinguish between when we need to shutdown and when we don't. Also remove the call to xs_tcp_shutdown() from xs_tcp_connect(), since xprt_connect() makes the same test. Signed-off-by: -
Trond Myklebust authored
If the socket is unconnected, and xprt_transmit() returns ENOTCONN, we currently give up the lock on the transport channel. Doing so means that the lock automatically gets assigned to the next task in the xprt->sending queue, and so that task needs to be woken up to do the actual connect. The following patch aims to avoid that unnecessary task switch. Signed-off-by: -
Tom Talpey authored
When mounting an NFS/RDMA server with the "-o proto=rdma" or "-o rdma" options, attempt to dynamically load the necessary "xprtrdma" client transport module. Doing so improves usability, while avoiding a static module dependency and any unnecesary resources. Signed-off-by:
-
Tom Talpey authored
Provide an api to attempt to load any necessary kernel RPC client transport module automatically. By convention, the desired module name is "xprt"+"transport name". For example, when NFS mounting with "-o proto=rdma", attempt to load the "xprtrdma" module. Signed-off-by:
-
Tom Talpey authored
Certain client rpc's which contain both lengthy page-contained metadata and a non-empty xdr_tail buffer require careful handling to avoid overlapped memory copying. Rearranging of existing rpcrdma marshaling code avoids it; this fixes an NFSv4 symlink creation error detected with connectathon basic/test8 to multiple servers. Signed-off-by:
-
Tom Talpey authored
Certain client-provided RPCRDMA chunk alignments result in an additional scatter/gather entry, which triggered nfs/rdma server assertions incorrectly. OpenSolaris nfs/rdma client connectathon testing was blocked by these in the special/locking section. Signed-off-by:
-
Trond Myklebust authored
Bryan Wu reports that when compiling NFS on nommu machines he gets a "defined but not used" error on nfs_file_mmap(). The easiest fix is simply to get rid of the special casing in NFS, and just always call generic_file_mmap() to set up the file. Signed-off-by: -
Trond Myklebust authored
The following patch is a combination of a patch by myself and Peter Staubach. Trond: If we allow other processes to dirty pages while a process is doing a consistency sync to disk, we can end up never making progress. Peter: Attached is a patch which addresses a continuing problem with the NFS client generating out of order WRITE requests. While this is compliant with all of the current protocol specifications, there are servers in the market which can not handle out of order WRITE requests very well. Also, this may lead to sub-optimal block allocations in the underlying file system on the server. This may cause the read throughputs to be reduced when reading the file from the server. Peter: There has been a lot of work recently done to address out of order issues on a systemic level. However, the NFS client is still susceptible to the problem. Out of order WRITE requests can occur when pdflush is in the middle of writing out pages while the process dirtying the pages calls generic_file_buffered_write which calls generic_perform_write which calls balance_dirty_pages_rate_limited which ends up calling writeback_inodes which ends up calling back into the NFS client to writes out dirty pages for the same file that pdflush happens to be working with. Signed-off-by:
Peter Staubach <staubach@redhat.com> [modification by Trond to merge the two similar patches] Signed-off-by:
-
Trond Myklebust authored
Signed-off-by: -
Trond Myklebust authored
Certain asynchronous operations such as write() do not expect (or care) that other metadata such as the file owner, mode, acls, ... change. All they want to do is update and/or check the change attribute, ctime, and mtime. By skipping the file owner and group update, we also avoid having to do a potential idmapper upcall for these asynchronous RPC calls. Signed-off-by: -
Trond Myklebust authored
Fix a bug whereby we would fail to create a mount point for a referral. Signed-off-by: -
Trond Myklebust authored
Signed-off-by: -
Trond Myklebust authored
Signed-off-by: -
Trond Myklebust authored
There is no point in using anything other than umode_t, since we copy the content pretty much directly into inode->i_mode. Signed-off-by: -
Trond Myklebust authored
We don't need the bitmap[] field anymore, since the 'valid' field tells us all we need to know about which attributes were filled in... Also move the pre-op attributes in order to improve the structure packing. Signed-off-by:
-
