[Zodb-checkins] CVS: ZODB3/ZEO - stats.py:1.19 simul.py:1.16

[Guido van Rossum]

Update of /cvs-repository/ZODB3/ZEO
In directory cvs.zope.org:/tmp/cvs-serv9408

Modified Files:
	stats.py simul.py 
Log Message:
Add -X option to enable a heavier-duty heuristic for skipping bad
records (requiring occasional seeks).


=== ZODB3/ZEO/stats.py 1.18 => 1.19 ===
--- ZODB3/ZEO/stats.py:1.18	Tue Oct  8 12:28:27 2002
+++ ZODB3/ZEO/stats.py	Fri Nov 22 11:42:29 2002
@@ -14,13 +14,15 @@
 ##############################################################################
 """Trace file statistics analyzer.
 
-Usage: stats.py [-h] [-i interval] [-q] [-s] [-S] [-v] tracefile
+Usage: stats.py [-h] [-i interval] [-q] [-s] [-S] [-v] [-X] tracefile
 -h: print histogram of object load frequencies
 -i: summarizing interval in minutes (default 15; max 60)
 -q: quiet; don't print summaries
 -s: print histogram of object sizes
 -S: don't print statistics
 -v: verbose; print each record
+-X: enable heuristic checking for misaligned records: oids > 2**32
+    will be rejected; this requires the tracefile to be seekable
 """
 
 """File format:
@@ -67,8 +69,9 @@
     print_size_histogram = 0
     print_histogram = 0
     interval = 900 # Every 15 minutes
+    heuristic = 0
     try:
-        opts, args = getopt.getopt(sys.argv[1:], "hi:qsSv")
+        opts, args = getopt.getopt(sys.argv[1:], "hi:qsSvX")
     except getopt.error, msg:
         usage(msg)
         return 2
@@ -90,6 +93,8 @@
             dostats = 0
         if o == "-v":
             verbose = 1
+        if o == '-X':
+            heuristic = 1
     if len(args) != 1:
         usage("exactly one file argument required")
         return 2
@@ -148,14 +153,24 @@
             if ts == 0:
                 # Must be a misaligned record caused by a crash
                 if not quiet:
-                    print "Skipping 8 bytes at offset", offset-8
+                    print "Skipping 8 bytes at offset", offset-8,
+                    print repr(r)
                 continue
-            r = f_read(16)
-            if len(r) < 16:
+            oid = f_read(8)
+            if len(oid) < 8:
                 break
-            offset += 16
+            if heuristic and oid[:4] != '\0\0\0\0':
+                # Heuristic for severe data corruption
+                print "Seeking back over bad oid at offset", offset,
+                print repr(r)
+                f.seek(-8, 1)
+                continue
+            offset += 8
+            serial = f_read(8)
+            if len(serial) < 8:
+                break
+            offset += 8
             records += 1
-            oid, serial = struct_unpack(">8s8s", r)
             if t0 is None:
                 t0 = ts
                 thisinterval = t0 / interval


=== ZODB3/ZEO/simul.py 1.15 => 1.16 ===
--- ZODB3/ZEO/simul.py:1.15	Wed Oct 16 17:35:32 2002
+++ ZODB3/ZEO/simul.py	Fri Nov 22 11:42:29 2002
@@ -14,7 +14,7 @@
 ##############################################################################
 """Cache simulation.
 
-Usage: simul.py [-bflyz] [-s size] tracefile
+Usage: simul.py [-bflyz] [-X] [-s size] tracefile
 
 Use one of -b, -f, -l, -y or -z select the cache simulator:
 -b: buddy system allocator
@@ -25,6 +25,8 @@
 
 Options:
 -s size: cache size in MB (default 20 MB)
+-X: enable heuristic checking for misaligned records: oids > 2**32
+    will be rejected; this requires the tracefile to be seekable
 
 Note: the buddy system allocator rounds the cache size up to a power of 2
 """
@@ -43,8 +45,9 @@
     MB = 1000*1000
     cachelimit = 20*MB
     simclass = ZEOCacheSimulation
+    heuristic = 0
     try:
-        opts, args = getopt.getopt(sys.argv[1:], "bflyzs:")
+        opts, args = getopt.getopt(sys.argv[1:], "bflyzs:X")
     except getopt.error, msg:
         usage(msg)
         return 2
@@ -61,6 +64,8 @@
             simclass = ZEOCacheSimulation
         if o == '-s':
             cachelimit = int(float(a)*MB)
+        if o == '-X':
+            heuristic = 1
     if len(args) != 1:
         usage("exactly one file argument required")
         return 2
@@ -112,12 +117,18 @@
             # Must be a misaligned record caused by a crash
             ##print "Skipping 8 bytes at offset", offset-8
             continue
-        r = f_read(16)
-        if len(r) < 16:
+        oid = f_read(8)
+        if len(oid) < 8:
             break
-        offset += 16
+        if heuristic and oid[:4] != '\0\0\0\0':
+            f.seek(-8, 1)
+            continue
+        offset += 8
+        serial = f_read(8)
+        if len(serial) < 8:
+            break
+        offset += 8
         records += 1
-        oid, serial = struct_unpack(">8s8s", r)
         # Decode the code
         dlen, version, code, current = (code & 0x7fffff00,
                                         code & 0x80,