MapReduce　is　a　kind　of　software　framework　for　easily　writing　applications　which　process　vast　amounts　of　data　on　large　clusters　of　commodity　hardware.　In　order　to　get　better　allocation　of　tasks　and　load　balancing,　the　MapReduce　work　mode　and　task　scheduling　algorithm　of　Hadoop　platform　is　analyzed　in　this　paper.　According　to　this　situation　that　the　number　of　tasks　of　the　smaller　weight　job　is　more,　while　that　of　the　larger　weight　job　is　less,　this　paper　introduces　the　idea　of　weighted　round-robin　scheduling　algorithm　into　the　task　scheduling　of　Hadoop　and　puts　forward　the　weight　update　rules　through　analyzing　all　the　situations　of　weight　update.　Experimental　result　indicates　that　it　is　effective　in　making　task　allocation　and　achieving　good　balance　when　it　is　applied　into　the　Hadoop　platform　which　uses　only　JobTracker　scheduling.　©　2013　ACADEMY　PUBLISHER.