Messages in this thread | | | Date | Tue, 17 Apr 2018 09:35:09 -0700 | From | Guenter Roeck <> | Subject | Re: Crashes/hung tasks with z3pool under memory pressure |
| |
On Tue, Apr 17, 2018 at 04:00:32PM +0200, Vitaly Wool wrote: > Hi Guenter, > > > [ ... ] > > > Ugh. Could you please keep that patch and apply this on top: > > > > > > diff --git a/mm/z3fold.c b/mm/z3fold.c > > > index c0bca6153b95..e8a80d044d9e 100644 > > > --- a/mm/z3fold.c > > > +++ b/mm/z3fold.c > > > @@ -840,6 +840,7 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) > > > kref_get(&zhdr->refcount); > > > list_del_init(&zhdr->buddy); > > > zhdr->cpu = -1; > > > + break; > > > } > > > list_del_init(&page->lru); > > > > > Much better, in a way. The system now takes much longer to crash, > > and the crash reason is a bit different. The log is too long to attach, > > so I copied it to [1]. > > > > crashdump.0002 Latest log > > 000[12]-Fix-attempt-[12].patch Patches applied on top of v4.17.0-rc1. > > thanks for the update. Let's start from a clean sheet. I believe this patch has to be applied anyway so could you please check if it solves the problem. >
Getting better; the log is much less noisy. Unfortunately, there are still locking problems, resulting in a hung task. I copied the log message to [1]. This is with [2] applied on top of v4.17-rc1.
Guenter
--- [1] http://server.roeck-us.net/qemu/z3pool/crashdump.0003 [2] http://server.roeck-us.net/qemu/z3pool/0001-Fix-attempt-3.patch
| |