Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 08 Oct 2013 14:56:53 -0500
From:      Pedro Giffuni <pfg@FreeBSD.org>
To:        dtrace@FreeBSD.org
Subject:   Dtrace providers wanted list
Message-ID:  <52546385.2050203@FreeBSD.org>

next in thread | raw e-mail | index | archive | help
Hello;

Sometime ago I looked around the list of Oracle's DTrace providers.

https://wikis.oracle.com/display/DTrace/Providers

We absolutely want them and although extremely useful as it is, DTrace 
won't be complete until we have them all ;). For the time being we 
should probably focus on getting the really critical ones though.

The first in the list that we don't have that I think is critical is 
mentioned in Brendan Gregg's FreeBSD specific blog post:

http://dtrace.org/blogs/brendan/2013/09/25/the-use-method-freebsd-performance-checklist/

"Tracing paging is tricker until the vminfo provider is added; you could 
try tracing from swap_pager_putpages() and swap_pager_getpages(), but I 
didn’t see an easy way to walk back to a thread struct; another approach 
may be via vm_fault_hold(). Good luck. ..."


Next in the list would be a scsi provider. I came out with this 
introductory post to the scsi list a while ago:

http://docs.freebsd.org/cgi/mid.cgi?51870B8F.5040306

There is more documentation on the net for the specific iscsi provider. 
For example:

http://dtrace.org/blogs/ahl/2007/07/04/iscsi-dtrace-provider-and-more-to-come/
http://www.solarisinternals.com/wiki/index.php/DTrace_Topics_iSCSI


The third critical provider that IMHO we must have is the CPU 
Performance Counter (CPC) Provider:
https://blogs.oracle.com/jonh/entry/finally_dtrace_meets_the_cpu

This is closely related to pmc(3) but obviously our implementation is 
completely different from the Solaris one.


Well, just though I should share the above links in the hope of 
motivating more DTrace provider porting. At this time our base Dtrace 
port is pretty good but we have the chicken and egg problem where 
developers don't know how useful DTrace really is because there is no 
provider for their code.

Cheers,

Pedro.



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?52546385.2050203>