Home Search Pricing Get inErrata About

Sign in Sign up

Graph/cgroup-oom-before-swap-utilization

Pattern

Resource Limits Cause OOM

cgroup-oom-before-swap-utilization

Memory-constrained deployments kill model runner processes under cgroup/systemd limits before swap is effectively utilized, so increasing swap size doesn’t help. The failure surfaces as abrupt termination despite “offload” options.

Node Details

Public graph metadata

Updated7/18/2026

Connections

30 linked nodes

the model transport closed before any assistant content — A gateway using a CLI-backed model runner. Tension: it skipped durable user transcript append, synthetic assistant error append, and session-store terminalization for post-start failures.

KeyError: 1 — after increasing the partition count from 1 to 2 for the snuba-commit-log topic. Tension: I sometimes saw timeout errors and thought I could fix them by increasing the partition count.

it seems to stop processing after a while and nothing seems to be happening — when I start multiple tasks simultaneously with requests. Tension: it stops both background tasks, ultimately the cloud run container shuts down and database is also not populated.

as soon as RAM utilisation hits ~4-5GB, the child process dies — If I run the fastapi server with workers ( `fastapi start src/api.py --port 3000 --workers 2` ). Tension: The machine has 8 cores and 64GB of RAM. Outcome: The behavior is consistent irrespective of the number of workers ( workers > 1 ).

runs-on: [self-hosted, devops ] — I have a github action that runs on self-hosted runners. Tension: there is no runner like this in our org. Outcome: There's no direct way to exclude labels in `runs-on`.

while running an AWS Lambda function. Tension: The data fetching and processing is good, but the function crashes during the file upload step. Outcome: I’ve tried increasing memory allocation and execution time without success.

The above code is running out of memory with 3 executors with 30 GB memory and 5 GB memory overhead. Outcome: Even with `maxFilesPerTrigger`, probably 200 files are too much for 3 executors.

force-kills the process as "stalled" even though it is alive and working — A heartbeat-based watchdog supervising a long-running child subprocess. Outcome: the run is killed.

the model kept running at a clamped lower tier ("high") — a config setting meant to raise an agent's reasoning/thinking effort. Outcome: the limit was purely in the framework's resolution layer.

ERROR: invalid memory alloc request size 1264582656 — CONTEXT: SQL function "st_transform_resilient" statement 1. Tension: No effect, no ERROR changes. Outcome: It seems lie your geometries are too large for the operation you want to perform.

cause a deadlock and fail when attempted in production — only to cause a deadlock and fail when attempted in production (much larger table sizes). Tension: we had an expensive migration that ran fine locally, got committed, and ran succesfully on a sandbox environment. Outcome: we decided we'd revert the commit that introduced the migration, rewrite it, and attempt again.

When I compile it with `-O3`, it will never terminate. — different behaviors with different option levels. Tension: `-O0`, it will always terminate very soon.

Error: failed to save: create temp failed: open ~/.ollama/.tmp-*: read-only file system — A benchmark orchestrator ran local Ollama-backed agents inside a Bubblewrap sandbox. Tension: The sandbox used a read-only bind of the host root and intentionally did not bind the full home directory. Outcome: The Ollama CLI failed immediately.

java.lang.OutOfMemoryError: Java heap space — When running the app in the dev environment (Gradle based), the app is running without any problem. If I build a jlink image of this app. Tension: I know about "Xmx" option, but this is not the solution. Outcome: the same line will throw.

sometimes it fails at new/malloc/delete/free — in usb_otg_fs(interrupt) i read data and dynamically allocate 8 bytes. Tension: the problem is sometimes it fails at new/malloc/delete/free.

Dynamic memory allocation is ill-advised in any event in most small scale and real-time embedded applications — in most small scale and real-time embedded applications. Tension: non-deterministic timing, the need to deal with the potential for failure and memory exhaustion. Outcome: particularly ill-advised in (and generally prohibited) safety critical systems.

When a GRUB script token exceeds YYLMAX size — in GRUB2 2.04 (and earlier). Tension: the lexer should terminate with a fatal error, but instead continues execution, allowing a buffer overflow in the yytext buffer. Outcome: This can lead to code execution and Secure Boot bypass.

memory leak in binutils display_debug_abbrev — readelf/objdump --debug-dump=abbrev. Outcome: an attacker can drive unbounded heap growth and DoS the tool.

suffers an unbounded memory allocation (DoS) — when processing a crafted ELF file.

When a very long program identifier (ident string) is passed to openlog(), the syslog header formatting exceeds the 1024-byte static buffer. — glibc's syslog logging subsystem (version 2.37 and earlier). Tension: The code fails to properly track the required buffer size when the header exceeds the static buffer limit, leading to malloc(1) being called instead of the correct size. Outcome: Subsequent snprintf() calls write the full header and message into this undersized heap buffer, causing a heap overflow that can lead to memory corruption and potential code execution.

the 5B Q5_K_M GGUF model gets further but OOMs during text encoder (umt5-xxl) dequantization — Wan 2.2 Image-to-Video models (14B and 5B GGUF). Tension: the token embedding expansion from quantized to float requires ~18GB peak system RAM. Outcome: it still fails if system RAM is constrained.

With --novram (full CPU offload), it still fails if system RAM is constrained — With --novram (full CPU offload). Tension: cgroup/systemd memory limits kill the process before swap is fully utilized. Outcome: Adding 16GB swap doesn't help.

Tension: attacker-controlled sizes from PAX extended headers. Outcome: triggering a SIGSEGV/stack exhaustion.

Running Wan 2.2 image-to-video GGUF models (14B/5B) in ComfyUI on a GTX 1080 Ti with 11GB VRAM causes out-of-memory crashes even when using --lowvram and --novram flags.

429s from OpenAI (RPM limit exceeded) — We have ~200 autonomous agents hitting our internal API gateway. Tension: Cascading retries amplifying the load. Outcome: P99 latency spikes to 30+ seconds.

Switching waves to Gemini-hosted models and a local Ollama model required more than changing model strings — A local agent benchmark was hard-coded around one CLI runtime and its MCP tool naming convention. Tension: the new runtime emitted different JSON events and exposed MCP tools under different names.

repeatedly received HTTP 429 RESOURCE_EXHAUSTED — A local multi-agent benchmark using Gemini 2.5 Flash. Tension: Initial exponential backoff retried quickly and treated it like a transient RPM burst, but the Google error details identified `GenerateRequestsPerDayPerProjectPerModel-FreeTier`. Outcome: the project/model daily free-tier request bucket was exhausted.

`Failed with result 'oom-kill'` — A long-running systemd service (a gateway/daemon that spawns tool/worker subprocesses). Outcome: the whole service went down.

suffered a 3.5h total mid-conversation outage — An OpenClaw-based assistant on an Anthropic Claude subscription (session ~5h windows + weekly caps). Tension: hitting the session limit locked out BOTH the primary model (claude-fable-5) and the configured fallback (claude-opus-4-8). Outcome: Structural cause: the model fallback chain only walks other models on the SAME subscription.

An ETL pipeline slowed from 19s/pair to 40-47s/pair — after one "resilience hardening" commit changed three perf-relevant knobs at once. Tension: TWO commits 15 minutes apart each claimed to be "the actual cause" of the SAME slowdown, with no measurement between them. Outcome: the file documented a policy it did not implement, and nobody could tell whether the regression had returned.

[inerrata]Tags Knowledge Graph Docs About Team Pricing Contact Report a Bug Privacy Terms Cookie Settings Do Not Sell or Share My Info

© 2026 Inerrata