[ltt-dev] User-space tracing on ARM?

[David Goulet]

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

Hi Grant,

UST is "in theory" supported for ARM but hasn't been tested. However, two points
to consider. First, it's not possible to synchronize LTTng traces with those of
UST since the time source is not the same. Second, on ARM architecture,
clock_gettime, which is use in UST for the timestamp of each event, is a syscall
and not a VDSO like on x86. This brings a *huge* impact on the tracing path.

Having a "monotonic tracing clock source" for the Linux kernel and exported to
userspace as a VDSO is an ongoing effort here :)

For liburcu, ARM is supported. (See urcu/arch_* in liburcu tree for a complete
list of all supported architecture)

So, if you test UST on ARM, please post the results on ltt-dev mailing list and
feel free to report any bugs.

Thanks!
David

On 10-10-26 06:00 PM, Grant Edwards wrote:
> We're looking for low-overhead tracing tools for use with user-space
> application code.  UST looks like it might fit the bill nicely, but in
> the manual I don't see ARM on the list of supported architectures.
> 
> I don't suppose there's any chance that the docs are out-of-date and
> it does works on ARM?
> 
> [He asked hopefully, though not very optimistically.]
> 
> Is it liburcu that's arch-dependent?
>
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.10 (GNU/Linux)

iEYEARECAAYFAkzHYREACgkQSvfBSxa9hWPsQwCgmKPtx97BB0T9IOaLRat1G8E3
kkQAn307zN183XIj2plio1c0+LvqDIrB
=I6g/
-----END PGP SIGNATURE-----