From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([209.51.188.92]:60632) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1hIkLR-0006bO-N8 for qemu-devel@nongnu.org; Mon, 22 Apr 2019 21:35:38 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1hIkLO-0007Sk-QU for qemu-devel@nongnu.org; Mon, 22 Apr 2019 21:35:37 -0400 Received: from indium.canonical.com ([91.189.90.7]:58502) by eggs.gnu.org with esmtps (TLS1.0:RSA_AES_128_CBC_SHA1:16) (Exim 4.71) (envelope-from ) id 1hIkLK-0007PY-2E for qemu-devel@nongnu.org; Mon, 22 Apr 2019 21:35:31 -0400 Received: from loganberry.canonical.com ([91.189.90.37]) by indium.canonical.com with esmtp (Exim 4.86_2 #2 (Debian)) id 1hIkLG-000596-BF for ; Tue, 23 Apr 2019 01:35:26 +0000 Received: from loganberry.canonical.com (localhost [127.0.0.1]) by loganberry.canonical.com (Postfix) with ESMTP id 382872E807D for ; Tue, 23 Apr 2019 01:35:26 +0000 (UTC) MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Date: Tue, 23 Apr 2019 01:29:40 -0000 From: =?utf-8?b?6LSe6LS15p2O?= <1805256@bugs.launchpad.net> Reply-To: Bug 1805256 <1805256@bugs.launchpad.net> Sender: bounces@canonical.com References: <154327283728.15443.11625169757714443608.malonedeb@soybean.canonical.com> Message-Id: <155598298071.13263.10695875240846950986.malone@wampee.canonical.com> Errors-To: bounces@canonical.com Subject: [Qemu-devel] [Bug 1805256] Re: qemu-img hangs on high core count ARM system List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org I can reproduce this problem with qemu.git/matser. It still exists in qemu.= git/matser. I found that when an IO return in worker threads and want to ca= ll aio_notify to wake up main_loop, but it found that ctx->notify_me is cle= ared to 0 by main_loop in aio_ctx_check by calling atomic_and(&ctx->notify_= me, ~1) . So worker thread won't write enventfd to notify main_loop.If such= a scene happens, the main_loop will hang: main loop worker thread1 worker= thread2 ---------------------------------------------------------------------------= -------------------- qemu_poll_ns aio_worker qemu_bh_schedule(pool->completion_bh) glib_pollfds_poll g_main_context_check aio_ctx_check atomic_and(&ctx->notify_me, ~1) aio_work= er qemu_bh_schedule(pool= ->completion_bh) /* do something for event */ qemu_poll_ns /* hangs !!!*/ As we known, ctx->notify_me will be visited by worker thread and main loop. I thank we should add a lock protection for ctx->notify_me to avoid this happend.what do you thank so? -- = You received this bug notification because you are a member of qemu- devel-ml, which is subscribed to QEMU. https://bugs.launchpad.net/bugs/1805256 Title: qemu-img hangs on high core count ARM system Status in QEMU: Confirmed Bug description: On the HiSilicon D06 system - a 96 core NUMA arm64 box - qemu-img frequently hangs (~50% of the time) with this command: qemu-img convert -f qcow2 -O qcow2 /tmp/cloudimg /tmp/cloudimg2 Where "cloudimg" is a standard qcow2 Ubuntu cloud image. This qcow2->qcow2 conversion happens to be something uvtool does every time it fetches images. Once hung, attaching gdb gives the following backtrace: (gdb) bt #0 0x0000ffffae4f8154 in __GI_ppoll (fds=3D0xaaaae8a67dc0, nfds=3D187650= 274213760, = timeout=3D, timeout@entry=3D0x0, sigmask=3D0xffffc123b= 950) at ../sysdeps/unix/sysv/linux/ppoll.c:39 #1 0x0000aaaabbefaf00 in ppoll (__ss=3D0x0, __timeout=3D0x0, __nfds=3D, = __fds=3D) at /usr/include/aarch64-linux-gnu/bits/poll2= .h:77 #2 qemu_poll_ns (fds=3D, nfds=3D, = timeout=3Dtimeout@entry=3D-1) at util/qemu-timer.c:322 #3 0x0000aaaabbefbf80 in os_host_main_loop_wait (timeout=3D-1) at util/main-loop.c:233 #4 main_loop_wait (nonblocking=3D) at util/main-loop.c:497 #5 0x0000aaaabbe2aa30 in convert_do_copy (s=3D0xffffc123bb58) at qemu-im= g.c:1980 #6 img_convert (argc=3D, argv=3D) at qemu-= img.c:2456 #7 0x0000aaaabbe2333c in main (argc=3D7, argv=3D) at qemu= -img.c:4975 Reproduced w/ latest QEMU git (@ 53744e0a182) To manage notifications about this bug go to: https://bugs.launchpad.net/qemu/+bug/1805256/+subscriptions