Date: Fri, 10 Nov 2006 23:49:33 +0100 (CET) From: "Arne H. Juul" <arnej@pvv.ntnu.no> To: Nikos Ntarmos <ntarmos@ceid.upatras.gr> Cc: freebsd-java@freebsd.org Subject: Re: Performance of Java on FBSD vs. others... Message-ID: <Pine.LNX.4.62.0611102345280.3696@decibel.pvv.ntnu.no> In-Reply-To: <20061110221501.GC72658@ace.b020.ceid.upatras.gr> References: <20061110203714.GA89006@ace.b020.ceid.upatras.gr> <20061110124459.M88944@turing> <20061110213313.GA72658@ace.b020.ceid.upatras.gr> <Pine.LNX.4.62.0611102249050.18941@decibel.pvv.ntnu.no> <20061110221501.GC72658@ace.b020.ceid.upatras.gr>
next in thread | previous in thread | raw e-mail | index | archive | help
On Sat, 11 Nov 2006, Nikos Ntarmos wrote: >>> I was using -Xms256m -Xmx1024m. Tried with -Xms1024m -Xmx1024m, again >>> without any noticeable difference. >> >> What's "top" look like after running this for a minute or two? You >> said you had 1G = 1024MB of RAM; trying to have a heap of 1024m you >> may be swapping like crazy, if so try with 600m to 800m. > > Nope, it's not swap that's killing it... The program i'm running is a > p2p network simulation; first, it generates a number of nodes, then it > populates the resulting overlay with data, then it queries it. During > the node generation part, memory requirements are in the vicinity of > 200-300 MBytes, then they go up as data items get added. However, the > difference in performance shows up even in this first stage: ~1000'' for > FreeBSD, ~210'' for win32, ~220 for linux. is it possible to post the program for others to test? (if there's no trade secrets or similar in it) I'd like to run it; I've been compiling my own version of the Java VM with various tweaks on FreeBSD 4 and this sounds like a better test than the programs I've been using so far. - Arne H. J.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.LNX.4.62.0611102345280.3696>