Significantly reduce peak memory usage when vpacket logging is enabled #694
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Instead of allocating numpy arrays for the virt_packet* arrays all at once, copying from the C arrays, and freeing the C arrays, simply transfer ownership of the C array memory to a numpy array object. With this fix, peak memory usage by virt_packet arrays is reduced to half.
yeganer
approved these changes
Jan 17, 2017
| cdef extern from "numpy/arrayobject.h": | ||
| void PyArray_ENABLEFLAGS(np.ndarray arr, int flags) | ||
|
|
||
| cdef c_array_to_numpy(void *ptr, int dtype, np.npy_intp N): |
There was a problem hiding this comment.
This is just a really small thing, but as we are using numpy API, I think we should use np.int_t dtype instead of int dtype.
There was a problem hiding this comment.
I'm not sure we should do this. The numpy reference declares this as an int: https://docs.scipy.org/doc/numpy/reference/c-api.array.html#c.PyArray_SimpleNewFromData
|
Just tested it with |
unoebauer
approved these changes
Jan 18, 2017
|
very good! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
@Heringer-Epson attempted a run with
on a system with 16GB of RAM (no swap) and got TARDIS killed by the OS just after the final iteration was finished.
Fix:
Instead of allocating numpy arrays for the virt_packet* arrays all at once, copying from the C arrays, and freeing the C arrays, simply transfer ownership of the C array memory to a numpy array object.
With this fix, peak memory usage by virt_packet arrays is reduced to half.