ACL - on duplicate name the rte_acl_create returns existing object instead of failure

2023-05-20 Thread Pawel Wodkowski
Hi, Following other parts of the DPDK library the rte_acl_create function should fail if ACL context with the same name already exists. Implicit ACL object sharing is not what is expected nor documented. Paweł

ACL library silently fail to classify packets if group is not 4b long in field definition

2023-05-12 Thread Pawel Wodkowski
Hi, I'm using version 20.05.0 but I believe current version is also affected. In I know that the ACL group must be constructed of 4 consecutive bytes. But when the group is not 4B long (eg. no need to check more than 2B) then the rte_acl_create() function return success but classification

Re: Strategy for contiguous packet payload processing using DPDK mbufs

2022-07-28 Thread Pawel Wodkowski
On 27.07.2022 17:03, Filip Matracki wrote: What strategy is recommended for a DPDK application that needs to process the payload of network packets in contiguous memory? 1. Don't care about the wasted memory? 2. Reassembly large packets into contiguous memory. 3. Use NIC features to redirect

Re: [dpdk-users] Round-robin packet distribution

2020-08-25 Thread Pawel Wodkowski
capturing financial market traffic over TCP/UDP, nothing really fancy. Thanks Il 8/18/20 3:50 PM, Pawel Wodkowski ha scritto: Flexible payload matching (aka RAW in flow API) works up to first 64b of the packet - at least in e1000, ixgbe and i40e. It will be easier if you can provide some details about

Re: [dpdk-users] Round-robin packet distribution

2020-08-18 Thread Pawel Wodkowski
Flexible payload matching (aka RAW in flow API) works up to first 64b of the packet - at least in e1000, ixgbe and i40e. It will be easier if you can provide some details about you network traffic. Paweł On 18.08.2020 14:40, Filip Janiszewski wrote: Hi, We had a look at that, and decided