Jamie Briant created MESOS-6118:
-----------------------------------

             Summary: Agent crashes under load
                 Key: MESOS-6118
                 URL: https://issues.apache.org/jira/browse/MESOS-6118
             Project: Mesos
          Issue Type: Bug
          Components: slave
    Affects Versions: 1.0.1
         Environment: Sep 01 20:49:10 ip-10-254-192-99 mesos-slave[1227]: I0901 
20:49:10.522084  1204 main.cpp:243] Build: 2016-08-26 23:06:27 by centos
Sep 01 20:49:10 ip-10-254-192-99 mesos-slave[1227]: I0901 20:49:10.522236  1204 
main.cpp:244] Version: 1.0.1
Sep 01 20:49:10 ip-10-254-192-99 mesos-slave[1227]: I0901 20:49:10.522251  1204 
main.cpp:247] Git tag: 1.0.1
Sep 01 20:49:10 ip-10-254-192-99 mesos-slave[1227]: I0901 20:49:10.522258  1204 
main.cpp:251] Git SHA: 3611eb0b7eea8d144e9b2e840e0ba16f2f659ee3
Sep 01 20:49:10 ip-10-254-192-99 mesos-slave[1227]: I0901 20:49:10.526270  1204 
logging.cpp:194] INFO level logging started!
Sep 01 20:49:10 ip-10-254-192-99 mesos-slave[1227]: I0901 20:49:10.532732  1204 
systemd.cpp:237] systemd version `219` detected
Sep 01 20:49:10 ip-10-254-192-99 mesos-slave[1227]: I0901 20:49:10.532768  1204 
main.cpp:342] Inializing systemd state
Sep 01 20:49:10 ip-10-254-192-99 mesos-slave[1227]: I0901 20:49:10.533128  1204 
systemd.cpp:304] Created systemd slice: 
`/run/systemd/system/mesos_executors.slice`
Sep 01 20:49:10 ip-10-254-192-99 mesos-slave[1227]: I0901 20:49:10.583580  1204 
systemd.cpp:325] Started systemd slice `mesos_executors.slice`
Sep 01 20:49:10 ip-10-254-192-99 mesos-slave[1227]: I0901 20:49:10.877017  1204 
containerizer.cpp:196] Using isolation: 
posix/cpu,posix/mem,filesystem/posix,network/cni
Sep 01 20:49:10 ip-10-254-192-99 mesos-slave[1227]: I0901 20:49:10.883193  1204 
linux_launcher.cpp:101] Using /sys/fs/cgroup/freezer as the freezer hierarchy 
for the Linux launcher
            Reporter: Jamie Briant


I have a framework which schedules thousands of short running (a few seconds to 
a few minutes) of tasks, over a period of several minutes. In 1.0.1, the slave 
process will crash every few minutes (with systemd restarting it).



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Reply via email to