Hi, @Varada , Abioy : Thanks a lot, will check it out. :) @gregory Farnum,Trying to store 10k 64MB objects on 30 PGs. Reed solomon technique does not crash so I am guessing there is some memory leak happening in the code my team wrote. Thanks and Regards, Elita lobo On Wed, Sep 28, 2016 at 12:21 PM, Gregory Farnum <gfarnum@xxxxxxxxxx> wrote: > > On Tue, Sep 27, 2016 at 10:21 PM, Elita Lobo <loboelita@xxxxxxxxx> wrote: > > Hi, > > > > I am using ceph for a research project and was trying to implement a > > new jerasure plugin. The code works perfectly when I try to put small > > objects ( 16Mb files) in a single pg but breaks when I am trying to > > put some really large object in a cluster having multiple pgs. I am > > pretty sure its a memory leak but not sure how to detect it. > > How big are these "really large object"s? Erasure coding can handle > much bigger objects than replication does, but there are still limits > beyond which stuff will go poorly. > -Greg > > > > > Can someone please suggest some tools that would help me detect > > memory leaks in ceph? > > > > Thanking you, > > Yours sincerely, > > Elita Lobo > > -- > > To unsubscribe from this list: send the line "unsubscribe ceph-devel" in > > the body of a message to majordomo@xxxxxxxxxxxxxxx > > More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
