<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><div class=""><br class=""></div><div class="">The default geode heartbeat timeout interval is 5 seconds, which is an eternity.</div><div class=""><br class=""></div><div class="">Some points/questions:</div><div class=""><br class=""></div><div class="">I’d recommend using either Solarflare’s sysjitter tool or Gil Tene’s jhiccup to quantify your OS jitter</div><div class="">Can you capture the output of vmstat 1 60 ?</div><div class="">What kind of EC2 instances are you using? Are they RHEL?</div><div class="">How much physical RAM does each instance have?</div><div class=""><div class="">Do you have THP enabled?</div><div class="">What is the value of vm.min_free_kbytes ?</div></div><div class=""><br class=""></div><div class=""><br class=""></div>How often do you see missed heartbeats?<div class="">What length of time do you see the Adjusting Workers message?</div><div class=""><br class=""></div><div class=""><br class=""></div><div class=""><br class=""></div><div class=""><br class=""></div><div class=""><br class=""></div><div class=""><br class=""><div><br class=""><blockquote type="cite" class=""><div class="">On Mar 13, 2023, at 4:42 AM, Evaristo José Camarero <<a href="mailto:evaristojosec@yahoo.es" class="">evaristojosec@yahoo.es</a>> wrote:</div><br class="Apple-interchange-newline"><div class=""><div class=""><div class="yahoo-style-wrap" style="font-family:Helvetica Neue, Helvetica, Arial, sans-serif;font-size:13px;"><div dir="ltr" data-setdir="false" class="">Hi there,</div><div dir="ltr" data-setdir="false" class=""><br class=""></div><div dir="ltr" data-setdir="false" class="">We are trying latest ZGC EAB for testing an Apache Geode Cluster (distributed Key Value store with similar use cases that Apache Cassandra)</div><div dir="ltr" data-setdir="false" class=""><br class=""></div><div dir="ltr" data-setdir="false" class="">We are using K8s, and we have PODs with 32 cores request (limit with 60 cores) per data node with 150GB heap per node.</div><div dir="ltr" data-setdir="false" class=""><br class=""></div><div dir="ltr" data-setdir="false" class=""><div class=""><div class=""> - -Xmx152000m</div><div class=""> - -Xms152000m</div><div class=""> - -XX:+UseZGC</div><div class=""> - -XX:SoftMaxHeapSize=136000m</div><div class=""><span style="white-space: pre-wrap;" class=""> </span> - -XX:ZAllocationSpikeTolerance=4.0 // We have some spiky workloads periodically </div><div class=""> - -XX:+UseNUMA<br class=""></div></div><br class=""></div><div dir="ltr" data-setdir="false" class=""><br class=""></div><div dir="ltr" data-setdir="false" class="">ZGC is working great in regard GC pauses with no allocation stalls at all during almost all the time. We observe higher CPU utilization that G1 (Around 20% for a heavy workload using flag <span class="">-XX:ZAllocationSpikeTolerance=4.0 that maybe is making ZGC more hungry than needed. We will play further with this</span>)</div><div dir="ltr" data-setdir="false" class=""><br class=""></div><div dir="ltr" data-setdir="false" class=""><br class=""></div><div dir="ltr" data-setdir="false" class="">BUT from time to time we see that Geode Clusters are missing heartbeats between and Geode logic shutdowns the JVM of the node with missing heartbeats. We believe that the main problem could be CPU starvation, because some seconds before this is happening we observe ZGC to use more workers for making the job done<br class=""><br class=""><div class=""><span class="ydp64d0df88ui-provider ydp64d0df88h ydp64d0df88r ydp64d0df88k ydp64d0df88u ydp64d0df88ag ydp64d0df88d ydp64d0df88ab ydp64d0df88n ydp64d0df88x ydp64d0df88g ydp64d0df88q ydp64d0df88aj ydp64d0df88ae ydp64d0df88j ydp64d0df88t ydp64d0df88c ydp64d0df88m ydp64d0df88ah ydp64d0df88w ydp64d0df88ac ydp64d0df88f ydp64d0df88p ydp64d0df88z ydp64d0df88i ydp64d0df88ak ydp64d0df88s ydp64d0df88ve ydp64d0df88b ydp64d0df88af ydp64d0df88l ydp64d0df88v ydp64d0df88e ydp64d0df88o ydp64d0df88ai ydp64d0df88y" dir="ltr">[2023-03-12T18:29:38.980+0000] Adjusting Workers for Young Generation: 1 -> 2<br class="">
[2023-03-12T18:29:39.781+0000] Adjusting Workers for Young Generation: 1 -> 3<br class="">
[2023-03-12T18:29:40.181+0000] Adjusting Workers for Young Generation: 1 -> 4<br class="">
[2023-03-12T18:29:40.382+0000] Adjusting Workers for Young Generation: 1 -> 5<br class="">
[2023-03-12T18:29:40.582+0000] Adjusting Workers for Young Generation: 1 -> 6<br class="">
[2023-03-12T18:29:40.782+0000] Adjusting Workers for Young Generation: 1 -> 7<br class="">
[2023-03-12T18:29:40.882+0000] Adjusting Workers for Young Generation: 1 -> 8<br class="">
[2023-03-12T18:29:40.982+0000] Adjusting Workers for Young Generation: 1 -> 10<br class="">
[2023-03-12T18:29:41.083+0000] Adjusting Workers for Young Generation: 1 -> 13<br class="">
[2023-03-12T18:29:41.183+0000] Adjusting Workers for Young Generation: 1 -> 16</span></div><br class=""></div><div dir="ltr" data-setdir="false" class=""><br class=""></div><div dir="ltr" data-setdir="false" class="">As commented we are using K8S with PODs that have 32 cores for request and 60 cores for limit (and it also true that our K8s workers are close to the limit in CPU utilization). ZGC is assuming on booting that machine has 60 cores (as logged). What is the best way to configure the ZGC to provide a hint to be tuned for a host with 32 cores (basically the 60 cores limit is just to avoid K8s produced throttling)? Is it using ParallelGCThreads flag? Any other thoughts?</div><div dir="ltr" data-setdir="false" class=""><br class=""></div><div dir="ltr" data-setdir="false" class="">Regards,</div><div dir="ltr" data-setdir="false" class=""><br class=""></div><div dir="ltr" data-setdir="false" class="">Evaristo</div><div dir="ltr" data-setdir="false" class=""><br class=""></div></div></div></div></blockquote></div><br class=""></div></body></html>