summaryrefslogtreecommitdiffstats
path: root/src
Commit message (Collapse)AuthorAgeFilesLines
* [FUSE] Wait a little longer before switching via new approachSimon Rettberg2016-03-231-8/+8
|
* [FUSE] Add new load balancing mechanismSimon Rettberg2016-03-231-12/+49
| | | | | | | | | | | | | | | | | | | | | | | | | The new mechanism is supposed to complement the existing RTT based balancing. While the RTT-averaging approach is better suited to react to sudden drastic changes in server latency. The new approach doesn't directly consider RTT, but keeps track of how many consecutive times each server was the best server when measuring the RTTs. The higher that counter rises, the more likely it will become that the connection switches over to that server. Eg.: Server 1 measures 600µs each time Server 2 measures 599µs each time After a while, in case server 1 is currently used, the connection will eventually switch over to server 2. The RTT-based mechanism would not switch over in this case, since the threshold that prevents constant switching between servers is not reached. The new approach is meant to handle scenarios where the network is generally fast, but it would still be beneficial from a network topology point of view if the clients switch to the slightly faster server, assuming it is closer to the client and thus less network segments are burdened.
* [SERVER] Fix formattingSimon Rettberg2016-03-229-57/+58
|
* [SERVER] (FreeBSD) Unlock send mutex on sendfile errorSimon Rettberg2016-03-221-0/+1
|
* compile dnbd3-fuse on FreeBSD without warning :)Sebastian2016-02-112-2/+4
|
* remove kernel build breaking includeSebastian2016-02-111-1/+0Star
|
* running FreeBSD sendfileSebastian2016-02-111-13/+36
|
* dnbd3server build success on freebsd :)Sebastian2016-02-119-30/+77
|
* cleanup commitsSebastian2016-02-1125-145/+47Star
|
* [SHARED] signal.h -> fdsignal.hSimon Rettberg2016-02-1014-15/+15
|
* dfskljgdslkfsdklgjSimon Rettberg2016-02-051-3/+3
|
* [SHARED] Fix linux detection on clangSimon Rettberg2016-02-051-4/+4
|
* [SHARED] Implement pipe() based signallingSimon Rettberg2016-02-054-71/+261
|
* First steps in make signals more abstract from the underlying mechanism; ↵Simon Rettberg2016-02-0510-129/+136
| | | | | | | | | | replace epoll with poll. We now don't assume that a signal equals a single fd (eventfd on Linux). The next step would be to create a version of signal.c that uses a pipe internally, so it can be used on other platforms, like *BSD. This is also the reason epoll was replaced with poll in uplink.c
* [SERVER] BREAKING: Get rid of pseudo case-insensitivityv2.1Simon Rettberg2016-02-019-54/+41Star
| | | | | | | | | | This was a wrong decision made long time ago, and it's broken in certain scenarios (eg. two servers serving from same NFS mount). Also it's of limited use anyways since it only supportes ASCII and would ignore umlauts, so blöd and BLÖD would still be considered two different images. So if you relied on this "feature" in any way, be careful when updating.
* [SERVER] Fix a lot of (mostly harmless) data racesSimon Rettberg2016-01-1113-94/+163
|
* [KERNEL/CLIENT] Several minor tweaks and changesSimon Rettberg2016-01-116-17/+20
| | | | | | | | | | - Disable panic timeout that reports errors to block layer by default - Get rid of "is_server" used by old proxy mode, introduce "honor_server_alts" that just controls whether we use alts provided by the server - Allow switching servers when we only have 3 RTT measurements - If using alts provided by server, don't ignore those that come from other servers than the initial one
* [FUSE] Handle SIGINT/SIGTERM to abort pending readsSimon Rettberg2015-12-172-1/+35
| | | | | | | | | Before, we would wait endlessly if there is a pending read request that doesn't get answered (e.g. because the server went down. That means you couldn't exit the client in that case. Now we use a signal handler to set a flag which causes the read to bail out and return EIO.
* [SERVER] Performance: Optimized some functions (gprof)Simon Rettberg2015-12-174-25/+45
| | | | | | | A run with gprof revealed that background replication is a huge CPU hog. The block selection was very slow and has been improved a lot. Minor improvements were made to other functions that scan the cache map of an image and are thus relatively slow.
* [SERVER] image_markComplete now handles locking so we remove() unlockedSimon Rettberg2015-12-172-15/+18
|
* [SERVER] Cancel scanning of image dir if _shutdown is setSimon Rettberg2015-12-162-4/+8
| | | | So you can cancel image loading on startup via Ctrl-C
* [SERVER] Fix image_calcBlockCrc32: Use 64bit for fileSize paramSimon Rettberg2015-12-161-22/+27
| | | | Using uint32_t for fileSize is not too clever :(
* [SERVER] More fine grained locking for RPC; better error loggingSimon Rettberg2015-12-167-68/+143
|
* [FUSE] Fix forking mode (not passing -f) by not spawning threads before ↵Simon Rettberg2015-12-163-30/+53
| | | | entering fuse_main
* [SERVER] Update config exampleSimon Rettberg2015-12-151-2/+6
|
* [SERVER] Remove non-working images from list, plus refactoringSimon Rettberg2015-12-158-134/+318
| | | | | | | | | | Now that we can automatically load unknown images from disk on request, it makes sense to remove non-working images from the image list. On future requests, we will look for them on disk again, which is nice in case of temporary storage hickups. Also, some more ore less related locking has been refined (loading images, replicating images)
* [SERVER] Make listen port configurableSimon Rettberg2015-12-143-3/+18
|
* [SERVER] Free memory on exit to get new valgrind high scoreSimon Rettberg2015-12-141-1/+4
|
* [SERVER] Disallow images starting with "." now that we allow load-on-demandSimon Rettberg2015-12-141-1/+2
| | | | | This will prevent hidden files from being exported to clients and also prevents directory traversal attacks ( ../../image.img )
* [SERVER] Support looking on disk if an unknown image is requestedSimon Rettberg2015-12-125-28/+116
|
* [SERVER] Nullpad images virtually at runtime instead of padding the actual fileSimon Rettberg2015-12-106-173/+158Star
|
* [FUSE] Make valgrind happy by initializing memory and not calling close() on -1Simon Rettberg2015-12-101-2/+4
|
* [FUSE] Fix stack overflow caused by stats dataSimon Rettberg2015-12-101-3/+5
|
* [SERVER] Remove redundant range checkSimon Rettberg2015-12-091-8/+0Star
|
* [SERVER] Use error code constants instead of magic valuesSimon Rettberg2015-12-071-4/+4
|
* [SERVER] Add missing nullptr check from refactoring, improve lockingSimon Rettberg2015-12-071-9/+11
|
* [FUSE] Fix formatting in /status outputSimon Rettberg2015-12-071-6/+4Star
|
* [FUSE] Fix embarrassing memcpy over two different structsSimon Rettberg2015-12-031-3/+6
|
* [FUSE] Add --log optionSimon Rettberg2015-12-031-12/+29
|
* [FUSE] Try to get caching rightSimon Rettberg2015-12-031-2/+3
|
* [SERVER] Update includes for moved log.hSimon Rettberg2015-12-0210-11/+11
|
* [FUSE] Add virtual status fileSimon Rettberg2015-12-025-16/+140
|
* [FUSE] Request alt servers from connected serverSimon Rettberg2015-12-022-26/+100
|
* [FUSE] Clean up command line handlingSimon Rettberg2015-12-021-37/+93
|
* [FUSE] Remove debug code that forced server switches all the timeSimon Rettberg2015-12-011-2/+1Star
|
* [FUSE] Fix losing requests on server changeSimon Rettberg2015-12-012-16/+26
|
* [FUSE] Stability improvements, runs for longer than a couple secs now :)Simon Rettberg2015-12-014-55/+75
|
* [FUSE] It works! Kinda...Simon Rettberg2015-11-307-206/+226
|
* [FUSE] Compiles againSimon Rettberg2015-11-306-59/+4Star
|
* [FUSE] Mid-refactoring, does not compileSimon Rettberg2015-11-2415-86/+360
|
generated by cgit v1.2.3-55-g7522 (git 2.39.0) at 2024-06-03 13:43:11 +0200