URGENT pg_xlog full impossible to restart ...

Hi,

I have my database stoping by itself during a vacuum full analyse;

Impossible to restart it ... I have this message :
Jul 17 22:03:09 stats-ugc postgres[7239]: [2-1] LOG:  database system was shut
down at 2004-07-17 20:53:06 CEST
Jul 17 22:03:09 stats-ugc postgres[7239]: [3-1] LOG:  checkpoint record is at
400/49FFE4B0
Jul 17 22:03:09 stats-ugc postgres[7239]: [4-1] LOG:  redo record is at
400/49FFE4B0; undo record is at 0/0; shutdown TRUE
Jul 17 22:03:09 stats-ugc postgres[7239]: [5-1] LOG:  next transaction ID:
499350; next OID: 1874767379
Jul 17 22:03:09 stats-ugc postgres[7239]: [6-1] PANIC:  could not write to
file "/usr/local/pgsql/data/pg_xlog/xlogtemp.7239": No space left on device
Jul 17 22:03:09 stats-ugc postgres[7236]: [2-1] LOG:  startup process (PID
7239) was terminated by signal 6
Jul 17 22:03:09 stats-ugc postgres[7236]: [3-1] LOG:  aborting startup due to
startup process failure

How to solve this ??? My pg_xlog partition is full ... :o(

Thanks !
--
Bill Footcow