storj/storagenode/storagenodedb/piecespaceused.go

234 lines
6.4 KiB
Go
Raw Normal View History

// Copyright (C) 2019 Storj Labs, Inc.
// See LICENSE for copying information.
package storagenodedb
import (
"context"
"database/sql"
"errors"
"github.com/zeebo/errs"
"storj.io/common/storj"
"storj.io/storj/storagenode/pieces"
)
// ErrPieceSpaceUsed represents errors from the piece spaced used database.
var ErrPieceSpaceUsed = errs.Class("piece space used error")
storagenode/storagenodedb: refactor both data access objects and migrations to support multiple DB connections (#3057) * Split the info.db database into multiple DBs using Backup API. * Remove location. Prev refactor assumed we would need this but don't. * Added VACUUM to reclaim space after splitting storage node databases. * Added unique names to SQLite3 connection hooks to fix testplanet. * Moving DB closing to the migration step. * Removing the closing of the versions DB. It's already getting closed. * Swapping the database connection references on reconnect. * Moved sqlite closing logic away from the boltdb closing logic. * Moved sqlite closing logic away from the boltdb closing logic. * Remove certificate and vouchers from DB split migration. * Removed vouchers and bumped up the migration version. * Use same constructor in tests for storage node databases. * Use same constructor in tests for storage node databases. * Adding method to access underlining SQL database connections and cleanup * Adding logging for migration diagnostics. * Moved migration closing database logic to minimize disk usage. * Cleaning up error handling. * Fix missing copyright. * Fix linting error. * Add test for migration 21 (#3012) * Refactoring migration code into a nicer to use object. * Refactoring migration code into a nicer to use object. * Fixing broken migration test. * Removed unnecessary code that is no longer needed now that we close DBs. * Removed unnecessary code that is no longer needed now that we close DBs. * Fixed bug where an invalid database path was being opened. * Fixed linting errors. * Renamed VersionsDB to LegacyInfoDB and refactored DB lookup keys. * Renamed VersionsDB to LegacyInfoDB and refactored DB lookup keys. * Fix migration test. NOTE: This change does not address new tables satellites and satellite_exit_progress * Removing v22 migration to move into it's own PR. * Removing v22 migration to move into it's own PR. * Refactored schema, rebind and configure functions to be re-useable. * Renamed LegacyInfoDB to DeprecatedInfoDB. * Cleaned up closeDatabase function. * Renamed storageNodeSQLDB to migratableDB. * Switched from using errs.Combine() to errs.Group in closeDatabases func. * Removed constructors from storage node data access objects. * Reformatted usage of const. * Fixed broken test snapshots. * Fixed linting error.
2019-09-18 17:17:28 +01:00
// PieceSpaceUsedDBName represents the database name.
const PieceSpaceUsedDBName = "piece_spaced_used"
storagenode: Include trash space when calculating space used This commit adds functionality to include the space used in the trash directory when calculating available space on the node. It also includes this trash value in the space used cache, with methods to keep the cache up-to-date as files are trashed, restored, and emptied. As part of the commit, the RestoreTrash and EmptyTrash methods have slightly changed signatures. RestoreTrash now also returns the keys that were restored, while EmptyTrash also returns the total disk space recovered. Each of these changes makes it possible to keep the cache up-to-date and know how much space is being used/recovered. Also changed is the signature of PieceStoreAccess.ContentSize method. Previously this method returns only the content size of the blob, removing the size of any header data. This method has been renamed `Size` and returns both the full disk size and content size of the blob. This allows us to only stat the file once, and in some instances (i.e. cache) knowing the full file size is useful. Note: This commit simply adds the trash size data to the piece size data we were already collecting. The piece size data is not accurate for all use-cases (e.g. because it does not contain piece header data); however, this commit does not fix that problem. Now that the ContentSize (Size) method returns the full size of the file, it should be easier to fix this problem in a future commit. Change-Id: I4a6cae09e262c8452a618116d1dc66b687f59f85
2019-12-21 13:11:24 +00:00
// trashTotalRowName is the special "satellite_id" used in the db to represent
// the total stored for trash. Similar to how we use NULL as a special value
// for satellite_id to represent the total for pieces, this value is used to
// identify the row storing the total for trash.
//
// It is intentionally an otherwise-invalid satellite_id (not 32 bytes) so that
// it cannot conflict with real satellite_id names.
storagenode: Include trash space when calculating space used This commit adds functionality to include the space used in the trash directory when calculating available space on the node. It also includes this trash value in the space used cache, with methods to keep the cache up-to-date as files are trashed, restored, and emptied. As part of the commit, the RestoreTrash and EmptyTrash methods have slightly changed signatures. RestoreTrash now also returns the keys that were restored, while EmptyTrash also returns the total disk space recovered. Each of these changes makes it possible to keep the cache up-to-date and know how much space is being used/recovered. Also changed is the signature of PieceStoreAccess.ContentSize method. Previously this method returns only the content size of the blob, removing the size of any header data. This method has been renamed `Size` and returns both the full disk size and content size of the blob. This allows us to only stat the file once, and in some instances (i.e. cache) knowing the full file size is useful. Note: This commit simply adds the trash size data to the piece size data we were already collecting. The piece size data is not accurate for all use-cases (e.g. because it does not contain piece header data); however, this commit does not fix that problem. Now that the ContentSize (Size) method returns the full size of the file, it should be easier to fix this problem in a future commit. Change-Id: I4a6cae09e262c8452a618116d1dc66b687f59f85
2019-12-21 13:11:24 +00:00
const trashTotalRowName = "trashtotal"
storagenode/storagenodedb: refactor both data access objects and migrations to support multiple DB connections (#3057) * Split the info.db database into multiple DBs using Backup API. * Remove location. Prev refactor assumed we would need this but don't. * Added VACUUM to reclaim space after splitting storage node databases. * Added unique names to SQLite3 connection hooks to fix testplanet. * Moving DB closing to the migration step. * Removing the closing of the versions DB. It's already getting closed. * Swapping the database connection references on reconnect. * Moved sqlite closing logic away from the boltdb closing logic. * Moved sqlite closing logic away from the boltdb closing logic. * Remove certificate and vouchers from DB split migration. * Removed vouchers and bumped up the migration version. * Use same constructor in tests for storage node databases. * Use same constructor in tests for storage node databases. * Adding method to access underlining SQL database connections and cleanup * Adding logging for migration diagnostics. * Moved migration closing database logic to minimize disk usage. * Cleaning up error handling. * Fix missing copyright. * Fix linting error. * Add test for migration 21 (#3012) * Refactoring migration code into a nicer to use object. * Refactoring migration code into a nicer to use object. * Fixing broken migration test. * Removed unnecessary code that is no longer needed now that we close DBs. * Removed unnecessary code that is no longer needed now that we close DBs. * Fixed bug where an invalid database path was being opened. * Fixed linting errors. * Renamed VersionsDB to LegacyInfoDB and refactored DB lookup keys. * Renamed VersionsDB to LegacyInfoDB and refactored DB lookup keys. * Fix migration test. NOTE: This change does not address new tables satellites and satellite_exit_progress * Removing v22 migration to move into it's own PR. * Removing v22 migration to move into it's own PR. * Refactored schema, rebind and configure functions to be re-useable. * Renamed LegacyInfoDB to DeprecatedInfoDB. * Cleaned up closeDatabase function. * Renamed storageNodeSQLDB to migratableDB. * Switched from using errs.Combine() to errs.Group in closeDatabases func. * Removed constructors from storage node data access objects. * Reformatted usage of const. * Fixed broken test snapshots. * Fixed linting error.
2019-09-18 17:17:28 +01:00
type pieceSpaceUsedDB struct {
dbContainerImpl
}
// Init creates the total pieces and total trash records if they don't already exist.
func (db *pieceSpaceUsedDB) Init(ctx context.Context) (err error) {
totalPiecesRow := db.QueryRowContext(ctx, `
SELECT total
FROM piece_space_used
storagenode: Include trash space when calculating space used This commit adds functionality to include the space used in the trash directory when calculating available space on the node. It also includes this trash value in the space used cache, with methods to keep the cache up-to-date as files are trashed, restored, and emptied. As part of the commit, the RestoreTrash and EmptyTrash methods have slightly changed signatures. RestoreTrash now also returns the keys that were restored, while EmptyTrash also returns the total disk space recovered. Each of these changes makes it possible to keep the cache up-to-date and know how much space is being used/recovered. Also changed is the signature of PieceStoreAccess.ContentSize method. Previously this method returns only the content size of the blob, removing the size of any header data. This method has been renamed `Size` and returns both the full disk size and content size of the blob. This allows us to only stat the file once, and in some instances (i.e. cache) knowing the full file size is useful. Note: This commit simply adds the trash size data to the piece size data we were already collecting. The piece size data is not accurate for all use-cases (e.g. because it does not contain piece header data); however, this commit does not fix that problem. Now that the ContentSize (Size) method returns the full size of the file, it should be easier to fix this problem in a future commit. Change-Id: I4a6cae09e262c8452a618116d1dc66b687f59f85
2019-12-21 13:11:24 +00:00
WHERE satellite_id IS NULL
AND satellite_id IS NOT ?;
`, trashTotalRowName)
storagenode: Include trash space when calculating space used This commit adds functionality to include the space used in the trash directory when calculating available space on the node. It also includes this trash value in the space used cache, with methods to keep the cache up-to-date as files are trashed, restored, and emptied. As part of the commit, the RestoreTrash and EmptyTrash methods have slightly changed signatures. RestoreTrash now also returns the keys that were restored, while EmptyTrash also returns the total disk space recovered. Each of these changes makes it possible to keep the cache up-to-date and know how much space is being used/recovered. Also changed is the signature of PieceStoreAccess.ContentSize method. Previously this method returns only the content size of the blob, removing the size of any header data. This method has been renamed `Size` and returns both the full disk size and content size of the blob. This allows us to only stat the file once, and in some instances (i.e. cache) knowing the full file size is useful. Note: This commit simply adds the trash size data to the piece size data we were already collecting. The piece size data is not accurate for all use-cases (e.g. because it does not contain piece header data); however, this commit does not fix that problem. Now that the ContentSize (Size) method returns the full size of the file, it should be easier to fix this problem in a future commit. Change-Id: I4a6cae09e262c8452a618116d1dc66b687f59f85
2019-12-21 13:11:24 +00:00
var piecesTotal int64
err = totalPiecesRow.Scan(&piecesTotal)
if err != nil {
if errors.Is(err, sql.ErrNoRows) {
storagenode: Include trash space when calculating space used This commit adds functionality to include the space used in the trash directory when calculating available space on the node. It also includes this trash value in the space used cache, with methods to keep the cache up-to-date as files are trashed, restored, and emptied. As part of the commit, the RestoreTrash and EmptyTrash methods have slightly changed signatures. RestoreTrash now also returns the keys that were restored, while EmptyTrash also returns the total disk space recovered. Each of these changes makes it possible to keep the cache up-to-date and know how much space is being used/recovered. Also changed is the signature of PieceStoreAccess.ContentSize method. Previously this method returns only the content size of the blob, removing the size of any header data. This method has been renamed `Size` and returns both the full disk size and content size of the blob. This allows us to only stat the file once, and in some instances (i.e. cache) knowing the full file size is useful. Note: This commit simply adds the trash size data to the piece size data we were already collecting. The piece size data is not accurate for all use-cases (e.g. because it does not contain piece header data); however, this commit does not fix that problem. Now that the ContentSize (Size) method returns the full size of the file, it should be easier to fix this problem in a future commit. Change-Id: I4a6cae09e262c8452a618116d1dc66b687f59f85
2019-12-21 13:11:24 +00:00
err = db.createInitTotalPieces(ctx)
if err != nil {
return ErrPieceSpaceUsed.Wrap(err)
}
}
}
totalTrashRow := db.QueryRowContext(ctx, `
storagenode: Include trash space when calculating space used This commit adds functionality to include the space used in the trash directory when calculating available space on the node. It also includes this trash value in the space used cache, with methods to keep the cache up-to-date as files are trashed, restored, and emptied. As part of the commit, the RestoreTrash and EmptyTrash methods have slightly changed signatures. RestoreTrash now also returns the keys that were restored, while EmptyTrash also returns the total disk space recovered. Each of these changes makes it possible to keep the cache up-to-date and know how much space is being used/recovered. Also changed is the signature of PieceStoreAccess.ContentSize method. Previously this method returns only the content size of the blob, removing the size of any header data. This method has been renamed `Size` and returns both the full disk size and content size of the blob. This allows us to only stat the file once, and in some instances (i.e. cache) knowing the full file size is useful. Note: This commit simply adds the trash size data to the piece size data we were already collecting. The piece size data is not accurate for all use-cases (e.g. because it does not contain piece header data); however, this commit does not fix that problem. Now that the ContentSize (Size) method returns the full size of the file, it should be easier to fix this problem in a future commit. Change-Id: I4a6cae09e262c8452a618116d1dc66b687f59f85
2019-12-21 13:11:24 +00:00
SELECT total
FROM piece_space_used
WHERE satellite_id = ?;
`, trashTotalRowName)
var trashTotal int64
err = totalTrashRow.Scan(&trashTotal)
if err != nil {
if errors.Is(err, sql.ErrNoRows) {
storagenode: Include trash space when calculating space used This commit adds functionality to include the space used in the trash directory when calculating available space on the node. It also includes this trash value in the space used cache, with methods to keep the cache up-to-date as files are trashed, restored, and emptied. As part of the commit, the RestoreTrash and EmptyTrash methods have slightly changed signatures. RestoreTrash now also returns the keys that were restored, while EmptyTrash also returns the total disk space recovered. Each of these changes makes it possible to keep the cache up-to-date and know how much space is being used/recovered. Also changed is the signature of PieceStoreAccess.ContentSize method. Previously this method returns only the content size of the blob, removing the size of any header data. This method has been renamed `Size` and returns both the full disk size and content size of the blob. This allows us to only stat the file once, and in some instances (i.e. cache) knowing the full file size is useful. Note: This commit simply adds the trash size data to the piece size data we were already collecting. The piece size data is not accurate for all use-cases (e.g. because it does not contain piece header data); however, this commit does not fix that problem. Now that the ContentSize (Size) method returns the full size of the file, it should be easier to fix this problem in a future commit. Change-Id: I4a6cae09e262c8452a618116d1dc66b687f59f85
2019-12-21 13:11:24 +00:00
err = db.createInitTotalTrash(ctx)
if err != nil {
return ErrPieceSpaceUsed.Wrap(err)
}
}
}
storagenode: Include trash space when calculating space used This commit adds functionality to include the space used in the trash directory when calculating available space on the node. It also includes this trash value in the space used cache, with methods to keep the cache up-to-date as files are trashed, restored, and emptied. As part of the commit, the RestoreTrash and EmptyTrash methods have slightly changed signatures. RestoreTrash now also returns the keys that were restored, while EmptyTrash also returns the total disk space recovered. Each of these changes makes it possible to keep the cache up-to-date and know how much space is being used/recovered. Also changed is the signature of PieceStoreAccess.ContentSize method. Previously this method returns only the content size of the blob, removing the size of any header data. This method has been renamed `Size` and returns both the full disk size and content size of the blob. This allows us to only stat the file once, and in some instances (i.e. cache) knowing the full file size is useful. Note: This commit simply adds the trash size data to the piece size data we were already collecting. The piece size data is not accurate for all use-cases (e.g. because it does not contain piece header data); however, this commit does not fix that problem. Now that the ContentSize (Size) method returns the full size of the file, it should be easier to fix this problem in a future commit. Change-Id: I4a6cae09e262c8452a618116d1dc66b687f59f85
2019-12-21 13:11:24 +00:00
return ErrPieceSpaceUsed.Wrap(err)
}
storagenode: Include trash space when calculating space used This commit adds functionality to include the space used in the trash directory when calculating available space on the node. It also includes this trash value in the space used cache, with methods to keep the cache up-to-date as files are trashed, restored, and emptied. As part of the commit, the RestoreTrash and EmptyTrash methods have slightly changed signatures. RestoreTrash now also returns the keys that were restored, while EmptyTrash also returns the total disk space recovered. Each of these changes makes it possible to keep the cache up-to-date and know how much space is being used/recovered. Also changed is the signature of PieceStoreAccess.ContentSize method. Previously this method returns only the content size of the blob, removing the size of any header data. This method has been renamed `Size` and returns both the full disk size and content size of the blob. This allows us to only stat the file once, and in some instances (i.e. cache) knowing the full file size is useful. Note: This commit simply adds the trash size data to the piece size data we were already collecting. The piece size data is not accurate for all use-cases (e.g. because it does not contain piece header data); however, this commit does not fix that problem. Now that the ContentSize (Size) method returns the full size of the file, it should be easier to fix this problem in a future commit. Change-Id: I4a6cae09e262c8452a618116d1dc66b687f59f85
2019-12-21 13:11:24 +00:00
func (db *pieceSpaceUsedDB) createInitTotalPieces(ctx context.Context) (err error) {
_, err = db.ExecContext(ctx, `
INSERT INTO piece_space_used (total, content_size) VALUES (0, 0)
`)
return ErrPieceSpaceUsed.Wrap(err)
}
storagenode: Include trash space when calculating space used This commit adds functionality to include the space used in the trash directory when calculating available space on the node. It also includes this trash value in the space used cache, with methods to keep the cache up-to-date as files are trashed, restored, and emptied. As part of the commit, the RestoreTrash and EmptyTrash methods have slightly changed signatures. RestoreTrash now also returns the keys that were restored, while EmptyTrash also returns the total disk space recovered. Each of these changes makes it possible to keep the cache up-to-date and know how much space is being used/recovered. Also changed is the signature of PieceStoreAccess.ContentSize method. Previously this method returns only the content size of the blob, removing the size of any header data. This method has been renamed `Size` and returns both the full disk size and content size of the blob. This allows us to only stat the file once, and in some instances (i.e. cache) knowing the full file size is useful. Note: This commit simply adds the trash size data to the piece size data we were already collecting. The piece size data is not accurate for all use-cases (e.g. because it does not contain piece header data); however, this commit does not fix that problem. Now that the ContentSize (Size) method returns the full size of the file, it should be easier to fix this problem in a future commit. Change-Id: I4a6cae09e262c8452a618116d1dc66b687f59f85
2019-12-21 13:11:24 +00:00
func (db *pieceSpaceUsedDB) createInitTotalTrash(ctx context.Context) (err error) {
_, err = db.ExecContext(ctx, `
INSERT INTO piece_space_used (total, content_size, satellite_id) VALUES (0, 0, ?)
storagenode: Include trash space when calculating space used This commit adds functionality to include the space used in the trash directory when calculating available space on the node. It also includes this trash value in the space used cache, with methods to keep the cache up-to-date as files are trashed, restored, and emptied. As part of the commit, the RestoreTrash and EmptyTrash methods have slightly changed signatures. RestoreTrash now also returns the keys that were restored, while EmptyTrash also returns the total disk space recovered. Each of these changes makes it possible to keep the cache up-to-date and know how much space is being used/recovered. Also changed is the signature of PieceStoreAccess.ContentSize method. Previously this method returns only the content size of the blob, removing the size of any header data. This method has been renamed `Size` and returns both the full disk size and content size of the blob. This allows us to only stat the file once, and in some instances (i.e. cache) knowing the full file size is useful. Note: This commit simply adds the trash size data to the piece size data we were already collecting. The piece size data is not accurate for all use-cases (e.g. because it does not contain piece header data); however, this commit does not fix that problem. Now that the ContentSize (Size) method returns the full size of the file, it should be easier to fix this problem in a future commit. Change-Id: I4a6cae09e262c8452a618116d1dc66b687f59f85
2019-12-21 13:11:24 +00:00
`, trashTotalRowName)
return ErrPieceSpaceUsed.Wrap(err)
}
// GetPieceTotal returns the total space used (total and contentSize) for all pieces stored.
func (db *pieceSpaceUsedDB) GetPieceTotals(ctx context.Context) (total int64, contentSize int64, err error) {
defer mon.Task()(&ctx)(&err)
row := db.QueryRowContext(ctx, `
SELECT total, content_size
FROM piece_space_used
WHERE satellite_id IS NULL;
`)
err = row.Scan(&total, &contentSize)
if err != nil {
if errors.Is(err, sql.ErrNoRows) {
return 0, 0, nil
}
return 0, 0, ErrPieceSpaceUsed.Wrap(err)
}
return total, contentSize, nil
}
// GetTrashTotal returns the total space used by all trash.
func (db *pieceSpaceUsedDB) GetTrashTotal(ctx context.Context) (total int64, err error) {
storagenode: Include trash space when calculating space used This commit adds functionality to include the space used in the trash directory when calculating available space on the node. It also includes this trash value in the space used cache, with methods to keep the cache up-to-date as files are trashed, restored, and emptied. As part of the commit, the RestoreTrash and EmptyTrash methods have slightly changed signatures. RestoreTrash now also returns the keys that were restored, while EmptyTrash also returns the total disk space recovered. Each of these changes makes it possible to keep the cache up-to-date and know how much space is being used/recovered. Also changed is the signature of PieceStoreAccess.ContentSize method. Previously this method returns only the content size of the blob, removing the size of any header data. This method has been renamed `Size` and returns both the full disk size and content size of the blob. This allows us to only stat the file once, and in some instances (i.e. cache) knowing the full file size is useful. Note: This commit simply adds the trash size data to the piece size data we were already collecting. The piece size data is not accurate for all use-cases (e.g. because it does not contain piece header data); however, this commit does not fix that problem. Now that the ContentSize (Size) method returns the full size of the file, it should be easier to fix this problem in a future commit. Change-Id: I4a6cae09e262c8452a618116d1dc66b687f59f85
2019-12-21 13:11:24 +00:00
defer mon.Task()(&ctx)(&err)
row := db.QueryRowContext(ctx, `
storagenode: Include trash space when calculating space used This commit adds functionality to include the space used in the trash directory when calculating available space on the node. It also includes this trash value in the space used cache, with methods to keep the cache up-to-date as files are trashed, restored, and emptied. As part of the commit, the RestoreTrash and EmptyTrash methods have slightly changed signatures. RestoreTrash now also returns the keys that were restored, while EmptyTrash also returns the total disk space recovered. Each of these changes makes it possible to keep the cache up-to-date and know how much space is being used/recovered. Also changed is the signature of PieceStoreAccess.ContentSize method. Previously this method returns only the content size of the blob, removing the size of any header data. This method has been renamed `Size` and returns both the full disk size and content size of the blob. This allows us to only stat the file once, and in some instances (i.e. cache) knowing the full file size is useful. Note: This commit simply adds the trash size data to the piece size data we were already collecting. The piece size data is not accurate for all use-cases (e.g. because it does not contain piece header data); however, this commit does not fix that problem. Now that the ContentSize (Size) method returns the full size of the file, it should be easier to fix this problem in a future commit. Change-Id: I4a6cae09e262c8452a618116d1dc66b687f59f85
2019-12-21 13:11:24 +00:00
SELECT total
FROM piece_space_used
WHERE satellite_id = ?
`, trashTotalRowName)
err = row.Scan(&total)
if err != nil {
if errors.Is(err, sql.ErrNoRows) {
storagenode: Include trash space when calculating space used This commit adds functionality to include the space used in the trash directory when calculating available space on the node. It also includes this trash value in the space used cache, with methods to keep the cache up-to-date as files are trashed, restored, and emptied. As part of the commit, the RestoreTrash and EmptyTrash methods have slightly changed signatures. RestoreTrash now also returns the keys that were restored, while EmptyTrash also returns the total disk space recovered. Each of these changes makes it possible to keep the cache up-to-date and know how much space is being used/recovered. Also changed is the signature of PieceStoreAccess.ContentSize method. Previously this method returns only the content size of the blob, removing the size of any header data. This method has been renamed `Size` and returns both the full disk size and content size of the blob. This allows us to only stat the file once, and in some instances (i.e. cache) knowing the full file size is useful. Note: This commit simply adds the trash size data to the piece size data we were already collecting. The piece size data is not accurate for all use-cases (e.g. because it does not contain piece header data); however, this commit does not fix that problem. Now that the ContentSize (Size) method returns the full size of the file, it should be easier to fix this problem in a future commit. Change-Id: I4a6cae09e262c8452a618116d1dc66b687f59f85
2019-12-21 13:11:24 +00:00
return total, nil
}
return total, ErrPieceSpaceUsed.Wrap(err)
}
return total, nil
}
// GetPieceTotalsForAllSatellites returns how much space used by pieces stored for each satelliteID.
func (db *pieceSpaceUsedDB) GetPieceTotalsForAllSatellites(ctx context.Context) (_ map[storj.NodeID]pieces.SatelliteUsage, err error) {
defer mon.Task()(&ctx)(&err)
rows, err := db.QueryContext(ctx, `
SELECT total, content_size, satellite_id
FROM piece_space_used
WHERE satellite_id IS NOT NULL
storagenode: Include trash space when calculating space used This commit adds functionality to include the space used in the trash directory when calculating available space on the node. It also includes this trash value in the space used cache, with methods to keep the cache up-to-date as files are trashed, restored, and emptied. As part of the commit, the RestoreTrash and EmptyTrash methods have slightly changed signatures. RestoreTrash now also returns the keys that were restored, while EmptyTrash also returns the total disk space recovered. Each of these changes makes it possible to keep the cache up-to-date and know how much space is being used/recovered. Also changed is the signature of PieceStoreAccess.ContentSize method. Previously this method returns only the content size of the blob, removing the size of any header data. This method has been renamed `Size` and returns both the full disk size and content size of the blob. This allows us to only stat the file once, and in some instances (i.e. cache) knowing the full file size is useful. Note: This commit simply adds the trash size data to the piece size data we were already collecting. The piece size data is not accurate for all use-cases (e.g. because it does not contain piece header data); however, this commit does not fix that problem. Now that the ContentSize (Size) method returns the full size of the file, it should be easier to fix this problem in a future commit. Change-Id: I4a6cae09e262c8452a618116d1dc66b687f59f85
2019-12-21 13:11:24 +00:00
AND satellite_id IS NOT ?
`, trashTotalRowName)
if err != nil {
if errors.Is(err, sql.ErrNoRows) {
return nil, nil
}
return nil, ErrPieceSpaceUsed.Wrap(err)
}
defer func() { err = errs.Combine(err, rows.Close()) }()
totalBySatellite := map[storj.NodeID]pieces.SatelliteUsage{}
for rows.Next() {
var total, contentSize int64
var satelliteID storj.NodeID
err = rows.Scan(&total, &contentSize, &satelliteID)
if err != nil {
return nil, ErrPieceSpaceUsed.Wrap(err)
}
totalBySatellite[satelliteID] = pieces.SatelliteUsage{
Total: total,
ContentSize: contentSize,
}
}
return totalBySatellite, rows.Err()
}
// UpdatePieceTotals updates the record for total spaced used with new total and contentSize values.
func (db *pieceSpaceUsedDB) UpdatePieceTotals(ctx context.Context, newTotal, newContentSize int64) (err error) {
defer mon.Task()(&ctx)(&err)
_, err = db.ExecContext(ctx, `
UPDATE piece_space_used
SET total = ?, content_size = ?
WHERE satellite_id IS NULL
`, newTotal, newContentSize)
return ErrPieceSpaceUsed.Wrap(err)
}
// UpdateTrashTotal updates the record for total spaced used with a new value.
storagenode: Include trash space when calculating space used This commit adds functionality to include the space used in the trash directory when calculating available space on the node. It also includes this trash value in the space used cache, with methods to keep the cache up-to-date as files are trashed, restored, and emptied. As part of the commit, the RestoreTrash and EmptyTrash methods have slightly changed signatures. RestoreTrash now also returns the keys that were restored, while EmptyTrash also returns the total disk space recovered. Each of these changes makes it possible to keep the cache up-to-date and know how much space is being used/recovered. Also changed is the signature of PieceStoreAccess.ContentSize method. Previously this method returns only the content size of the blob, removing the size of any header data. This method has been renamed `Size` and returns both the full disk size and content size of the blob. This allows us to only stat the file once, and in some instances (i.e. cache) knowing the full file size is useful. Note: This commit simply adds the trash size data to the piece size data we were already collecting. The piece size data is not accurate for all use-cases (e.g. because it does not contain piece header data); however, this commit does not fix that problem. Now that the ContentSize (Size) method returns the full size of the file, it should be easier to fix this problem in a future commit. Change-Id: I4a6cae09e262c8452a618116d1dc66b687f59f85
2019-12-21 13:11:24 +00:00
func (db *pieceSpaceUsedDB) UpdateTrashTotal(ctx context.Context, newTotal int64) (err error) {
defer mon.Task()(&ctx)(&err)
_, err = db.ExecContext(ctx, `
UPDATE piece_space_used
SET total = ?
WHERE satellite_id = ?
`, newTotal, trashTotalRowName)
return ErrPieceSpaceUsed.Wrap(err)
}
// UpdatePieceTotalsForAllSatellites updates each record with new values for each satelliteID.
func (db *pieceSpaceUsedDB) UpdatePieceTotalsForAllSatellites(ctx context.Context, newTotalsBySatellites map[storj.NodeID]pieces.SatelliteUsage) (err error) {
defer mon.Task()(&ctx)(&err)
for satelliteID, vals := range newTotalsBySatellites {
if vals.ContentSize == 0 && vals.Total == 0 {
if err := db.deleteTotalBySatellite(ctx, satelliteID); err != nil {
return ErrPieceSpaceUsed.Wrap(err)
}
continue
}
_, err = db.ExecContext(ctx, `
INSERT INTO piece_space_used (total, content_size, satellite_id)
VALUES (?, ?, ?)
ON CONFLICT (satellite_id)
DO UPDATE SET total = ?, content_size = ?
WHERE satellite_id = ?
`, vals.Total, vals.ContentSize, satelliteID, vals.Total, vals.ContentSize, satelliteID)
if err != nil {
if errors.Is(err, sql.ErrNoRows) {
continue
}
return ErrPieceSpaceUsed.Wrap(err)
}
}
return nil
}
func (db *pieceSpaceUsedDB) deleteTotalBySatellite(ctx context.Context, satelliteID storj.NodeID) (err error) {
defer mon.Task()(&ctx)(&err)
_, err = db.ExecContext(ctx, `
DELETE FROM piece_space_used
WHERE satellite_id = ?
`, satelliteID)
if err != nil {
return err
}
return nil
}