Hi Alexis, Yes compaction happens on data files -1. What my disk latency is high for SSDs which been only used for commit log2. Why my compaction is not catching up with my write traffic in spite of low CPU, low memory and low JVM usage.I am adding more details to this thread.Thanks,Jayant K KenjaleOn Wed, Apr 17, 2013 at 6:58 PM, Alexis Rodríguez <firstname.lastname@example.org> wrote:Jay,I believe that compaction occurs on the data directories and not in the commitlog.On Wed, Apr 17, 2013 at 7:58 PM, Jay Svc <email@example.com> wrote:Hi Alexis,Thank you for your response.My commit log is on SSD. which shows me 30 to 40 ms of disk latency.When I ran iostat; I see "await" 26ms to 30 ms for my commit log disk. My CPU is less than 18% used.How I reduce the disk latency for my commit log disk. They are SSDs.Thank you in advance,JayOn Wed, Apr 17, 2013 at 3:58 PM, Alexis Rodríguez <firstname.lastname@example.org> wrote:
:DJay, check if your disk(s) utilization allows you to change the configuration the way Edward suggest. iostat -xkcd 1 will show you how much of your disk(s) are in use.On Wed, Apr 17, 2013 at 5:26 PM, Edward Capriolo <email@example.com> wrote:
three things:1) compaction throughput is fairly low (yaml nodetool)2) concurrent compactions is fairly low (yaml)3) multithreaded compaction might be off in your versionTry raising these things. Otherwise consider option 4.4)$$$$$$$$$$$$$$$$$$$$$$$ RAID,RAM<CPU$$$$$$$$$$$$$$On Wed, Apr 17, 2013 at 4:01 PM, Jay Svc <firstname.lastname@example.org> wrote:
I have a high write traffic to my Cassandra cluster. I experience a very high number of pending compactions. As I expect higher writes, The pending compactions keep increasing. Even when I stop my writes it takes several hours to finishing pending compactions.
My CF is configured with LCS, with sstable_size_mb=20M. My CPU is below 20%, JVM memory usage is between 45%-55%. I am using Cassandra 1.1.9.
How can I increase the compaction rate so it will run bit faster to match my write speed?
Your inputs are appreciated.