On Thu, 19 Jun 2025 21:18:43 +0800 (CST) <jiang.kun2@xxxxxxxxxx> wrote: > From: Yaxin Wang <wang.yaxin@xxxxxxxxxx> > > Problem > ======= > The "getdelays" can only display the latency of a single task > by specifying a PID, but it has the following limitations: > 1. single-task perspective: only supports querying the > latency (CPU, I/O, memory, etc.) of an individual task via > PID and cannot provide a global analysis of high-latency > processes across the system. > 2. lack of High-Latency process awareness: when the overall > system latency is high (e.g., a spike in CPU latency), there > is no way to quickly identify the top N processes contributing > to the highest latency. > 3. poor interactivity: It lacks dynamic sorting and refresh > capabilities (similar to top), making it difficult to monitor > latency changes in real time. > > Solution > ======== > To address these limitations, we introduce the "delaytop" with > the following capabilities: > 1. system view: monitors latency metrics (CPU, I/O, memory, IRQ, > etc.) for all system processes > 2. supports field-based sorting (e.g., default sort by CPU latency > in descending order) > 3. dynamic interactive interface: > focus on specific processes with --pid; > limit displayed entries with --processes 20; > control monitoring duration with --iterations; > > Use case > ======== > bash# ./delaytop Looks nice, thanks. > tools/accounting/Makefile | 2 +- > tools/accounting/delaytop.c | 673 ++++++++++++++++++++++++++++++++++++ > 2 files changed, 674 insertions(+), 1 deletion(-) > create mode 100644 tools/accounting/delaytop.c Some documentation would be nicer ;) hp2:/usr/src/25> grep -rli getdelays Documentation Documentation/translations/zh_CN/accounting/delay-accounting.rst Documentation/translations/zh_CN/accounting/taskstats.rst Documentation/accounting/delay-accounting.rst Documentation/accounting/cgroupstats.rst Documentation/accounting/taskstats.rst
