palloc failures...still...

Morning everyone...

    After upgrading the server to -current, which is meant for
release on April 15th, I'm still receiving a palloc() failure, as shown
below.

    The server is a 486DX with 64Meg of RAM, and the able that is
being searched is *only* 5k records large...and the query below will
return *only* 1 of those records...

Apr 10 01:59:47 clio radiusd[22585]: query failed: select uniq_id from \
    radlog where uniq_id='237286618' and stop_time=0 and \
    term_server='isdn-1.trends.ca';
Apr 10 01:59:47 clio radiusd[22585]: query failed: FATAL 1:  palloc \
    failure: memory exhausted


    And, I'm still getting alot of:

FATAL 1:  btree: BTP_CHAIN flag was expected
FATAL 1:  btree: BTP_CHAIN flag was expected
FATAL 1:  btree: BTP_CHAIN flag was expected
FATAL 1:  btree: BTP_CHAIN flag was expected
FATAL 1:  btree: BTP_CHAIN flag was expected
FATAL 1:  btree: BTP_CHAIN flag was expected
FATAL 1:  btree: BTP_CHAIN flag was expected
FATAL 1:  btree: BTP_CHAIN flag was expected
FATAL 1:  btree: BTP_CHAIN flag was expected