Date: Fri, 24 Dec 2021 15:08:08 +0200 From: Andriy Gapon <avg@FreeBSD.org> To: FreeBSD Current <current@FreeBSD.org>, FreeBSD Hackers <hackers@freebsd.org> Subject: schedgraph.d experience, per-CPU buffers, pipes Message-ID: <02d9ca2a-2fd7-942b-f411-be007ef88327@FreeBSD.org>
next in thread | raw e-mail | index | archive | help
I would like to share some experience or maybe rather a warning about using
DTrace for tracing scheduling events. Unlike KTR which has a global circular
buffer, DTrace with bufpolicy=ring uses per-CPU circular buffers. So, if there
is an asymmetry in processor load, the buffers will fill and wrap-around at
different speeds. In the end, they might have approximately equal numbers of
events but those may cover very different time intervals. So, some additional
post-processing is required to find the latest event among first ones of each
per-CPU buffer. Any traces from before that would have information gaps
("missing" processors) and would be very confusing.
Also, I noticed that processes passing a lot of data through pipes produce a lot
of scheduling events as they seem to get blocked and unlocked every few
microseconds (on a modern performant system with the default pipe sizing
configuration). That contributes to a quick wrap-around of circular buffers.
--
Andriy Gapon
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?02d9ca2a-2fd7-942b-f411-be007ef88327>