CI performance test results might be misleading

[Morten Brørup]

I know it's too late for this patch [1], but I am afraid it was performance tested using test-pmd with RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE [2], so the test didn't involve the function fixed by this patch: rte_pktmbuf_prefree_seg().

If so, the performance test results were completely irrelevant. The same goes for other patches related to code bypassed by RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE.

RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE is a performance optimization with many application limitations, and should not be enabled for performance testing in the CI environment. Alternatively, performance testing can be performed both with and without this optimization.

[1] https://patchwork.dpdk.org/project/dpdk/patch/20210113132734.1636-1-olivier.matz@6wind.com/
[2] http://git.dpdk.org/dpdk/commit/app/test-pmd/testpmd.c?id=07e5f7bd65718461e4c63757248b9c7bab08341f