[Ksummit-2008-discuss] DTrace

Matthew Wilcox matthew at wil.cx
Fri Jun 27 08:50:18 PDT 2008


On Fri, Jun 27, 2008 at 10:23:33AM -0500, James Bottomley wrote:
> DTrace is more a piece of sun marketing coolaid which they use to beat
> us up at every opportunity.

Sure.  And it's working, even amongst open source people who're supposed
to be immune to marketing ;-)

> We actually have a reasonably functional equivalent piece of technology
> called systemtap.
> 
> When I go around end users, I find people in two camps:  The ones who've
> drunk the sun coolaid and won't take anything on linux that isn't a
> fully replicated dtrace (sort of like windows people who demand the
> availability of outlook on linux) and people who are migrating to Linux
> and trying to use systemtap for tracing.  These latter seem to have a
> number of genuine concerns including latency, the time it takes to
> actually go from command executing to functional trace, the inability to
> trace user programs (dtrace can) and concerns about the amount of
> perturbation the probes actually place inside the kernel.

The ability to trace userspace programs is the key one for the postgres
people.  They get reports saying how long queries took to execute, which
tables were accessed, how long locks (postgres locks, that is, not
kernel ones) were held, cache hits, cache misses, etc.  It's _really_
useful for Postgres developers and admins.  And they only get it on
Solaris and MacOS, not Linux.

-- 
Intel are signing my paycheques ... these opinions are still mine
"Bill, look, we understand that you're interested in selling us this
operating system, but compare it to ours.  We can't possibly take such
a retrograde step."


More information about the Ksummit-2008-discuss mailing list