Intermittent issue with long concurrent marking phase

Srini Padman srini_was at yahoo.com
Fri Sep 30 08:57:46 PDT 2011


A quick follow up on this:

Testing with JRE 1.6.0_26 (which we were hoping to upgrade to), our QE team has reported a JVM crash (zipped crash dump file attached). This seems almost exactly the same as the one reported here (supposedly introduced in update 25 and fixed in update 27, which would put us right in the crosshairs):

http://bugs.sun.com/bugdatabase/view_bug.do?bug_id=7042582
http://bugs.sun.com/bugdatabase/view_bug.do?bug_id=7013538

Before I assume that: the suggested workaround is -XX:-DoEscapeAnalysis - does this mean that the default is +DoEscapeAnalysis? In other words, is that bug something that affects everybody or only those who explicitly use -XX:+DoEscapeAnalysis? We don't use +DoEscapeAnalysis explicitly, so there is no reason for it to affect us if this is not an option enabled by default.

Of course, we are confirming that this is not merely a matter of memory constraints (seems unlikely, since the tests are the same as were run on previous JREs).

Regards,
Srini.

--- On Fri, 9/30/11, Srini Padman <srini_was at yahoo.com> wrote:

> From: Srini Padman <srini_was at yahoo.com>
> Subject: Re: Intermittent issue with long concurrent marking phase
> To: Y.S.Ramakrishna at oracle.com
> Cc: hotspot-gc-use at openjdk.java.net
> Date: Friday, September 30, 2011, 9:05 AM
> Hi Ramki,
>  
> Apologies, both for mis-reading your original response (re:
> long initial-mark phases) and for choosing the wrong list.
> Thank you very much for redirecting it to gc-use. 
> 
> I just want to clarify a couple of points from your last
> response, for the record.
> 
> To answer the question about the long stop-the-world
> initial marking phase: this is the longest I know of, but we
> have seen other instances where it lasted 3-4 seconds. In
> those cases as well, the "user/sys" times were much smaller
> than the "real" time so things clearly seem to be completely
> stalled. Also as a matter of background - the reason we
> moved to using the CMS collectors was that, prior to this,
> we were occasionally seeing extremely long (sometimes
> lasting more than a minute) full GCs. It is quite possible
> that the same factors that caused such long full GCs in the
> past are causing somewhat shorter (but still not _short_)
> initial mark with the CMS collector. In any case, I didn't
> view this as being related to 6692906 to begin with, and am
> glad to get confirmation that you don't think it is either.
> 
> Regarding your point "A definite symptom of 6692906 can be
> diagnosed if the JVM completely stalls into a livelock (a
> few threads in the JVM intermittently active, but your
> application will forever stop  forward progress from that
> point on). It doesn't look like you have observed that
> latter symptom however?" - my understanding of the symptom
> (based on the summary at http://mail.openjdk.java.net/pipermail/hotspot-gc-dev/2010-February/001549.html,
> for example) was that the wait/stall resolves itself after
> tens of seconds for reasons unknown. Our symptom is closer
> to this, in that the application does not stop _forever_
> from that point onwards. [It is entirely possible that there
> were further findings beyond what is in the posting that I
> am not aware of.]
> 
> We will initiate efforts to reach out to JVM support - of
> course, in the meanwhile, any feedback or help on this forum
> is very welcome!
> 
> Regards,
> Srini.
> 
> --- On Thu, 9/29/11, Y. S. Ramakrishna <y.s.ramakrishna at oracle.com>
> wrote:
> 
> 
> From: Y. S. Ramakrishna <y.s.ramakrishna at oracle.com>
> Subject: Re: Intermittent issue with long concurrent
> marking phase
> To: "Srini Padman" <srini_was at yahoo.com>
> Cc: hotspot-gc-use at openjdk.java.net
> Date: Thursday, September 29, 2011, 8:54 PM
> 
> 
> Hi Srini -- As I indicated, if you cannot upgrade easily to
> test
> if the issue is fixed, you should probably engage JVM
> support to
> get to a proper diagnosis of the issue affecting your
> production systems.
> 
> more inline below ...
> 
> On 09/29/11 07:44, Srini Padman wrote:
> > Hi Ramki,
> >  Thank you very much for your reply.
> >  It is not *always* that the concurrent marking phase
> takes this long, although it happens often enough. For
> example, in the full GC log corresponding to the snippet I
> pasted in my posting (attached, zipped) there is only that
> one instance.
> 
> I see that there is one instance of the long _initial-mark_
> pause
> and as i stated the whole process seems stalled at that
> time.
> It's definitely not the stall/livelock issue of CR
> 6692906.
> 
> [In other words, you may be dealing with several different
> issues
> here and you will need to disentangle them.]
> 
> >  I think I know why you are asking - based on my
> understanding of Bug # 6692906 (more accurately, based on
> discussions around it on this list), I was under the
> impression that such long CM phases will happen all the time
> (if they happen at all). Does the fact that it is
> intermittent raise the possibility that this is a different
> issue? I realize that you might not be able to answer this
> based on the bits of information you have, but perhaps the
> full GC log will tell you something that you don't already
> know.
> 
> Again, my question about once/many was only about the long
> initial mark pause
> of which there is exactly one in your log.
> 
> The stall of mutators during concurrent marking, which you
> are
> conjecturing is 6692906, is a different issue: for that you
> should
> either upgrade and test, or seek JVM support help. It is
> definitely
> possible that the symptoms of 6692906 will happen
> infrequently or
> intermittently. A definite symptom of 6692906 can be
> diagnosed if
> the JVM completely stalls into a livelock (a few threads in
> the
> JVM intermittently active, but your application will
> forever
> stop forward progress from that point on). It doesn't look
> like
> you have observed that latter symptom however?
> 
> Sorry I can't really help more at this time, but perhaps
> someone
> from the community may be able to. But I really suggest
> either
> an upgrade or seeking JVM support help. (This is not a
> professional
> support alias.)
> 
> In general, the GC-use alias is better suited to questions
> such as this.
> GC-dev should be used for GC development questions
> involving
> the main development trunk. Issues of uses in the field of
> older versions should be addressed to hotspot-gc-use at o.j.n
> So I've taken the liberty to send this to hotspot-gc-use at o.j.n
> 
> All the best!
> -- ramki
> 
> >  Regards,
> > Srini.
> > 
> > --- On *Thu, 9/29/11, Ramki Ramakrishna /<y.s.ramakrishna at oracle.com>/*
> wrote:
> > 
> > 
> >     From: Ramki Ramakrishna <y.s.ramakrishna at oracle.com>
> >     Subject: Re: Intermittent issue with long
> concurrent marking phase
> >     To: "Srini Padman" <srini_was at yahoo.com>
> >     Cc: hotspot-gc-dev at openjdk.java.net
> >     Date: Thursday, September 29, 2011, 4:24 AM
> > 
> >     Hi Srini -- (inline below)
> > 
> >     On 9/28/2011 4:50 AM, Srini Padman wrote:
> >> 
> >>     Questions:
> >>          1\ is it clear based on the
> description above that the issue is
> >>     identical to 6692906 (http://bugs.sun.com/view_bug.do?bug_id=6692906)?
> >> 
> > 
> >     Very likely the same bug.
> > 
> >>     2\ will we benefit by upgrading to a more
> recent JRE [1.6.0_26
> >>     being the one under consideration]?
> >> 
> > 
> >     Definitely worth trying.
> > 
> >>     3\ I have seen recommendations to use
> >>     "-XX:-CMSConcurrentMTEnabled" on some web
> forums - but I have
> >>     concerns about this; if we don't allow for
> concurrent marking to
> >>     use multiple threads, then isnt there a
> danger of marking
> >>     proceeding so slowly that we might end up
> running out of memory
> >>     i.e., garbage created much faster than it
> is collected]?
> >> 
> > 
> >     Your concerns are very legitimate (especially
> given the length of
> >     the concurrent mark phase) and the number of
> cores you have.
> > 
> >>          Any help is greatly appreciated.
> Please let me know if any
> >>     additional information is needed at all. I
> haven't attached the
> >>     full GC log (it caused problems with
> posting) but will gladly send
> >>     it directly to anybody who would like.
> >> 
> > 
> >     The long initial mark pause is definitely
> concerning -- Does it show
> >     up regularly
> >     in the GC logs or is the snippet above an
> anomaly? Curisously, as
> >     the process time
> >     shows, the user and system time are both low
> but the elapsed time is
> >     very large.
> >     That looks like a total stall of the process,
> and I have no conjectures
> >     based on available data.
> > 
> >     I suggest talking with your Java support folk
> if you reproduce this
> >     after upgrading to
> >     6u28 (or whatever).
> > 
> >     best regards.
> >     -- ramki
> > 
> >> 
> >>     Regards,
> >>     Srini.
> >> 
> 
>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: app02_hs_err_pid29448.zip
Type: application/x-zip-compressed
Size: 7741 bytes
Desc: not available
Url : http://mail.openjdk.java.net/pipermail/hotspot-gc-dev/attachments/20110930/76d081b1/attachment-0001.bin 
-------------- next part --------------
_______________________________________________
hotspot-gc-use mailing list
hotspot-gc-use at openjdk.java.net
http://mail.openjdk.java.net/mailman/listinfo/hotspot-gc-use


More information about the hotspot-gc-dev mailing list