The use of Mesos in production for cassandra was a failure due to the inability to reserve network bandwidth as Mesos can only allocate cpu and memory profiles to a task. So, assuming you are either running on dedicated/manually controlled VM's, or are no running a product/meaningful data storage footprint, your questions are relevant. Otherwise Mesos is not a viable solution. Note this same issue hit me at several clients with jenkens CI workloads as well. Look at K8S for these contra-Mesos scenarios.
<======> "When I finish a project for a client, I have ... learned their issues with life, their personal secrets, I have come to care about them. Once the project is over, I lose them as if I lost family. For the client, however, they’ve just dismissed a service worker." ... "Thought on the Gig Economy" by Francine Brevetti *Daemeon C.M. Reiydelle* *email: daeme...@gmail.com <daeme...@gmail.com>* *San Francisco 1.415.501.0198/London 44 020 8144 9872/Skype daemeon.c.m.reiydelle* On Mon, Jun 25, 2018 at 8:12 AM, Pierre Mavro <p.ma...@criteo.com> wrote: > Hi, > > Regarding the limits in linux cgroups (as used in Kubernetes/Mesos), I > was wondering if there are any recommendation (didn't find anything on > this topic). > > In general on Java 8 running instances, it is advised to run those > options to take into account cgroup environment: > > -XX:+UnlockExperimentalVMOptions -XX:+UseCGroupMemoryLimitForHeap > > Other tuning options for this exists (ex: MaxRAMFraction), I was > wondering if there is any information somewhere about it. > > Thanks in advance > > Pierre > > > --------------------------------------------------------------------- > To unsubscribe, e-mail: dev-unsubscr...@cassandra.apache.org > For additional commands, e-mail: dev-h...@cassandra.apache.org > >
