glusterfs.git, branch 2.0.0rc8

Check return value of afr_sh_select_source.

2009-04-20T12:31:24+00:00

If select_source returns -1, abort self-heal.

Signed-off-by: Anand V. Avati

change errno EINVAL to ENOENT in case of all fuse_* calls for fuse_reply_err ()

2009-04-20T12:31:07+00:00

Seen "rm -rf" returns EINVAL in case fuse_loc_fill fails when there is a race condition which can happen when multiple "rm -rf" are done on a same directory listing from multiple terminals.

Signed-off-by: Anand V. Avati

Minor fix in afr_sh_build_pending_matrix.

2009-04-20T10:51:32+00:00

Remove incorrect check for xattr[i] being NULL.

Signed-off-by: Anand V. Avati

inode.c - NULL check for the extra __inode_search performed, when presented inode is not hashed.

2009-04-20T07:45:12+00:00

This bug fixes #967

afr-transaction: handle double flushes

2009-04-20T06:30:50+00:00

__if_fd_pre_op_done - reset fd_ctx->pre_op_done to 0 so that double flushes do not result in two xattrop() calls

client_protocol_reconnect - do not send notify of CHILD_DOWN event if errno from transport_connect() was EINPROGRES

2009-04-20T02:38:26+00:00

This bug was racing between a CHILD_UP from poll thread resulting from the event_register() of the new socket called in fuse thread. CHILD_UP would sometimes overtake the CHILD_DOWN for EINPROGRESS. So replicate would receive CHILD_DOWN as the latest event. This resulted in self-heal not happening etc.

keep ctx->page_size fixed at 128KB but only add the margin for iobufs which are created

2009-04-18T07:57:21+00:00

enhancement to migrate-unify-to-distribute.sh

2009-04-18T06:12:52+00:00

added migration script from unify based setup to distribute based setup

2009-04-18T05:45:23+00:00

Signed-off-by: Anand V. Avati

pruning buffer margin - do not destroy if no other non-filled arenas are in the pool

2009-04-17T21:19:03+00:00