Dear folks,<br><br>I've been tried to use replicated stripped volumes with 3.3. unsuccessfully due to <a href="https://bugzilla.redhat.com/show_bug.cgi?id=861423">https://bugzilla.redhat.com/show_bug.cgi?id=861423</a> and I then proceed to try 3.4.0qa5. I then find out that the bug was solved and I could use replicated stripped volume with the new version. Amazingly, write performance was quite astonishing.<br>
<br>The problem I'm facing now is in the read process: It's horribly slow. When I open a file to edit using the gluster native client, it takes a few seconds and sometimes I got an error refering to file has been modified while I was editing it. There's a ruby application reading the files and I got continuously timeout errors.<br>
<br>I'm using 4 bricks with Centos 6.3 with the following structure:<br>Type: Striped-Replicate<br>Volume ID: 23dbb8dd-5cb3-4c71-9702-7c16ee9a3b3b<br>Status: Started<br>Number of Bricks: 1 x 2 x 2 = 4<br>Transport-type: tcp<br>
Bricks:<br>Brick1: 10.0.51.31:/gfs<br>Brick2: 10.0.51.32:/gfs<br>Brick3: 10.0.51.33:/gfs<br>Brick4: 10.0.51.34:/gfs<br>Options Reconfigured:<br>performance.quick-read: on<br>performance.io-thread-count: 32<br>performance.cache-max-file-size: 128MB<br>
performance.cache-size: 256MB<br>performance.io-cache: on<br>cluster.stripe-block-size: 2MB<br>nfs.disable: on<br><br>I started profiling and found out one node with absurd latency figures. I stopped the node and the problem moved to another brick:<br>
%-latency Avg-latency Min-Latency Max-Latency No. of calls Fop<br> --------- ----------- ----------- ----------- ------------ ----<br> 99.94 551292.41 us 10.00 us 1996709.00 us 361 FINODELK<br>
<br>Could anyone provide some information how to debug this problem? Currently the volume is not usable due to the horrible delay.<br><br>Thank you very much in advance,<br>Samuel.<br>