Rupert and the UNH-IOL pointed out that an Interop test which uses the ib_read_bw (perftest) benchmark fails on Intel True Scale HCAs. This test was succeeding with RC2, and started failing with RC3. I am sorry that our QA team did not find this bug with RC3.
We have investigated and found that perftest was upgraded from v1.8 to v2.0 on 11/19/12, between RC3 and RC4. We verified that with the qib driver in OFED-3.5 RC4 and the perftest RPM from RC2, we pass the tests. We also ran a similar qperf RDMA read test with qperf and qib from RC4 and that test passed. We are working to isolate the bug and develop a fix. We suspect the perftest changes, but the ib_read_* benchmarks may just have changed enough to start checking a part of the spec which hasn't been tested before in Interop tests. So it may be a qib driver issue. The EWG standard practice is that if a significant bug fix goes in, we would need another RC to enable others to easily test it. But perhaps it depends on whether the bug is in perftest, qib or elsewhere. In any case, we don't want a GA build until this issue is solved. Regards, Tom _______________________________________________ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg
