Skip to contentSkip to conversation

Porting "jump labels" to userspace (was: Re: [ltt-dev] LTTng-UST vs SystemTap userspace tracing benchmarks)

DISCUSSION Mathieu Desnoyers 6 participants 9 messages Feb 16, 2011 – Feb 17, 2011 5 messages not in the archive

lore
Share & tools
lore
#5 lore raw
In reply to a message not in the archive

[ Adding the relevant people in CC for jump label discussion ]

Quoted 18 lines · * Roland McGrath ([email protected]) wrote:

Stefan was referring to #4 in your taxonomy.

It's indeed the case that what UST uses today is an always-there normal C code sequence that loads global variables to decide whether to make indirect function calls. I don't recall off hand how many layers of function calls to the libust DSO and such there are in either the disabled or enabled cases. At best, there is the always the overhead of several instructions and at least one load in the hot code path, and the i-cache pollution that goes with that.

It's indeed the cast that what Systemtap uses today is a sometimes-inserted normal breakpoint instruction, which is indeed a software interrupt that requires kernel mediation. When disabled, there is as close to zero overhead as you can have, being a tiny placeholder instruction sequence (currently just one nop), so the runtime overhead is under a cycle and the i-cache pollution is the smallest possible unit (one instruction, being just one byte on x86).

Quoted 16 lines

The "sweet spot" between the two is to have overhead close to Systemtap's epsilon for a disabled probe, while having overhead close to UST's pure-user method when a probe is enabled. In the in-kernel context, this is what the Linux kernel's latest code (still being hashed out, but mostly done) has for kernel tracepoints using the so-called "jump label" method. That is also possible for sdt markers with some careful consideration and attention to machine-specific details for each machine architecture of concern. It entails making the placeholder in the hot code path slightly larger (at least for x86, it has to be a "long nop", being probably neglibly more runtime overhead, and a few bytes more i-cache pollution), and adding some additional static code outside the hot path. The work to enable or disable a probe becomes just as costly as the current Systemtap method, since it involves modifying the program text in place (inserting jump instructions rather than breakpoint ones). Once enabled, the runtime work of the probes firing can be very much like what UST does today.

Actually, creating the equivalent of the jump labels for userspace is on our list of "things to do" for the UST project.

If Jason and other jump label contributors agree to dual-license the jump label generic and per-arch implementations under both GPLv2 and LGPLv2.1, we could probably re-use a large part of this code to create a static jump label library for userspace. The concerned authors are precisely: Jason for generic and x86 code, Steven for some improvements in generic code and David S. Miller for the sparc port. After things settle down with the current jump label changes proposed by Peter Zijlstra, we might also want to ask for his permission to LGPLize his changes.

Thanks,

Mathieu

Quoted 4 lines

Thanks,
Roland

Signature · 4 lines
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
#6 lore raw

IMHO there is not really so much to the in-kernel implementation that it's worth attempting to reuse the code in userland. Pretty much all the work is in the details of the implementation that would naturally differ a lot in a different context. If you understand the mechanism and the machine details, then implementing it well for a userland context is not a big deal and is cleaner to do from scratch than shoe-horning kernel-centric code into a wildly different context.

Thanks,
Roland

#12 lore raw

Re: Porting "jump labels" to userspace

In reply to Mathieu Desnoyers

On 02/16/2011 12:00 PM, Mathieu Desnoyers wrote:
[...]>

Quoted 12 lines

Actually, creating the equivalent of the jump labels for userspace is on our list of "things to do" for the UST project.

If Jason and other jump label contributors agree to dual-license the jump label generic and per-arch implementations under both GPLv2 and LGPLv2.1, we could probably re-use a large part of this code to create a static jump label library for userspace. The concerned authors are precisely: Jason for generic and x86 code, Steven for some improvements in generic code and David S. Miller for the sparc port. After things settle down with the current jump label changes proposed by Peter Zijlstra, we might also want to ask for his permission to LGPLize his changes.

FWIW: MIPS jump label support is now in as of:

94bb0c1 (MIPS: jump label: Add MIPS support.)

I would be the author of that.

David Daney

#7 lore raw

Re: Porting "jump labels" to userspace

In reply to Roland McGrath
Quoted 8 lines · Roland McGrath

IMHO there is not really so much to the in-kernel implementation that it's worth attempting to reuse the code in userland. Pretty much all the work is in the details of the implementation that would naturally differ a lot in a different context. If you understand the mechanism and the machine details, then implementing it well for a userland context is not a big deal and is cleaner to do from scratch than shoe-horning kernel-centric code into a wildly different context.

Good point.

Certainly the details of maintaining instruction cache coherency may be different in userspace.

David Daney

#13 lore raw

Re: Porting "jump labels" to userspace

In reply to David Daney
Quoted 14 lines · * David Daney ([email protected]) wrote:

On 02/16/2011 12:00 PM, Mathieu Desnoyers wrote:
[...]>

Quoted 12 lines

Actually, creating the equivalent of the jump labels for userspace is on our list of "things to do" for the UST project.

If Jason and other jump label contributors agree to dual-license the jump label generic and per-arch implementations under both GPLv2 and LGPLv2.1, we could probably re-use a large part of this code to create a static jump label library for userspace. The concerned authors are precisely: Jason for generic and x86 code, Steven for some improvements in generic code and David S. Miller for the sparc port. After things settle down with the current jump label changes proposed by Peter Zijlstra, we might also want to ask for his permission to LGPLize his changes.

Quoted 5 lines

FWIW: MIPS jump label support is now in as of:

94bb0c1 (MIPS: jump label: Add MIPS support.)

I would be the author of that.

Sorry David, my tree was a bit outdated from Linus's head :)

Mathieu

Quoted 2 lines

David Daney

Signature · 4 lines
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
#8 lore raw

Re: Porting "jump labels" to userspace

In reply to David Daney
Quoted 10 lines · * David Daney ([email protected]) wrote:
Quoted 8 lines · Roland McGrath

IMHO there is not really so much to the in-kernel implementation that it's worth attempting to reuse the code in userland. Pretty much all the work is in the details of the implementation that would naturally differ a lot in a different context. If you understand the mechanism and the machine details, then implementing it well for a userland context is not a big deal and is cleaner to do from scratch than shoe-horning kernel-centric code into a wildly different context.

Quoted 4 lines

Good point.

Certainly the details of maintaining instruction cache coherency may be different in userspace.

Indeed, the arch-specific parts will need some extra care (which might, in the worse case scenario, require to suspend a whole process during the update), but the generic code in jump_label.c and jump_label.h could certainly be reused.

Thanks,

Mathieu

Quoted 2 lines

David Daney

Signature · 4 lines
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com
#9 lore raw

Re: Porting "jump labels" to userspace

Quoted 11 lines · Mathieu Desnoyers
Quoted 10 lines · * David Daney ([email protected]) wrote:
Quoted 8 lines · Roland McGrath

IMHO there is not really so much to the in-kernel implementation that it's worth attempting to reuse the code in userland. Pretty much all the work is in the details of the implementation that would naturally differ a lot in a different context. If you understand the mechanism and the machine details, then implementing it well for a userland context is not a big deal and is cleaner to do from scratch than shoe-horning kernel-centric code into a wildly different context.

Quoted 8 lines
Quoted 4 lines

Good point.

Certainly the details of maintaining instruction cache coherency may be different in userspace.

Indeed, the arch-specific parts will need some extra care (which might, in the worse case scenario, require to suspend a whole process during the update), but the generic code in jump_label.c and jump_label.h could certainly be reused.

We talk about 500 lines of code, where half of it is modules specific and the whole thing is full of kernelims. IMNSHO, that's faster reimplemented from scratch than writing all the mails and get the authors to sign off on the license change.

Thanks,

tglx

#10 lore raw

Re: Porting "jump labels" to userspace

Quoted 4 lines · Thomas Gleixner

We talk about 500 lines of code, where half of it is modules specific and the whole thing is full of kernelims. IMNSHO, that's faster reimplemented from scratch than writing all the mails and get the authors to sign off on the license change.

That and I'm not going to consent with an LGPL license, I'm an avid GPLv2 fan as various people already know ;-)

#11 lore raw

Re: Porting "jump labels" to userspace

Quoted 9 lines · Peter Zijlstra
Quoted 4 lines · Thomas Gleixner

We talk about 500 lines of code, where half of it is modules specific and the whole thing is full of kernelims. IMNSHO, that's faster reimplemented from scratch than writing all the mails and get the authors to sign off on the license change.

That and I'm not going to consent with an LGPL license, I'm an avid GPLv2 fan as various people already know ;-)

Ditto for me.

Thanks,

Ingo