[Xen-devel] Xen performance related work needed

[Olivier Lambert <lambert.olivier@xxxxxxxxx>]

Hi there!

In a possible scenario where I (and a whole academic team) could work
on improving Xen, what are the major areas requiring
exploration/optimizations? Ideally, part that would be not that hard
to work on, but allow high potential "reward".

From my perspective, storage is probably a side that could be
massively improved, but it's only based on my perception of Xen
(especially on NVMe drives, where IOPS are high and latency small).

So this question had a broad spectrum: in your opinion, the best ratio
between effort and reward to improve perfs in general (could be
storage, network, compute).

I know security impact since side channel attack is huge, so it could
be interesting to have new contributors more focused directly on
perfs/optimizations.

Any ideas and pointers toward those areas are welcome!

Best,

Oliver

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel