[SERVER-3822] after upgrade to 2.0.0 mongo starts consuming all cpu resources locking the system, complains of memory leak Created: 13/Sep/11  Updated: 11/Jul/16  Resolved: 07/Oct/11

Status: Closed
Project: Core Server
Component/s: Concurrency
Affects Version/s: 2.0.0
Fix Version/s: 2.0.1, 2.1.0

Type: Bug Priority: Major - P3
Reporter: ttt Assignee: Eliot Horowitz (Inactive)
Resolution: Done Votes: 0
Labels: cpu2
Remaining Estimate: Not Specified
Time Spent: Not Specified
Original Estimate: Not Specified
Environment:

centos 5.6 x64


Issue Links:
Depends
Related
Operating System: Linux
Participants:

 Description   

as never before, mongo started consuming full 4 cores of cpu resulting in system locking for minutes

also complains:

Tue Sep 13 03:09:50 [conn16410] warning: virtual size (40690MB) - mapped size (34768MB) is large. could indicate a memory leak
Tue Sep 13 03:09:55 [conn16410] warning: virtual size (39779MB) - mapped size (34768MB) is large. could indicate a memory leak



 Comments   
Comment by Eliot Horowitz (Inactive) [ 07/Oct/11 ]

https://github.com/mongodb/mongo/commit/61bb89fb9cfa47f8ceab6cc37f4b7c74fe005d23

Comment by auto [ 06/Oct/11 ]

Author:

{u'login': u'erh', u'name': u'Eliot Horowitz', u'email': u'eliot@10gen.com'}

Message: Revert "Wait 1ms between attempt to grab posix_spinlock SERVER-3822"

This reverts commit 2ebc3ba2c8c2eb2ad022edbd600545ebdd5f2989.
Branch: master
https://github.com/mongodb/mongo/commit/61d26a0e8cc53ce383ef69e8311de2decd37b057

Comment by auto [ 05/Oct/11 ]

Author:

{u'login': u'RedBeard0531', u'name': u'Mathias Stearn', u'email': u'mathias@10gen.com'}

Message: Wait 1ms between attempt to grab posix_spinlock SERVER-3822
Branch: master
https://github.com/mongodb/mongo/commit/2ebc3ba2c8c2eb2ad022edbd600545ebdd5f2989

Comment by Mathias Stearn [ 22/Sep/11 ]

We've seen a few similar cases and are trying to track down the details. If you could do the following and send us the output files it would help us greatly:

In mongo shell:
use DBNAME
db.createCollection('system.profile',

{capped:true, size:100*1024*1024}

)
db.setProfilingLevel(1)

Wait 10 minutes

At bash shell:
mongoexport -c 'system.indexes' -d DBNAME
mongodump -c 'system.profile' -d DBNAME

Comment by ttt [ 13/Sep/11 ]

unfortunately, i have forgotten to save that info :/, so won't be able to
provide that info until i get opportunity to arrange a test, sorry.

Comment by Eliot Horowitz (Inactive) [ 13/Sep/11 ]

Can you send db.serverStatus() and mongostat output?

Generated at Thu Feb 08 03:04:09 UTC 2024 using Jira 9.7.1#970001-sha1:2222b88b221c4928ef0de3161136cc90c8356a66.