DAOS-16327 control: Update dmg storage query usage for MD-on-SSD P2 (#…

…15418)

Update dmg storage query usage for MD-on-SSD P2

Signed-off-by: Tom Nabarro <[email protected]>

src/control/cmd/dmg/pretty/pool.go

@@ -57,32 +57,45 @@ func printTierBytesRow(fmtName string, tierBytes uint64, numRanks int) txtfmt.Ta
 	}
 }
 
-func getPoolCreateRespRows(mdOnSSD bool, tierBytes []uint64, tierRatios []float64, numRanks int) (title string, rows []txtfmt.TableRow) {
+func getPoolCreateRespRows(tierBytes []uint64, tierRatios []float64, numRanks int) (title string, rows []txtfmt.TableRow) {
 	title = "Pool created with "
 	tierName := "SCM"
-	if mdOnSSD {
-		tierName = "Metadata"
-	}
 
 	for tierIdx, tierRatio := range tierRatios {
 		if tierIdx > 0 {
 			title += ","
 			tierName = "NVMe"
-			if mdOnSSD {
-				tierName = "Data"
-			}
 		}
 
 		title += PrintTierRatio(tierRatio)
 		fmtName := fmt.Sprintf("Storage tier %d (%s)", tierIdx, tierName)
-		if mdOnSSD {
-			fmtName = tierName + " Storage"
+		rows = append(rows, printTierBytesRow(fmtName, tierBytes[tierIdx], numRanks))
+	}
+	title += " storage tier ratio"
+
+	return
+}
+
+func getPoolCreateRespRowsMDOnSSD(tierBytes []uint64, tierRatios []float64, numRanks int, memFileBytes uint64) (title string, rows []txtfmt.TableRow) {
+	title = "Pool created with "
+	tierName := "Metadata"
+
+	for tierIdx, tierRatio := range tierRatios {
+		if tierIdx > 0 {
+			title += ","
+			tierName = "Data"
 		}
+
+		title += PrintTierRatio(tierRatio)
+		fmtName := tierName + " Storage"
 		rows = append(rows, printTierBytesRow(fmtName, tierBytes[tierIdx], numRanks))
 	}
 	title += " storage tier ratio"
 
-	return title, rows
+	// Print memory-file size for MD-on-SSD.
+	rows = append(rows, printTierBytesRow("Memory File Size", memFileBytes, numRanks))
+
+	return
 }
 
 // PrintPoolCreateResponse generates a human-readable representation of the pool create
@@ -122,17 +135,14 @@ func PrintPoolCreateResponse(pcr *control.PoolCreateResp, out io.Writer, opts ..
 		"Total Size": humanize.Bytes(totalSize * uint64(numRanks)),
 	})
 
-	mdOnSsdEnabled := pcr.MemFileBytes > 0
-
-	title, tierRows := getPoolCreateRespRows(mdOnSsdEnabled, pcr.TierBytes, tierRatios,
-		numRanks)
-
-	// Print memory-file to meta-blob ratio for MD-on-SSD.
-	if mdOnSsdEnabled {
-		tierRows = append(tierRows, printTierBytesRow("Memory File Size",
-			pcr.MemFileBytes, numRanks))
+	var title string
+	var tierRows []txtfmt.TableRow
+	if pcr.MemFileBytes > 0 {
+		title, tierRows = getPoolCreateRespRowsMDOnSSD(pcr.TierBytes, tierRatios, numRanks,
+			pcr.MemFileBytes)
+	} else {
+		title, tierRows = getPoolCreateRespRows(pcr.TierBytes, tierRatios, numRanks)
 	}
-
 	fmtArgs = append(fmtArgs, tierRows...)
 
 	_, err := fmt.Fprintln(out, txtfmt.FormatEntity(title, fmtArgs))

src/control/cmd/dmg/pretty/storage_nvme_test.go

@@ -25,7 +25,7 @@ func TestPretty_PrintNVMeController(t *testing.T) {
 	ctrlrWithSmd := func(idx int32, roleBits int) *storage.NvmeController {
 		c := storage.MockNvmeController(idx)
 		sd := storage.MockSmdDevice(nil, idx)
-		sd.Roles = storage.BdevRoles{storage.OptionBits(roleBits)}
+		sd.Roles = storage.BdevRolesFromBits(roleBits)
 		sd.Rank = ranklist.Rank(idx)
 		c.SmdDevices = []*storage.SmdDevice{sd}
 		return c

src/control/cmd/dmg/pretty/storage_query.go

@@ -9,21 +9,29 @@ package pretty
 import (
 	"fmt"
 	"io"
+	"sort"
 	"strings"
 
 	"github.com/dustin/go-humanize"
 	"github.com/pkg/errors"
 
+	"github.com/daos-stack/daos/src/control/common"
 	"github.com/daos-stack/daos/src/control/lib/control"
 	"github.com/daos-stack/daos/src/control/lib/txtfmt"
 	"github.com/daos-stack/daos/src/control/server/storage"
 )
 
+var (
+	errNoMetaRole        = errors.New("no meta role detected")
+	errInconsistentRoles = errors.New("roles inconsistent between hosts")
+	errInsufficientScan  = errors.New("insufficient info in scan response")
+)
+
 // PrintHostStorageUsageMap generates a human-readable representation of the supplied
 // HostStorageMap struct and writes utilization info to the supplied io.Writer.
-func PrintHostStorageUsageMap(hsm control.HostStorageMap, out io.Writer) error {
+func PrintHostStorageUsageMap(hsm control.HostStorageMap, out io.Writer) {
 	if len(hsm) == 0 {
-		return nil
+		return
 	}
 
 	hostsTitle := "Hosts"
@@ -44,19 +52,243 @@ func PrintHostStorageUsageMap(hsm control.HostStorageMap, out io.Writer) error {
 		hosts := getPrintHosts(hss.HostSet.RangedString())
 		row := txtfmt.TableRow{hostsTitle: hosts}
 		storage := hss.HostStorage
-		row[scmTitle] = humanize.Bytes(storage.ScmNamespaces.Total())
-		row[scmFreeTitle] = humanize.Bytes(storage.ScmNamespaces.Free())
-		row[scmUsageTitle] = storage.ScmNamespaces.PercentUsage()
-		row[nvmeTitle] = humanize.Bytes(storage.NvmeDevices.Total())
-		row[nvmeFreeTitle] = humanize.Bytes(storage.NvmeDevices.Free())
-		row[nvmeUsageTitle] = storage.NvmeDevices.PercentUsage()
+
+		sns := storage.ScmNamespaces
+		row[scmTitle] = humanize.Bytes(sns.Total())
+		scmFree := sns.Free()
+		row[scmFreeTitle] = humanize.Bytes(scmFree)
+		row[scmUsageTitle] = common.PercentageString(sns.Total()-scmFree, sns.Total())
+
+		ncs := storage.NvmeDevices
+		row[nvmeTitle] = humanize.Bytes(ncs.Total())
+		nvmeFree := ncs.Free()
+		row[nvmeFreeTitle] = humanize.Bytes(nvmeFree)
+		row[nvmeUsageTitle] = common.PercentageString(ncs.Total()-nvmeFree, ncs.Total())
+
 		table = append(table, row)
 	}
 
+	tablePrint.Format(table)
+}
+
+const (
+	metaRole  = storage.BdevRoleMeta
+	dataRole  = storage.BdevRoleData
+	rankTitle = "Rank"
+)
+
+// Return role combinations for each tier that contains either a meta or data role.
+func getTierRolesForHost(nvme storage.NvmeControllers, metaRolesLast, dataRolesLast *storage.BdevRoles) error {
+	roles := make(map[int]*storage.BdevRoles)
+	for _, c := range nvme {
+		if c.Roles().HasMeta() {
+			if _, exists := roles[metaRole]; !exists {
+				roles[metaRole] = c.Roles()
+			}
+		} else if c.Roles().HasData() {
+			if _, exists := roles[dataRole]; !exists {
+				roles[dataRole] = c.Roles()
+			}
+		}
+	}
+
+	if roles[metaRole].IsEmpty() {
+		return errNoMetaRole
+	}
+
+	if !metaRolesLast.IsEmpty() {
+		// Indicates valid "last" values exist so check consistency.
+		if *roles[metaRole] != *metaRolesLast {
+			return errInconsistentRoles
+		}
+		if roles[dataRole].IsEmpty() {
+			if !dataRolesLast.IsEmpty() {
+				return errInconsistentRoles
+			}
+		} else {
+			if *roles[dataRole] != *dataRolesLast {
+				return errInconsistentRoles
+			}
+		}
+	} else {
+		*metaRolesLast = *roles[metaRole]
+		if !roles[dataRole].IsEmpty() {
+			*dataRolesLast = *roles[dataRole]
+		}
+	}
+
+	return nil
+}
+
+// Print which roles each tier is assigned, only print tiers with meta or data roles.
+// Currently tier-list hardcoded to (META/DATA) but this can be extended.
+func printTierRolesTable(hsm control.HostStorageMap, out, dbg io.Writer) ([]storage.BdevRoles, error) {
+	tierTitle := "Tier"
+	rolesTitle := "Roles"
+
+	tablePrint := txtfmt.NewTableFormatter(tierTitle, rolesTitle)
+	tablePrint.InitWriter(out)
+	table := []txtfmt.TableRow{}
+
+	// Currently only tiers with meta and data are of interest so select implicitly.
+	var metaRoles, dataRoles storage.BdevRoles
+	for _, key := range hsm.Keys() {
+		err := getTierRolesForHost(hsm[key].HostStorage.NvmeDevices, &metaRoles, &dataRoles)
+		if err != nil {
+			hSet := hsm[key].HostSet
+			fmt.Fprintf(dbg, "scan resp for hosts %q: %+v\n", hSet, hsm[key].HostStorage)
+			return nil, errors.Wrapf(err, "hosts %q", hSet)
+		}
+	}
+
+	if metaRoles.IsEmpty() {
+		fmt.Fprintf(dbg, "scan resp: %+v\n", hsm)
+		return nil, errInsufficientScan
+	}
+
+	rolesToShow := []storage.BdevRoles{metaRoles}
+	if !dataRoles.IsEmpty() {
+		// Print data role row if assigned to a separate tier from meta role.
+		rolesToShow = append(rolesToShow, dataRoles)
+	}
+	for i, roles := range rolesToShow {
+		table = append(table, txtfmt.TableRow{
+			// Starting tier index of 1.
+			tierTitle:  fmt.Sprintf("T%d", i+1),
+			rolesTitle: roles.String(),
+		})
+	}
+
+	tablePrint.Format(table)
+	return rolesToShow, nil
+}
+
+func getRowTierTitles(i int, showUsable bool) []string {
+	totalTitle := fmt.Sprintf("T%d-Total", i)
+	freeTitle := fmt.Sprintf("T%d-Free", i)
+	if showUsable {
+		freeTitle = fmt.Sprintf("T%d-Usable", i)
+	}
+	usageTitle := fmt.Sprintf("T%d-Usage", i)
+
+	return []string{totalTitle, freeTitle, usageTitle}
+}
+
+type roleDevsMap map[storage.BdevRoles]storage.NvmeControllers
+type rankRoleDevsMap map[int]roleDevsMap
+
+func iterRankRoleDevs(nvme storage.NvmeControllers, tierRoles []storage.BdevRoles, dbg io.Writer, rankRoleDevs rankRoleDevsMap) error {
+	for _, nd := range nvme {
+		if len(nd.SmdDevices) == 0 || nd.SmdDevices[0] == nil {
+			fmt.Fprintf(dbg, "no smd for %s\n", nd.PciAddr)
+			continue
+		}
+		rank := int(nd.Rank())
+		if _, exists := rankRoleDevs[rank]; !exists {
+			rankRoleDevs[rank] = make(roleDevsMap)
+		}
+		roles := nd.Roles()
+		if roles == nil {
+			return errors.New("unexpected nil roles")
+		}
+		for _, rolesWant := range tierRoles {
+			if *roles != rolesWant {
+				continue
+			}
+			fmt.Fprintf(dbg, "add r%d-%s roles %q tot/avail/usabl %d/%d/%d\n", rank,
+				nd.PciAddr, roles, nd.Total(), nd.Free(), nd.Usable())
+			rankRoleDevs[rank][rolesWant] = append(
+				rankRoleDevs[rank][rolesWant], nd)
+			break
+		}
+	}
+
+	return nil
+}
+
+func getRankRolesRow(rank int, tierRoles []storage.BdevRoles, roleDevs roleDevsMap, showUsable bool) txtfmt.TableRow {
+	row := txtfmt.TableRow{rankTitle: fmt.Sprintf("%d", rank)}
+	for i, roles := range tierRoles {
+		titles := getRowTierTitles(i+1, showUsable)
+		totalTitle, freeTitle, usageTitle := titles[0], titles[1], titles[2]
+		devs, exists := roleDevs[roles]
+		if !exists {
+			row[totalTitle] = "-"
+			row[freeTitle] = "-"
+			row[usageTitle] = "-"
+			continue
+		}
+		row[totalTitle] = humanize.Bytes(devs.Total())
+		free := devs.Free()
+		// Handle special case where SSDs with META but without DATA should show usable
+		// space as bytes available in regards to META space. Usable bytes is only
+		// calculated for SSDs with DATA role.
+		if showUsable && !(roles.HasMeta() && !roles.HasData()) {
+			free = devs.Usable()
+		}
+		row[freeTitle] = humanize.Bytes(free)
+		row[usageTitle] = common.PercentageString(devs.Total()-free, devs.Total())
+	}
+
+	return row
+}
+
+// Print usage table with row for each rank and column for each tier.
+func printTierUsageTable(hsm control.HostStorageMap, tierRoles []storage.BdevRoles, out, dbg io.Writer, showUsable bool) error {
+	if len(tierRoles) == 0 {
+		return errors.New("no table role data to show")
+	}
+	titles := []string{rankTitle}
+	for i := range tierRoles {
+		titles = append(titles, getRowTierTitles(i+1, showUsable)...)
+	}
+
+	tablePrint := txtfmt.NewTableFormatter(titles...)
+	tablePrint.InitWriter(out)
+	table := []txtfmt.TableRow{}
+
+	// Build controllers-to-roles-to-rank map.
+	rankRoleDevs := make(rankRoleDevsMap)
+	for _, key := range hsm.Keys() {
+		err := iterRankRoleDevs(hsm[key].HostStorage.NvmeDevices, tierRoles, dbg,
+			rankRoleDevs)
+		if err != nil {
+			return errors.Wrapf(err, "host %q", hsm[key].HostSet)
+		}
+	}
+
+	var ranks []int
+	for rank := range rankRoleDevs {
+		ranks = append(ranks, rank)
+	}
+	sort.Ints(ranks)
+
+	for _, rank := range ranks {
+		table = append(table,
+			getRankRolesRow(rank, tierRoles, rankRoleDevs[rank], showUsable))
+	}
+
 	tablePrint.Format(table)
 	return nil
 }
 
+// PrintHostStorageUsageMapMdOnSsd generates a human-readable representation of the supplied
+// HostStorageMap struct and writes utilization info to the supplied io.Writer in a format
+// relevant to MD-on-SSD mode.
+func PrintHostStorageUsageMapMdOnSsd(hsm control.HostStorageMap, out, dbg io.Writer, showUsable bool) error {
+	if len(hsm) == 0 {
+		return nil
+	}
+
+	tierRoles, err := printTierRolesTable(hsm, out, dbg)
+	if err != nil {
+		return err
+	}
+	fmt.Fprintf(out, "\n")
+
+	return printTierUsageTable(hsm, tierRoles, out, dbg, showUsable)
+}
+
 // NVMe controller namespace ID (NSID) should only be displayed if >= 1. Zero value should be
 // ignored in display output.
 func printSmdDevice(dev *storage.SmdDevice, iw io.Writer, opts ...PrintConfigOption) error {