That looks like it. I've pushed the limits up to 65k and turned down the testing for now. Otherwise machines were dropping like flies.
On 26 Aug, 2010,at 04:16 PM, Dan Washusen <firstname.lastname@example.org> wrote:
On Thu, Aug 26, 2010 at 2:05 PM, Aaron Morton <email@example.com>
Under 0.7.0 beta1 am seeing cassandra run out of files handles...
at java.ioRandomAccessFile.open(Native Method)
If I look at the file descriptors for the process I can see it already has 1,958 for to the file
sudo ls -l /proc/20862/fd | grep "ObjectIndex-e-31-Data.db" | wc -l
Out of a total of 2044.
Other nodes in the cluster have a similar number of fd's - around 2k with the majority to one SSTable.
I did not experience this under 0.6 so just checking if this sounds OK and I should just increase the number of handles or if it's a bug?