Thanks,
It seems that the bottleneck can be the lookup in these userspace when
we have lots of new flows.
My question is how many table we can have in the userspace?
How many entry the kernel table can have?
Why did you use one table for each wildcards set, and not use tree based
data structures like R+ - trees?
Masoud
On 2/6/2012 7:39 PM, Jesse Gross wrote:
On Mon, Feb 6, 2012 at 6:28 PM, Masood Moshref Javadi
<[email protected]> wrote:
Assuming that what I said is correct, I have these questions:
What is the mechanism to find the matched facet in the kernel module
(hashmap) ?
A hash table.
the performance of lookup depends on the number of tables (as all tables
will be checked) and the hashmap in each table. How many tables can we have?
There is only one table in the kernel regardless of the userspace configuration.
Is there any maximum bound on the number of facets in the kernel module?
Userspace adjusts it based on load to keep the most active flows in
the kernel while not incurring too much overhead on keeping track of
stats.
_______________________________________________
discuss mailing list
[email protected]
http://openvswitch.org/mailman/listinfo/discuss
