On Wed, 2014-06-04 at 11:45 -0700, Jun Wu wrote:
> The test setup includes one host and one target. The target exposes 10
> hard drives (or 10 LUNs) on one fcoe port. The single initiator runs
> 10 fio processes simultaneously to the 10 target drives through fcoe
> vn2vn. This is a simple configuration that other people may also want
> to try.
>
> >Exchange 0x6e4 is aborted and then target still sending frame, while
> >later should not occur but first setting up abort with 0 msec timeout
> >doesn not look correct either and it is different that 8000 ms on
> >initiator side.
>
> Should target stop sending frame after abort? I still see a lot of 0
> msec messages on target side. Is this something that should be
> addressed?
>
> >Reducing retries could narrow down to early aborts is the cause here,
> >can you try with REC disabled on initiator side for that using this
> >change ?
>
> By disabling REC have you confirmed that the early aborts is the
> cause? Is the abort caused by 0 msec timeout?
>
The 0 msec timeout still look really suspicious..
IIRC, these timeout values are exchanged in the FLOGI request packet,
and/or in a separate Request Timeout Value (RTV) packet..
It might be worthwhile to track down where these zero-length settings
are coming from, as it might be a indication of what's wrong.
How about the following patch to dump these values..?
Also just curious, have you tried running these two hosts in
point-to-point mode without the switch to see if the same types of
issues occur..? It might be useful to help isolate the problem space a
bit.
Vasu, any other ideas here..?
--nab
diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c
index e01a298..72b8676 100644
--- a/drivers/scsi/libfc/fc_lport.c
+++ b/drivers/scsi/libfc/fc_lport.c
@@ -379,6 +379,7 @@ static void fc_lport_flogi_fill(struct fc_lport *lport,
sp->sp_tot_seq = htons(255); /* seq. we accept */
sp->sp_rel_off = htons(0x1f);
sp->sp_e_d_tov = htonl(lport->e_d_tov);
+ printk("fc_lport_flogi_fill sp->sp_e_d_tov: %u\n",
sp->sp_e_d_tov);
cp->cp_rdfs = htons((u16) lport->mfs);
cp->cp_con_seq = htons(255);
@@ -1766,7 +1767,9 @@ void fc_lport_flogi_resp(struct fc_seq *sp, struct
fc_frame *fp,
csp_flags = ntohs(flp->fl_csp.sp_features);
r_a_tov = ntohl(flp->fl_csp.sp_r_a_tov);
+ printk("fc_lport_flogi_resp: r_a_tov: %u\n", r_a_tov);
e_d_tov = ntohl(flp->fl_csp.sp_e_d_tov);
+ printk("fc_lport_flogi_resp: e_d_tov %u\n", e_d_tov);
if (csp_flags & FC_SP_FT_EDTR)
e_d_tov /= 1000000;
@@ -1795,6 +1798,9 @@ void fc_lport_flogi_resp(struct fc_seq *sp, struct
fc_frame *fp,
fc_lport_enter_dns(lport);
}
+ printk("fc_lport_flogi_resp: lport->e_d_tov: %u\n", lport->e_d_tov);
+ printk("fc_lport_flogi_resp: lport->r_a_tov: %u\n", lport->r_a_tov);
+
out:
fc_frame_free(fp);
err:
diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index 589ff9a..4cdb055 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -142,7 +142,9 @@ static struct fc_rport_priv *fc_rport_create(struct
fc_lport *lport,
rdata->event = RPORT_EV_NONE;
rdata->flags = FC_RP_FLAGS_REC_SUPPORTED;
rdata->e_d_tov = lport->e_d_tov;
+ printk("fc_rport_create: rdata->e_d_tov: %u\n", rdata->e_d_tov);
rdata->r_a_tov = lport->r_a_tov;
+ printk("fc_rport_create: rdata->r_a_tov: %u\n", rdata->r_a_tov);
rdata->maxframe_size = FC_MIN_MAX_PAYLOAD;
INIT_DELAYED_WORK(&rdata->retry_work, fc_rport_timeout);
INIT_WORK(&rdata->event_work, fc_rport_work);
@@ -286,7 +288,9 @@ static void fc_rport_work(struct work_struct *work)
rpriv->rp_state = rdata->rp_state;
rpriv->flags = rdata->flags;
rpriv->e_d_tov = rdata->e_d_tov;
+ printk("fc_rport_work: rpriv->e_d_tov: %u\n", rpriv->e_d_tov);
rpriv->r_a_tov = rdata->r_a_tov;
+ printk("rpriv->r_a_tov: rpriv->r_a_tov: %u\n", rpriv->r_a_tov);
mutex_unlock(&rdata->rp_mutex);
if (rport_ops && rport_ops->event_callback) {
@@ -638,10 +642,14 @@ static int fc_rport_login_complete(struct fc_rport_priv
*rdata,
* E_D_TOV is not valid on an incoming FLOGI request.
*/
e_d_tov = ntohl(flogi->fl_csp.sp_e_d_tov);
+ printk("fc_rport_login_complete e_d_tov: %u\n", e_d_tov);
if (csp_flags & FC_SP_FT_EDTR)
e_d_tov /= 1000000;
- if (e_d_tov > rdata->e_d_tov)
+ if (e_d_tov > rdata->e_d_tov) {
+ printk("fc_rport_login_complete rdata->e_d_tov %u\n",
+ rdata->e_d_tov);
rdata->e_d_tov = e_d_tov;
+ }
}
rdata->maxframe_size = fc_plogi_get_maxframe(flogi, lport->mfs);
return 0;
@@ -690,8 +698,11 @@ static void fc_rport_flogi_resp(struct fc_seq *sp, struct
fc_frame *fp,
if (!flogi)
goto bad;
r_a_tov = ntohl(flogi->fl_csp.sp_r_a_tov);
- if (r_a_tov > rdata->r_a_tov)
+ printk("fc_rport_flogi_resp r_a_tov: %u\n", r_a_tov);
+ if (r_a_tov > rdata->r_a_tov) {
+ printk("fc_rport_flogi_resp rdata->r_a_tov: %u\n",
rdata->r_a_tov);
rdata->r_a_tov = r_a_tov;
+ }
if (rdata->ids.port_name < lport->wwpn)
fc_rport_enter_plogi(rdata);
@@ -971,6 +982,7 @@ static void fc_rport_enter_plogi(struct fc_rport_priv
*rdata)
return;
}
rdata->e_d_tov = lport->e_d_tov;
+ printk("fc_rport_enter_plogi: rdata->e_d_tov: %u\n", rdata->e_d_tov);
if (!lport->tt.elsct_send(lport, rdata->ids.port_id, fp, ELS_PLOGI,
fc_rport_plogi_resp, rdata,
@@ -1183,12 +1195,16 @@ static void fc_rport_rtv_resp(struct fc_seq *sp, struct
fc_frame *fp,
if (tov == 0)
tov = 1;
rdata->r_a_tov = tov;
+ printk("fc_rport_rtv_resp rdata->r_a_tov: %u\n",
+ rdata->r_a_tov);
tov = ntohl(rtv->rtv_e_d_tov);
if (toq & FC_ELS_RTV_EDRES)
tov /= 1000000;
if (tov == 0)
tov = 1;
rdata->e_d_tov = tov;
+ printk("fc_rport_rtv_resp rdata->e_d_tov: %u\n",
+ rdata->e_d_tov);
}
}
_______________________________________________
fcoe-devel mailing list
[email protected]
http://lists.open-fcoe.org/mailman/listinfo/fcoe-devel
