Comment #3 on issue 256 by [email protected]: [patch] decrease resident
memory usage.
http://code.google.com/p/address-sanitizer/issues/detail?id=256
The difference in resident set size is 1Mb, or 0.2% of the overall size.
This is not a convincing gain.
Also, a benchmarks should
- have less unrelated logic (no trees, nodes, etc. Just malloc/free)
- have multiple threads, all malloc-intensive
- have small allocations as well as large allocations
- have most of the malloc-ed memory actually used
Note also, that once we free the large malloc-ed block we call
FlushUnneededASanShadowMemory (madvise((void*)addr, size, MADV_DONTNEED);)
so if the large blocks are actually freed, the shadow should be fully freed
as well.
--
You received this message because this project is configured to send all
issue notifications to this address.
You may adjust your notification preferences at:
https://code.google.com/hosting/settings
--
You received this message because you are subscribed to the Google Groups
"address-sanitizer" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/groups/opt_out.
