Re: [dpdk-dev] [PATCH v2 0/7] Address reader-writer concurrency in rte_hash

2018-10-10 Thread Honnappa Nagarahalli
Hi Yipeng, I will rebase this further with your V7 and submit V3. Please let me know if you have any comments in the meantime. Due to time constraints, I do not plan to support lock-free for extended bucket feature in this release. I will add that support in the next release. Please let

[dpdk-dev] [PATCH v2 0/7] Address reader-writer concurrency in rte_hash

2018-10-10 Thread Honnappa Nagarahalli
Currently, reader-writer concurrency problems in rte_hash are addressed using reader-writer locks. Use of reader-writer locks results in following issues: 1) In many of the use cases for the hash table, writer threads are running on control plane. If the writer is preemp