Commit 59661212 authored by tsutomu.owa@toshiba.co.jp's avatar tsutomu.owa@toshiba.co.jp Committed by David Teigland
Browse files

DLM: retry rcom when dlm_wait_function is timed out. 



If a node sends a DLM_RCOM_STATUS command and an error occurs on the
receiving side, the DLM_RCOM_STATUS_REPLY response may not be returned.
We retransmitted the DLM_RCOM_STATUS command so that we do not wait for
an infinite response.

Signed-off-by: default avatarTadashi Miyauchi <miyauchi@toshiba-tops.co.jp>
Signed-off-by: default avatarTsutomu Owa <tsutomu.owa@toshiba.co.jp>
Signed-off-by: default avatarDavid Teigland <teigland@redhat.com>
parent c7355827

fs/dlm/rcom.c

+6 −0
Original line number Diff line number Diff line
@@ -155,6 +155,7 @@ int dlm_rcom_status(struct dlm_ls *ls, int nodeid, uint32_t status_flags) 
		goto out;

	}



retry:

	error = create_rcom(ls, nodeid, DLM_RCOM_STATUS,

			    sizeof(struct rcom_status), &rc, &mh);

	if (error)
@@ -169,6 +170,8 @@ int dlm_rcom_status(struct dlm_ls *ls, int nodeid, uint32_t status_flags) 


	error = dlm_wait_function(ls, &rcom_response);

	disallow_sync_reply(ls);

	if (error == -ETIMEDOUT)

		goto retry;

	if (error)

		goto out;
@@ -276,6 +279,7 @@ int dlm_rcom_names(struct dlm_ls *ls, int nodeid, char *last_name, int last_len) 


	ls->ls_recover_nodeid = nodeid;



retry:

	error = create_rcom(ls, nodeid, DLM_RCOM_NAMES, last_len, &rc, &mh);

	if (error)

		goto out;
@@ -288,6 +292,8 @@ int dlm_rcom_names(struct dlm_ls *ls, int nodeid, char *last_name, int last_len) 


	error = dlm_wait_function(ls, &rcom_response);

	disallow_sync_reply(ls);

	if (error == -ETIMEDOUT)

		goto retry;

 out:

	return error;

}

fs/dlm/recover.c

+4 −0
Original line number Diff line number Diff line
@@ -52,6 +52,10 @@ int dlm_wait_function(struct dlm_ls *ls, int (*testfn) (struct dlm_ls *ls)) 
					dlm_config.ci_recover_timer * HZ);

		if (rv)

			break;

		if (test_bit(LSFL_RCOM_WAIT, &ls->ls_flags)) {

			log_debug(ls, "dlm_wait_function timed out");

			return -ETIMEDOUT;

		}

	}



	if (dlm_recovery_stopped(ls)) {

CRA Git | Maintained and supported by SUSTech CRA and CCSE