zdb: add --class=(normal|special|...) to filter blocks by alloc class

When counting blocks to generate block size histograms (`-bb`), accept a
`--class=` argument (as a comma-separated list of either "normal",
"special", "dedup" or "other") to only consider blocks that belong to
these metaslab classes.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Ivan Shapovalov <intelfx@intelfx.name>
Closes #16999

cmd/zdb/zdb.c

@@ -109,6 +109,7 @@ extern uint_t zfs_btree_verify_intensity;
 enum {
 	ARG_ALLOCATED = 256,
 	ARG_BLOCK_BIN_MODE,
+	ARG_BLOCK_CLASSES,
 };
 
 static const char cmdname[] = "zdb";
@@ -141,6 +142,13 @@ static enum {
 	BIN_ASIZE,
 } block_bin_mode = BIN_AUTO;
 
+static enum {
+	CLASS_NORMAL = 1 << 1,
+	CLASS_SPECIAL = 1 << 2,
+	CLASS_DEDUP = 1 << 3,
+	CLASS_OTHER = 1 << 4,
+} block_classes = 0;
+
 static void snprintf_blkptr_compact(char *, size_t, const blkptr_t *,
     boolean_t);
 static void mos_obj_refd(uint64_t);
@@ -761,6 +769,10 @@ usage(void)
 	    "block statistics\n");
 	(void) fprintf(stderr, "           --bin=(lsize|psize|asize) "
 	    "bin blocks based on this size in all three columns\n");
+	(void) fprintf(stderr,
+	    "           --class=(normal|special|dedup|other)[,...]\n"
+	    "                                     only consider blocks from "
+	    "these allocation classes\n");
 	(void) fprintf(stderr, "        -B --backup                  "
 	    "backup stream\n");
 	(void) fprintf(stderr, "        -c --checksum                "
@@ -5840,6 +5852,20 @@ dump_size_histograms(zdb_cb_t *zcb)
 		printf("(note: all categories are binned separately)\n");
 		break;
 	}
+	if (block_classes != 0) {
+		char buf[256] = "";
+		if (block_classes & CLASS_NORMAL)
+			strlcat(buf, "\"normal\", ", sizeof (buf));
+		if (block_classes & CLASS_SPECIAL)
+			strlcat(buf, "\"special\", ", sizeof (buf));
+		if (block_classes & CLASS_DEDUP)
+			strlcat(buf, "\"dedup\", ", sizeof (buf));
+		if (block_classes & CLASS_OTHER)
+			strlcat(buf, "\"other\", ", sizeof (buf));
+		buf[strlen(buf)-2] = '\0';
+		printf("(note: only blocks in these classes are counted: %s)\n",
+		    buf);
+	}
 	/*
 	 * Print the first line titles
 	 */
@@ -6189,6 +6215,38 @@ skipped:
 		return;
 	}
 
+	if (block_classes != 0) {
+		spa_config_enter(zcb->zcb_spa, SCL_CONFIG, FTAG, RW_READER);
+
+		uint64_t vdev = DVA_GET_VDEV(&bp->blk_dva[0]);
+		uint64_t offset = DVA_GET_OFFSET(&bp->blk_dva[0]);
+		vdev_t *vd = vdev_lookup_top(zcb->zcb_spa, vdev);
+		ASSERT(vd != NULL);
+		metaslab_t *ms = vd->vdev_ms[offset >> vd->vdev_ms_shift];
+		ASSERT(ms != NULL);
+		metaslab_group_t *mg = ms->ms_group;
+		ASSERT(mg != NULL);
+		metaslab_class_t *mc = mg->mg_class;
+		ASSERT(mc != NULL);
+
+		spa_config_exit(zcb->zcb_spa, SCL_CONFIG, FTAG);
+
+		int class;
+		if (mc == spa_normal_class(zcb->zcb_spa)) {
+			class = CLASS_NORMAL;
+		} else if (mc == spa_special_class(zcb->zcb_spa)) {
+			class = CLASS_SPECIAL;
+		} else if (mc == spa_dedup_class(zcb->zcb_spa)) {
+			class = CLASS_DEDUP;
+		} else {
+			class = CLASS_OTHER;
+		}
+
+		if (!(block_classes & class)) {
+			goto hist_skipped;
+		}
+	}
+
 	/*
 	 * The binning histogram bins by powers of two up to
 	 * SPA_MAXBLOCKSIZE rather than creating bins for
@@ -6225,6 +6283,7 @@ skipped:
 	zcb->zcb_asize_len[bin] += BP_GET_ASIZE(bp);
 	zcb->zcb_asize_total += BP_GET_ASIZE(bp);
 
+hist_skipped:
 	if (!do_claim)
 		return;
 
@@ -9469,6 +9528,8 @@ main(int argc, char **argv)
 		    ARG_ALLOCATED},
 		{"bin",			required_argument,	NULL,
 		    ARG_BLOCK_BIN_MODE},
+		{"class",		required_argument,	NULL,
+		    ARG_BLOCK_CLASSES},
 		{0, 0, 0, 0}
 	};
 
@@ -9596,6 +9657,45 @@ main(int argc, char **argv)
 				usage();
 			}
 			break;
+
+		case ARG_BLOCK_CLASSES: {
+			char *buf = strdup(optarg), *tok = buf, *next,
+			    *save = NULL;
+
+			while ((next = strtok_r(tok, ",", &save)) != NULL) {
+				tok = NULL;
+
+				if (strcmp(next, "normal") == 0) {
+					block_classes |= CLASS_NORMAL;
+				} else if (strcmp(next, "special") == 0) {
+					block_classes |= CLASS_SPECIAL;
+				} else if (strcmp(next, "dedup") == 0) {
+					block_classes |= CLASS_DEDUP;
+				} else if (strcmp(next, "other") == 0) {
+					block_classes |= CLASS_OTHER;
+				} else {
+					(void) fprintf(stderr,
+					    "--class=\"%s\" must be a "
+					    "comma-separated list of either "
+					    "\"normal\", \"special\", "
+					    "\"asize\" or \"other\"; "
+					    "got \"%s\"\n",
+					    optarg, next);
+					usage();
+				}
+			}
+
+			if (block_classes == 0) {
+				(void) fprintf(stderr,
+				    "--class= must be a comma-separated "
+				    "list of either \"normal\", \"special\", "
+				    "\"asize\" or \"other\"; got empty\n");
+				usage();
+			}
+
+			free(buf);
+			break;
+		}
 		default:
 			usage();
 			break;

man/man8/zdb.8

@@ -154,6 +154,10 @@ For instance, with
 .Fl -bin Ns = Ns Li lsize ,
 a block with lsize of 16K and psize of 4K will be added to the 16K bin
 in all three columns.
+.It Fl -class Ns = Ns ( Li normal Ns | Ns Li special Ns | Ns Li dedup Ns | Ns Li other ) Ns Op , Ns …
+When used with
+.Fl bb ,
+only consider blocks from these allocation classes.
 .It Fl B , -backup
 Generate a backup stream, similar to
 .Nm zfs Cm send ,