About Read Requests 21 Planning a Cassandra Cluster Deployment 22 Selecting Hardware 22 Memory 22 CPU 22 Disk 23 Network 23 Planning an Amazon EC2 Cluster 23 Capacity Planning 24 Calculating Usable This is frequently a problem for applications dealing with timestamped data. • More administrative overhead to load balance the cluster. An ordered partitioner requires administrators to manually calculate choosing appropriate hardware depends on selecting the right balance of the following resources: Memory, CPU, Disk, and Network. Memory The more memory a Cassandra node has, the better read performance will

Cloud Base 7.1.8 + • IMPALA-11457 Fix regression with unknown disk id • HDDS-4970 Significant overhead when DataNode is over-subscribed • HDDS-7135 ofs file input stream should support StreamCapabilities Cloud Base 7.1.8 + • IMPALA-11457 Fix regression with unknown disk id • HDDS-4970 Significant overhead when DataNode is over-subscribed • HDDS-7135 ofs file input stream should support StreamCapabilities Apache Ozone 1.3.0 + Apache Impala 4.1.1 Testbed 3 x master nodes, 16 x DataNodes CPU 2 x Intel(R) Xeon(R) Gold 6230 CPU @ 2.10GHz/20 cores memory 384GB ( 12 x 32GB DDR4 @ 2933MHz) OS Boot Cisco Boot

Accelerate Istio-CNI with ebpf Xu Yizhou & Guo Ruijing #IstioCon Agenda ● Istio-CNI ● tcp/ip stack overhead between sidecar and service ● Background knowledge of ebpf ● Acceleration for Inbound/Outbound/Envoy functionality provided by the istio-init container. #IstioCon Tcp/ip stack overhead between sidecar and service Overhead sidecar traffic from 3 scopes ● Inbound ● Outbound ● Envoy to Envoy(same

Current Istio functionality meets user needs ○ Measured feature introduction ● Reducing operational overhead ○ Maintenance ○ Upgrades ○ Debugging https://istio.io/latest/blog/2020/tradewinds-2020/ #IstioCon

pilot resolved this issue. • Tune CPU/MEM to ensure enough capacity Leveraged Metrics to monitor Istio & Knative components’ CPU and MEM under workload to avoid CPU throttling and OOM and ensure enough Istio 1.5.4: Istio scalability optimization during Knative Service provisioning Project Component CPU MEM HorizontalPodAutoscaler (HPA) request limit request limit Istio (1.7.3) istio- ingressgateway accelerate the whole debug and fix process: https://github.com/knative-sandbox/kperf ● Get Istio CPU/MEM stats: https://github.com/istio/istio/wiki/Analyzing-Istio- Performance ● Debugging Envoy and

support eBay scale ■ Proxy config convergence time (CDS, EDS, LDS, RDS push times) ■ Resource usage (CPU, memory, etc.) ○ Secondary Goal ■ Fine-tune configuration params - debounce interval, push concurrency Main Takeaways ○ P99.9 time from single Pilot instance to 0 - 3,000 sidecars < 1 second ○ Pilot CPU & memory within acceptable limits: < 10 cores, 25 GB memory ○ Pilot can scale horizontally ● Need

operation ○ Secure, channel based IO ● Application advantage ○ Low latency ○ High bandwidth ○ Low CPU consumption ● Istio: cross-node Proxy to Proxy kernel bypass w/ HW acceleration #IstioCon Quick

3. 4. Note: Make sure the extension you are importing matches your operating system and CPU architecture to ensure compatibility. When connecting to a remote SQLite database in DBeaver: Specify activity MySQL InnoDB data, InnoDB memory, Key Efficiency, Queries, Server sessions, Traffic Oracle CPU usage, Global Query Stats, IO Stats, Memory usage, Memory usage by components PostgreSQL Block IO

3. 4. Note: Make sure the extension you are importing matches your operating system and CPU architecture to ensure compatibility. When connecting to a remote SQLite database in DBeaver: Specify activity MySQL InnoDB data, InnoDB memory, Key Efficiency, Queries, Server sessions, Traffic Oracle CPU usage, Global Query Stats, IO Stats, Memory usage, Memory usage by components PostgreSQL Block IO

were developed, which use the graphics processor on the graphics card instead of consuming valuable CPU resources. Almost all modern graphics cards have a built-in acceleration to display 3D. Ubuntu can