[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250713001942027bne2UhpkDuiSVPMxA3LZj@zte.com.cn>
Date: Sun, 13 Jul 2025 00:19:42 +0800 (CST)
From: <yang.yang29@....com.cn>
To: <wang.yaxin@....com.cn>, <fan.yu9@....com.cn>
Cc: <bsingharora@...il.com>, <akpm@...ux-foundation.org>, <david@...hat.com>,
<linux-kernel@...r.kernel.org>, <linux-mm@...ck.org>,
<linux-doc@...r.kernel.org>, <wang.yong12@....com.cn>,
<he.peilin@....com.cn>, <tu.qiang35@....com.cn>,
<qiu.yutan@....com.cn>, <zhang.yunkai@....com.cn>,
<xu.xin16@....com.cn>, <jiang.kun2@....com.cn>
Subject: Re: [PATCH linux next] delaytop: add psi info to show system delay
> bash# ./delaytop
> System Pressure Information: (avg10/avg60/avg300/total)
> CPU: full: 0.0%/ 0.0%/ 0.0%/0 some: 0.1%/ 0.0%/ 0.0%/14216596
> Memory: full: 0.0%/ 0.0%/ 0.0%/34010659 some: 0.0%/ 0.0%/ 0.0%/35406492
> IO: full: 0.1%/ 0.0%/ 0.0%/51029453 some: 0.1%/ 0.0%/ 0.0%/55330465
> IRQ: full: 0.0%/ 0.0%/ 0.0%/0
I see the unit of PSI and task delay are different, they are microseconds
and milliseconds. We'd better keep the units aligned for better user
understanding.
And what about split the output of each delay into different lines just as
PSI, this help us to better compare the results of some and full.
bash# cat /proc/pressure/cpu
some avg10=0.00 avg60=0.00 avg300=0.00 total=682581546
full avg10=0.00 avg60=0.00 avg300=0.00 total=0
For example:
bash# ./delaytop
System Pressure Information: (avg10/avg60/avg300/total)
CPU some: 0.1%/ 0.0%/ 0.0%/14216596
CPU full: 0.0%/ 0.0%/ 0.0%/0
Memory some: 0.0%/ 0.0%/ 0.0%/35406492
Memory full: 0.0%/ 0.0%/ 0.0%/34010659
Powered by blists - more mailing lists