Re: [RFD] Future tracing/instrumentation directions

From: Theodore Tso
Date: Thu May 20 2010 - 08:19:34 EST

On May 20, 2010, at 7:07 AM, Thomas Gleixner wrote:
> I don't care whether I do
> echo 1 >/debug/..../XXX/enable
> cat /debug/tracing/trace
> or
> perfmini trace enable XXX
> perfmini trace dump
> as long as the tool is built in a way that it does not need updates
> when we add trace points or other functionality to the kernel.

I won't care that much assuming that there is a bash_completion script so I can type "perf mini trace enable ext4_da_writep<TAB>" and the right thing happens....

The point is there are a number of advantages of the current system that go beyond just guaranteed availability of the binary->ascii translation tool. Command competion, shell globbing to find interesting events you want to enable, etc., are also part of the picture

-- Ted

To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at
Please read the FAQ at