14:17:10 <jbk> heh
14:50:37 <jbk> just as a sanity check -- for mac_ether_offload_info_t the size of the 'data' portion of the packet (bytes after TCP/UDP header) would be meoi_len - sum(meoi_l[234]_hlen), right? (assuming the respective MEIO_L[234]INFO_SET flags are set)
14:51:36 <jbk> (there's apparently an azure bug w/ UDP checksum offload that requires knowing this to avoid
15:09:59 <rzezeski> jbk: that sounds correct
15:10:47 <jbk> ok.. i figured.. but always hate to assume and then find out i'm wrong the hard way :)
15:15:53 <gwr> richlowe: file another issue? :)
16:06:08 <jbk> hrm though.. i suppose by the time we get the packet for TX, it's too late to say 'hey, we can't do it on this packet' isn't it?
19:32:39 <richlowe> gwr: #18194 (fenix?)
19:32:40 <fenix> BUG 18194: test-runner default output directory doesn't work (New)
19:32:40 <fenix> ↳ https://www.illumos.org/issues/18194
20:02:34 <jbk> heh.. test-runner feels like the gift that keeps on giving :)
20:03:38 <richlowe> jbk: it's been great for years and years, and it's notably not either of Sun's frameworks...
20:03:47 <richlowe> though I think STF is in there somewhere for zfs
20:06:47 <richlowe> my favourite is still dtest, because absolutely as simple as it possibly can be
20:13:02 <nomad> Unfortunate name. I see it as "detest" which is clearly a wrong feeling for something helpful.
20:14:09 <richlowe> it's the dtrace test runner.  The pun might be intentional, they're punny people
20:14:29 <richlowe> and it's not a simpson's reference, so that only helps the chances of it being something else
20:14:41 <jbk> or 'dee (the) test'
20:15:07 <jbk> unlike my illumos branch named 'theperlthe' :)
20:15:12 <jbk> (speaking of simpsons references)
21:43:23 <gwr> You touch it you own it :)
21:47:52 <alanc> they still don't beat the linker aliens for getting puns into /usr/bin, with crle, moe, & lari
22:32:32 <richlowe> gwr: not so much that, as every time I merge with you I find something new.  The vast majority have been my fault 
22:48:51 <richlowe> I had let enough false "32-bit" tests through it actually makes a noticeable different to runtime too :\