(Illustration by Gaich Muramatsu)
Hello, I am using a simple coda-setup and I am trying to store some larger files (ISO-Images) >500M < 2G on a volume. The client and server are are different machines and the server is non-replicated. IMHO strange things happen: If I copy a file on the client into coda, the client first writes to the local cache and then starts transmitting the file contents, when the local op has finished. OK, normal. The transmission is quite slow: It does by far not use the available bandwidth (100Mbit net, coda write traffic uses up to ~7 Mbit). 1) First odacon reports something about a store operation. If this finishes successfully, everything is fine. If something (like a disconnect) disturbs this "store", the file will apparently never reach the server (see below). During this longer store operation (about 15min) the server responds normally to Probe calls and seems to be alive to the clients. 2) After some disconnect within the store the client will eventually reconnect to the server and start a reintegration (reported in codacon). Then a 'backfetch' is reported. The speed is the same as above. When this operation starts, the server becomes *unreachable* to 'Probe' attempts from any client! If this happens the client will disconnect from the server, although it still transmits (slowly) the file contents. The server will after a while also drop the connection to the client. The transmitted data is then never reintegrated into the volume on the server, but after sending the whole file, the server will be reachable again, and restart the reintegration, when the respective volume is hit on the client. Again and again ... Questions: a) I guess this is not wanted? Why is backfetch blocking the other calls and store is different? b) Is there a way to improve the performance. What is the bottleneck? Are there tuning parameters? Or is it just due to RVM? All things happened to Coda 6.0.14 running on kernel 2.6.9 with 100 Mbit Network and 0.8-3.0 GHz Processors. server RVM has 40MByte Size and can fit fully into RAM (although only 10M RSS are used now). Any hints are very welcome Martin -- +-[Martin Ginkel]-------------[mailto:mginkel(at)mpi-magdeburg.mpg.de]-+ | MPI Magdeburg, Zi S2.09 Sandtorstr. 1, D-39106 Magdeburg, Germany | | There ain't no devil, ther'e just God when he's drunk. Tom W. | | | +-[tel/fax: +49 391 6110 482/529]----[http://www.mpi-magdeburg.mpg.de]-+Received on 2006-02-27 07:45:35