From 53e2c875cf97df8337f7ddb5124df2fc6dd37bca Mon Sep 17 00:00:00 2001 From: Jeff Darcy Date: Tue, 7 Mar 2017 18:36:58 -0500 Subject: glusterd: don't queue attach reqs before connecting This was causing USS tests to fail. The underlying problem here is that if we try to queue the attach request too soon after starting a brick process then the socket code will get an error trying to write to the still-unconnected socket. Its response is to shut down the socket, which causes the queued attach requests to be force-unwound. There's nothing to retry them, so they effectively never happen and those bricks (second and succeeding for a snapshot) never become available. We *do* have a retry loop for attach requests, but currently break out as soon as a request is queued - not actually sent. The fix is to modify that loop so it will wait some more if the rpc connection isn't even complete yet. Now we break out only when we have a completed connection *and* a queued request. Change-Id: Ib6be13646f1fa9072b4a944ab5f13e1b29084841 BUG: 1430148 Signed-off-by: Jeff Darcy Reviewed-on: https://review.gluster.org/16868 Smoke: Gluster Build System NetBSD-regression: NetBSD Build System CentOS-regression: Gluster Build System Reviewed-by: Prashanth Pai --- xlators/mgmt/glusterd/src/glusterd-utils.c | 29 ++++++++++++++++++----------- 1 file changed, 18 insertions(+), 11 deletions(-) diff --git a/xlators/mgmt/glusterd/src/glusterd-utils.c b/xlators/mgmt/glusterd/src/glusterd-utils.c index 9df10011a59..2169a69add0 100644 --- a/xlators/mgmt/glusterd/src/glusterd-utils.c +++ b/xlators/mgmt/glusterd/src/glusterd-utils.c @@ -4913,22 +4913,29 @@ my_callback (struct rpc_req *req, struct iovec *iov, int count, void *v_frame) int send_attach_req (xlator_t *this, struct rpc_clnt *rpc, char *path, int op) { - int ret = -1; - struct iobuf *iobuf = NULL; - struct iobref *iobref = NULL; - struct iovec iov = {0, }; - ssize_t req_size = 0; - call_frame_t *frame = NULL; - gd1_mgmt_brick_op_req brick_req; - void *req = &brick_req; - void *errlbl = &&err; - extern struct rpc_clnt_program gd_brick_prog; + int ret = -1; + struct iobuf *iobuf = NULL; + struct iobref *iobref = NULL; + struct iovec iov = {0, }; + ssize_t req_size = 0; + call_frame_t *frame = NULL; + gd1_mgmt_brick_op_req brick_req; + void *req = &brick_req; + void *errlbl = &&err; + struct rpc_clnt_connection *conn; + extern struct rpc_clnt_program gd_brick_prog; if (!rpc) { gf_log (this->name, GF_LOG_ERROR, "called with null rpc"); return -1; } + conn = &rpc->conn; + if (!conn->connected || conn->disconnected) { + gf_log (this->name, GF_LOG_INFO, "not connected yet"); + return -1; + } + brick_req.op = op; brick_req.name = path; brick_req.input.input_val = NULL; @@ -5046,7 +5053,7 @@ attach_brick (xlator_t *this, (void) build_volfile_path (full_id, path, sizeof(path), NULL); int tries = 0; - while (tries++ <= 10) { + while (tries++ <= 15) { ret = send_attach_req (this, other_brick->rpc, path, GLUSTERD_BRICK_ATTACH); if (!ret) { -- cgit