Thanks so much for the info… I will read the relevant code and/or JIRA issues since I’m not sure what the trigger for on/off heap is yet, and maybe open a ticket for recycling. Hopefully in the short term we can mitigate our fragmentation problem trivially - we upped JVM memory on some nodes last night and fingers crossed it’s been good so far (for those nodes)… but in either case we’ll be early testers of 2.1 in beta.
Thanks, Graham. On May 21, 2014, at 2:20 AM, Benedict Elliott Smith <belliottsm...@datastax.com> wrote: > Graham, > > This is largely fixed in 2.1 with the introduction of partially off-heap > memtables - the slabs reside off-heap, so do not cause any GC issues. > > As it happens the changes would also permit us to recycle on-heap slabs > reasonable easily as well, so feel free to file a ticket for that, although > it won't be back ported to 2.0. > > > On 21 May 2014 00:57, graham sanderson <gra...@vast.com> wrote: > >> So i’ve been tinkering a bit with CMS config because we are still seeing >> fairly frequent full compacting GC due to framgentation/promotion failure >> >> As mentioned below, we are usually too fragmented to promote new in-flight >> memtables. >> >> This is likely caused by sudden write spikes (which we do have), though >> actually the problems don’t generally happen at that time of our largest >> write spikes (though any write spikes likely cause spill of both new >> memtables along with many other new objects of unknown size into the >> tenured gen, so they cause fragmentation if not immediate GC issue). We >> have lots of things going on in this multi-tenant cluster (GC pauses are of >> course extra bad, since they cause spike in hinted-handoff on other nodes >> which were already busy etc…) >> >> Anyway, considering possibilities: >> >> 0) Try and make our application behavior more steady state - this is >> probably possible, but there are lots of other things (e.g. compaction, >> opscenter, repair etc.) which are both tunable and generally throttle-able >> to think about too. >> 1) Play with tweaking PLAB configs to see if we can ease fragmentation >> (I’d be curious what the “crud” is in particular that is getting spilled - >> presumably it is larger objects since it affects the binary tree of large >> objects) >> 2) Given the above, if we can guarantee even > 24 hours without full GC, I >> don’t think we’d mind running a regular rolling re-start on the servers >> during off hours (note usually the GCs don’t have a visible impact, but >> when they hit multiple machines at once they can) >> 3) Zing is seriously an option, if it would save us large amounts of >> tuning, and constant worry about the “next” thing tweaking the allocation >> patterns - does anyone have any experience with Zing & Cassandra >> 4) Given that we expect periodic bursts of writes, >> memtable_total_space_in_mb is bounded, we are not actually short of memory >> (it just gets fragmented), I’m wondering if anyone has played with pinning >> (up to or initially?) that many 1MB chunks of memory via SlabAllocator and >> re-using… It will get promoted once, and then these 1M chunks won’t be part >> of the subsequent promotion hassle… it will probably also allow more crud >> to die in eden under write load since we aren’t allocating these large >> chunks in eden at the same time. Anyway, I had a little look at the code, >> and the life cycles of memtables is not trivial, but was considering >> attempting a patch to play with… anyone have any thoughts? >> >> Basically in summary, the Slab allocator helps by allocating and freeing >> lots of objects at the same time, however any time slabs are allocated >> under load, we end up promoting them with whatever other live stuff in eden >> is still there. If we only do this once and reuse the slabs, we are likely >> to minimize our promotion problem later (at least for these large objects) >> >> On May 16, 2014, at 9:37 PM, graham sanderson <gra...@vast.com> wrote: >> >>> Excellent - thank you… >>> >>> On May 16, 2014, at 7:08 AM, Samuel CARRIERE <samuel.carri...@urssaf.fr> >> wrote: >>> >>>> Hi, >>>> This is arena allocation of memtables. See here for more infos : >>>> http://www.datastax.com/dev/blog/whats-new-in-cassandra-1-0-performance >>>> >>>> >>>> >>>> >>>> De : graham sanderson <gra...@vast.com> >>>> A : dev@cassandra.apache.org, >>>> Date : 16/05/2014 14:03 >>>> Objet : Things that are about 1M big >>>> >>>> >>>> >>>> So just throwing this out there for those for whom this might ring a >> bell. >>>> >>>> I?m debugging some CMS memory fragmentation issues on 2.0.5 - and >>>> interestingly enough most of the objects giving us promotion failures >> are >>>> of size 131074 (dwords) - GC logging obviously doesn?t say what those >> are, >>>> but I?d wager money they are either 1M big byte arrays, or less likely >>>> 256k entry object arrays backing large maps >>>> >>>> So not strictly critical to solving my problem, but I was wondering if >>>> anyone can think of any heap allocated C* objects which are (with no >>>> significant changes to standard cassandra config) allocated in 1M >> chunks. >>>> (It would save me scouring the code, or a 9 gig heap dump if I need to >>>> figure it out!) >>>> >>>> Thanks, >>>> >>>> Graham >>> >> >>
smime.p7s
Description: S/MIME cryptographic signature