Ouroboros main repository http://133.ip-51-38-114.eu/cgit/ouroboros/atom?h=0.3 2016-10-26T18:09:21+00:00 2016-10-26T18:09:21+00:00 dimitri staessens dimitri.staessens@intec.ugent.be 2016-10-26T17:30:52+00:00 urn:sha1:963537079c7d5a9f9fb39355fb0e3b84a78eaa0b The steps for flow deallocation have been further refined. An operation ipcp_flow_fini() which wait for all SDUs to be read from a flow has been added. The shim IPCPs and the local IPCP have been adapted to this new API. Deallocation messages have been removed from the shim IPCPs, since there is insufficient state synchronisation between them to make this work reliably. 2016-10-26T13:30:13+00:00 dimitri staessens dimitri.staessens@intec.ugent.be 2016-10-26T13:30:13+00:00 urn:sha1:f60e18adc78afaf4d07a10e6fe8aec3767e0ca11 ipcpd: Add threadpool for main loop 2016-10-26T13:10:28+00:00 Sander Vrijders sander.vrijders@intec.ugent.be 2016-10-26T12:59:43+00:00 urn:sha1:188aba280f7c5b80b868cb1527fce9d45702a196 This adds a threadpool for the main loop of the IPCPs. Before there was a single thread handling each request, which could result in starvation since performing name queries at the same time as enrolling a normal IPCP was impossible. 2016-10-25T10:57:15+00:00 dimitri staessens dimitri.staessens@intec.ugent.be 2016-10-25T10:57:15+00:00 urn:sha1:cce79395b5a9f75d3fe1b14bf5df44795d680ca4 2016-10-23T21:00:15+00:00 dimitri staessens dimitri.staessens@intec.ugent.be 2016-10-23T21:00:15+00:00 urn:sha1:b23e3024d12c28b01426cc37d5adf03f9c1bea88 Deallocation was reverted to a synchronoous operation between the AP, IRMd and IPCP in order to avoid inconsistent states of the port_id. Fixes some memory leaks, particularly the shm_flow_set is now closed upon deallocation. 2016-10-22T11:27:02+00:00 dimitri staessens dimitri.staessens@intec.ugent.be 2016-10-21T18:13:41+00:00 urn:sha1:3cafbf3cfe5c58a6988dbfc4c29148ebb804f5c2 This has the code checked with -Wcast-qual and -Wconversion flags. These flags were removed because SWIG generated code fails. 2016-10-21T12:17:51+00:00 dimitri staessens dimitri.staessens@intec.ugent.be 2016-10-20T17:52:02+00:00 urn:sha1:02976060919566d1a217b818ca8f33297700d56d This stabilises flow allocation now that the rbuffs are created upon flow allocation. Only the IRMd can sync this process sufficiently. 2016-10-21T12:17:51+00:00 dimitri staessens dimitri.staessens@intec.ugent.be 2016-10-19T20:25:46+00:00 urn:sha1:f516b51169020ea1957010fbd1005d746f01b1d9 The fast path will now use an incoming ring buffer per flow per process. This necessitated the development of a new method for the asynchronous io call, which is now based on an event queue system for scalability (fqueue). The ipcpd's and tools have been updated to this API. 2016-10-15T17:42:52+00:00 dimitri staessens dimitri.staessens@intec.ugent.be 2016-10-15T17:30:27+00:00 urn:sha1:b8b05e3b1980146ab8acb40cbe77e0271634c688 2016-10-11T11:45:02+00:00 dimitri staessens dimitri.staessens@intec.ugent.be 2016-10-11T11:39:43+00:00 urn:sha1:c69dd846c5aa2bed4db16961c5774a20cea7f828 This will allow to finalize deallocating flows until all SDUs have been processed. Read and write calls will now block when a flow was deallocated. Replaces NULL checks in the fast path with asserts.