<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: tanelpoder</title><link>https://news.ycombinator.com/user?id=tanelpoder</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 14 Oct 2026 13:59:58 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=tanelpoder" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by tanelpoder in "Norway should buy OpenAI"]]></title><description><![CDATA[
<p>Norway is not part of EU (if by EU you meant European Union, not just a country in Europe)</p>
]]></description><pubDate>Tue, 18 Aug 2026 20:46:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=49352460</link><dc:creator>tanelpoder</dc:creator><comments>https://news.ycombinator.com/item?id=49352460</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49352460</guid></item><item><title><![CDATA[New comment by tanelpoder in "How Do I Profile eBPF Code?"]]></title><description><![CDATA[
<p>Last month I wrote a tool called "brr" - eBPF Runtime Reporter and Profiler. It displays a <i>bpftop</i>-like eBPF program summary, but you can also zoom into any program to see its source code lines (if available) and profile the eBPF program activity and any kernel code activity called/caused by the eBPF program for the full picture of where your eBPF program time/latency is spent.<p>I wrote it mostly with Codex for my own use, but just pushed the latest release to GitHub (with screenshots) in case anyone else is interested:<p><a href="https://github.com/tanelpoder/brr" rel="nofollow">https://github.com/tanelpoder/brr</a></p>
]]></description><pubDate>Tue, 28 Jul 2026 18:30:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=49087986</link><dc:creator>tanelpoder</dc:creator><comments>https://news.ycombinator.com/item?id=49087986</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49087986</guid></item><item><title><![CDATA[Characterizing Metastable Faults and Failures]]></title><description><![CDATA[
<p>Article URL: <a href="http://muratbuffalo.blogspot.com/2026/07/characterizing-metastable-faults-and.html">http://muratbuffalo.blogspot.com/2026/07/characterizing-metastable-faults-and.html</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=49010226">https://news.ycombinator.com/item?id=49010226</a></p>
<p>Points: 6</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 22 Jul 2026 17:23:43 +0000</pubDate><link>http://muratbuffalo.blogspot.com/2026/07/characterizing-metastable-faults-and.html</link><dc:creator>tanelpoder</dc:creator><comments>https://news.ycombinator.com/item?id=49010226</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49010226</guid></item><item><title><![CDATA[Benchmarking coding agents on Databricks' multi-million line codebase]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.databricks.com/blog/benchmarking-coding-agents-databricks-multi-million-line-codebase">https://www.databricks.com/blog/benchmarking-coding-agents-databricks-multi-million-line-codebase</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48837696">https://news.ycombinator.com/item?id=48837696</a></p>
<p>Points: 161</p>
<p># Comments: 69</p>
]]></description><pubDate>Wed, 08 Jul 2026 21:30:09 +0000</pubDate><link>https://www.databricks.com/blog/benchmarking-coding-agents-databricks-multi-million-line-codebase</link><dc:creator>tanelpoder</dc:creator><comments>https://news.ycombinator.com/item?id=48837696</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48837696</guid></item><item><title><![CDATA[High-cardinality metrics at scale: why the standard playbook is wrong]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.netdata.cloud/blog/high-cardinality-metrics-observability-scale/">https://www.netdata.cloud/blog/high-cardinality-metrics-observability-scale/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48832475">https://news.ycombinator.com/item?id=48832475</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 08 Jul 2026 14:30:32 +0000</pubDate><link>https://www.netdata.cloud/blog/high-cardinality-metrics-observability-scale/</link><dc:creator>tanelpoder</dc:creator><comments>https://news.ycombinator.com/item?id=48832475</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48832475</guid></item><item><title><![CDATA[HammerDB v6.0 Response Times, Percentiles and Reservoir Sampling]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.hammerdb.com/blog/uncategorized/hammerdb-v6-0-response-times-percentiles-and-reservoir-sampling/">https://www.hammerdb.com/blog/uncategorized/hammerdb-v6-0-response-times-percentiles-and-reservoir-sampling/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48778462">https://news.ycombinator.com/item?id=48778462</a></p>
<p>Points: 4</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 03 Jul 2026 18:45:28 +0000</pubDate><link>https://www.hammerdb.com/blog/uncategorized/hammerdb-v6-0-response-times-percentiles-and-reservoir-sampling/</link><dc:creator>tanelpoder</dc:creator><comments>https://news.ycombinator.com/item?id=48778462</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48778462</guid></item><item><title><![CDATA[Observability Engineering book, 2nd Edition [pdf]]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.honeycomb.io/observability-engineering-oreilly-book">https://www.honeycomb.io/observability-engineering-oreilly-book</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48719611">https://news.ycombinator.com/item?id=48719611</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 29 Jun 2026 14:19:32 +0000</pubDate><link>https://www.honeycomb.io/observability-engineering-oreilly-book</link><dc:creator>tanelpoder</dc:creator><comments>https://news.ycombinator.com/item?id=48719611</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48719611</guid></item><item><title><![CDATA[Cramming 1M (Scaled to Zero) Virtual Machines in a Single Box]]></title><description><![CDATA[
<p>Article URL: <a href="https://unikraft.com/blog/1m-vms-single-box/">https://unikraft.com/blog/1m-vms-single-box/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48709259">https://news.ycombinator.com/item?id=48709259</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 28 Jun 2026 17:04:22 +0000</pubDate><link>https://unikraft.com/blog/1m-vms-single-box/</link><dc:creator>tanelpoder</dc:creator><comments>https://news.ycombinator.com/item?id=48709259</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48709259</guid></item><item><title><![CDATA[rdmatop: Cross-Provider Htop for RDMA Traffic]]></title><description><![CDATA[
<p>Article URL: <a href="https://uccl-project.github.io/posts/rdma-monitoring/">https://uccl-project.github.io/posts/rdma-monitoring/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48699996">https://news.ycombinator.com/item?id=48699996</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 27 Jun 2026 17:20:26 +0000</pubDate><link>https://uccl-project.github.io/posts/rdma-monitoring/</link><dc:creator>tanelpoder</dc:creator><comments>https://news.ycombinator.com/item?id=48699996</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48699996</guid></item><item><title><![CDATA[Apache Kafka's log compaction corrupts data]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.redpanda.com/blog/kafka-log-compaction-bug-fix-streaming">https://www.redpanda.com/blog/kafka-log-compaction-bug-fix-streaming</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48691190">https://news.ycombinator.com/item?id=48691190</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 26 Jun 2026 19:52:11 +0000</pubDate><link>https://www.redpanda.com/blog/kafka-log-compaction-bug-fix-streaming</link><dc:creator>tanelpoder</dc:creator><comments>https://news.ycombinator.com/item?id=48691190</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48691190</guid></item><item><title><![CDATA[A MCP server that supports mainstream eBook formats including ePub, PDF and more]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/onebirdrocks/ebook-mcp">https://github.com/onebirdrocks/ebook-mcp</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48689233">https://news.ycombinator.com/item?id=48689233</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 26 Jun 2026 17:21:44 +0000</pubDate><link>https://github.com/onebirdrocks/ebook-mcp</link><dc:creator>tanelpoder</dc:creator><comments>https://news.ycombinator.com/item?id=48689233</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48689233</guid></item><item><title><![CDATA[Silk is a stackful-fiber library, scheduler with a work-stealing loop, io_uring]]></title><description><![CDATA[
<p>Article URL: <a href="https://clickhouse.com/blog/silk">https://clickhouse.com/blog/silk</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48688618">https://news.ycombinator.com/item?id=48688618</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 26 Jun 2026 16:34:34 +0000</pubDate><link>https://clickhouse.com/blog/silk</link><dc:creator>tanelpoder</dc:creator><comments>https://news.ycombinator.com/item?id=48688618</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48688618</guid></item><item><title><![CDATA[Packet_edit_meme page cache poisoning vulnerability (CVE-2026-46331)]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/sgkdev/packet_edit_meme">https://github.com/sgkdev/packet_edit_meme</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48688054">https://news.ycombinator.com/item?id=48688054</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 26 Jun 2026 15:49:11 +0000</pubDate><link>https://github.com/sgkdev/packet_edit_meme</link><dc:creator>tanelpoder</dc:creator><comments>https://news.ycombinator.com/item?id=48688054</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48688054</guid></item><item><title><![CDATA[Modern GPU Programming for MLSys Book]]></title><description><![CDATA[
<p>Article URL: <a href="https://mlc.ai/modern-gpu-programming-for-mlsys/">https://mlc.ai/modern-gpu-programming-for-mlsys/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48682645">https://news.ycombinator.com/item?id=48682645</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 26 Jun 2026 05:27:03 +0000</pubDate><link>https://mlc.ai/modern-gpu-programming-for-mlsys/</link><dc:creator>tanelpoder</dc:creator><comments>https://news.ycombinator.com/item?id=48682645</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48682645</guid></item><item><title><![CDATA[OpenAI will delay GPT-5.6 after Trump administration request]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.theverge.com/ai-artificial-intelligence/957372/openai-will-delay-gpt-5-6-after-trump-administration-request">https://www.theverge.com/ai-artificial-intelligence/957372/openai-will-delay-gpt-5-6-after-trump-administration-request</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48680194">https://news.ycombinator.com/item?id=48680194</a></p>
<p>Points: 36</p>
<p># Comments: 2</p>
]]></description><pubDate>Thu, 25 Jun 2026 22:49:33 +0000</pubDate><link>https://www.theverge.com/ai-artificial-intelligence/957372/openai-will-delay-gpt-5-6-after-trump-administration-request</link><dc:creator>tanelpoder</dc:creator><comments>https://news.ycombinator.com/item?id=48680194</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48680194</guid></item><item><title><![CDATA[Direct I/O for Cassandra Compaction: Cutting p99 Read Latency by 5x]]></title><description><![CDATA[
<p>Article URL: <a href="https://lightfoot.dev/direct-i-o-for-cassandra-compaction-cutting-p99-read-latency-by-5x/">https://lightfoot.dev/direct-i-o-for-cassandra-compaction-cutting-p99-read-latency-by-5x/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48676274">https://news.ycombinator.com/item?id=48676274</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 25 Jun 2026 17:01:30 +0000</pubDate><link>https://lightfoot.dev/direct-i-o-for-cassandra-compaction-cutting-p99-read-latency-by-5x/</link><dc:creator>tanelpoder</dc:creator><comments>https://news.ycombinator.com/item?id=48676274</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48676274</guid></item><item><title><![CDATA[Show HN: Profiler and Runtime Reporter for eBPF programs (brr)]]></title><description><![CDATA[
<p>Here's something I've been using for eBPF program profiling & optimization purposes and just published it as it has made my "performance nerd life" easier.<p>This is a tool for profiling eBPF programs themselves, probe->kernel activity, interactions with shared hash maps, etc.<p>Since eBPF programs are pieces of machine code residing in (kernel) address space, you could profile them with standard perf just like any other kernel function. However, perf alone won't show you other useful metrics like number of executions and average eBPF program runtime, like <i>bpftop</i> does. Also, I want an easy way to map CPU samples to original source code lines, where possible.<p>I wanted to <i>unify</i> both approaches, display the bpftop-style call count & probe latency, with the ability to drill down inside where the eBPF program spends most of it's time.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48582232">https://news.ycombinator.com/item?id=48582232</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 18 Jun 2026 07:57:17 +0000</pubDate><link>https://github.com/tanelpoder/brr/</link><dc:creator>tanelpoder</dc:creator><comments>https://news.ycombinator.com/item?id=48582232</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48582232</guid></item><item><title><![CDATA[Learning VPP: Filtering Packets at 100GbE Line Rate]]></title><description><![CDATA[
<p>Article URL: <a href="https://haryachyy.wordpress.com/2026/06/17/vpp-packet-filtering-100gbe-line-rate/">https://haryachyy.wordpress.com/2026/06/17/vpp-packet-filtering-100gbe-line-rate/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48579714">https://news.ycombinator.com/item?id=48579714</a></p>
<p>Points: 3</p>
<p># Comments: 1</p>
]]></description><pubDate>Thu, 18 Jun 2026 02:08:28 +0000</pubDate><link>https://haryachyy.wordpress.com/2026/06/17/vpp-packet-filtering-100gbe-line-rate/</link><dc:creator>tanelpoder</dc:creator><comments>https://news.ycombinator.com/item?id=48579714</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48579714</guid></item><item><title><![CDATA[Hands-On with Flink: Calling LLMs from Flink]]></title><description><![CDATA[
<p>Article URL: <a href="https://medium.com/@katyagorshkova/hands-on-with-flink-part-6-calling-llms-from-flink-e5cc7e5f0440">https://medium.com/@katyagorshkova/hands-on-with-flink-part-6-calling-llms-from-flink-e5cc7e5f0440</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48527963">https://news.ycombinator.com/item?id=48527963</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 14 Jun 2026 15:09:43 +0000</pubDate><link>https://medium.com/@katyagorshkova/hands-on-with-flink-part-6-calling-llms-from-flink-e5cc7e5f0440</link><dc:creator>tanelpoder</dc:creator><comments>https://news.ycombinator.com/item?id=48527963</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48527963</guid></item><item><title><![CDATA[Glacial Valley]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/deedy/glacial-valley">https://github.com/deedy/glacial-valley</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48510629">https://news.ycombinator.com/item?id=48510629</a></p>
<p>Points: 5</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 12 Jun 2026 23:33:56 +0000</pubDate><link>https://github.com/deedy/glacial-valley</link><dc:creator>tanelpoder</dc:creator><comments>https://news.ycombinator.com/item?id=48510629</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48510629</guid></item></channel></rss>