Hi all, just sharing, I think I found what's wrong in this SolrCloud deploy. Looking at Solr Metrics I see the SEARCHER.new entry that increments very rapidly, one, two or even three times every 5 seconds.
SEARCHER.new: 11848 ... 3/4 seconds ... SEARCHER.new: 11849 ... 5 seconds ... SEARCHER.new: 11850 It seems there is something that is committing frequently and looking at UPDATE.updateHandler.commits basically I see the same numbers, but a little bit higher. On Fri, Mar 18, 2022 at 11:56 PM Shawn Heisey <apa...@elyograg.org> wrote: > On 3/18/22 12:35, Vincenzo D'Amore wrote: > > The INDEX.size is 70GB, what do you think if I raise the size allocated > > from the JVM to 64GB in order to have the index in memory? > > Solr and Java do not put the index into memory. The OS does. If you > raise the heap size, there will be LESS memory available for caching the > index. > > The advice to use a 31GB heap is because as soon as the max heap size > hits 32GB, Java switches from 32 bit pointers to 64 bit pointers. > Specifying a 32GB heap actually means the program will get LESS memory > than a max heap of 31GB. I once researched it (not very deeply), and I > think the break-even point for software like Solr doesn't occur until > the heap size is well beyond 40GB. So in many cases, 31GB is a better > setting. > > Thanks, > Shawn > > -- Vincenzo D'Amore
