dnbd3.git/src/server, branch fuse_cow_2 Distributed Network Block Device 3 --rewrite for Kernel 3.x https://git.openslx.org/dnbd3.git/atom/src/server?h=fuse_cow_2 2021-06-16T09:41:16+00:00 [BUILD] Add check for stdatomic.h support 2021-06-16T09:41:16+00:00 Manuel Bentele 2021-06-16T09:33:31+00:00 urn:sha1:a04431a3125de160ca082b27ee31fa1e1037cea9 [SERVER] Add minRequestSize: Enlarge relayed requests 2021-05-11T07:43:37+00:00 Simon Rettberg 2021-05-11T07:43:37+00:00 urn:sha1:609ca9001343b90338d9e61d63ffc78b5b99a63c Any request from a client being relayed to an uplink server will have its size extended to this value. It will also be applied to background replication requests, if the BGR mode is FULL. As request coalescing is currently very primitive, this setting should usually be left diabled, and bgrWindowSize used instead, if appropriate. If you enable this, set it to something large (1M+), or it might have adverse effects. [SERVER] Fix UB 2021-05-11T07:43:08+00:00 Simon Rettberg 2021-05-11T07:43:08+00:00 urn:sha1:12cd8117e210f4da384540e4a1205e3172cf7ceb [SERVER] Honor uplinkTimeout directly when connecting to alt-server 2021-05-10T15:35:07+00:00 Simon Rettberg 2021-05-10T15:35:07+00:00 urn:sha1:3bcbfcdd700d333fb655ea9e91ad6a0f6b8f2159 [KERNEL] Improve debug output in net.c 2021-04-20T13:49:48+00:00 Simon Rettberg 2021-04-20T13:49:48+00:00 urn:sha1:27784cd0f009f1750e9ad213b1c0910b98ffdb44 [KERNEL] Removes duplicate word 'of' in license headers 2021-04-16T06:20:06+00:00 Manuel Bentele 2021-04-16T06:20:06+00:00 urn:sha1:f7cca217a3696980a72564f57bad4597ddbe9df5 [SERVER] Mark uplink requests with BGR/prefetch flags and handle them 2021-04-14T12:55:26+00:00 Simon Rettberg 2021-04-14T12:55:26+00:00 urn:sha1:8b303a6c68079a3db781b2a361707719406279e3 Incoming requests from clients might actually be prefetch jobs from another downstream proxy. Don't do prefetching for those, as this would cascade upwars in the proxy chain (prefetch for a prefetch of a prefetch) Incoming requests might also be background replication. Don't relay those if we're not configured for background replication as well. [SERVER] Make prefetching synchronous 2021-04-14T11:17:59+00:00 Simon Rettberg 2021-04-13T14:41:26+00:00 urn:sha1:0be00336f97a7ef3590ee803d4ad19e305aa1583 There is a race condition where we process the next request from the same client faster than the OS will schedule the async prefetch job, rendering it a NOOP in the best case (request ranges match) or fetching redundant data from the upstream server (prefetch range is larger than actual request by client). Make prefetching synchronous to prevent this race condition. [SERVER] Fix compiler warning 2021-03-22T13:28:11+00:00 Simon Rettberg 2021-03-22T13:28:11+00:00 urn:sha1:f559a3bed428fb2dce5a23e7c04aecf45c99a39e [BUILD] Build picohttpparser as independent library 2021-03-11T17:18:37+00:00 Manuel Bentele 2021-03-11T16:05:24+00:00 urn:sha1:f5a3dd5fa08f39c2331e0a4faf42ece96dc3d93b