On Tue, Mar 16, 2021 at 06:47:39PM +0000, Luis Chamberlain wrote:
> On Tue, Mar 16, 2021 at 05:46:45PM +0000, Luis Chamberlain wrote:
> > I've managed to reproduce blktests block/009 failures with kdevops [0]
> > on linux-next tag next-20210304 with a current failure rate average of
> > 1/448 (3 counted failures so far).
> 
> Confirmed on next-20210316 with current failure rate at 1/1008

Just in case this was a scsi_debug issue instead (I am covering that
prospect on another bug just for scsi_debug korg#212337 [0]) I tried
a userspace solution based on what I have observed I still can reproduce
this block/009 failure. The failure rate is much lower though, I have it
now at 1/1705 but alas it is still failing.

[0] https://bugzilla.kernel.org/show_bug.cgi?id=212337

The patch below demonstrates the exra settle work for scsi_debug
attempted, and with it, this is still failing. So either the settle
work needs *more* effort, or this is a real issue.

diff --git a/common/scsi_debug b/common/scsi_debug
index b48cdc9..ecdbcc6 100644
--- a/common/scsi_debug
+++ b/common/scsi_debug
@@ -8,13 +8,42 @@ _have_scsi_debug() {
        _have_modules scsi_debug
 }
 
+# As per korg#212337 [0] we must do more work in userspace to settle
+# scsi_debug devices a bit more carefully.
+
+# [0] https://bugzilla.kernel.org/show_bug.cgi?id=212337
+_settle_scsi_debug_device() {
+       SCSI_DEBUG_MAX_WAIT=10
+       SCSI_DEBUG_COUNT_WAIT_LOOP=0
+       while true ; do
+               if [[ -b $1 ]]; then
+                       SCSI_DEBUG_LSOF_COUNT=$(lsof $1 | wc -l)
+                       if [[ $SCSI_DEBUG_LSOF_COUNT -ne 0 ]]; then
+                               sleep 1;
+                       else
+                               break
+                       fi
+               else
+                       # Let device come up
+                       sleep 1
+
+                       let 
SCSI_DEBUG_COUNT_WAIT_LOOP=$SCSI_DEBUG_COUNT_WAIT_LOOP+1
+                       if [[ $SCSI_DEBUG_COUNT_WAIT_LOOP -ge 
$SCSI_DEBUG_MAX_WAIT ]]; then
+                               break
+                       fi
+               fi
+       done
+}
+
 _init_scsi_debug() {
        if ! modprobe -r scsi_debug || ! modprobe scsi_debug "$@"; then
                return 1
        fi
-
        udevadm settle
 
+       # Allow dependencies to load
+       sleep 1
+
        local host_sysfs host target_sysfs target
        SCSI_DEBUG_HOSTS=()
        SCSI_DEBUG_TARGETS=()
@@ -43,6 +72,10 @@ _init_scsi_debug() {
                return 1
        fi
 
+       for i in $SCSI_DEBUG_DEVICES ; do
+               _settle_scsi_debug_device /dev/$i
+       done
+
        return 0
 }
 

Reply via email to