Ok, this whole topic usually gives me heartburn. So I'll just point out an interesting blog on this from Mike McCandless: http://blog.mikemccandless.com/2011/04/just-say-no-to-swapping.html
At least tuning swappiness to 0 will tell you whether it's real or phantom. Of course I'd be trying it on a test machine, not prod! FWIW, Erick On Tue, Aug 27, 2013 at 5:50 PM, Shawn Heisey <s...@elyograg.org> wrote: > On 8/27/2013 3:32 PM, vsilgalis wrote: > >> thanks for the quick reply. >> >> I made to rule out what I could around how Linux is handling this stuff. >> Yes I'm using the default swappiness setting of 60, but at this point it >> looks like the machine is swapping now because of low memory. >> >> Here is the vmstat and free -m results: >> <http://lucene.472066.n3.**nabble.com/file/n4086882/** >> vmstat_free_output.png<http://lucene.472066.n3.nabble.com/file/n4086882/vmstat_free_output.png> >> > >> >> >> Here is my top sorted by mem: >> <http://lucene.472066.n3.**nabble.com/file/n4086882/top_**output.png<http://lucene.472066.n3.nabble.com/file/n4086882/top_output.png> >> > >> >> Again, I feel like I might be missing something but not sure what. >> > > You are right, it is definitely swapping, and it's more than a little bit. > I don't see any indication on the top output that anything other than Java > is using a lot of memory, so I don't know what's using the swap. Just to > be sure we have the right info, can you give me the output of the following > command? > > ps aux --sort -rss | cut -c1-80 | head -n 10 > > This looks like your Java (or maybe something else on the box) may be > misbehaving very badly. Can you go to your Solr UI dashboard and get me a > screenshot? I need all the info from the JVM-Memory and JVM sections, > including the whole JVM section. If you have a lot of jvm args, you may > need to scroll down to see them all at once. > > Thanks, > Shawn > >
