Distributed Network Block Device 3 --rewrite for Kernel 3.x https://git.openslx.org/dnbd3.git/atom/src/server/uplink.h?h=isfant 2020-10-16T15:15:49+00:00 2020-10-16T15:15:49+00:00 Manuel Bentele 2020-10-16T15:15:49+00:00 urn:sha1:969496f15e1e0359e26c2c6e995ad4ef82720f86 This change restructures the source code directories, separates shared form non-shared application code and adds CMake dependencies. These dependencies allow the tracking of changes and trigger a rebuild of those build targets where changed files are involved. WARNING: Note that the support of the DNBD3_SERVER_AFL build option is not supported yet. Thus, the option should be never turned on. 2020-07-28T15:49:17+00:00 Simon Rettberg 2020-07-28T15:49:17+00:00 urn:sha1:e4dec3562e6cab27e1a3f40165e4c0d9d0bf05c9 Still needs some cleanup and optimizations, variable naming sucks, comments, etc. 2020-03-13T15:03:29+00:00 Simon Rettberg 2020-03-13T15:03:29+00:00 urn:sha1:290d3478f245bb7d2112bb781286a9fbae42b983 - Now uses linked lists instead of huge array - Does prefetch data on client requests - Can have multiple replication requests in-flight 2019-08-27T14:13:07+00:00 Simon Rettberg 2019-08-27T14:13:07+00:00 urn:sha1:69f5bf408b9587a6e2008fba2224c2d506f1a895 First step towards less locking for proxy mode 2019-08-22T14:14:27+00:00 Simon Rettberg 2019-08-22T14:14:27+00:00 urn:sha1:5fb4ef278be86fb6bda487f65ec4855d830bf4e5 Alt-Server checks are now run using the threadpool, so we don't need a queue and dedicated thread anymore. The rtt history is now kept per uplink, so many uplinks won't overwhelm the history, making its time window very short. Also the fail counter is now split up; a global one for when the server actually isn't reachable, a local (per-uplink) one for when the server is reachable but doesn't serve the requested image. 2019-08-18T19:31:56+00:00 Simon Rettberg 2019-08-18T19:31:56+00:00 urn:sha1:da0950ad342bae3b40a74bf82dba6c1f82e7eb57 * Change link to uplink everywhere * dnbd3_connection_t -> dnbd3_uplink_t 2017-10-17T10:08:55+00:00 Simon Rettberg 2017-10-17T10:08:55+00:00 urn:sha1:102705470366b871109d2c3bf182c151ab71eb01 We steal 8 bits from the request offset to count hops when requests get relayed by proxies. This still leaves plenty of bits for the offset (56 bits, supporting images of up to 72 petabytes). This is used to detect proxy cycles. The algorithm is not perfect but should prevent endless relays of the same request. This is backwards compatible to old clients and servers, as the server only ever sets the hopcount in relayed requests if the upstream server is using protocol version 3 or newer, and clients are automatically upwards compatible as there is practically no image larger than 74PB, so the newly introduced hop count field is always 0 even in requests from old clients. 2016-02-10T23:09:39+00:00 Sebastian 2016-02-10T20:14:40+00:00 urn:sha1:34ddebc84cb9ea933cfdb9cc3fa688b6a2fae78e 2015-05-05T16:18:32+00:00 Stephan Schwaer 2015-05-05T16:18:32+00:00 urn:sha1:d3ee0d21a16b6e696297b8e1f0c4ad8abdecca37 2015-05-04T15:23:42+00:00 Stephan Schwaer 2015-05-04T15:23:42+00:00 urn:sha1:fa900b4658b21294682760bdf84071cbb2b79aa4