<!DOCTYPE html>
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
</head>
<body>
<blockquote type="cite"
cite="mid:CA+TuoW3uB+J5dxQjZCTkvdJXrG1VYY2Hh+2dWdcV3eWd=J_3qA@mail.gmail.com">
<div dir="ltr">
<div class="gmail_quote gmail_quote_container">
<blockquote class="gmail_quote"
style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><br>
> > What about syscall load?<br>
> ><br>
> <br>
> Do you mean as reported by the time command?<br>
> Or do you mean something else?<br>
<br>
I believe this would be reported by the strace command,
tracking<br>
read and write syscalls. My theory is that with a varying
blocksizes,<br>
it will impact the number of trips into kernel space, and
therefore<br>
CPU load.<br>
<br>
A fast machine may be able to keep up with, and saturate,
available<br>
disk bandwidth. So even with the same throughput, CPU load
and syscall<br>
counts may differ. If so, then a slower machine may care
about blocksize.<br>
</blockquote>
</div>
<div><br clear="all">
</div>
<div style="font-size:small" class="gmail_default">That makes
perfect sense: the more round trips into the kernel and out</div>
<div style="font-size:small" class="gmail_default">the more CPU
utilization.</div>
<div style="font-size:small" class="gmail_default"><br>
</div>
<div style="font-size:small" class="gmail_default">I just
thought that "syscall load" is a metric that can be displayed
by some</div>
<div style="font-size:small" class="gmail_default">utility, like
load average, hence the question.<br>
</div>
</div>
</blockquote>
<p>glances has IOWAIT showing way often. And of course, that wait is
inside of a<br>
syscall (probably ?), but it points to culprit -- device
operations.<br>
</p>
</body>
</html>