09:56:58 <paulf> I'm looking at an x86 testcase with a 16byte overaligned struct and new isn't using https://github.com/facebook/zst
09:57:06 <paulf> argh wrong paste
09:57:10 <paulf> operator new(unsigned int, std::align_val_t)
09:58:41 <paulf> is there a g++ option to make is use aligned new?
10:00:02 <paulf> 000c3460 T operator new(unsigned int, std::align_val_t)@@CXXABI_1.3.11
10:02:42 <paulf> -std=c++17 -faligned-new don't change anything
10:48:01 <tsoome> which gcc are you using?
10:59:40 <paulf> gcc (OpenIndiana 13.3.0-oi-0) 13.3.0
11:27:47 <tsoome> you can try 14, it is also available on oi
12:04:52 <paulf> same problem
12:55:35 <tsoome> no idea then. I havent tracked gcc that much and I guess my google is just as good as yours:D
16:27:32 <Kurlon_> Well, that's a fail. My test box hangs drive IO under load. Ye olde LSI 1068E in IT mode, it just dies, no kernel messages or anything.
17:47:03 <tsoome> Kurlon_  which and how many disks?
17:47:12 <tsoome> sata?
17:47:25 <Kurlon_> 8 x Samsung 850 Pro 128GB SSDs
17:47:28 <Kurlon_> SATA
17:47:47 <Kurlon_> I'm seeing lots of reports of that being an issue on these specific cards.
17:48:07 <tsoome> I see...
17:49:05 <Kurlon_> So, plan B is back to an IBM M5014 that'll get flashed to IT mode for 4 of the drives, 4 more off the onboard intel chipset SATA with an unhappy bend in the connector.
17:52:20 <Kurlon_> Or... not, no IT mode firmware for this antique.
18:39:55 <Kurlon_> For $30 on eBay plus some updated SAS cables I can get a 9300-8i, feels like the way to roll.
20:19:03 <Kurlon_> For now, M5014 setup with four raid 0 virt drives, one for each SSD, other four on the chipset SATA, seems to be behaving OK.
20:19:31 <Kurlon_> Actually getting a bit better throughput with things split over two controllers.
20:25:39 <richlowe> I have no idea about the GCC thing above either, but C++ choices are usually mystery to me
20:28:30 <Kurlon_> w
20:59:26 <Kurlon_> Interesting side effect of this bad storage setup, during a scrub the 'virt' drives report an IO count 10 times what the bare SATA drives do, but the total k/s matches.
23:47:03 <sommerfeld> Kurlon_: 4k vs 512 byte sector sizes, perhaps?