# cgroups

cgroups are a Linux kernel feature for organizing processes into hierarchical groups and limiting or monitoring their resource usage.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Utilization shows how busy a node is. PSI shows which workloads are waiting.

DevFeed: [Utilization shows how busy a node is. PSI shows which workloads are waiting.](<https://devfeed.tech/articles/utilization-shows-how-busy-a-node-is-psi-shows-which-workloads-are-waiting-141940.md>)

Original publisher: [Read original article](<https://www.groundcover.com/blog/utilization-shows-how-busy-a-node-is-psi-shows-which-workloads-are-waiting>)

Author: Anais Dotis

Published: 2026-11-18T10:03:00Z

Content type: article

Language: en

Sources: [Ground Cover](<https://devfeed.tech/sources/ground-cover.md>)

Topics: [cgroups](<https://devfeed.tech/topics/cgroups.md>), [scheduling](<https://devfeed.tech/topics/scheduling.md>), [cloud service outage management](<https://devfeed.tech/topics/cloud-service-outage-management.md>)

Tags: [aws-fargate](<https://devfeed.tech/tags/aws-fargate.md>), [byoc](<https://devfeed.tech/tags/byoc.md>), [cgroup-v2](<https://devfeed.tech/tags/cgroup-v2.md>), [checkout](<https://devfeed.tech/tags/checkout.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [delay](<https://devfeed.tech/tags/delay.md>), [ebpf](<https://devfeed.tech/tags/ebpf.md>), [i-o](<https://devfeed.tech/tags/i-o.md>), [kubelet](<https://devfeed.tech/tags/kubelet.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [kubernetes-1-36](<https://devfeed.tech/tags/kubernetes-1-36.md>), [latency](<https://devfeed.tech/tags/latency.md>), [memory](<https://devfeed.tech/tags/memory.md>), [node](<https://devfeed.tech/tags/node.md>), [waiting](<https://devfeed.tech/tags/waiting.md>)

### AI overview

PSI measures time workloads stall while waiting for CPU, memory, or I/O, revealing contention that utilization averages can miss. It reports "some" (at least one task stalled) and "full" (all non-idle tasks stalled) over 10-, 60-, and 300-second windows and as cumulative stall time. Kubernetes 1.36 exposes PSI at node, Pod, and container levels through the Summary API and `/metrics/cadvisor`; it requires Linux kernel 4.20+, cgroup v2, and kernel PSI enabled, and is unavailable on Windows. Kubernetes exposes the signal for monitoring but does not use it for scheduling, autoscaling, or eviction decisions. PSI can identify a stalled workload but not the cause, so interpreting it requires time-aligned usage data from neighboring workloads. The text says groundcover does not yet collect PSI or use it in Autonomous Infrastructure; both are described as roadmap work.

### Source excerpt

CPU or memory usage data does not show whether any workload is delayed because it cannot get CPU, memory or I/O when it needs it, and that delay is what users experience as latency and failed requests. Pressure Stall Information (PSI) measures the delay directly, and as of Kubernetes 1.36 the kubelet exposes it as a stable feature.

## Your CPU limits aren't stopping noisy neighbors

DevFeed: [Your CPU limits aren't stopping noisy neighbors](<https://devfeed.tech/articles/your-cpu-limits-aren-t-stopping-noisy-neighbors-141936.md>)

Original publisher: [Read original article](<https://www.groundcover.com/blog/cpu-limits-arent-stopping-noisy-neighbors>)

Author: Anais Dotis

Published: 2026-11-18T10:00:00Z

Content type: article

Language: en

Sources: [Ground Cover](<https://devfeed.tech/sources/ground-cover.md>)

Topics: [cgroups](<https://devfeed.tech/topics/cgroups.md>), [scheduling](<https://devfeed.tech/topics/scheduling.md>), [autoscaling](<https://devfeed.tech/topics/autoscaling.md>), [Performance Testing](<https://devfeed.tech/topics/performance-testing.md>)

Tags: [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-infrastructure](<https://devfeed.tech/tags/autonomous-infrastructure.md>), [bin-packing](<https://devfeed.tech/tags/bin-packing.md>), [byoc](<https://devfeed.tech/tags/byoc.md>), [cfs](<https://devfeed.tech/tags/cfs.md>), [cgroup](<https://devfeed.tech/tags/cgroup.md>), [cgroups](<https://devfeed.tech/tags/cgroups.md>), [clusters](<https://devfeed.tech/tags/clusters.md>), [combined](<https://devfeed.tech/tags/combined.md>), [congestion-control](<https://devfeed.tech/tags/congestion-control.md>), [container](<https://devfeed.tech/tags/container.md>), [containers](<https://devfeed.tech/tags/containers.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cpu-time](<https://devfeed.tech/tags/cpu-time.md>), [groundcover](<https://devfeed.tech/tags/groundcover.md>), [latency](<https://devfeed.tech/tags/latency.md>), [limits](<https://devfeed.tech/tags/limits.md>), [memory](<https://devfeed.tech/tags/memory.md>), [nodes](<https://devfeed.tech/tags/nodes.md>), [oom](<https://devfeed.tech/tags/oom.md>)

### AI overview

Node-level contention explains why accurate per-workload sizing can still leave a cluster unstable: scheduling uses requests, while independently chosen P95 requests do not account for workloads peaking together. Under CPU contention, requests set proportional CPU weight; CPU limits impose quotas that can throttle a container even when other cores are idle. Memory has no proportional sharing: exceeding a limit can trigger an immediate OOM kill, while node pressure can lead to evictions or OOM kills. The post presents groundcover Autonomous Infrastructure as addressing this by using node-level CPU and memory history to identify overlapping peaks, adjust requests within operator-defined bounds, and apply changes to running Pods. It also says this requires high-resolution, per-container history linked to node and workload, and describes groundcover's eBPF sensor and BYOC storage as its collection approach.

### Source excerpt

This post explains what a noisy neighbor is, why CPU requests (not CPU limits) determine how CPU time is divided under contention, and why memory contention ends in OOM kills and evictions instead of added latency. It then explains why sizing each workload at a percentile of its own usage still overloads nodes, and how groundcover's Autonomous Infrastructure addresses that.

## Modal becomes a gVisor maintainer

DevFeed: [Modal becomes a gVisor maintainer](<https://devfeed.tech/articles/modal-becomes-a-gvisor-maintainer-129819.md>)

Original publisher: [Read original article](<https://modal.com/blog/modal-gvisor-maintainer>)

Author: Luis Capelo

Published: 2026-11-11T12:00:00Z

Content type: article

Language: en

Sources: [Modal](<https://devfeed.tech/sources/modal.md>)

Topics: [virtualization](<https://devfeed.tech/topics/virtualization.md>), [gpudirect rdma](<https://devfeed.tech/topics/gpudirect-rdma.md>), [rdma](<https://devfeed.tech/topics/rdma.md>), [cgroups](<https://devfeed.tech/topics/cgroups.md>), [GPU rendering](<https://devfeed.tech/topics/gpu-rendering.md>), [Cloud Gaming](<https://devfeed.tech/topics/cloud-gaming.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [amazon-s3](<https://devfeed.tech/tags/amazon-s3.md>), [aws](<https://devfeed.tech/tags/aws.md>), [bare-metal](<https://devfeed.tech/tags/bare-metal.md>), [blackwell](<https://devfeed.tech/tags/blackwell.md>), [blackwell-gpu](<https://devfeed.tech/tags/blackwell-gpu.md>), [clickhouse](<https://devfeed.tech/tags/clickhouse.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-gaming](<https://devfeed.tech/tags/cloud-gaming.md>), [cloud-native-computing-foundation](<https://devfeed.tech/tags/cloud-native-computing-foundation.md>), [clusters](<https://devfeed.tech/tags/clusters.md>), [containers](<https://devfeed.tech/tags/containers.md>), [gvisor](<https://devfeed.tech/tags/gvisor.md>), [modal](<https://devfeed.tech/tags/modal.md>)

### AI overview

Modal is joining gVisor's maintainers as the project moves to CNCF governance, building on its use of gVisor for more than 40 million containers a day. gVisor places a Go-based application kernel (the Sentry) between container workloads and the host kernel, then layers Linux isolation controls around it; unlike hardware virtualization, it can run on Linux machines without nested virtualization. Modal cites multi-tenant isolation, GPU access through nvproxy, roughly 25 ms startup with 12 MB memory overhead, checkpoint and restore, and portability across clouds and bare-metal systems as reasons for choosing it. Its upstream work includes GPU driver and workload support, an RDMA proxy for multi-node training, snapshots, and filesystem and shared-memory performance improvements. The article reports about 99% of native bus bandwidth in NCCL all-reduce benchmarks for RDMA and describes multi-GPU snapshots and GPUDirect Storage as ongoing work. Modal's vision is broader accelerator support, portable state, and faster I/O under neutral, multi-vendor governance.

### Source excerpt

Modal runs upwards of 40 million gVisor containers every day. Here's why we bet on it, what we've built into it, and where we want to take it next.

## MTRDMA: Lightweight User-Space Control-Plane Isolation for Multi-Tenant RDMA

DevFeed: [MTRDMA: Lightweight User-Space Control-Plane Isolation for Multi-Tenant RDMA](<https://devfeed.tech/articles/mtrdma-lightweight-user-space-control-plane-isolation-for-multi-tenant-rdma-126800.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.11991>)

Author: Hongyu Wang, Peihao Huang, Bangbo Liang, Lei Wang, Guo Chen

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [control-plane](<https://devfeed.tech/topics/control-plane.md>), [rdma](<https://devfeed.tech/topics/rdma.md>), [cgroups](<https://devfeed.tech/topics/cgroups.md>), [Process](<https://devfeed.tech/topics/process.md>), [thread safe data sharing](<https://devfeed.tech/topics/thread-safe-data-sharing.md>)

Tags: [atomic](<https://devfeed.tech/tags/atomic.md>), [cache](<https://devfeed.tech/tags/cache.md>), [cgroup](<https://devfeed.tech/tags/cgroup.md>), [collector](<https://devfeed.tech/tags/collector.md>), [concurrent](<https://devfeed.tech/tags/concurrent.md>), [containers](<https://devfeed.tech/tags/containers.md>), [control-plane](<https://devfeed.tech/tags/control-plane.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [isolation](<https://devfeed.tech/tags/isolation.md>), [ledger](<https://devfeed.tech/tags/ledger.md>), [lightweight](<https://devfeed.tech/tags/lightweight.md>), [networking](<https://devfeed.tech/tags/networking.md>), [overhead](<https://devfeed.tech/tags/overhead.md>), [pair](<https://devfeed.tech/tags/pair.md>), [quota](<https://devfeed.tech/tags/quota.md>), [rdma](<https://devfeed.tech/tags/rdma.md>), [region](<https://devfeed.tech/tags/region.md>), [user](<https://devfeed.tech/tags/user.md>), [zero-copy](<https://devfeed.tech/tags/zero-copy.md>)

### AI overview

MTRDMA isolates RDMA control-plane resources on commodity RNICs to prevent one tenant's activity from degrading others. It intercepts library-level control-plane operations and enforces hierarchical quotas while preserving the zero-copy data path. Its mechanisms include atomic shared-memory quota state with per-process cached admission (~0.13 μs), a hybrid collector that reclaims orphaned quota within seconds, and rdma-cgroup caps with ledger-kernel reconciliation to bound and detect residual tampering. On ConnectX-6, it reduced victim degradation under Queue Pair cache exhaustion from 94.5% to 0.08%, also protected against Memory Region cache exhaustion, and supported 256 concurrent tenants with negligible data-plane overhead.

### Source excerpt

arXiv:2611.11991v1 Announce Type: new Abstract: In managed multi-tenant clouds, RDMA's lack of control-plane (CP) resource isolation lets a noisy tenant exhaust shared NIC microarchitectural caches, degrading victim throughput by up to 96.4\%. Data-path schedulers leave CP resources unprotected, and hardware approaches require FPGAs or SmartNICs rather than the commodity RNICs operators already deploy. We present MTRDMA, a lightweight user-space CP isolation mechanism for commodity RNICs, applicable to managed runtimes such as containers and sandboxed processes. MTRDMA intercepts library-level CP operations to enforce hierarchical quotas while preserving the zero-copy data path, using atomic shared-memory quota state with per-process cached admission (${\sim}$0.13\,$\mu$s), a hybrid garbage collector that reclaims orphaned quota within seconds, and rdma-cgroup caps with ledger--kernel reconciliation to bound and detect residual tampering. On ConnectX-6 RNICs, MTRDMA cuts victim degradation under Queue Pair (QP) cache exhaustion from 94.5\% to 0.08\%, extends protection to Memory Region (MR) cache exhaustion, and scales to 256 concurrent tenants with negligible data-plane overhead.

## Taming Autonomous AI Agents with Rootless Docker

DevFeed: [Taming Autonomous AI Agents with Rootless Docker](<https://devfeed.tech/articles/taming-autonomous-ai-agents-with-rootless-docker-121591.md>)

Original publisher: [Read original article](<https://hackernoon.com/taming-autonomous-ai-agents-with-rootless-docker?source=rss>)

Author: Siva Sai Krishna Suryadevara

Published: 2026-11-06T15:00:45Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Docker](<https://devfeed.tech/topics/docker.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [cgroups](<https://devfeed.tech/topics/cgroups.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-ai-agents](<https://devfeed.tech/tags/autonomous-ai-agents.md>), [cgroups](<https://devfeed.tech/tags/cgroups.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [container-security](<https://devfeed.tech/tags/container-security.md>), [docker](<https://devfeed.tech/tags/docker.md>), [docker-engine-api](<https://devfeed.tech/tags/docker-engine-api.md>), [docker-hardening](<https://devfeed.tech/tags/docker-hardening.md>), [docker-security](<https://devfeed.tech/tags/docker-security.md>), [linux](<https://devfeed.tech/tags/linux.md>), [linux-containers](<https://devfeed.tech/tags/linux-containers.md>), [mcp-servers](<https://devfeed.tech/tags/mcp-servers.md>), [namespaces](<https://devfeed.tech/tags/namespaces.md>), [rootless-docker](<https://devfeed.tech/tags/rootless-docker.md>)

### AI overview

Rootless Docker can bound the host impact of autonomous coding agents, but only if they use the rootless daemon's socket and cannot fall back to the rootful system socket. User namespaces map container root to the service account and subordinate host IDs; cgroups v2 with systemd can limit resources, though limits may be silently ignored when the cgroup driver is `none` or controllers are not delegated. The article recommends a dedicated low-privilege account, explicit per-container memory, CPU and PID limits, and restrictive settings such as dropping capabilities, read-only filesystems and disabled networking where possible. Rootless networking uses user-mode drivers such as `slirp4netns`, with lower throughput and separate host firewall concerns. Configure agents and MCP servers to honor `DOCKER_HOST`, discover `$XDG_RUNTIME_DIR/docker.sock`, and allow the rootful socket only by policy; rootless Docker is an execution boundary, not an application-level policy proxy.

### Source excerpt

How rootless Docker, Linux user namespaces, and cgroups v2 contain autonomous AI coding agents without escalating to host root privileges.

## Linux Developers Look To Drop RT\_GROUP\_SCHED As It's "Broken Beyond Repair"

DevFeed: [Linux Developers Look To Drop RT\_GROUP\_SCHED As It's "Broken Beyond Repair"](<https://devfeed.tech/articles/linux-developers-look-to-drop-rt-group-sched-as-it-s-broken-beyond-repair-120975.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/Linux-Drop-RT_GROUP_SCHED>)

Author: Michael Larabel

Published: 2026-11-06T11:09:14Z

Content type: news

Language: en

Sources: [Phoronix](<https://devfeed.tech/sources/phoronix.md>)

Topics: [Linux Kernel](<https://devfeed.tech/topics/linux-kernel.md>), [cgroups](<https://devfeed.tech/topics/cgroups.md>), [Linux](<https://devfeed.tech/topics/linux.md>), [scheduling](<https://devfeed.tech/topics/scheduling.md>), [deprecated](<https://devfeed.tech/topics/deprecated.md>)

Tags: [cgroups](<https://devfeed.tech/tags/cgroups.md>), [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [developers](<https://devfeed.tech/tags/developers.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [linux](<https://devfeed.tech/tags/linux.md>), [linux-benchmarking](<https://devfeed.tech/tags/linux-benchmarking.md>), [linux-hardware-benchmarks](<https://devfeed.tech/tags/linux-hardware-benchmarks.md>), [linux-hardware-reviews](<https://devfeed.tech/tags/linux-hardware-reviews.md>), [linux-how-to](<https://devfeed.tech/tags/linux-how-to.md>), [linux-performance](<https://devfeed.tech/tags/linux-performance.md>), [linux-server-benchmarks](<https://devfeed.tech/tags/linux-server-benchmarks.md>), [open-source-graphics](<https://devfeed.tech/tags/open-source-graphics.md>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [scheduling](<https://devfeed.tech/tags/scheduling.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>)

### AI overview

Linux kernel developers have proposed removing RT_GROUP_SCHED, a cgroups v1-era feature that the patch author calls "broken beyond repair." The excerpt says cgroup v2 cannot assign the runtime needed for SCHED_FIFO or SCHED_RR tasks, while the root group's runtime constrains reducing the global real-time runtime setting. SCHED_DEADLINE tasks can be scheduled, but admission control is stuck unless disabled through the same sysctl. The author says major distributions already disable the feature and points to the DL fair server's RT throttling and ongoing work on hierarchical constant bandwidth servers as alternatives. Some users may still depend on the code, and kernel developers have raised whether deprecation should precede removal; the excerpt says the patch is likely to advance, not that removal is complete.

### Source excerpt

Linux kernel developers are looking at dropping the RT_GROUP_SCHED feature that is used for group scheduling of real-time tasks using cgroups...

## Demystifying Linux Cgroups: The Hidden Engine Powering Docker and Kubernetes

DevFeed: [Demystifying Linux Cgroups: The Hidden Engine Powering Docker and Kubernetes](<https://devfeed.tech/articles/demystifying-linux-cgroups-the-hidden-engine-powering-docker-and-kubernetes-121431.md>)

Original publisher: [Read original article](<https://blog.devops.dev/demystifying-linux-cgroups-the-hidden-engine-powering-docker-and-kubernetes-e6627f9fe75d?source=rss----33f8b2d9a328---4>)

Author: Techie Crow

Published: 2026-11-06T09:45:56Z

Content type: article

Language: en

Sources: [DevOps.dev](<https://devfeed.tech/sources/devops-dev.md>)

Topics: [cgroups](<https://devfeed.tech/topics/cgroups.md>), [Linux Kernel](<https://devfeed.tech/topics/linux-kernel.md>), [Linux](<https://devfeed.tech/topics/linux.md>), [Docker](<https://devfeed.tech/topics/docker.md>)

Tags: [cgroup](<https://devfeed.tech/tags/cgroup.md>), [cgroups](<https://devfeed.tech/tags/cgroups.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cluster](<https://devfeed.tech/tags/cluster.md>), [containers](<https://devfeed.tech/tags/containers.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [devops](<https://devfeed.tech/tags/devops.md>), [devops-engineer](<https://devfeed.tech/tags/devops-engineer.md>), [docker](<https://devfeed.tech/tags/docker.md>), [google](<https://devfeed.tech/tags/google.md>), [groups](<https://devfeed.tech/tags/groups.md>), [i-o](<https://devfeed.tech/tags/i-o.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [kubernetes-yaml-manifests](<https://devfeed.tech/tags/kubernetes-yaml-manifests.md>), [linux](<https://devfeed.tech/tags/linux.md>), [linux-kernel](<https://devfeed.tech/tags/linux-kernel.md>), [memory](<https://devfeed.tech/tags/memory.md>), [node](<https://devfeed.tech/tags/node.md>), [performance](<https://devfeed.tech/tags/performance.md>), [pod](<https://devfeed.tech/tags/pod.md>)

### AI overview

Linux cgroups are kernel controls for allocating, restricting, prioritizing, and monitoring resources used by groups of processes. The excerpt identifies memory, CPU, and disk I/O as resources that can be capped, and says cgroups can prioritize CPU or disk throughput under system pressure. It frames cgroups as underlying resource controls relevant to containers, but the excerpt does not explain how they map to Kubernetes settings or determine pod priority.

### Source excerpt

Ever wondered how your server handles hundreds of isolated containers without losing its mind? Or how Kubernetes ensures that a single... Continue reading on DevOps.dev "

## How We Stabilized a Bazel CI Runner by Fixing Resource Limits and Container Cleanup

DevFeed: [How We Stabilized a Bazel CI Runner by Fixing Resource Limits and Container Cleanup](<https://devfeed.tech/articles/how-we-stabilized-a-bazel-ci-runner-by-fixing-resource-limits-and-container-cleanup-114855.md>)

Original publisher: [Read original article](<https://hackernoon.com/how-we-stabilized-a-bazel-ci-runner-by-fixing-resource-limits-and-container-cleanup?source=rss>)

Author: Daniil Romashov

Published: 2026-11-03T15:21:51Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [bazel](<https://devfeed.tech/topics/bazel.md>), [cgroups](<https://devfeed.tech/topics/cgroups.md>), [scheduling](<https://devfeed.tech/topics/scheduling.md>), [Integration testing](<https://devfeed.tech/topics/integration-testing.md>)

Tags: [bazel](<https://devfeed.tech/tags/bazel.md>), [builds](<https://devfeed.tech/tags/builds.md>), [c-plus-plus](<https://devfeed.tech/tags/c-plus-plus.md>), [cache](<https://devfeed.tech/tags/cache.md>), [capacity](<https://devfeed.tech/tags/capacity.md>), [cfs](<https://devfeed.tech/tags/cfs.md>), [cgroups](<https://devfeed.tech/tags/cgroups.md>), [ci](<https://devfeed.tech/tags/ci.md>), [ci-cd](<https://devfeed.tech/tags/ci-cd.md>), [cleanup](<https://devfeed.tech/tags/cleanup.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [container](<https://devfeed.tech/tags/container.md>), [container-cleanup](<https://devfeed.tech/tags/container-cleanup.md>), [container-images](<https://devfeed.tech/tags/container-images.md>), [containers](<https://devfeed.tech/tags/containers.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cpus](<https://devfeed.tech/tags/cpus.md>), [docker](<https://devfeed.tech/tags/docker.md>), [gitlab-runner](<https://devfeed.tech/tags/gitlab-runner.md>), [limits](<https://devfeed.tech/tags/limits.md>), [monorepo](<https://devfeed.tech/tags/monorepo.md>), [oom](<https://devfeed.tech/tags/oom.md>), [oom-killer](<https://devfeed.tech/tags/oom-killer.md>), [resource](<https://devfeed.tech/tags/resource.md>), [runner](<https://devfeed.tech/tags/runner.md>)

### AI overview

Bazel CI jobs were being OOM-killed because a runner with 6 cores and 62 GiB of memory had no per-job cgroup limits, while jobs acted on stale configuration promising 5 CPUs and 24 GiB each. After three days of tuning, the runner stabilized at five jobs with a hard 11 GiB memory cap per job; Bazel's local resource estimate was set below that cap, using measured 6.68 GiB RSS rather than an 11.37 GiB working set that included reclaimable page cache. Hard CPU quotas caused heavy throttling, so CPU allocation was made fair while the memory cap remained strict. The team also moved linting and review tasks to a lighter runner. Separately, integration-test helper containers launched through the Docker SDK outlived canceled CI jobs because cleanup in finally blocks was skipped and the containers lacked the labels used by garbage collection. Adding the Testcontainers label at each launch site made them eligible for cleanup. The account emphasizes verifying runner capacity and labeling all containers; it describes one environment and does not establish a universal configuration.

### Source excerpt

Bazel builds kept getting OOM-killed on a CI runner whose config promised 25 CPUs it did not have. How hard cgroup caps and three days of retuning settled the m

## I was wrong! zswap IS better than zram

DevFeed: [I was wrong! zswap IS better than zram](<https://devfeed.tech/articles/i-was-wrong-zswap-is-better-than-zram-102576.md>)

Original publisher: [Read original article](<https://linuxblog.io/zswap-better-than-zram/>)

Author: Hayden James

Published: 2026-10-27T12:30:49Z

Content type: opinion

Language: en

Sources: [Hayden James](<https://devfeed.tech/sources/hayden-james.md>)

Topics: [Linux Kernel](<https://devfeed.tech/topics/linux-kernel.md>), [Linux](<https://devfeed.tech/topics/linux.md>), [cgroups](<https://devfeed.tech/topics/cgroups.md>), [GRUB](<https://devfeed.tech/topics/grub.md>), [XFS](<https://devfeed.tech/topics/xfs.md>)

Tags: [algorithm](<https://devfeed.tech/tags/algorithm.md>), [applications](<https://devfeed.tech/tags/applications.md>), [block](<https://devfeed.tech/tags/block.md>), [blog](<https://devfeed.tech/tags/blog.md>), [boot](<https://devfeed.tech/tags/boot.md>), [builds](<https://devfeed.tech/tags/builds.md>), [cache](<https://devfeed.tech/tags/cache.md>), [caching](<https://devfeed.tech/tags/caching.md>), [capacity](<https://devfeed.tech/tags/capacity.md>), [charged](<https://devfeed.tech/tags/charged.md>), [compression](<https://devfeed.tech/tags/compression.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [configure](<https://devfeed.tech/tags/configure.md>), [container](<https://devfeed.tech/tags/container.md>), [containers](<https://devfeed.tech/tags/containers.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [cpu-time](<https://devfeed.tech/tags/cpu-time.md>), [demand](<https://devfeed.tech/tags/demand.md>), [desktop](<https://devfeed.tech/tags/desktop.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [linux](<https://devfeed.tech/tags/linux.md>), [performance](<https://devfeed.tech/tags/performance.md>), [server](<https://devfeed.tech/tags/server.md>), [sysadmins](<https://devfeed.tech/tags/sysadmins.md>), [zram](<https://devfeed.tech/tags/zram.md>), [zswap](<https://devfeed.tech/tags/zswap.md>)

### AI overview

The author now recommends zswap as the usual choice for modern systems with disk swap, especially when swap use is large or variable and storage is fast. Zswap caches compressed pages in RAM up to a pool limit, then evicts pages to backing swap; the author says this uses memory dynamically, reduces NVMe writes, and avoids the performance and suspend/resume problems they encountered after using half their RAM for zram. Their desktop uses zswap with an NVMe swap file. Zram remains useful on small or diskless systems and systems with very slow storage, but the author advises keeping its size around 20-30% of RAM and warns that it can compete with the working set and page cache. For cgroup-limited servers, the author favors zswap because zram memory is not charged to the owning cgroup, while zswap pages are.

### Source excerpt

Update (October 2026): I first published this article on September 1, 2025. In March 2026, kernel developer Chris Down published Debunking zswap and zram myths, which reaches the same conclusion: if in doubt, prefer zswap. Continue reading...

## 5 Commands to Protect Critical Apps From the Linux OOM Killer

DevFeed: [5 Commands to Protect Critical Apps From the Linux OOM Killer](<https://devfeed.tech/articles/5-commands-to-protect-critical-apps-from-the-linux-oom-killer-95340.md>)

Original publisher: [Read original article](<https://www.tecmint.com/stop-oom-killer-killing-apps/>)

Author: Ravi Saive

Published: 2026-10-22T09:49:33Z

Content type: tutorial

Language: en

Sources: [Tecmint: Linux Howtos, Tutorials & Guides](<https://devfeed.tech/sources/tecmint-linux-howtos-tutorials-guides.md>)

Topics: [Linux](<https://devfeed.tech/topics/linux.md>), [cgroups](<https://devfeed.tech/topics/cgroups.md>), [Kernel](<https://devfeed.tech/topics/kernel.md>)

Tags: [almalinux](<https://devfeed.tech/tags/almalinux.md>), [application](<https://devfeed.tech/tags/application.md>), [applications](<https://devfeed.tech/tags/applications.md>), [apps](<https://devfeed.tech/tags/apps.md>), [apt](<https://devfeed.tech/tags/apt.md>), [btrfs](<https://devfeed.tech/tags/btrfs.md>), [cat](<https://devfeed.tech/tags/cat.md>), [cgroups](<https://devfeed.tech/tags/cgroups.md>), [chmod](<https://devfeed.tech/tags/chmod.md>), [commands](<https://devfeed.tech/tags/commands.md>), [conf](<https://devfeed.tech/tags/conf.md>), [database](<https://devfeed.tech/tags/database.md>), [debian](<https://devfeed.tech/tags/debian.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [linux](<https://devfeed.tech/tags/linux.md>), [linux-commands](<https://devfeed.tech/tags/linux-commands.md>), [linux-oom-killer](<https://devfeed.tech/tags/linux-oom-killer.md>), [memory](<https://devfeed.tech/tags/memory.md>), [oom](<https://devfeed.tech/tags/oom.md>), [oom-score-adj](<https://devfeed.tech/tags/oom-score-adj.md>), [out-of-memory](<https://devfeed.tech/tags/out-of-memory.md>), [process](<https://devfeed.tech/tags/process.md>), [systemd-memorymax](<https://devfeed.tech/tags/systemd-memorymax.md>)

### AI overview

The excerpt presents five ways to manage Linux out-of-memory events: inspect kernel logs and process OOM scores; adjust a running process with `choom` or persist its priority through systemd's `OOMScoreAdjust`; limit a service with cgroups v2 `MemoryHigh` and `MemoryMax`; add swap for short memory spikes; and use `systemd-oomd` to respond to sustained memory pressure. It distinguishes temporary process adjustments from persistent service settings, and explains that cgroup limits confine OOM kills to the affected service. Full immunity with `OOMScoreAdjust=-1000` can leave the kernel with no killable process and cause a system panic. The excerpt notes platform limits: Btrfs needs a specially created swap file, and Rocky Linux/RHEL may require enabling PSI before `systemd-oomd` can monitor pressure. Swap buys time but does not fix leaks; ongoing OOM events still call for addressing the cause or adding memory.

### Source excerpt

The post 5 Commands to Protect Critical Apps From the Linux OOM Killer first appeared on Tecmint: Linux Howtos, Tutorials & Guides . Your database keeps disappearing overnight, and the only clue is a kernel line saying "Out of memory: Killed process". Here's The post 5 Commands to Protect Critical Apps From the Linux OOM Killer first appeared on Tecmint: Linux Howtos, Tutorials & Guides.

## Meta Makes Improvements To Kernfs Scalability With Linux 7.4

DevFeed: [Meta Makes Improvements To Kernfs Scalability With Linux 7.4](<https://devfeed.tech/articles/meta-makes-improvements-to-kernfs-scalability-with-linux-7-4-92569.md>)

Original publisher: [Read original article](<https://www.phoronix.com/news/Linux-7.4-Kernfs-Scalability>)

Author: Michael Larabel

Published: 2026-10-21T09:54:53Z

Content type: news

Language: en

Sources: [Phoronix](<https://devfeed.tech/sources/phoronix.md>)

Topics: [Linux Kernel](<https://devfeed.tech/topics/linux-kernel.md>), [Linux](<https://devfeed.tech/topics/linux.md>), [cgroups](<https://devfeed.tech/topics/cgroups.md>)

Tags: [desktop-linux](<https://devfeed.tech/tags/desktop-linux.md>), [linux-7-4](<https://devfeed.tech/tags/linux-7-4.md>), [linux-benchmarking](<https://devfeed.tech/tags/linux-benchmarking.md>), [linux-hardware-benchmarks](<https://devfeed.tech/tags/linux-hardware-benchmarks.md>), [linux-hardware-reviews](<https://devfeed.tech/tags/linux-hardware-reviews.md>), [linux-how-to](<https://devfeed.tech/tags/linux-how-to.md>), [linux-performance](<https://devfeed.tech/tags/linux-performance.md>), [linux-server-benchmarks](<https://devfeed.tech/tags/linux-server-benchmarks.md>), [meta](<https://devfeed.tech/tags/meta.md>), [open-source-graphics](<https://devfeed.tech/tags/open-source-graphics.md>), [phoronix](<https://devfeed.tech/tags/phoronix.md>), [phoronix-test-suite](<https://devfeed.tech/tags/phoronix-test-suite.md>), [scalability](<https://devfeed.tech/tags/scalability.md>), [ubuntu-benchmarks](<https://devfeed.tech/tags/ubuntu-benchmarks.md>), [ubuntu-hardware](<https://devfeed.tech/tags/ubuntu-hardware.md>)

### AI overview

Meta engineer Shakeel Butt authored 18 patches for Linux 7.4 to address Kernfs scalability bottlenecks that had left cgroup-related interfaces stuck for long periods. The changes improve lock handling and fix bugs. In a reported 8-CPU VM workload with concurrent cgroup churn, network-device renames, and device changes while readers traversed cgroupfs and sysfs, four patches reduced the two reported kernfs_rwsem read-contention counts from 48,593,360 and 1,744,517 to 1,280,280 and 429,846; reader path-walk throughput improved 35-53%. The excerpt gives no broader workload results.

### Source excerpt

Kernfs as the functions/frameworks used for creating pseudo file-systems on Linux like sysfs and configfs have seen some nice scalability work carried out by Meta. After Meta engineers discovered some system daemons getting stuck for minutes on their massive fleet of servers, they uncovered some scalability bottlenecks within Kernfs that now look to be resolved for Linux 7.4...

## Inside the PLC Runtime: What OpenPLC v4 Reveals About Its Linux Environment

DevFeed: [Inside the PLC Runtime: What OpenPLC v4 Reveals About Its Linux Environment](<https://devfeed.tech/articles/inside-the-plc-runtime-what-openplc-v4-reveals-about-its-linux-environment-92544.md>)

Original publisher: [Read original article](<https://hackernoon.com/inside-the-plc-runtime-what-openplc-v4-reveals-about-its-linux-environment?source=rss>)

Author: RUGERO Tesla

Published: 2026-10-21T08:08:43Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Linux](<https://devfeed.tech/topics/linux.md>), [observability](<https://devfeed.tech/topics/observability.md>), [cgroups](<https://devfeed.tech/topics/cgroups.md>), [control-plane](<https://devfeed.tech/topics/control-plane.md>)

Tags: [affinity](<https://devfeed.tech/tags/affinity.md>), [application](<https://devfeed.tech/tags/application.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [bits](<https://devfeed.tech/tags/bits.md>), [buffer](<https://devfeed.tech/tags/buffer.md>), [build](<https://devfeed.tech/tags/build.md>), [c](<https://devfeed.tech/tags/c.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [cgroups](<https://devfeed.tech/tags/cgroups.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [environment](<https://devfeed.tech/tags/environment.md>), [industrial-control-systems](<https://devfeed.tech/tags/industrial-control-systems.md>), [investigation](<https://devfeed.tech/tags/investigation.md>), [linux](<https://devfeed.tech/tags/linux.md>), [networking](<https://devfeed.tech/tags/networking.md>), [openplc-architecture](<https://devfeed.tech/tags/openplc-architecture.md>), [openplc-runtime-v4](<https://devfeed.tech/tags/openplc-runtime-v4.md>), [permissions](<https://devfeed.tech/tags/permissions.md>), [plc](<https://devfeed.tech/tags/plc.md>), [processes](<https://devfeed.tech/tags/processes.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [security](<https://devfeed.tech/tags/security.md>), [sockets](<https://devfeed.tech/tags/sockets.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

### AI overview

The OpenPLC Runtime v4 baseline maps its processes, local sockets, network state, Linux permissions, capabilities, memory mappings, scheduling, and cgroup limits inside a Docker container. After `plc_main` was killed, the supervisor restarted it, but the replacement could not find expected `libplc_*.so` files and remained in `EMPTY`. The snapshot showed Unix sockets for runtime, logging, and supervisor control; published port 502 had no visible Modbus TCP listener at inspection time. The process had `CAP_NET_RAW`, normal time-sharing scheduling, and no CPU or memory maximum in the inspected cgroup files; a request for `SCHED_FIFO` priority 99 failed. These are observations from one state, not vulnerability findings or proof of external reachability, hardware access limits, runtime timing, or behavior under other failures. The image used the mutable `latest` tag, so the author recommends recording its digest and runtime version for reproducibility.

### Source excerpt

Explore OpenPLC Runtime v4's architecture, processes, sockets, permissions, and Linux environment in this hands-on PLC security investigation.

## Linux 7.3 release - Main Changes, Arm, RISC-V, and MIPS architectures

DevFeed: [Linux 7.3 release - Main Changes, Arm, RISC-V, and MIPS architectures](<https://devfeed.tech/articles/linux-7-3-release-main-changes-arm-risc-v-and-mips-architectures-90278.md>)

Original publisher: [Read original article](<https://www.cnx-software.com/2026/10/20/linux-7-3-release-main-changes-arm-risc-v-and-mips-architectures/>)

Author: Jean-Luc Aufranc (CNXSoft)

Published: 2026-10-19T17:01:56Z

Content type: news

Language: en

Sources: [CNX Software - Embedded Systems News](<https://devfeed.tech/sources/cnx-software-embedded-systems-news.md>)

Topics: [Linux Kernel](<https://devfeed.tech/topics/linux-kernel.md>), [RISC-V](<https://devfeed.tech/topics/riscv.md>), [trust](<https://devfeed.tech/topics/trust.md>), [cgroups](<https://devfeed.tech/topics/cgroups.md>), [io\_uring](<https://devfeed.tech/topics/io-uring.md>), [Beta channel](<https://devfeed.tech/topics/beta-channel.md>)

Tags: [alibaba](<https://devfeed.tech/tags/alibaba.md>), [alibaba-t-head](<https://devfeed.tech/tags/alibaba-t-head.md>), [allwinner](<https://devfeed.tech/tags/allwinner.md>), [allwinner-a-series](<https://devfeed.tech/tags/allwinner-a-series.md>), [allwinner-h-series](<https://devfeed.tech/tags/allwinner-h-series.md>), [amlogic](<https://devfeed.tech/tags/amlogic.md>), [apple](<https://devfeed.tech/tags/apple.md>), [arm](<https://devfeed.tech/tags/arm.md>), [asus](<https://devfeed.tech/tags/asus.md>), [banana-pi](<https://devfeed.tech/tags/banana-pi.md>), [beagleboard](<https://devfeed.tech/tags/beagleboard.md>), [broadcom-bcmxxxx](<https://devfeed.tech/tags/broadcom-bcmxxxx.md>), [btrfs](<https://devfeed.tech/tags/btrfs.md>), [embedded-systems](<https://devfeed.tech/tags/embedded-systems.md>), [ext-4](<https://devfeed.tech/tags/ext-4.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [linus-torvalds](<https://devfeed.tech/tags/linus-torvalds.md>), [linux](<https://devfeed.tech/tags/linux.md>), [linux-7-x](<https://devfeed.tech/tags/linux-7-x.md>), [mediatek](<https://devfeed.tech/tags/mediatek.md>), [mediatek-filogic](<https://devfeed.tech/tags/mediatek-filogic.md>), [mediatek-mt65xx](<https://devfeed.tech/tags/mediatek-mt65xx.md>), [mediatek-mt8xxx](<https://devfeed.tech/tags/mediatek-mt8xxx.md>), [mediatek-wi-fi](<https://devfeed.tech/tags/mediatek-wi-fi.md>), [microsemi](<https://devfeed.tech/tags/microsemi.md>), [mips](<https://devfeed.tech/tags/mips.md>), [motorola](<https://devfeed.tech/tags/motorola.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [nvidia-jetson](<https://devfeed.tech/tags/nvidia-jetson.md>), [nxp-i-mx](<https://devfeed.tech/tags/nxp-i-mx.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [orange-pi](<https://devfeed.tech/tags/orange-pi.md>), [qualcomm](<https://devfeed.tech/tags/qualcomm.md>), [qualcomm-qcs](<https://devfeed.tech/tags/qualcomm-qcs.md>), [qualcomm-snapdragon](<https://devfeed.tech/tags/qualcomm-snapdragon.md>), [radxa](<https://devfeed.tech/tags/radxa.md>), [raspberry-pi](<https://devfeed.tech/tags/raspberry-pi.md>), [release](<https://devfeed.tech/tags/release.md>), [risc-v](<https://devfeed.tech/tags/risc-v.md>), [rockchip](<https://devfeed.tech/tags/rockchip.md>), [rockchip-rk35xx](<https://devfeed.tech/tags/rockchip-rk35xx.md>), [rockchip-rvxxxx](<https://devfeed.tech/tags/rockchip-rvxxxx.md>), [samsung](<https://devfeed.tech/tags/samsung.md>), [samsung-exynos](<https://devfeed.tech/tags/samsung-exynos.md>), [sifive](<https://devfeed.tech/tags/sifive.md>), [single-board-computer](<https://devfeed.tech/tags/single-board-computer.md>), [sony](<https://devfeed.tech/tags/sony.md>), [sophgo](<https://devfeed.tech/tags/sophgo.md>), [spacemit](<https://devfeed.tech/tags/spacemit.md>), [starfive](<https://devfeed.tech/tags/starfive.md>), [texas-instruments-sitara](<https://devfeed.tech/tags/texas-instruments-sitara.md>), [toradex](<https://devfeed.tech/tags/toradex.md>), [under](<https://devfeed.tech/tags/under.md>), [variscite](<https://devfeed.tech/tags/variscite.md>), [xiaomi](<https://devfeed.tech/tags/xiaomi.md>)

### AI overview

Linux 7.3 has been released with changes across Arm, RISC-V, and MIPS, alongside updates to GPU memory management, filesystems, FUSE, cgroups, and hardware support. The release includes scheduler and driver changes, performance improvements, and new device support.

### Source excerpt

Linus Torvalds announced the release of Linux 7.3 on LKML last Sunday: It's Sunday afternoon, and this week I somehow kept my wits together long enough to keep track of the day of the week, so the release isn't randomly delayed. Will wonders never cease? Anyway, nothing very special seems to have happened this last week, so as expected the final 7.3 is out, and thus tomorrow the merge window for 7.4 opens. Except I'm on my annual family vacation, so instead of merging anything first thing in the morning, I'll spend most of the day on a boat and under water. I'll get back to merging in the afternoon, but I expect my schedule to be a bit unusual for a while. I hope I can still complete the merge window in the usual two weeks, but it may be that I'll end up with an extra week of merging [...] The post Linux 7.3 release - Main Changes, Arm, RISC-V, and MIPS architectures appeared first on CNX Software - Embedded Systems News.

## Linux 7.3 is out, speeds up ext4 and low-VRAM AMD GPUs

DevFeed: [Linux 7.3 is out, speeds up ext4 and low-VRAM AMD GPUs](<https://devfeed.tech/articles/linux-7-3-is-out-speeds-up-ext4-and-low-vram-amd-gpus-89796.md>)

Original publisher: [Read original article](<https://www.omgubuntu.co.uk/2026/10/linux-7-3-features>)

Author: Joey Sneddon

Published: 2026-10-19T02:28:18Z

Content type: news

Language: en

Sources: [OMG! Ubuntu](<https://devfeed.tech/sources/omg-ubuntu.md>)

Topics: [Linux](<https://devfeed.tech/topics/linux.md>), [Ext4](<https://devfeed.tech/topics/ext4.md>), [GPU optimization](<https://devfeed.tech/topics/gpu-optimization.md>), [cgroups](<https://devfeed.tech/topics/cgroups.md>), [io\_uring](<https://devfeed.tech/topics/io-uring.md>), [radeon-gpu-profiler](<https://devfeed.tech/topics/radeon-gpu-profiler.md>), [Steam Deck](<https://devfeed.tech/topics/steam-deck.md>)

Tags: [amd](<https://devfeed.tech/tags/amd.md>), [ext4](<https://devfeed.tech/tags/ext4.md>), [linux](<https://devfeed.tech/tags/linux.md>), [linux-kernel](<https://devfeed.tech/tags/linux-kernel.md>), [news](<https://devfeed.tech/tags/news.md>), [performance](<https://devfeed.tech/tags/performance.md>), [scheduling](<https://devfeed.tech/tags/scheduling.md>), [ubuntu](<https://devfeed.tech/tags/ubuntu.md>), [vram](<https://devfeed.tech/tags/vram.md>)

### AI overview

Linux 7.3 improves performance for AMD GPUs with limited VRAM, ext4 and other filesystems, and CPU scheduling across groups of processes. The release also adds hardware support, including an initial driver for the 2026 Steam Controller, and early support for Apple M3 Pro, Max, and Ultra chips.

### Source excerpt

Linux 7.3 is out with faster ext4, better performance on AMD GPUs with low VRAM and a new cgroup scheduling mode. 2026 Steam Controller driver debuts. You're reading Linux 7.3 is out, speeds up ext4 and low-VRAM AMD GPUs, a blog post from OMG! Ubuntu. Do not reproduce elsewhere without permission.

## btop: Monitor CPU, Memory, Disk, and Network in Linux

DevFeed: [btop: Monitor CPU, Memory, Disk, and Network in Linux](<https://devfeed.tech/articles/btop-monitor-cpu-memory-disk-and-network-in-linux-77116.md>)

Original publisher: [Read original article](<https://www.tecmint.com/btop-system-monitoring-tool-for-linux/>)

Author: Ravi Saive

Published: 2026-10-08T05:43:58Z

Content type: tutorial

Language: en

Sources: [Tecmint: Linux Howtos, Tutorials & Guides](<https://devfeed.tech/sources/tecmint-linux-howtos-tutorials-guides.md>)

Topics: [Linux](<https://devfeed.tech/topics/linux.md>), [cgroups](<https://devfeed.tech/topics/cgroups.md>)

Tags: [btop-system-monitor](<https://devfeed.tech/tags/btop-system-monitor.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [linux](<https://devfeed.tech/tags/linux.md>), [linux-cpu-and-memory-monitoring](<https://devfeed.tech/tags/linux-cpu-and-memory-monitoring.md>), [linux-real-time-monitoring](<https://devfeed.tech/tags/linux-real-time-monitoring.md>), [linux-system-monitoring](<https://devfeed.tech/tags/linux-system-monitoring.md>), [memory](<https://devfeed.tech/tags/memory.md>), [monitoring-tools](<https://devfeed.tech/tags/monitoring-tools.md>), [network](<https://devfeed.tech/tags/network.md>)

### AI overview

The guide explains how to install and use btop, a Linux terminal monitor that combines live CPU, memory, disk, network, and process information. It covers troubleshooting resource bottlenecks, filtering and signaling processes, configuring the display, connecting over SSH, and keeping monitoring overhead low.

### Source excerpt

The post btop: Monitor CPU, Memory, Disk, and Network in Linux first appeared on Tecmint: Linux Howtos, Tutorials & Guides . When a server slows down, top gives you a list of processes, but it does not immediately tell you whether The post btop: Monitor CPU, Memory, Disk, and Network in Linux first appeared on Tecmint: Linux Howtos, Tutorials & Guides.

## The Shift to cgroup v2 in Kubernetes: What You Need to Know

DevFeed: [The Shift to cgroup v2 in Kubernetes: What You Need to Know](<https://devfeed.tech/articles/the-shift-to-cgroup-v2-in-kubernetes-what-you-need-to-know-65880.md>)

Original publisher: [Read original article](<https://kubernetes.io/blog/2026/10/06/kubernetes-cgroups-v2-shift/>)

Author: Paco Xu

Published: 2026-10-06T18:00:00Z

Content type: tutorial

Language: en

Sources: [Kubernetes Blog](<https://devfeed.tech/sources/kubernetes-blog.md>)

Topics: [cgroups](<https://devfeed.tech/topics/cgroups.md>), [Linux](<https://devfeed.tech/topics/linux.md>), [Headless Browser](<https://devfeed.tech/topics/headless-browser.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [cgroups](<https://devfeed.tech/tags/cgroups.md>), [clusters](<https://devfeed.tech/tags/clusters.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [containers](<https://devfeed.tech/tags/containers.md>), [control](<https://devfeed.tech/tags/control.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [deprecation](<https://devfeed.tech/tags/deprecation.md>), [error](<https://devfeed.tech/tags/error.md>), [isolation](<https://devfeed.tech/tags/isolation.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [linux](<https://devfeed.tech/tags/linux.md>), [maintenance](<https://devfeed.tech/tags/maintenance.md>), [management](<https://devfeed.tech/tags/management.md>), [memory](<https://devfeed.tech/tags/memory.md>), [migrate](<https://devfeed.tech/tags/migrate.md>), [upgrade](<https://devfeed.tech/tags/upgrade.md>)

### AI overview

Kubernetes is deprecating cgroup v1, with the kubelet defaulting to reject cgroup v1 nodes from v1.35 and fallback support scheduled for removal in v1.38. The article explains migration requirements and cgroup v2 behavior, including Memory QoS, resource controls, runtime configuration, and diagnostic commands.

### Source excerpt

In Linux, cgroups (control groups) are a kernel feature used for managing system resources. Kubernetes uses cgroups to allocate resources like CPU and memory to containers, ensuring that applications run smoothly without interfering with each other. With the release of Kubernetes v1.31, support for v1 cgroup management moved into maintenance mode. Support for v2 cgroup management has been stable since Kubernetes v1.25. Compared with cgroup v1, cgroup v2 provides a single unified hierarchy, a more consistent interface, and a stronger foundation for resource isolation and modern resource-management features. Deprecation of cgroup v1 Kubernetes has deprecated cgroup v1. Starting with Kubernetes v1.35, failCgroupV1 defaults to true, so the kubelet does not start on a cgroup v1 node by default. Administrators can temporarily set failCgroupV1: false in the kubelet configuration file, but removal will follow the Kubernetes deprecation policy. Further removal work is tracked in KEP-5573: Remove cgroup v1 support. If you are still on a release older than v1.35, migrate every Linux node to cgroup v2 before upgrading, or plan to set the temporary failCgroupV1: false override. If you are already on v1.35 or later, confirm that every Linux node runs cgroup v2 (or that you intentionally keep the override). Under the default configuration, a remaining cgroup v1 node fails during kubelet startup. For kubeadm-managed clusters, Kubernetes v1.35 also makes this an earlier, stricter check. The SystemVerification preflight check, provided by k8s.io/system-validators, returns an error during kubeadm init, kubeadm join, and kubeadm upgrade when it detects cgroup v1 with kubelet v1.35 or later; with an older kubelet, the check remains a warning. See kubernetes/system-validators#1.12.1 release notes for details. The top FAQs cover three main areas: why to migrate, the benefits and drawbacks, and key points to keep in mind when using cgroup v2. Limitations of cgroup v1 and Improvements with

## VM Sandboxes: Full computers for agents

DevFeed: [VM Sandboxes: Full computers for agents](<https://devfeed.tech/articles/vm-sandboxes-full-computers-for-agents-79958.md>)

Original publisher: [Read original article](<https://modal.com/blog/vm-sandboxes-agent-computers>)

Author: Amit Prasad

Published: 2026-10-01T00:00:00Z

Content type: release

Language: en

Sources: [Modal](<https://devfeed.tech/sources/modal.md>)

Topics: [Docker Sandboxes](<https://devfeed.tech/topics/docker-sandboxes.md>), [DeepSeek Harness](<https://devfeed.tech/topics/dsh.md>), [cgroups](<https://devfeed.tech/topics/cgroups.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [cgroups](<https://devfeed.tech/tags/cgroups.md>), [container](<https://devfeed.tech/tags/container.md>), [containers](<https://devfeed.tech/tags/containers.md>), [sandboxes](<https://devfeed.tech/tags/sandboxes.md>), [vm](<https://devfeed.tech/tags/vm.md>)

### AI overview

Modal has made VM Sandboxes generally available, offering full Linux virtual machines for agents that need capabilities such as Docker, local databases, development servers, graphical environments, or Linux kernel features. The VM runtime shares APIs and image support with Modal's existing gVisor sandboxes, while existing workloads can continue using gVisor by default. Early customers use the VMs for coding sessions, legal agent evaluations, and agent simulations.

### Source excerpt

VM Sandboxes are built for those who need to give their agents the power of a full computer.

## \[$\] The kernel from a PostgreSQL point of view

DevFeed: [\[$\] The kernel from a PostgreSQL point of view](<https://devfeed.tech/articles/the-kernel-from-a-postgresql-point-of-view-62119.md>)

Original publisher: [Read original article](<https://lwn.net/Articles/1096827/>)

Author: corbet

Published: 2026-09-29T15:42:30Z

Content type: news

Language: en

Sources: [LWN.net](<https://devfeed.tech/sources/lwn-net.md>)

Topics: [Linux Kernel](<https://devfeed.tech/topics/linux-kernel.md>), [PostgreSQL](<https://devfeed.tech/topics/postgresql.md>), [io\_uring](<https://devfeed.tech/topics/io-uring.md>), [database-optimization](<https://devfeed.tech/topics/database-optimization.md>), [cgroups](<https://devfeed.tech/topics/cgroups.md>)

Tags: [asynchronous](<https://devfeed.tech/tags/asynchronous.md>), [atomic](<https://devfeed.tech/tags/atomic.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [bugs](<https://devfeed.tech/tags/bugs.md>), [cache](<https://devfeed.tech/tags/cache.md>), [copy-on-write](<https://devfeed.tech/tags/copy-on-write.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [crashes](<https://devfeed.tech/tags/crashes.md>), [database](<https://devfeed.tech/tags/database.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [linux](<https://devfeed.tech/tags/linux.md>), [linux-kernel](<https://devfeed.tech/tags/linux-kernel.md>), [performance](<https://devfeed.tech/tags/performance.md>), [postgresql](<https://devfeed.tech/tags/postgresql.md>)

### AI overview

PostgreSQL's evolving I/O and threading plans both depend on Linux kernel behavior, and closer collaboration could help address problems that affect more than the database. PostgreSQL is moving toward threads and asynchronous I/O; Freund has experimented with io_uring but found worker threads can perform well, while direct I/O is expected to remain optional because tuning it alongside other applications is difficult. The article highlights kernel gains in writeback and reclaim, alongside issues including scalability cliffs tied partly to CPU idle states, slow or unsuitable futex options, limited control-group out-of-memory handling, fragmentation from fallocate-based checkpoint reservations, and io_uring memory and buffer constraints. PostgreSQL testing could expose kernel regressions and improve real-world benchmarks, but developers face barriers such as unfamiliarity with kernel practices and limited organizational connections.

### Source excerpt

Andres Freund has a few claims to fame, but chief among them is his many years of work to improve the performance of the PostgreSQL relational database management system. That work requires working with -- or around -- many Linux kernel features and behaviors. He put in an appearance at the 2026 edition of Kernel Recipes to talk about his experience working with the kernel project, how the kernel could better support applications like PostgreSQL, and some interesting developments in the PostgreSQL world.

## Isolate Untrusted Code Execution with Rootless Docker and gVisor

DevFeed: [Isolate Untrusted Code Execution with Rootless Docker and gVisor](<https://devfeed.tech/articles/isolate-untrusted-code-execution-with-rootless-docker-and-gvisor-59032.md>)

Original publisher: [Read original article](<https://www.sitepoint.com/isolate-untrusted-code-rootless-docker-gvisor/>)

Author: SitePoint Team

Published: 2026-09-23T18:15:43Z

Content type: tutorial

Language: en

Sources: [SitePoint](<https://devfeed.tech/sources/sitepoint.md>)

Topics: [Docker](<https://devfeed.tech/topics/docker.md>), [Kernel](<https://devfeed.tech/topics/kernel.md>), [cgroups](<https://devfeed.tech/topics/cgroups.md>), [Docker Compose](<https://devfeed.tech/topics/docker-compose.md>), [distroless](<https://devfeed.tech/topics/distroless.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>)

Tags: [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [cgroups](<https://devfeed.tech/tags/cgroups.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [distroless](<https://devfeed.tech/tags/distroless.md>), [docker](<https://devfeed.tech/tags/docker.md>), [docker-compose](<https://devfeed.tech/tags/docker-compose.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [programming](<https://devfeed.tech/tags/programming.md>), [sandboxing](<https://devfeed.tech/tags/sandboxing.md>), [web-security](<https://devfeed.tech/tags/web-security.md>)

### AI overview

A tutorial on isolating untrusted code in multi-tenant execution environments by combining rootless Docker with gVisor. It covers Linux kernel isolation risks, cgroups v2, seccomp, distroless images, Docker Compose, resource limits, and escape testing.

### Source excerpt

Harden your multi-tenant and AI code execution infrastructure by deploying rootless Docker paired with gVisor user-space kernel sandboxing. Continue reading Isolate Untrusted Code Execution with Rootless Docker and gVisor on SitePoint.

## Introducing YugabyteDB Resource Governance

DevFeed: [Introducing YugabyteDB Resource Governance](<https://devfeed.tech/articles/introducing-yugabytedb-resource-governance-80952.md>)

Original publisher: [Read original article](<https://www.yugabyte.com/introducing-yugabytedb-resource-governance/>)

Author: Kyle Hailey

Published: 2026-09-02T20:58:53Z

Content type: release

Language: en

Sources: [The Distributed SQL Blog](<https://devfeed.tech/sources/the-distributed-sql-blog.md>)

Topics: [database-optimization](<https://devfeed.tech/topics/database-optimization.md>), [cgroups](<https://devfeed.tech/topics/cgroups.md>), [cost-optimization](<https://devfeed.tech/topics/cost-optimization.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [isolation](<https://devfeed.tech/tags/isolation.md>), [resource-governance](<https://devfeed.tech/tags/resource-governance.md>), [yugabytedb](<https://devfeed.tech/tags/yugabytedb.md>)

### AI overview

YugabyteDB Resource Governance distributes CPU among databases sharing a cluster using Linux cgroups and elastic fair-share allocation. It accounts for foreground queries and associated background work, with optional CPU caps that limit consumption without reserving capacity. The article explains configuration and early-access availability, with general availability targeted for version 2026.2.

### Source excerpt

Discover how YugabyteDB Resource Governance helps organizations safely consolidate more databases on shared infrastructure without sacrificing predictable performance. Plus, learn how fair CPU sharing and workload controls prevent noisy neighbors, improve resource utilization, and provide the isolation needed to confidently run multi-tenant workloads at scale. The post Introducing YugabyteDB Resource Governance appeared first on Yugabyte.

## From Linux Primitives to Kubernetes Security Contexts

DevFeed: [From Linux Primitives to Kubernetes Security Contexts](<https://devfeed.tech/articles/from-linux-primitives-to-kubernetes-security-contexts-19144.md>)

Original publisher: [Read original article](<https://learnkube.com/security-contexts>)

Author: Dave Altena

Published: 2025-08-11T00:00:00Z

Content type: article

Language: en

Sources: [Learnk8s](<https://devfeed.tech/sources/learnk8s.md>)

Topics: [Security](<https://devfeed.tech/topics/security.md>), [container](<https://devfeed.tech/topics/container.md>), [Linux](<https://devfeed.tech/topics/linux.md>), [cgroups](<https://devfeed.tech/topics/cgroups.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [cgroups](<https://devfeed.tech/tags/cgroups.md>), [configure](<https://devfeed.tech/tags/configure.md>), [container](<https://devfeed.tech/tags/container.md>), [containers](<https://devfeed.tech/tags/containers.md>), [context](<https://devfeed.tech/tags/context.md>), [docker](<https://devfeed.tech/tags/docker.md>), [field](<https://devfeed.tech/tags/field.md>), [filesystem](<https://devfeed.tech/tags/filesystem.md>), [filesystems](<https://devfeed.tech/tags/filesystems.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [kubernetes-security](<https://devfeed.tech/tags/kubernetes-security.md>), [linux](<https://devfeed.tech/tags/linux.md>), [low-level](<https://devfeed.tech/tags/low-level.md>), [namespaces](<https://devfeed.tech/tags/namespaces.md>), [networking](<https://devfeed.tech/tags/networking.md>), [pods](<https://devfeed.tech/tags/pods.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

Containers in Kubernetes run as Linux processes on the host kernel, isolated with namespaces, cgroups, and a separate virtual filesystem. Kubernetes does not impose a non-root policy: the image's default user applies unless overridden. A pod's `securityContext` declaratively configures process behavior, but Kubernetes passes those settings to the container runtime, which maps them to kernel features. The excerpt identifies controls for choosing the container user, managing Linux capabilities, using read-only filesystems, and blocking privilege escalation; it explains that root access can increase host privilege-escalation risk if a container is compromised. The supplied text ends as it begins discussing syscalls, so it does not provide the configuration details or practical YAML steps.

### Source excerpt

Dive deep into Kubernetes Security Contexts and learn how to manage security settings for your pods and containers.

## What is a container?

DevFeed: [What is a container?](<https://devfeed.tech/articles/what-is-a-container-12539.md>)

Original publisher: [Read original article](<http://brooker.co.za/blog/2023/06/19/container.html>)

Author: Marc Brooker

Published: 2023-06-19T00:00:00Z

Content type: article

Language: en

Sources: [Marc Brooker's](<https://devfeed.tech/sources/marc-brooker-s-blog.md>)

Topics: [container](<https://devfeed.tech/topics/container.md>), [container images](<https://devfeed.tech/topics/container-images.md>), [container native](<https://devfeed.tech/topics/container-native.md>), [cgroups](<https://devfeed.tech/topics/cgroups.md>), [Linux Kernel](<https://devfeed.tech/topics/linux-kernel.md>)

Tags: [applications](<https://devfeed.tech/tags/applications.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-lambda](<https://devfeed.tech/tags/aws-lambda.md>), [cgroups](<https://devfeed.tech/tags/cgroups.md>), [container](<https://devfeed.tech/tags/container.md>), [container-image](<https://devfeed.tech/tags/container-image.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [development](<https://devfeed.tech/tags/development.md>), [docker](<https://devfeed.tech/tags/docker.md>), [ecs](<https://devfeed.tech/tags/ecs.md>), [isolation](<https://devfeed.tech/tags/isolation.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [linux](<https://devfeed.tech/tags/linux.md>), [namespaces](<https://devfeed.tech/tags/namespaces.md>), [operating-system](<https://devfeed.tech/tags/operating-system.md>), [packaging](<https://devfeed.tech/tags/packaging.md>), [practices](<https://devfeed.tech/tags/practices.md>), [security](<https://devfeed.tech/tags/security.md>), [semantics](<https://devfeed.tech/tags/semantics.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

"Container" can mean four related but independent things: packaging an application with dependencies for a minimal runtime; practices built around that packaging; operating-system isolation tools such as Linux chroot, cgroups, namespaces, and seccomp; or implementations such as Docker, Kubernetes, and ECS. Packaging predates the other categories, and practices do not require particular tools. Linux interfaces underpin many implementations, though the excerpt says most semantics can be provided in other ways. AWS Lambda's container image support mainly concerns packaging. The claim that containers are not a security boundary mainly concerns isolation tools and implementations, while packaging and related practices can benefit security. The practical advice is to clarify which meaning is intended.

### Source excerpt

What is a container? What are words, anyway? A common cause of confusion and miscommunication I see is different people using different definitions of words. Sometimes the definitions are subtly different (as with availability). Sometimes they're completely different, and we're just talking about different things entirely. A common example is the word container, a popular term for a popular technology that means at least four different things. An approach to packaging an application along with its dependencies (sometimes a whole operating system user space), that can then run on a minimal runtime environment with a clear contract4. A set of development, deployment, architectural, and operational approaches built around applications packaged this way. A set of operational, security, and performance isolation tools that allow multiple applications to share an operating system without interfering with each other. On Linux, this tools include chroot, cgroups, namespaces, seccomp, and others. A set of implementations of these practices (the proper nouns, Docker, Kubernetes, ECS, etc). These four definitions are surprisingly independent. The idea of packaging applications this way predates the other three, and will likely be around after they are gone. The practices and approaches are enabled by the tools, but don't really require them. The Linux kernel-level interfaces, and the semantics and security they provide, are a basis for many of the implementations today, but most of the semantics are available in different ways1. To pick an example, when we talk about container image support in AWS Lambda3 we mostly mean the first one: enabling customers to get the advantages of packaging their code that way, with a small overlap with practices (some become easier to use with this support available), and the fourth (some of these tools can be used to create the images in ways that fit into a broader ecosystem). Or, to pick another example, when people say containers are not a s

## On Bypassing eBPF Security Monitoring

DevFeed: [On Bypassing eBPF Security Monitoring](<https://devfeed.tech/articles/on-bypassing-ebpf-security-monitoring-92019.md>)

Original publisher: [Read original article](<https://blog.doyensec.com/2022/10/11/ebpf-bypass-security-monitoring.html>)

Published: 2022-10-10T22:00:00Z

Content type: article

Language: en

Sources: [Doyensec](<https://devfeed.tech/sources/doyensec.md>)

Topics: [eBPF](<https://devfeed.tech/topics/ebpf.md>), [Threat monitoring](<https://devfeed.tech/topics/threat-monitoring.md>), [Endpoint security](<https://devfeed.tech/topics/endpoint-security.md>), [observability](<https://devfeed.tech/topics/observability.md>), [cgroups](<https://devfeed.tech/topics/cgroups.md>)

Tags: [auditing](<https://devfeed.tech/tags/auditing.md>), [automation](<https://devfeed.tech/tags/automation.md>), [bypass](<https://devfeed.tech/tags/bypass.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [container](<https://devfeed.tech/tags/container.md>), [container-security](<https://devfeed.tech/tags/container-security.md>), [ddos](<https://devfeed.tech/tags/ddos.md>), [detection](<https://devfeed.tech/tags/detection.md>), [doyensec](<https://devfeed.tech/tags/doyensec.md>), [doyensecurity](<https://devfeed.tech/tags/doyensecurity.md>), [ebpf](<https://devfeed.tech/tags/ebpf.md>), [execution](<https://devfeed.tech/tags/execution.md>), [exploit](<https://devfeed.tech/tags/exploit.md>), [feature](<https://devfeed.tech/tags/feature.md>), [hacking](<https://devfeed.tech/tags/hacking.md>), [infosec](<https://devfeed.tech/tags/infosec.md>), [intrusion-detection](<https://devfeed.tech/tags/intrusion-detection.md>), [kernel](<https://devfeed.tech/tags/kernel.md>), [linux](<https://devfeed.tech/tags/linux.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [network](<https://devfeed.tech/tags/network.md>), [observability](<https://devfeed.tech/tags/observability.md>), [offensive](<https://devfeed.tech/tags/offensive.md>), [pentest](<https://devfeed.tech/tags/pentest.md>), [pentester](<https://devfeed.tech/tags/pentester.md>), [performance](<https://devfeed.tech/tags/performance.md>), [reverse-engineering](<https://devfeed.tech/tags/reverse-engineering.md>), [security](<https://devfeed.tech/tags/security.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>)

### AI overview

eBPF monitoring can miss activity when its hooks, event scope, or data capture are incomplete. The excerpt describes execution bypasses such as userland process-image replacement that avoids `execve`, unmonitored syscall variants, and misleading executable paths; network gaps from monitoring only egress or overlooking socket operations; and delayed commands or process reparenting that can escape session or cgroup tracking. It also identifies truncated or dropped events under BPF stack, loop, and ring-buffer limits, plus risks from changing file descriptors and working directories. Defenses discussed include auditing which events and kernel versions an agent covers, correlating sessions carefully, using seccomp-BPF to restrict later `bpf()` calls with architecture-aware syscall checks, and protecting BPF loader libraries and runtime environments. The article notes that exposure depends on agent design and kernel constraints; the supplied text is an excerpt.

### Source excerpt

There are many security solutions available today that rely on the Extended Berkeley Packet Filter (eBPF) features of the Linux kernel to monitor kernel functions. Such a paradigm shift in the latest monitoring technologies is being driven by a variety of reasons. Some of them are motivated by performance needs in an increasingly cloud-dominated world, among others. The Linux kernel always had kernel tracing capabilities such as kprobes (2.6.9), ftrace (2.6.27 and later), perf (2.6.31), or uprobes (3.5), but with BPF it's finally possible to run kernel-level programs on events and consequently modify the state of the system, without needing to write a kernel module. This has dramatic implications for any attacker looking to compromise a system and go undetected, opening new areas of research and application. Nowadays, eBFP-based programs are used for DDoS mitigations, intrusion detection, container security, and general observability. In 2021 Teleport introduced a new feature called Enhanced Session Recording to close some monitoring gaps in Teleport's audit abilities. All issues reported have been promptly fixed, mitigated or documented as described in their public Q4 2021 report. Below you can see an illustration of how we managed to bypass eBPF-based controls, along with some ideas on how red teams or malicious actors could evade these new intrusion detection mechanisms. These techniques can be generally applied to other targets while attempting to bypass any security monitoring solution based on eBPF: A few words on how eBPF works Common shortcomings & potential bypasses (here be dragons) 1. Understand which events are caught 1.1 Execution bypasses 1.2 Network bypasses 2. Delayed execution 3. Evade scoped event monitoring based on cgroup 4. Memory limits and loss of events 5. Never trust the userspace 6. Abuse the lack of seccomp-bpf & kernel discrepancies 7. Interfere with the agents A few words on how eBPF works Extended BPF programs are written in a high-leve

## Kubernetes Limits: Mastering CPU and Memory Constraints

DevFeed: [Kubernetes Limits: Mastering CPU and Memory Constraints](<https://devfeed.tech/articles/kubernetes-limits-mastering-cpu-and-memory-constraints-80037.md>)

Original publisher: [Read original article](<https://www.groundcover.com/blog/kubernetes-limits>)

Author: Noam Levy

Published: 2022-06-15T00:00:00Z

Content type: tutorial

Language: en

Sources: [Ground Cover](<https://devfeed.tech/sources/ground-cover.md>)

Topics: [cgroups](<https://devfeed.tech/topics/cgroups.md>)

Tags: [auto-scaling](<https://devfeed.tech/tags/auto-scaling.md>), [autoscaling](<https://devfeed.tech/tags/autoscaling.md>), [cpu-throttling](<https://devfeed.tech/tags/cpu-throttling.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [limits](<https://devfeed.tech/tags/limits.md>), [memory](<https://devfeed.tech/tags/memory.md>)

### AI overview

The article explains how Kubernetes CPU and memory requests and limits affect scheduling, resource isolation, throttling, memory-related container termination, and workload reliability. It recommends basing settings on observed workload patterns, warns that CPU limits can degrade performance for spiky workloads, and discusses QoS classes, namespace quotas, monitoring, and autoscaling.

### Source excerpt

Understand Kubernetes limits and their role in optimizing CPU and memory usage, while effectively managing dynamic workloads

[Next page](<https://devfeed.tech/topics/cgroups.md?cursor=WyIyMDIyLTA2LTE1VDAwOjAwOjAwKzAwOjAwIiwgIjg2MTZiZTcwLTFlMWYtNGUwZS1iMzIxLTk0Y2Q4OGEwNjg3OCJd>)