[prev in list] [next in list] [prev in thread] [next in thread] 

List:       linux-edac
Subject:    [PATCH v2 3/8] rasdaemon: ras-mc-ctl: Add memory failure events
From:       Shiju Jose <shiju.jose () huawei ! com>
Date:       2021-01-25 17:14:50
Message-ID: 20210125171455.1886-4-shiju.jose () huawei ! com
[Download RAW message or body]

Add supporting memory failure errors (memory_failure_event)
to the ras-mc-ctl tool.

Sample Log,
ras-mc-ctl --summary
...
Memory failure events summary:
        Delayed errors: 4
        Failed errors: 1
...

ras-mc-ctl --errors
...
Memory failure events:
1 2020-10-28 23:20:41 -0800 error: pfn=0x204000000, page_type=free buddy page, \
action_result=Delayed 2 2020-10-28 23:31:38 -0800 error: pfn=0x204000000, \
page_type=free buddy page, action_result=Delayed 3 2020-10-28 23:54:54 -0800 error: \
pfn=0x205000000, page_type=free buddy page, action_result=Delayed 4 2020-10-29 \
00:12:25 -0800 error: pfn=0x204000000, page_type=free buddy page, \
action_result=Delayed 5 2020-10-29 00:26:36 -0800 error: pfn=0x204000000, \
page_type=free buddy page, action_result=Failed

Signed-off-by: Shiju Jose <shiju.jose@huawei.com>
---
 util/ras-mc-ctl.in | 36 +++++++++++++++++++++++++++++++++++-
 1 file changed, 35 insertions(+), 1 deletion(-)

diff --git a/util/ras-mc-ctl.in b/util/ras-mc-ctl.in
index d8abdbd..eebcc4e 100755
--- a/util/ras-mc-ctl.in
+++ b/util/ras-mc-ctl.in
@@ -1120,7 +1120,7 @@ sub summary
 {
     require DBI;
     my ($query, $query_handle, $out);
-    my ($err_type, $label, $mc, $top, $mid, $low, $count, $msg);
+    my ($err_type, $label, $mc, $top, $mid, $low, $count, $msg, $action_result);
     my ($etype, $severity, $etype_string, $severity_string);
     my ($dev_name, $dev);
     my ($mpidr);
@@ -1225,6 +1225,22 @@ sub summary
     }
     $query_handle->finish;
 
+    # Memory failure errors
+    $query = "select action_result, count(*) from memory_failure_event group by \
action_result"; +    $query_handle = $dbh->prepare($query);
+    $query_handle->execute();
+    $query_handle->bind_columns(\($action_result, $count));
+    $out = "";
+    while($query_handle->fetch()) {
+        $out .= "\t$action_result errors: $count\n";
+    }
+    if ($out ne "") {
+        print "Memory failure events summary:\n$out\n";
+    } else {
+        print "No Memory failure errors.\n\n";
+    }
+    $query_handle->finish;
+
     # MCE mce_record errors
     $query = "select error_msg, count(*) from mce_record group by error_msg";
     $query_handle = $dbh->prepare($query);
@@ -1253,6 +1269,7 @@ sub errors
     my ($bus_name, $dev_name, $driver_name, $reporter_name);
     my ($dev, $sector, $nr_sector, $error, $rwbs, $cmd);
     my ($error_count, $affinity, $mpidr, $r_state, $psci_state);
+    my ($pfn, $page_type, $action_result);
 
     my $dbh = DBI->connect("dbi:SQLite:dbname=$dbname", "", "", {});
 
@@ -1384,6 +1401,23 @@ sub errors
     }
     $query_handle->finish;
 
+    # Memory failure errors
+    $query = "select id, timestamp, pfn, page_type, action_result from \
memory_failure_event order by id"; +    $query_handle = $dbh->prepare($query);
+    $query_handle->execute();
+    $query_handle->bind_columns(\($id, $timestamp, $pfn, $page_type, \
$action_result)); +    $out = "";
+    while($query_handle->fetch()) {
+        $out .= "$id $timestamp error: ";
+        $out .= "pfn=$pfn, page_type=$page_type, action_result=$action_result\n";
+    }
+    if ($out ne "") {
+        print "Memory failure events:\n$out\n";
+    } else {
+        print "No Memory failure errors.\n\n";
+    }
+    $query_handle->finish;
+
     # MCE mce_record errors
     $query = "select id, timestamp, mcgcap, mcgstatus, status, addr, misc, ip, tsc, \
walltime, cpu, cpuid, apicid, socketid, cs, bank, cpuvendor, bank_name, error_msg, \
mcgstatus_msg, mcistatus_msg, user_action, mc_location from mce_record order by id";  \
                $query_handle = $dbh->prepare($query);
-- 
2.17.1


[prev in list] [next in list] [prev in thread] [next in thread]