From: Jagannathan Raman <jag.raman@oracle.com>
To: qemu-devel@nongnu.org
Cc: elena.ufimtseva@oracle.com, fam@euphon.net,
john.g.johnson@oracle.com, kraxel@redhat.com,
jag.raman@oracle.com, quintela@redhat.com, mst@redhat.com,
armbru@redhat.com, kanth.ghatraju@oracle.com, thuth@redhat.com,
ehabkost@redhat.com, konrad.wilk@oracle.com, dgilbert@redhat.com,
liran.alon@oracle.com, stefanha@redhat.com, rth@twiddle.net,
kwolf@redhat.com, berrange@redhat.com, mreitz@redhat.com,
ross.lagerwall@citrix.com, marcandre.lureau@gmail.com,
pbonzini@redhat.com
Subject: [RFC v4 PATCH 30/49] multi-process: send heartbeat messages to remote
Date: Thu, 24 Oct 2019 05:09:11 -0400 [thread overview]
Message-ID: <14c33104778e77fcf2e7f0df2a1dd96fbcaf49d7.1571905346.git.jag.raman@oracle.com> (raw)
In-Reply-To: <cover.1571905346.git.jag.raman@oracle.com>
In-Reply-To: <cover.1571905346.git.jag.raman@oracle.com>
From: Elena Ufimtseva <elena.ufimtseva@oracle.com>
In order to detect remote processes which are hung, the
proxy periodically sends heartbeat messages to confirm if
the remote process is alive
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
---
hw/proxy/qemu-proxy.c | 101 +++++++++++++++++++++++++++++++++++++++++++++++
include/io/mpqemu-link.h | 1 +
2 files changed, 102 insertions(+)
diff --git a/hw/proxy/qemu-proxy.c b/hw/proxy/qemu-proxy.c
index fc1c731..691b991 100644
--- a/hw/proxy/qemu-proxy.c
+++ b/hw/proxy/qemu-proxy.c
@@ -53,14 +53,96 @@
#include "hw/boards.h"
#include "include/qemu/log.h"
+QEMUTimer *hb_timer;
static void pci_proxy_dev_realize(PCIDevice *dev, Error **errp);
static void setup_irqfd(PCIProxyDev *dev);
+static void pci_dev_exit(PCIDevice *dev);
+static void start_heartbeat_timer(void);
+static void stop_heartbeat_timer(void);
+static void childsig_handler(int sig, siginfo_t *siginfo, void *ctx);
+static void broadcast_msg(MPQemuMsg *msg, bool need_reply);
+
+static void childsig_handler(int sig, siginfo_t *siginfo, void *ctx)
+{
+ /* TODO: Add proper handler. */
+ printf("Child (pid %d) is dead? Signal is %d, Exit code is %d.\n",
+ siginfo->si_pid, siginfo->si_signo, siginfo->si_code);
+}
+
+static void broadcast_msg(MPQemuMsg *msg, bool need_reply)
+{
+ PCIProxyDev *entry;
+ unsigned int pid;
+ int wait;
+
+ QLIST_FOREACH(entry, &proxy_dev_list.devices, next) {
+ if (need_reply) {
+ wait = eventfd(0, EFD_NONBLOCK);
+ msg->num_fds = 1;
+ msg->fds[0] = wait;
+ }
+
+ mpqemu_msg_send(entry->mpqemu_link, msg, entry->mpqemu_link->com);
+ if (need_reply) {
+ pid = (uint32_t)wait_for_remote(wait);
+ close(wait);
+ /* TODO: Add proper handling. */
+ if (pid) {
+ need_reply = 0;
+ }
+ }
+ }
+}
+
+#define NOP_INTERVAL 1000000
+
+static void remote_ping(void *opaque)
+{
+ MPQemuMsg msg;
+
+ memset(&msg, 0, sizeof(MPQemuMsg));
+
+ msg.num_fds = 0;
+ msg.cmd = PROXY_PING;
+ msg.bytestream = 0;
+ msg.size = 0;
+
+ broadcast_msg(&msg, true);
+ timer_mod(hb_timer, qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + NOP_INTERVAL);
+
+}
+
+void start_heartbeat_timer(void)
+{
+ hb_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL,
+ remote_ping,
+ &proxy_dev_list);
+ timer_mod(hb_timer, qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + NOP_INTERVAL);
+
+}
+
+static void stop_heartbeat_timer(void)
+{
+ timer_del(hb_timer);
+ timer_free(hb_timer);
+}
+
+static void set_sigchld_handler(void)
+{
+ struct sigaction sa_sigterm;
+ memset(&sa_sigterm, 0, sizeof(sa_sigterm));
+ sa_sigterm.sa_sigaction = childsig_handler;
+ sa_sigterm.sa_flags = SA_SIGINFO | SA_NOCLDWAIT | SA_NOCLDSTOP;
+ sigaction(SIGCHLD, &sa_sigterm, NULL);
+}
static void proxy_ready(PCIDevice *dev)
{
PCIProxyDev *pdev = PCI_PROXY_DEV(dev);
setup_irqfd(pdev);
+ set_sigchld_handler();
+ start_heartbeat_timer();
}
static void set_remote_opts(PCIDevice *dev, QDict *qdict, unsigned int cmd)
@@ -259,6 +341,7 @@ static void pci_proxy_dev_class_init(ObjectClass *klass, void *data)
PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
k->realize = pci_proxy_dev_realize;
+ k->exit = pci_dev_exit;
k->config_read = pci_proxy_read_config;
k->config_write = pci_proxy_write_config;
}
@@ -397,6 +480,24 @@ static void pci_proxy_dev_realize(PCIDevice *device, Error **errp)
dev->proxy_ready = proxy_ready;
}
+static void pci_dev_exit(PCIDevice *pdev)
+{
+ PCIProxyDev *entry, *sentry;
+ PCIProxyDev *dev = PCI_PROXY_DEV(pdev);
+
+ stop_heartbeat_timer();
+
+ QLIST_FOREACH_SAFE(entry, &proxy_dev_list.devices, next, sentry) {
+ if (entry->remote_pid == dev->remote_pid) {
+ QLIST_REMOVE(entry, next);
+ }
+ }
+
+ if (!QLIST_EMPTY(&proxy_dev_list.devices)) {
+ start_heartbeat_timer();
+ }
+}
+
static void send_bar_access_msg(PCIProxyDev *dev, MemoryRegion *mr,
bool write, hwaddr addr, uint64_t *val,
unsigned size, bool memory)
diff --git a/include/io/mpqemu-link.h b/include/io/mpqemu-link.h
index 3145b0e..16a913b 100644
--- a/include/io/mpqemu-link.h
+++ b/include/io/mpqemu-link.h
@@ -72,6 +72,7 @@ typedef enum {
DRIVE_OPTS,
DEVICE_ADD,
DEVICE_DEL,
+ PROXY_PING,
MAX,
} mpqemu_cmd_t;
--
1.8.3.1
next prev parent reply other threads:[~2019-10-24 9:31 UTC|newest]
Thread overview: 140+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-24 9:08 [RFC v4 PATCH 00/49] Initial support of multi-process qemu Jagannathan Raman
2019-10-24 9:08 ` [RFC v4 PATCH 01/49] multi-process: memory: alloc RAM from file at offset Jagannathan Raman
2019-10-24 9:08 ` [RFC v4 PATCH 02/49] multi-process: util: Add qemu_thread_cancel() to cancel running thread Jagannathan Raman
2019-11-13 15:30 ` Stefan Hajnoczi
2019-11-13 15:38 ` Jag Raman
2019-11-13 15:51 ` Daniel P. Berrangé
2019-11-13 16:04 ` Jag Raman
2019-11-13 16:35 ` Daniel P. Berrangé
2019-10-24 9:08 ` [RFC v4 PATCH 03/49] multi-process: add a command line option for debug file Jagannathan Raman
2019-11-13 15:35 ` Stefan Hajnoczi
2019-10-24 9:08 ` [RFC v4 PATCH 04/49] multi-process: Add stub functions to facilate build of multi-process Jagannathan Raman
2019-10-24 9:08 ` [RFC v4 PATCH 05/49] multi-process: Add config option for multi-process QEMU Jagannathan Raman
2019-10-24 9:08 ` [RFC v4 PATCH 06/49] multi-process: build system for remote device process Jagannathan Raman
2019-10-24 9:08 ` [RFC v4 PATCH 07/49] multi-process: define mpqemu-link object Jagannathan Raman
2019-11-11 16:41 ` Stefan Hajnoczi
2019-11-13 15:47 ` Jag Raman
2019-11-13 15:53 ` Stefan Hajnoczi
2019-11-18 15:26 ` Jag Raman
2019-10-24 9:08 ` [RFC v4 PATCH 08/49] multi-process: add functions to synchronize proxy and remote endpoints Jagannathan Raman
2019-10-24 9:08 ` [RFC v4 PATCH 09/49] multi-process: setup PCI host bridge for remote device Jagannathan Raman
2019-11-13 16:07 ` Stefan Hajnoczi
2019-11-18 15:25 ` Jag Raman
2019-11-21 10:37 ` Stefan Hajnoczi
2019-10-24 9:08 ` [RFC v4 PATCH 10/49] multi-process: setup a machine object for remote device process Jagannathan Raman
2019-11-13 16:22 ` Stefan Hajnoczi
2019-11-18 15:29 ` Jag Raman
2019-10-24 9:08 ` [RFC v4 PATCH 11/49] multi-process: setup memory manager for remote device Jagannathan Raman
2019-11-13 16:33 ` Stefan Hajnoczi
2019-11-13 16:34 ` Jag Raman
2019-10-24 9:08 ` [RFC v4 PATCH 12/49] multi-process: remote process initialization Jagannathan Raman
2019-11-13 16:38 ` Stefan Hajnoczi
2019-10-24 9:08 ` [RFC v4 PATCH 13/49] multi-process: introduce proxy object Jagannathan Raman
2019-11-21 11:09 ` Stefan Hajnoczi
2019-10-24 9:08 ` [RFC v4 PATCH 14/49] mutli-process: build remote command line args Jagannathan Raman
2019-11-21 11:23 ` Stefan Hajnoczi
2019-10-24 9:08 ` [RFC v4 PATCH 15/49] multi-process: PCI BAR read/write handling for proxy & remote endpoints Jagannathan Raman
2019-11-21 11:33 ` Stefan Hajnoczi
2019-10-24 9:08 ` [RFC v4 PATCH 16/49] multi-process: Add LSI device proxy object Jagannathan Raman
2019-11-21 11:35 ` Stefan Hajnoczi
2019-10-24 9:08 ` [RFC v4 PATCH 17/49] multi-process: Synchronize remote memory Jagannathan Raman
2019-11-21 11:44 ` Stefan Hajnoczi
2019-10-24 9:08 ` [RFC v4 PATCH 18/49] multi-process: create IOHUB object to handle irq Jagannathan Raman
2019-11-21 12:02 ` Stefan Hajnoczi
2019-10-24 9:09 ` [RFC v4 PATCH 19/49] multi-process: configure remote side devices Jagannathan Raman
2019-11-21 12:05 ` Stefan Hajnoczi
2019-10-24 9:09 ` [RFC v4 PATCH 20/49] multi-process: add qdev_proxy_add to create proxy devices Jagannathan Raman
2019-11-21 12:16 ` Stefan Hajnoczi
2019-10-24 9:09 ` [RFC v4 PATCH 21/49] multi-process: remote: add setup_devices and setup_drive msg processing Jagannathan Raman
2019-10-24 9:09 ` [RFC v4 PATCH 22/49] multi-process: remote: use fd for socket from parent process Jagannathan Raman
2019-10-24 9:09 ` [RFC v4 PATCH 23/49] multi-process: remote: add create_done condition Jagannathan Raman
2019-10-24 9:09 ` [RFC v4 PATCH 24/49] multi-process: add processing of remote drive and device command line Jagannathan Raman
2019-10-24 9:09 ` [RFC v4 PATCH 25/49] multi-process: Introduce build flags to separate remote process code Jagannathan Raman
2019-10-24 9:09 ` [RFC v4 PATCH 26/49] multi-process: refractor vl.c code to re-use in remote Jagannathan Raman
2019-10-24 9:09 ` [RFC v4 PATCH 27/49] multi-process: add remote option Jagannathan Raman
2019-10-24 9:09 ` [RFC v4 PATCH 28/49] multi-process: add remote options parser Jagannathan Raman
2019-10-24 9:09 ` [RFC v4 PATCH 29/49] multi-process: add parse_cmdline in remote process Jagannathan Raman
2019-10-24 9:09 ` Jagannathan Raman [this message]
2019-11-11 16:27 ` [RFC v4 PATCH 30/49] multi-process: send heartbeat messages to remote Stefan Hajnoczi
2019-11-13 16:01 ` Jag Raman
2019-11-21 12:19 ` Stefan Hajnoczi
2019-10-24 9:09 ` [RFC v4 PATCH 31/49] multi-process: handle heartbeat messages in remote process Jagannathan Raman
2019-10-24 9:09 ` [RFC v4 PATCH 32/49] multi-process: Use separate MMIO communication channel Jagannathan Raman
2019-11-11 16:21 ` Stefan Hajnoczi
2019-11-13 16:14 ` Jag Raman
2019-11-21 12:31 ` Stefan Hajnoczi
2019-10-24 9:09 ` [RFC v4 PATCH 33/49] multi-process: perform device reset in the remote process Jagannathan Raman
2019-11-11 16:19 ` Stefan Hajnoczi
2019-11-13 16:15 ` Jag Raman
2019-10-24 9:09 ` [RFC v4 PATCH 34/49] multi-process/mon: choose HMP commands based on target Jagannathan Raman
2019-10-24 9:09 ` [RFC v4 PATCH 35/49] multi-process/mon: stub functions to enable QMP module for remote process Jagannathan Raman
2019-10-24 9:09 ` [RFC v4 PATCH 36/49] multi-process/mon: enable QMP module support in the " Jagannathan Raman
2019-10-24 9:09 ` [RFC v4 PATCH 37/49] multi-process/mon: Refactor monitor/chardev functions out of vl.c Jagannathan Raman
2019-10-24 9:09 ` [RFC v4 PATCH 38/49] multi-process/mon: Initialize QMP module for remote processes Jagannathan Raman
2019-10-24 9:09 ` [RFC v4 PATCH 39/49] multi-process: prevent duplicate memory initialization in remote Jagannathan Raman
2019-10-24 9:09 ` [RFC v4 PATCH 40/49] multi-process/mig: build migration module in the remote process Jagannathan Raman
2019-10-24 9:09 ` [RFC v4 PATCH 41/49] multi-process/mig: Enable VMSD save in the Proxy object Jagannathan Raman
2019-11-13 15:50 ` Daniel P. Berrangé
2019-11-13 16:32 ` Jag Raman
2019-11-13 17:11 ` Daniel P. Berrangé
2019-11-18 15:42 ` Jag Raman
2019-11-22 10:34 ` Dr. David Alan Gilbert
2019-10-24 9:09 ` [RFC v4 PATCH 42/49] multi-process/mig: Send VMSD of remote to " Jagannathan Raman
2019-10-24 9:09 ` [RFC v4 PATCH 43/49] multi-process/mig: Load VMSD in the proxy object Jagannathan Raman
2019-10-24 9:09 ` [RFC v4 PATCH 44/49] multi-process/mig: refactor runstate_check into common file Jagannathan Raman
2019-10-24 9:09 ` [RFC v4 PATCH 45/49] multi-process/mig: Synchronize runstate of remote process Jagannathan Raman
2019-11-11 16:17 ` Stefan Hajnoczi
2019-11-13 16:33 ` Jag Raman
2019-10-24 9:09 ` [RFC v4 PATCH 46/49] multi-process/mig: Restore the VMSD in " Jagannathan Raman
2019-10-24 9:09 ` [RFC v4 PATCH 47/49] multi-process: Enable support for multiple devices in remote Jagannathan Raman
2019-11-11 16:15 ` Stefan Hajnoczi
2019-11-13 16:21 ` Jag Raman
2019-10-24 9:09 ` [RFC v4 PATCH 48/49] multi-process: add the concept description to docs/devel/qemu-multiprocess Jagannathan Raman
2019-10-25 19:33 ` Elena Ufimtseva
2019-11-07 15:50 ` Stefan Hajnoczi
2019-11-11 15:41 ` Stefan Hajnoczi
2019-10-24 9:09 ` [RFC v4 PATCH 49/49] multi-process: add configure and usage information Jagannathan Raman
2019-11-07 14:02 ` Stefan Hajnoczi
2019-11-07 14:33 ` Michael S. Tsirkin
2019-11-08 11:17 ` Stefan Hajnoczi
2019-11-08 11:32 ` Daniel P. Berrangé
2019-11-07 14:39 ` Daniel P. Berrangé
2019-11-07 15:53 ` Jag Raman
2019-11-08 11:14 ` Stefan Hajnoczi
2019-10-25 2:08 ` [RFC v4 PATCH 00/49] Initial support of multi-process qemu no-reply
2019-10-25 2:08 ` no-reply
2019-10-25 2:10 ` no-reply
2019-11-21 12:46 ` Stefan Hajnoczi
2019-12-10 6:47 ` [RFC v4 PATCH 00/49] Initial support of multi-process qemu - status update Elena Ufimtseva
2019-12-13 10:41 ` Stefan Hajnoczi
2019-12-16 19:46 ` Elena Ufimtseva
2019-12-16 19:57 ` Felipe Franciosi
2019-12-17 16:33 ` Stefan Hajnoczi
2019-12-17 22:57 ` Felipe Franciosi
2019-12-18 0:00 ` Paolo Bonzini
2019-12-19 13:36 ` Stefan Hajnoczi
2019-12-20 17:15 ` John G Johnson
2020-01-02 10:00 ` Stefan Hajnoczi
2020-01-02 10:04 ` Stefan Hajnoczi
2019-12-19 11:55 ` Stefan Hajnoczi
2019-12-19 12:33 ` Felipe Franciosi
2019-12-19 12:55 ` Daniel P. Berrangé
2019-12-20 9:47 ` Stefan Hajnoczi
2019-12-20 9:50 ` Paolo Bonzini
2019-12-20 14:14 ` Felipe Franciosi
2019-12-20 15:25 ` Alex Williamson
2019-12-20 16:00 ` Felipe Franciosi
2020-02-25 9:16 ` Thanos Makatos
2019-12-20 10:22 ` Daniel P. Berrangé
2020-01-02 10:42 ` Stefan Hajnoczi
2020-01-02 11:03 ` Felipe Franciosi
2020-01-02 18:55 ` Marc-André Lureau
2020-01-08 16:31 ` Stefan Hajnoczi
2020-01-03 15:59 ` Stefan Hajnoczi
2020-01-14 1:56 ` John G Johnson
2020-01-17 17:25 ` Dr. David Alan Gilbert
2019-12-19 16:40 ` Jag Raman
2019-12-19 12:50 ` Daniel P. Berrangé
2019-12-19 16:46 ` Daniel P. Berrangé
2020-01-02 16:01 ` Elena Ufimtseva
2020-01-03 15:00 ` Stefan Hajnoczi
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=14c33104778e77fcf2e7f0df2a1dd96fbcaf49d7.1571905346.git.jag.raman@oracle.com \
--to=jag.raman@oracle.com \
--cc=armbru@redhat.com \
--cc=berrange@redhat.com \
--cc=dgilbert@redhat.com \
--cc=ehabkost@redhat.com \
--cc=elena.ufimtseva@oracle.com \
--cc=fam@euphon.net \
--cc=john.g.johnson@oracle.com \
--cc=kanth.ghatraju@oracle.com \
--cc=konrad.wilk@oracle.com \
--cc=kraxel@redhat.com \
--cc=kwolf@redhat.com \
--cc=liran.alon@oracle.com \
--cc=marcandre.lureau@gmail.com \
--cc=mreitz@redhat.com \
--cc=mst@redhat.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=quintela@redhat.com \
--cc=ross.lagerwall@citrix.com \
--cc=rth@twiddle.net \
--cc=stefanha@redhat.com \
--cc=thuth@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).