[Orca-checkins] r398 - trunk/orca/data_gatherers/orcallator

[dmberezin at hotmail.com]

Author: dmberezin at hotmail.com
Date: Mon Oct 11 12:10:53 2004
New Revision: 398

Modified:
   trunk/orca/data_gatherers/orcallator/orcallator.se
Log:
Fix for kio.nread bug in SE

* data_gatherers/orcallator/orcallator.se
  (get_new_kstat_data): new function
  (orca_io_info_update): add code to re-read kstat data if kio.nread appears to
  be corrupt.
  SE appears to have a bug - occasionally kio.nread is erroneously set to 0. It
  looks like a memory management problem somewhere deep in SE's code, since
  this problem is related to any memory allocation calls elsewhere in the
  script. For example, a call to "renew" inside kstat traversing loop will
  cause nread to be 0 in the next iteration of the loop. "Data fixing" code,
  dealing with this issue, was removed in revision 392. This patch introduces a
  new function to re-read affected kstat, instead of ignoring bad data.
  I can add a few more "if" statements to cover the case when re-read data is
  still bad, but I think this will be an overkill, since we should trust SE to
  some degree :-).


Modified: trunk/orca/data_gatherers/orcallator/orcallator.se
==============================================================================
--- trunk/orca/data_gatherers/orcallator/orcallator.se	(original)
+++ trunk/orca/data_gatherers/orcallator/orcallator.se	Mon Oct 11 12:10:53 2004
@@ -339,6 +339,37 @@
   uint          _rcnt;          // Count of elements in run state
 };
 
+// SE appears to have a bug - occasionally kio.nread is erroneously set to 0.
+// This function is used to re-read data for a given kstat.
+ulong get_new_kstat_data(kstat_t okp[1]) {
+  ulong         ul;
+  kstat_ctl_t   kc[1];
+  kstat_t       nkp[1];
+  kstat_t       rkp[1];
+
+  // Return old data if no match found
+  rkp = okp;
+  // Initialize kstat control structure
+  kc[0] = kstat_open();
+  // Traverse the chain looking for matching kstat
+  for (ul=kc[0].kc_chain; ul!=0; ul=nkp[0].ks_next) {
+    nkp[0] = *((kstat_t *) ul);
+    if (nkp[0].ks_type     == okp[0].ks_type &&
+        nkp[0].ks_class    == okp[0].ks_class &&
+        nkp[0].ks_name     == okp[0].ks_name &&
+        nkp[0].ks_instance == okp[0].ks_instance ) {
+      if (kstat_read(kc, nkp, 0) == -1) {
+        perror("get_new_kstat_data:kstat_read error");
+        exit(1);
+      }
+      rkp = nkp;
+      break;
+    }
+  }
+  kstat_close(kc);
+  return  rkp[0].ks_data;
+}
+
 // Define globals for tracking kstat io data.
 io_dev_info_t   ORCA_io_dev_info[];
 int             ORCA_io_dev_count=0;
@@ -408,6 +439,17 @@
         }
         ORCA_io_dev_info[iodev].short_name   = nkp[0].ks_name;
         ORCA_io_dev_info[iodev].dev_class    = nkp[0].ks_class;
+
+        // Check if kio data is valid, and re-read kstat if it is not.
+        // At this time, only kio.nread appears to have occasional problems,
+        // but we check the other three just in case.
+        // It is possible for these statistics to be 0, in such case
+        // kio data will remain the same.
+        if (kio.writes == 0 || kio.nwritten == 0 ||
+            kio.reads  == 0 || kio.nread    == 0) {
+          kio = *((kstat_io_t *) get_new_kstat_data(nkp));
+        }
+
         ORCA_io_dev_info[iodev]._writes      = kio.writes;
         ORCA_io_dev_info[iodev]._nwritten    = kio.nwritten;
         ORCA_io_dev_info[iodev]._wlastupdate = kio.wlastupdate;
@@ -422,6 +464,15 @@
         ORCA_io_dev_info[iodev]._rcnt        = kio.rcnt;
         ORCA_io_dev_count++;
       }
+      // Check if kio data is valid, and re-read kstat if it is not.
+      // At this time, only kio.nread appears to have occasional problems,
+      // but we check the other three just in case.
+      if (kio.writes   < ORCA_io_dev_info[iodev]._writes ||
+          kio.nwritten < ORCA_io_dev_info[iodev]._nwritten ||
+          kio.reads    < ORCA_io_dev_info[iodev]._reads ||
+          kio.nread    < ORCA_io_dev_info[iodev]._nread) {
+        kio = *((kstat_io_t *) get_new_kstat_data(nkp));
+      }
 
       elapsed_etime = (kio.wlastupdate-ORCA_io_dev_info[iodev]._wlastupdate);
       if (elapsed_etime == 0) {