Distributed Network Block Device 3 --rewrite for Kernel 3.x https://git.openslx.org/dnbd3.git/atom/src/kernel/dnbd3_main.h?h=fuse_cow_2 2021-06-16T09:41:00+00:00 2021-06-16T09:41:00+00:00 Manuel Bentele 2021-06-15T10:26:14+00:00 urn:sha1:75e9f49df8ff7f00a2c28ee1e30f1d87bcce4bca 2021-04-16T06:20:06+00:00 Manuel Bentele 2021-04-16T06:20:06+00:00 urn:sha1:f7cca217a3696980a72564f57bad4597ddbe9df5 2021-03-26T12:44:47+00:00 Simon Rettberg 2021-03-26T12:44:47+00:00 urn:sha1:3a7891e26aec9e5d15d21a78cb317926d96f51e9 Similar logic already exists in the fuse client: Count how many times in a row a server was fastest when measuring RTTs, and lower the switching threshold more the higher the count gets. 2021-03-24T15:07:15+00:00 Simon Rettberg 2021-03-24T15:07:15+00:00 urn:sha1:c73bc9413da8bc964d82e0a58525c7280cc1a456 Convert dnbd3_host_t to struct sockaddr immediately when adding alt servers, so we don't have to convert it every time we establish a connection. Additionally we can now use %pISpc in printf-like functions instead of having if/else constructs whenever we want to print an address. 2021-03-23T15:00:55+00:00 Simon Rettberg 2021-03-23T15:00:55+00:00 urn:sha1:b9c11caeb31d1066979b8554f565f24abfe475f6 2021-03-12T13:52:47+00:00 Manuel Bentele 2021-03-12T13:52:47+00:00 urn:sha1:52a4ac3ede9b5bbc8015105d6fd5524c70e9bef5 2020-11-19T12:48:14+00:00 Simon Rettberg 2020-11-19T12:48:14+00:00 urn:sha1:a1caec1f2bebe09f685716f13d7b55f84d8a8145 Previously disconnect was protected against concurrent calls, but connect wasn't. It was easy to crash the kernel when calling connect and disconnect IOCTLs in a tight loop concurrently. A global lock was introduced to make sure only one caller can change the connection state at a time. dev->connection_lock needs to be aquired when calling dnbd3_net_connect or _disconnect. This atomic_t based locking mechanism should be turned into a mutex in a next step, relying on mutex_trylock for cases where we don't have the cmpxchg-schedule() loop. Along the way it was noticed that the send/receive timeouts don't apply to kernel_connect, which might have been the case in older 3.x kernel versions. A crude workaround using nonblocking connect has been introduced to emulate this, but a clean solution for this is welcomed. Also, devices are now properly closed on module unload. 2020-11-10T06:42:40+00:00 Manuel Bentele 2020-11-10T06:42:40+00:00 urn:sha1:5a430387ffc52d1520e3c6bbc7ef664b282c9644 This patch adds the feature to manually switch the dnbd3-server to a specified server. The switching is implemented by the use of the ioctl call SWITCH. 2020-11-09T05:54:54+00:00 Manuel Bentele 2020-11-09T05:54:54+00:00 urn:sha1:03db52349890088b8ceaec17736bbd2d0769b52a This patch changes the probing logic to select the first available dnbd3-server submitted by the ioctl OPEN call. All other specified dnbd3-servers are added to the alternative server list and do not have to be available. 2020-11-06T11:44:43+00:00 Manuel Bentele 2020-11-06T11:44:43+00:00 urn:sha1:ef92307fd49e75482c7599caf68685afc1807512 The ioctl OPEN call for DNBD3 devices exposed by the dnbd3 Linux kernel module, is extended with a fixed array of dnbd3 hosts. The fixed array allows the dnbd3-client to submit host information (IP address and port) of multiple dnbd3-servers. This information is used to probe all submitted dnbd3-servers and add them to the alternative dnbd3-server list. If at least one dnbd3-server is not reachable, the OPEN ioctl call will abort with an error code.