Hi guys,
What has been your experience of using DPDK based app's in NUMA mode with
multiple sockets where some cores are present on one socket and other cores on
some other socket.
I am migrating my application from one intel machine with 8 cores, all in one
socket to a 32 core machine where 1
Hi Prashant,
Based on our experience, using DPDK cross CPU sockets may indeed result in
some performance degradation (~10% for our application vs. staying
in socket. YMMV based on HW, application structure, etc.).
Regarding CPU utilization on core 1, the one picking up traffic: perhaps I
had mis
>
> What has been your experience of using DPDK based app's in NUMA mode
> with multiple sockets where some cores are present on one socket and
> other cores on some other socket.
>
> I am migrating my application from one intel machine with 8 cores, all in
> one socket to a 32 core machine where
Hi Etai,
Ofcourse all DPDK threads consume 100 % (unless some waits are introduced for
some power saving etc., all typical DPDK threads are while(1) loops)
When I said core 1 is unusually busy, I meant to say that it is not able to
read beyond 2 Gbps or so and the packets are dropping at NIC.
(I
Hi Prashant,
May be you could monitor RAM, QPI and PCIe activity with
http://software.intel.com/en-us/articles/intel-performance-counter-monitor-a
-better-way-to-measure-cpu-utilization
It may ease investigating the issue.
Fran?ois-Fr?d?ric
> -Message d'origine-
> De?: dev [mailto:dev-
1) I have two apps that need to communicate on the same machine . Is it
possible to have these two apps communicating via dpdk without referencing
a nic ?
2) The apps need to run on an amazon vm. How can you run dpdk on an amazon
vm with only one nic if the above is not possible ?
Hi,
There are following code in function ixgbe_xmit_pkts,
if ((txq->nb_tx_desc - txq->nb_tx_free) > txq->tx_free_thresh) {
ixgbe_xmit_cleanup(txq);
}
My understanding is, nb_tx_desc means total number of descriptors in
ring and nx_tx_free represents how many descr
Hi Qing,
The idea is that we do not want to clean the descriptor ring until we have used
"enough" descriptors.
So (nb_tx_desc -nb_tx_free) tells us how many descriptors we've used. Once
we've used "enough" (i.e. tx_free_thresh) then we will try to clean the
descriptor ring.
If you look at the
8 matches
Mail list logo
