From 414f50434aa2463202a5b35e844f4125dd1a7101 Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Wed, 22 Jan 2020 14:11:25 +1100 Subject: [PATCH] selftests/eeh: Bump EEH wait time to 60s Some newer cards supported by aacraid can take up to 40s to recover after an EEH event. This causes spurious failures in the basic EEH self-test since the current maximim timeout is only 30s. Fix the immediate issue by bumping the timeout to a default of 60s, and allow the wait time to be specified via an environmental variable (EEH_MAX_WAIT). Reported-by: Steve Best Suggested-by: Douglas Miller Signed-off-by: Oliver O'Halloran Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200122031125.25991-1-oohall@gmail.com --- tools/testing/selftests/powerpc/eeh/eeh-functions.sh | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/powerpc/eeh/eeh-functions.sh b/tools/testing/selftests/powerpc/eeh/eeh-functions.sh index 26112ab5cdf4..f52ed92b53e7 100755 --- a/tools/testing/selftests/powerpc/eeh/eeh-functions.sh +++ b/tools/testing/selftests/powerpc/eeh/eeh-functions.sh @@ -53,9 +53,13 @@ eeh_one_dev() { # is a no-op. echo $dev >/sys/kernel/debug/powerpc/eeh_dev_check - # Enforce a 30s timeout for recovery. Even the IPR, which is infamously - # slow to reset, should recover within 30s. - max_wait=30 + # Default to a 60s timeout when waiting for a device to recover. This + # is an arbitrary default which can be overridden by setting the + # EEH_MAX_WAIT environmental variable when required. + + # The current record holder for longest recovery time is: + # "Adaptec Series 8 12G SAS/PCIe 3" at 39 seconds + max_wait=${EEH_MAX_WAIT:=60} for i in `seq 0 ${max_wait}` ; do if pe_ok $dev ; then -- 2.39.5