You could start out by finding more about where the memory is going. Try running:
echo ::kmastat | mdb -k a few times as the kernel memory grows and compare them to see what kind of kernel memory is being used. You take a memory dump You can use the information at https://docs.oracle.com/cd/E19455-01/806-5194/6je7ktflt/index.html to steer you further. On 12/18/2018 2:07 AM, skeletor wrote: > Hello. > > I have an application statsd (https://github.com/etsy/statsd) written > on nodejs. It receive around 800krps metrics (udp trafic) and works > fine on Solaris 11.3. After upgrade OS to 11.4 (nodejs version remains > the same, like on 11.3) kernel memory ("Regular Kernel" from output > 'echo ::memstat | mdb -k') grows very quickly (30Gb per minute) until > the whole memory is over and server hangs. Size/Res memory of the > application statsd not grows. > > I tried to restrict size of user_reserve_hint_pct, but nothing was > changes. > > Is there any way to determine why kernel memory grows and how to fix it? > -- All working systems eventually start to exhibit their own agenda. Oracle <http://www.oracle.com> Brian Utterback | Principal Software Engineer Phone: +16038973049 <tel:+16038973049> https://oracle.zoom.us/s/2728168892 https://myoracle.webex.com/join/brian.utterback Oracle Systems/Solaris Networking 1 Oracle Dr. | Nashua, NH 03062 ------------------------------------------------------------------------ I have not lost my mind. It's backed up in the cloud somewhere. ------------------------------------------------------------------------ Green Oracle <http://www.oracle.com/commitment> Oracle is committed to developing practices and products that help protect the environment ------------------------------------------- dtrace-discuss Archives: https://www.listbox.com/member/archive/184261/=now Modify Your Subscription: https://www.listbox.com/member/?member_id=25769126 Powered by Listbox: https://www.listbox.com
