+CC Andrew Rybchenko as co-signer on the mempool patch in mainline. > From: luca.bocca...@gmail.com [mailto:luca.bocca...@gmail.com] > Sent: Monday, 28 November 2022 11.53 > > Hi all, > > Here is a list of patches targeted for stable release 20.11.7. > > The planned date for the final release is the 12th of December. > > Please help with testing and validation of your use cases and report > any issues/results with reply-all to this mail. For the final release > the fixes and reported validations will be added to the release notes. > > A release candidate tarball can be found at: > > https://dpdk.org/browse/dpdk-stable/tag/?id=v20.11.7-rc1 > > These patches are located at branch 20.11 of dpdk-stable repo: > https://dpdk.org/browse/dpdk-stable/
The link with pre-selected branch seems to be: https://git.dpdk.org/dpdk-stable/?h=20.11 [...] > Morten Brørup (2): > eal/x86: add 256 bytes copy for AVX2 LGTM. > mempool: fix get objects from mempool with cache Reviewed stable release patch [1], comparing it to the accepted mainline patch [2]. [1]: https://git.dpdk.org/dpdk-stable/commit/?h=20.11&id=26cb4c81b552594292f7c744afb904f01700dfe8 [2]: https://patchwork.dpdk.org/project/dpdk/patch/20221007104450.2567961-1-andrew.rybche...@oktetlabs.ru/ This is not correct: + __MEMPOOL_STAT_ADD(mp, get_success_bulk, 1); + __MEMPOOL_STAT_ADD(mp, get_success_objs, n); The old macro did more, so it should be: + __MEMPOOL_STAT_ADD(mp, get_success, n); This is only visible if built with RTE_LIBRTE_MEMPOOL_DEBUG. Besides that, it looks perfectly good to me. PS: The upstream commit hash links in the stable release patches (e.g. in [1]) don't seem to work. They lead to a page saying "Bad commit reference". I don't know if this is expected behavior or not.
