aboutsummaryrefslogtreecommitdiff
path: root/src/backend/tcop/postgres.c
diff options
context:
space:
mode:
authorRobert Haas <rhaas@postgresql.org>2011-01-29 08:08:41 -0500
committerRobert Haas <rhaas@postgresql.org>2011-01-29 08:08:41 -0500
commit7f242d880b5b5d9642675517466d31373961cf98 (patch)
tree81245187cb86ff5448819d86b84257056e1fc7ca /src/backend/tcop/postgres.c
parentb2826ad52d72195317a13c2074a5cd002c98a338 (diff)
downloadpostgresql-7f242d880b5b5d9642675517466d31373961cf98.tar.gz
postgresql-7f242d880b5b5d9642675517466d31373961cf98.zip
Try to avoid running with a full fsync request queue.
When we need to insert a new entry and the queue is full, compact the entire queue in the hopes of making room for the new entry. Doing this on every insertion might worsen contention on BgWriterCommLock, but when the queue it's full, it's far better than allowing the backend to perform its own fsync, per testing by Greg Smith as reported in http://archives.postgresql.org/pgsql-hackers/2011-01/msg02665.php Original idea from Greg Smith. Patch by me. Review by Chris Browne and Greg Smith
Diffstat (limited to 'src/backend/tcop/postgres.c')
0 files changed, 0 insertions, 0 deletions