> -----Original Message----- > From: Chris Wilson [mailto:chris@xxxxxxxxxxxxxxxxxx] > Sent: Wednesday, July 29, 2015 2:16 PM > To: Gore, Tim > Cc: Morton, Derek J; intel-gfx@xxxxxxxxxxxxxxxxxxxxx; Wood, Thomas > Subject: Re: [PATCH i-g-t] tests/gem_render_linear_blits: Increase > min swap required > > On Wed, Jul 29, 2015 at 01:10:23PM +0000, Gore, Tim wrote: > > I don’t see how this implies a kernel bug. It seems like a test > > problem (my subtest as it happens). I was unaware of Android systems > > with small swap partitions (or indeed any swap at all). Not sure I can > > understand the logic of such a tiny swap partition but given the > > situation, unless we can accurately characterise the memory usage of > > the test in advance then we have to either skip the test for small > > swap, or try to monitor memory usage in an ongoing way during the test. > > If the system has enough resources to run the test (that is enough physical to > run an individual batch plus enough swap to hold the rest), then the test > must not oom. > -Chris > > -- > Chris Wilson, Intel Open Source Technology Centre Maybe my test is flawed. To force the use of swap memory I calculate count In order to fill (available-ram + swap/2) with buffer objects. So the physical ram gets completely filled and then further buffer objects are created to force the use of swap. Because the swap partition is so much smaller than the ram in this system, a relatively small error in calculating count (due to overheads) leads to the swap filling up and oom. Tim Tim Gore Intel Corporation (UK) Ltd. - Co. Reg. #1134945 - Pipers Way, Swindon SN3 1RJ _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx http://lists.freedesktop.org/mailman/listinfo/intel-gfx
