Hello VPP Experts,
Wanted to know, Similar to Linux, if any atomic operation is available in VPP?
Intention is to use atomic operations in place of Locking.
Linux:
long atomic64_add_return(int i, atomic64_t *v) Atomically add i to v and return
the result
long atomic64_sub_return(int i, atomic64_t
Hi Marina,
In that case you should be good. If you think the os is not mmap-ing memory on
the right numa, maybe try clib_mem_set_numa_affinity/set_mempolicy.
Also note that “show memory” shows memory allocated through clib_mem_*
functions but, as you’ve noticed, pool_init_fixed directly call
On Fri, May 28, 2021 at 10:32:06AM -0500, Matthew Smith via lists.fd.io wrote:
> Hi Mike,
>
> The first problem you mentioned (packets matching a route are not sent when
> the next hop has not been resolved at the time the route is added) is
> likely fixed by this patch:
>
> e2353a7f6 linux-cp: A
Hi Florin,
I am using VLIB_WORKER_INIT_ FUNCTION
But pool_init_fixed function calls mmap
How can I force mmap to allocate the memory on the curtent Numa node?
And when I call show memry, show threads I get this:
vpp# show threads
ID Name Type LWP Sched Policy (Prior
Hi Marina,
You might be able to with a VLIB_MAIN_LOOP_ENTER_FUNCTION handler.
Regards,
Florin
> On Jun 2, 2021, at 10:57 AM, marina.vasilev...@insidepacket.com wrote:
>
> Hi,
> Is it possible to create a fixed size pool on the worker's numa node?
> I am using pool_init_fixed.
> I have worker
Hi Sastry,
Inline.
> On Jun 1, 2021, at 11:48 AM, Sastry Sista wrote:
>
> Hi Florin,
>
>Thank you for the bit more clarity. I have few
> question further to the items:
>
> 1. In a single worker case, What is the difference between session_handle
> from vppcom_sessio
Hi,
Is it possible to create a fixed size pool on the worker's numa node?
I am using pool_init_fixed.
I have workers running on 2 numa nodes and I need pool per worker.
Thanks
-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#19518): https://lists.fd
