From: Joe Jin <joe.jin@oracle.com>
To: Dave Scott <Dave.Scott@citrix.com>,
"Liuqiming (John)" <john.liuqiming@huawei.com>
Cc: Zheng Li <dev@zheng.li>, "Luis R. Rodriguez" <mcgrof@suse.com>,
Luonengjun <luonengjun@huawei.com>,
xen-devel <xen-devel@lists.xen.org>,
Fanhenglong <fanhenglong@huawei.com>,
Ian Jackson <Ian.Jackson@citrix.com>
Subject: Re: Lots of connections led oxenstored stuck
Date: Mon, 11 Aug 2014 08:35:37 +0800 [thread overview]
Message-ID: <53E80FD9.3010002@oracle.com> (raw)
In-Reply-To: <56117839-54D7-410D-9008-25F5F18514FA@citrix.com>
On 08/08/14 17:37, Dave Scott wrote:
>
> On 8 Aug 2014, at 09:35, Liuqiming (John) <john.liuqiming@huawei.com> wrote:
>
>> In oxenstored it use "select" for incoming socket, so I don't think it can handle more than 1024 socket connections.
>
> That’s true.
The problem is when oxenstored does not respond any request anymore even all
thread exited, with my reproducer, when you executed it and all threads exited,
"xm list -l" will stuck.
Thanks,
Joe
>
> In the long term I’d like to use Lwt which internally uses libev and has a more scalable event loop.
>
> In the short term I think Zheng Li (cc:d) may have a prototype patch to work around this issue. Is this right, Zheng?
>
> Cheers,
> Dave
>
>>
>>> -----Original Message-----
>>> From: xen-devel-bounces@lists.xen.org
>>> [mailto:xen-devel-bounces@lists.xen.org] On Behalf Of Joe Jin
>>> Sent: Friday, August 08, 2014 3:01 PM
>>> To: David Scott; Luis R. Rodriguez; Ian Jackson
>>> Cc: xen-devel
>>> Subject: [Xen-devel] Lots of connections led oxenstored stuck
>>>
>>> Hi,
>>>
>>> During internal test on Xen-4.3-stable we found sometime when restarted
>>> Xen, it stuck and does not response any request, xenstored.log filled
>>> out below stuff:
>>> [20140702T21:00:41.564Z|error|xenstored] caught exception
>>> Unix.Unix_error(15, "accept", "")
>>>
>>> I created reproducer which will create 2000 connections to oxenstored,
>>> after
>>> ran the reproducer, "xm list --long" will stuck, oxenstored does not
>>> response anymore, same test case passed when use xenstored, any input
>>> will appreciate!
>>>
>>> /*
>>> * This program used to test oxenstored connections stuck issue.
>>> * please compile by below command:
>>> * gcc -o client client.c -lpthread
>>> */
>>> #include <stdio.h>
>>> #include <sys/socket.h>
>>> #include <sys/un.h>
>>> #include <unistd.h>
>>> #include <string.h>
>>> #include <pthread.h>
>>> #include <stdlib.h>
>>> #include <errno.h>
>>>
>>>
>>> void *main_thread(void *arg)
>>> {
>>> struct sockaddr_un address;
>>> int socket_fd, nbytes;
>>> char buffer[256];
>>> int i;
>>> extern int errno;
>>>
>>> memcpy(&i, arg, sizeof(i));
>>> socket_fd = socket(PF_UNIX, SOCK_STREAM, 0);
>>> if (socket_fd < 0) {
>>> fprintf(stderr, "socket() %dth failed, errno=%d\n", i, errno);
>>> return;
>>> }
>>> fprintf(stderr, "socket() %dth ok!\n", i);
>>>
>>> /* start with a clean address structure */
>>> memset(&address, 0, sizeof(struct sockaddr_un));
>>>
>>> address.sun_family = AF_UNIX;
>>> snprintf(address.sun_path, 1024, "/var/run/xenstored/socket");
>>>
>>> if (connect(socket_fd,
>>> (struct sockaddr *) &address,
>>> sizeof(struct sockaddr_un)) != 0) {
>>> fprintf(stderr, "connect() %d failed, error=%d", i, errno);
>>> return;
>>> }
>>> fprintf(stderr, "connec() %dth ok!\n", i);
>>>
>>> while (1)
>>> sleep(1);
>>> if (arg) {
>>> free(arg);
>>> arg = NULL;
>>> }
>>>
>>> return;
>>> }
>>>
>>> int main(void)
>>> {
>>> int i;
>>> for (i = 0; i < 2000; i++) {
>>> void *arg = malloc(sizeof(i));
>>> memset(arg, 0, sizeof(i));
>>> memcpy(arg, &i, sizeof(i));
>>> pthread_t thread;
>>> if (pthread_create(&thread, NULL, main_thread, arg) != 0) {
>>> perror("pthread_create:");
>>> break;
>>> }
>>> }
>>> /* Wait all children exit */
>>> sleep(3);
>>> return 0;
>>> }
>>> /* end */
>>>
>>> Thanks,
>>> Joe
>>>
>>> _______________________________________________
>>> Xen-devel mailing list
>>> Xen-devel@lists.xen.org
>>> http://lists.xen.org/xen-devel
>
>
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@lists.xen.org
> http://lists.xen.org/xen-devel
>
next prev parent reply other threads:[~2014-08-11 0:35 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-08-08 7:01 Lots of connections led oxenstored stuck Joe Jin
2014-08-08 8:35 ` Liuqiming (John)
2014-08-08 9:37 ` Dave Scott
2014-08-11 0:35 ` Joe Jin [this message]
2014-08-11 9:41 ` Dave Scott
2014-08-12 0:19 ` Joe Jin
2014-08-14 8:33 ` Joe Jin
2014-08-26 8:15 ` Joe Jin
2014-08-26 9:02 ` Zheng Li
2014-08-27 1:59 ` Joe Jin
2014-08-27 10:16 ` Zheng Li
2014-08-11 16:58 ` Zheng Li
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=53E80FD9.3010002@oracle.com \
--to=joe.jin@oracle.com \
--cc=Dave.Scott@citrix.com \
--cc=Ian.Jackson@citrix.com \
--cc=dev@zheng.li \
--cc=fanhenglong@huawei.com \
--cc=john.liuqiming@huawei.com \
--cc=luonengjun@huawei.com \
--cc=mcgrof@suse.com \
--cc=xen-devel@lists.xen.org \
/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).