DLPX-68992 [Backport of DLPX-68991 to 6.0.2.0] Fix zpool history unbo…

…unded memory usage

In original implementation, zpool history will read the whole history
before printing anything, causing memory usage goes unbounded. We fix
this by breaking it into read-print iterations.

Reviewed-by: Tom Caputi <tcaputi@datto.com>
Reviewed-by: Matt Ahrens <matt@delphix.com>
Reviewed-by: Igor Kozhukhov <igor@dilos.org>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Chunwei Chen <david.chen@nutanix.com>
Closes openzfs#9516

cmd/zpool/zpool_main.c

@@ -8528,24 +8528,12 @@ typedef struct hist_cbdata {
 	boolean_t internal;
 } hist_cbdata_t;
 
-/*
- * Print out the command history for a specific pool.
- */
-static int
-get_history_one(zpool_handle_t *zhp, void *data)
+static void
+print_history_records(nvlist_t *nvhis, hist_cbdata_t *cb)
 {
-	nvlist_t *nvhis;
 	nvlist_t **records;
 	uint_t numrecords;
-	int ret, i;
-	hist_cbdata_t *cb = (hist_cbdata_t *)data;
-
-	cb->first = B_FALSE;
-
-	(void) printf(gettext("History for '%s':\n"), zpool_get_name(zhp));
-
-	if ((ret = zpool_get_history(zhp, &nvhis)) != 0)
-		return (ret);
+	int i;
 
 	verify(nvlist_lookup_nvlist_array(nvhis, ZPOOL_HIST_RECORD,
 	    &records, &numrecords) == 0);
@@ -8649,8 +8637,32 @@ get_history_one(zpool_handle_t *zhp, void *data)
 		(void) printf("]");
 		(void) printf("\n");
 	}
+}
+
+/*
+ * Print out the command history for a specific pool.
+ */
+static int
+get_history_one(zpool_handle_t *zhp, void *data)
+{
+	nvlist_t *nvhis;
+	int ret;
+	hist_cbdata_t *cb = (hist_cbdata_t *)data;
+	uint64_t off = 0;
+	boolean_t eof = B_FALSE;
+
+	cb->first = B_FALSE;
+
+	(void) printf(gettext("History for '%s':\n"), zpool_get_name(zhp));
+
+	while (!eof) {
+		if ((ret = zpool_get_history(zhp, &nvhis, &off, &eof)) != 0)
+			return (ret);
+
+		print_history_records(nvhis, cb);
+		nvlist_free(nvhis);
+	}
 	(void) printf("\n");
-	nvlist_free(nvhis);
 
 	return (ret);
 }

include/libzfs.h

@@ -432,7 +432,8 @@ typedef enum {
 extern char *zpool_vdev_name(libzfs_handle_t *, zpool_handle_t *, nvlist_t *,
     int name_flags);
 extern int zpool_upgrade(zpool_handle_t *, uint64_t);
-extern int zpool_get_history(zpool_handle_t *, nvlist_t **);
+extern int zpool_get_history(zpool_handle_t *, nvlist_t **, uint64_t *,
+    boolean_t *);
 extern int zpool_events_next(libzfs_handle_t *, nvlist_t **, int *, unsigned,
     int);
 extern int zpool_events_clear(libzfs_handle_t *, int *);

lib/libzfs/libzfs_pool.c

@@ -4330,33 +4330,37 @@ get_history(zpool_handle_t *zhp, char *buf, uint64_t *off, uint64_t *len)
  * Retrieve the command history of a pool.
  */
 int
-zpool_get_history(zpool_handle_t *zhp, nvlist_t **nvhisp)
+zpool_get_history(zpool_handle_t *zhp, nvlist_t **nvhisp, uint64_t *off,
+    boolean_t *eof)
 {
 	char *buf;
 	int buflen = 128 * 1024;
-	uint64_t off = 0;
 	nvlist_t **records = NULL;
 	uint_t numrecords = 0;
 	int err, i;
+	uint64_t start = *off;
 
 	buf = malloc(buflen);
 	if (buf == NULL)
 		return (ENOMEM);
-	do {
+	/* process about 1MB a time */
+	while (*off - start < 1024 * 1024) {
 		uint64_t bytes_read = buflen;
 		uint64_t leftover;
 
-		if ((err = get_history(zhp, buf, &off, &bytes_read)) != 0)
+		if ((err = get_history(zhp, buf, off, &bytes_read)) != 0)
 			break;
 
 		/* if nothing else was read in, we're at EOF, just return */
-		if (!bytes_read)
+		if (!bytes_read) {
+			*eof = B_TRUE;
 			break;
+		}
 
 		if ((err = zpool_history_unpack(buf, bytes_read,
 		    &leftover, &records, &numrecords)) != 0)
 			break;
-		off -= leftover;
+		*off -= leftover;
 		if (leftover == bytes_read) {
 			/*
 			 * no progress made, because buffer is not big enough
@@ -4368,9 +4372,7 @@ zpool_get_history(zpool_handle_t *zhp, nvlist_t **nvhisp)
 			if (buf == NULL)
 				return (ENOMEM);
 		}
-
-		/* CONSTCOND */
-	} while (1);
+	}
 
 	free(buf);