Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1257698 > unrolled thread

[PATCH v2 0/4] Add online file check feature

Back to article view | Back to linux.kernel

Contents

  [PATCH v2 0/4] Add online file check feature Gang He <ghe@suse.com> - 2015-10-28 07:30 +0100
    [PATCH v2 4/4] ocfs2: check/fix inode block for online file check Gang He <ghe@suse.com> - 2015-10-28 07:30 +0100
    [PATCH v2 2/4] ocfs2: sysfile interfaces for online file check Gang He <ghe@suse.com> - 2015-10-28 07:30 +0100
    Re: [Ocfs2-devel] [PATCH v2 0/4] Add online file check feature Srinivas Eeda <srinivas.eeda@oracle.com> - 2015-10-28 17:40 +0100
      Re: [Ocfs2-devel] [PATCH v2 0/4] Add online file check feature "Gang He" <ghe@suse.com> - 2015-10-29 06:10 +0100
        Re: [Ocfs2-devel] [PATCH v2 0/4] Add online file check feature Srinivas Eeda <srinivas.eeda@oracle.com> - 2015-10-29 08:50 +0100
          Re: [Ocfs2-devel] [PATCH v2 0/4] Add online file check feature "Gang He" <ghe@suse.com> - 2015-10-29 09:30 +0100

#1257698 — [PATCH v2 0/4] Add online file check feature

When there are errors in the ocfs2 filesystem,
they are usually accompanied by the inode number which caused the error.
This inode number would be the input to fixing the file.
One of these options could be considered:
A file in the sys filesytem which would accept inode numbers.
This could be used to communication back what has to be fixed or is fixed.
You could write:
$# echo "CHECK <inode>" > /sys/fs/ocfs2/devname/filecheck
or
$# echo "FIX <inode>" > /sys/fs/ocfs2/devname/filecheck

Compare with first version, I use strncasecmp instead of double strncmp
functions. Second, update the source file contribution vendor.

Gang He (4):
  ocfs2: export ocfs2_kset for online file check
  ocfs2: sysfile interfaces for online file check
  ocfs2: create/remove sysfile for online file check
  ocfs2: check/fix inode block for online file check

 fs/ocfs2/Makefile      |   3 +-
 fs/ocfs2/filecheck.c   | 566 +++++++++++++++++++++++++++++++++++++++++++++++++
 fs/ocfs2/filecheck.h   |  48 +++++
 fs/ocfs2/inode.c       | 196 ++++++++++++++++-
 fs/ocfs2/inode.h       |   3 +
 fs/ocfs2/ocfs2_trace.h |   2 +
 fs/ocfs2/stackglue.c   |   3 +-
 fs/ocfs2/stackglue.h   |   2 +
 fs/ocfs2/super.c       |   5 +
 9 files changed, 820 insertions(+), 8 deletions(-)
 create mode 100644 fs/ocfs2/filecheck.c
 create mode 100644 fs/ocfs2/filecheck.h

-- 
2.1.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [next] | [standalone]

#1257702 — [PATCH v2 4/4] ocfs2: check/fix inode block for online file check

Implement online check or fix inode block during
reading a inode block to memory.

Signed-off-by: Gang He <ghe@suse.com>
---
 fs/ocfs2/inode.c       | 196 +++++++++++++++++++++++++++++++++++++++++++++++--
 fs/ocfs2/ocfs2_trace.h |   2 +
 2 files changed, 192 insertions(+), 6 deletions(-)

diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index b254416..d811698 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -53,6 +53,7 @@
 #include "xattr.h"
 #include "refcounttree.h"
 #include "ocfs2_trace.h"
+#include "filecheck.h"
 
 #include "buffer_head_io.h"
 
@@ -74,6 +75,13 @@ static int ocfs2_truncate_for_delete(struct ocfs2_super *osb,
 				    struct inode *inode,
 				    struct buffer_head *fe_bh);
 
+static int ocfs2_filecheck_read_inode_block_full(struct inode *inode,
+			struct buffer_head **bh, int flags, int type);
+static int ocfs2_filecheck_validate_inode_block(struct super_block *sb,
+			struct buffer_head *bh);
+static int ocfs2_filecheck_repair_inode_block(struct super_block *sb,
+			struct buffer_head *bh);
+
 void ocfs2_set_inode_flags(struct inode *inode)
 {
 	unsigned int flags = OCFS2_I(inode)->ip_attr;
@@ -127,6 +135,7 @@ struct inode *ocfs2_ilookup(struct super_block *sb, u64 blkno)
 struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags,
 			 int sysfile_type)
 {
+	int rc = 0;
 	struct inode *inode = NULL;
 	struct super_block *sb = osb->sb;
 	struct ocfs2_find_inode_args args;
@@ -161,12 +170,17 @@ struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags,
 	}
 	trace_ocfs2_iget5_locked(inode->i_state);
 	if (inode->i_state & I_NEW) {
-		ocfs2_read_locked_inode(inode, &args);
+		rc = ocfs2_read_locked_inode(inode, &args);
 		unlock_new_inode(inode);
 	}
 	if (is_bad_inode(inode)) {
 		iput(inode);
-		inode = ERR_PTR(-ESTALE);
+		if ((flags & OCFS2_FI_FLAG_FILECHECK_CHK) ||
+			(flags & OCFS2_FI_FLAG_FILECHECK_FIX))
+			/* Return OCFS2_FILECHECK_ERR_XXX related errno */
+			inode = ERR_PTR(rc);
+		else
+			inode = ERR_PTR(-ESTALE);
 		goto bail;
 	}
 
@@ -494,16 +508,32 @@ static int ocfs2_read_locked_inode(struct inode *inode,
 	}
 
 	if (can_lock) {
-		status = ocfs2_read_inode_block_full(inode, &bh,
-						     OCFS2_BH_IGNORE_CACHE);
+		if (args->fi_flags & OCFS2_FI_FLAG_FILECHECK_CHK)
+			status = ocfs2_filecheck_read_inode_block_full(inode,
+						&bh, OCFS2_BH_IGNORE_CACHE, 0);
+		else if (args->fi_flags & OCFS2_FI_FLAG_FILECHECK_FIX)
+			status = ocfs2_filecheck_read_inode_block_full(inode,
+						&bh, OCFS2_BH_IGNORE_CACHE, 1);
+		else
+			status = ocfs2_read_inode_block_full(inode,
+						&bh, OCFS2_BH_IGNORE_CACHE);
 	} else {
 		status = ocfs2_read_blocks_sync(osb, args->fi_blkno, 1, &bh);
 		/*
 		 * If buffer is in jbd, then its checksum may not have been
 		 * computed as yet.
 		 */
-		if (!status && !buffer_jbd(bh))
-			status = ocfs2_validate_inode_block(osb->sb, bh);
+		if (!status && !buffer_jbd(bh)) {
+			if (args->fi_flags & OCFS2_FI_FLAG_FILECHECK_CHK)
+				status = ocfs2_filecheck_validate_inode_block(
+								osb->sb, bh);
+			else if (args->fi_flags & OCFS2_FI_FLAG_FILECHECK_FIX)
+				status = ocfs2_filecheck_repair_inode_block(
+								osb->sb, bh);
+			else
+				status = ocfs2_validate_inode_block(
+								osb->sb, bh);
+		}
 	}
 	if (status < 0) {
 		mlog_errno(status);
@@ -531,6 +561,14 @@ static int ocfs2_read_locked_inode(struct inode *inode,
 
 	BUG_ON(args->fi_blkno != le64_to_cpu(fe->i_blkno));
 
+	if (buffer_dirty(bh)) {
+		status = ocfs2_write_block(osb, bh, INODE_CACHE(inode));
+		if (status < 0) {
+			mlog_errno(status);
+			goto bail;
+		}
+	}
+
 	status = 0;
 
 bail:
@@ -1385,6 +1423,152 @@ bail:
 	return rc;
 }
 
+static int ocfs2_filecheck_validate_inode_block(struct super_block *sb,
+			       struct buffer_head *bh)
+{
+	int rc = 0;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data;
+
+	trace_ocfs2_filecheck_validate_inode_block(
+		(unsigned long long)bh->b_blocknr);
+
+	BUG_ON(!buffer_uptodate(bh));
+
+	if (!OCFS2_IS_VALID_DINODE(di)) {
+		mlog(ML_ERROR,
+			"Filecheck: invalid dinode #%llu: signature = %.*s\n",
+			(unsigned long long)bh->b_blocknr, 7, di->i_signature);
+		rc = -OCFS2_FILECHECK_ERR_INVALIDINO;
+		goto bail;
+	}
+
+	rc = ocfs2_validate_meta_ecc(sb, bh->b_data, &di->i_check);
+	if (rc) {
+		mlog(ML_ERROR,
+			"Filecheck: checksum failed for dinode %llu\n",
+			(unsigned long long)bh->b_blocknr);
+		rc = -OCFS2_FILECHECK_ERR_BLOCKECC;
+		goto bail;
+	}
+
+	if (le64_to_cpu(di->i_blkno) != bh->b_blocknr) {
+		mlog(ML_ERROR,
+			"Filecheck: invalid dinode #%llu: i_blkno is %llu\n",
+			(unsigned long long)bh->b_blocknr,
+			(unsigned long long)le64_to_cpu(di->i_blkno));
+		rc = -OCFS2_FILECHECK_ERR_BLOCKNO;
+		goto bail;
+	}
+
+	if (!(di->i_flags & cpu_to_le32(OCFS2_VALID_FL))) {
+		mlog(ML_ERROR,
+			"Filecheck: invalid dinode #%llu: OCFS2_VALID_FL not set\n",
+			(unsigned long long)bh->b_blocknr);
+		rc = -OCFS2_FILECHECK_ERR_VALIDFLAG;
+		goto bail;
+	}
+
+	if (le32_to_cpu(di->i_fs_generation) !=
+	    OCFS2_SB(sb)->fs_generation) {
+		mlog(ML_ERROR,
+			"Filecheck: invalid dinode #%llu: fs_generation is %u\n",
+			(unsigned long long)bh->b_blocknr,
+			le32_to_cpu(di->i_fs_generation));
+		rc = -OCFS2_FILECHECK_ERR_GENERATION;
+		goto bail;
+	}
+
+bail:
+	return rc;
+}
+
+static int ocfs2_filecheck_repair_inode_block(struct super_block *sb,
+			       struct buffer_head *bh)
+{
+	int rc;
+	int changed = 0;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data;
+
+	rc = ocfs2_filecheck_validate_inode_block(sb, bh);
+	/* Can't fix invalid inode block */
+	if (!rc || rc == -OCFS2_FILECHECK_ERR_INVALIDINO)
+		return rc;
+
+	trace_ocfs2_filecheck_repair_inode_block(
+		(unsigned long long)bh->b_blocknr);
+
+	if (ocfs2_is_hard_readonly(OCFS2_SB(sb)) ||
+		ocfs2_is_soft_readonly(OCFS2_SB(sb))) {
+		mlog(ML_ERROR,
+			"Filecheck: try to repair dinode #%llu on readonly filesystem\n",
+			(unsigned long long)bh->b_blocknr);
+		return -OCFS2_FILECHECK_ERR_READONLY;
+	}
+
+	if (le64_to_cpu(di->i_blkno) != bh->b_blocknr) {
+		di->i_blkno = cpu_to_le64(bh->b_blocknr);
+		changed = 1;
+		mlog(ML_ERROR,
+			"Filecheck: reset dinode #%llu: i_blkno to %llu\n",
+			(unsigned long long)bh->b_blocknr,
+			(unsigned long long)le64_to_cpu(di->i_blkno));
+	}
+
+	if (!(di->i_flags & cpu_to_le32(OCFS2_VALID_FL))) {
+		di->i_flags |= cpu_to_le32(OCFS2_VALID_FL);
+		changed = 1;
+		mlog(ML_ERROR,
+			"Filecheck: reset dinode #%llu: OCFS2_VALID_FL is set\n",
+			(unsigned long long)bh->b_blocknr);
+	}
+
+	if (le32_to_cpu(di->i_fs_generation) !=
+	    OCFS2_SB(sb)->fs_generation) {
+		di->i_fs_generation = cpu_to_le32(OCFS2_SB(sb)->fs_generation);
+		changed = 1;
+		mlog(ML_ERROR,
+			"Filecheck: reset dinode #%llu: fs_generation to %u\n",
+			(unsigned long long)bh->b_blocknr,
+			le32_to_cpu(di->i_fs_generation));
+	}
+
+	if (changed ||
+		ocfs2_validate_meta_ecc(sb, bh->b_data, &di->i_check)) {
+		ocfs2_compute_meta_ecc(sb, bh->b_data, &di->i_check);
+		mark_buffer_dirty(bh);
+		mlog(ML_ERROR,
+			"Filecheck: reset dinode #%llu: compute meta ecc\n",
+			(unsigned long long)bh->b_blocknr);
+	}
+
+	return 0;
+}
+
+static int
+ocfs2_filecheck_read_inode_block_full(struct inode *inode,
+		struct buffer_head **bh, int flags, int type)
+{
+	int rc;
+	struct buffer_head *tmp = *bh;
+
+	if (!type) /* Check inode block */
+		rc = ocfs2_read_blocks(INODE_CACHE(inode),
+				OCFS2_I(inode)->ip_blkno,
+				1, &tmp, flags,
+				ocfs2_filecheck_validate_inode_block);
+	else /* Repair inode block */
+		rc = ocfs2_read_blocks(INODE_CACHE(inode),
+				OCFS2_I(inode)->ip_blkno,
+				1, &tmp, flags,
+				ocfs2_filecheck_repair_inode_block);
+
+	/* If ocfs2_read_blocks() got us a new bh, pass it up. */
+	if (!rc && !*bh)
+		*bh = tmp;
+
+	return rc;
+}
+
 int ocfs2_read_inode_block_full(struct inode *inode, struct buffer_head **bh,
 				int flags)
 {
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index 6cb019b..d9205e0 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -1540,6 +1540,8 @@ DEFINE_OCFS2_ULL_INT_EVENT(ocfs2_read_locked_inode);
 DEFINE_OCFS2_INT_INT_EVENT(ocfs2_check_orphan_recovery_state);
 
 DEFINE_OCFS2_ULL_EVENT(ocfs2_validate_inode_block);
+DEFINE_OCFS2_ULL_EVENT(ocfs2_filecheck_validate_inode_block);
+DEFINE_OCFS2_ULL_EVENT(ocfs2_filecheck_repair_inode_block);
 
 TRACE_EVENT(ocfs2_inode_is_valid_to_delete,
 	TP_PROTO(void *task, void *dc_task, unsigned long long ino,
-- 
2.1.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]

#1257703 — [PATCH v2 2/4] ocfs2: sysfile interfaces for online file check

Implement online file check sysfile interfaces, e.g.
how to create the related sysfile according to device name,
how to display/handle file check request from the sysfile.

Signed-off-by: Gang He <ghe@suse.com>
---
 fs/ocfs2/Makefile    |   3 +-
 fs/ocfs2/filecheck.c | 566 +++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/ocfs2/filecheck.h |  48 +++++
 fs/ocfs2/inode.h     |   3 +
 4 files changed, 619 insertions(+), 1 deletion(-)
 create mode 100644 fs/ocfs2/filecheck.c
 create mode 100644 fs/ocfs2/filecheck.h

diff --git a/fs/ocfs2/Makefile b/fs/ocfs2/Makefile
index ce210d4..e27e652 100644
--- a/fs/ocfs2/Makefile
+++ b/fs/ocfs2/Makefile
@@ -41,7 +41,8 @@ ocfs2-objs := \
 	quota_local.o		\
 	quota_global.o		\
 	xattr.o			\
-	acl.o
+	acl.o	\
+	filecheck.o
 
 ocfs2_stackglue-objs := stackglue.o
 ocfs2_stack_o2cb-objs := stack_o2cb.o
diff --git a/fs/ocfs2/filecheck.c b/fs/ocfs2/filecheck.c
new file mode 100644
index 0000000..f12ed1f
--- /dev/null
+++ b/fs/ocfs2/filecheck.c
@@ -0,0 +1,566 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * filecheck.c
+ *
+ * Code which implements online file check.
+ *
+ * Copyright (C) 2015 Novell.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation, version 2.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/kmod.h>
+#include <linux/fs.h>
+#include <linux/kobject.h>
+#include <linux/sysfs.h>
+#include <linux/sysctl.h>
+#include <cluster/masklog.h>
+
+#include "ocfs2.h"
+#include "ocfs2_fs.h"
+#include "stackglue.h"
+#include "inode.h"
+
+#include "filecheck.h"
+
+
+/* File check error strings,
+ * must correspond with error number in header file.
+ */
+static const char * const ocfs2_filecheck_errs[] = {
+	"SUCCESS",
+	"FAILED",
+	"INPROGRESS",
+	"READONLY",
+	"INVALIDINO",
+	"BLOCKECC",
+	"BLOCKNO",
+	"VALIDFLAG",
+	"GENERATION",
+	"UNSUPPORTED"
+};
+
+static DEFINE_SPINLOCK(ocfs2_filecheck_sysfs_lock);
+static LIST_HEAD(ocfs2_filecheck_sysfs_list);
+
+struct ocfs2_filecheck {
+	struct list_head fc_head;	/* File check entry list head */
+	spinlock_t fc_lock;
+	unsigned int fc_max;	/* Maximum number of entry in list */
+	unsigned int fc_size;	/* Current entry count in list */
+	unsigned int fc_done;	/* File check entries are done in list */
+};
+
+struct ocfs2_filecheck_sysfs_entry {
+	struct list_head fs_list;
+	atomic_t fs_count;
+	struct super_block *fs_sb;
+	struct kset *fs_kset;
+	struct ocfs2_filecheck *fs_fcheck;
+};
+
+#define OCFS2_FILECHECK_MAXSIZE		100
+#define OCFS2_FILECHECK_MINSIZE		10
+
+/* File check operation type */
+enum {
+	OCFS2_FILECHECK_TYPE_CHK = 0,	/* Check a file */
+	OCFS2_FILECHECK_TYPE_FIX,	/* Fix a file */
+	OCFS2_FILECHECK_TYPE_SET = 100	/* Set file check options */
+};
+
+struct ocfs2_filecheck_entry {
+	struct list_head fe_list;
+	unsigned long fe_ino;
+	unsigned int fe_type;
+	unsigned short fe_done:1;
+	unsigned short fe_status:15;
+};
+
+struct ocfs2_filecheck_args {
+	unsigned int fa_type;
+	union {
+		unsigned long fa_ino;
+		unsigned int fa_len;
+	};
+};
+
+static const char *
+ocfs2_filecheck_error(int errno)
+{
+	if (!errno)
+		return ocfs2_filecheck_errs[errno];
+
+	BUG_ON(errno < OCFS2_FILECHECK_ERR_START ||
+			errno > OCFS2_FILECHECK_ERR_END);
+	return ocfs2_filecheck_errs[errno - OCFS2_FILECHECK_ERR_START + 1];
+}
+
+static ssize_t ocfs2_filecheck_show(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					char *buf);
+static ssize_t ocfs2_filecheck_store(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					const char *buf, size_t count);
+static struct kobj_attribute ocfs2_attr_filecheck =
+					__ATTR(filecheck, S_IRUSR | S_IWUSR,
+					ocfs2_filecheck_show,
+					ocfs2_filecheck_store);
+
+static int ocfs2_filecheck_sysfs_wait(atomic_t *p)
+{
+	schedule();
+	return 0;
+}
+
+static void
+ocfs2_filecheck_sysfs_free(struct ocfs2_filecheck_sysfs_entry *entry)
+{
+	struct ocfs2_filecheck_entry *p;
+
+	if (!atomic_dec_and_test(&entry->fs_count))
+		wait_on_atomic_t(&entry->fs_count, ocfs2_filecheck_sysfs_wait,
+						TASK_UNINTERRUPTIBLE);
+
+	spin_lock(&entry->fs_fcheck->fc_lock);
+	while (!list_empty(&entry->fs_fcheck->fc_head)) {
+		p = list_first_entry(&entry->fs_fcheck->fc_head,
+				struct ocfs2_filecheck_entry, fe_list);
+		list_del(&p->fe_list);
+		BUG_ON(!p->fe_done); /* To free a undone file check entry */
+		kfree(p);
+	}
+	spin_unlock(&entry->fs_fcheck->fc_lock);
+
+	kset_unregister(entry->fs_kset);
+	kfree(entry->fs_fcheck);
+	kfree(entry);
+}
+
+static void
+ocfs2_filecheck_sysfs_add(struct ocfs2_filecheck_sysfs_entry *entry)
+{
+	spin_lock(&ocfs2_filecheck_sysfs_lock);
+	list_add_tail(&entry->fs_list, &ocfs2_filecheck_sysfs_list);
+	spin_unlock(&ocfs2_filecheck_sysfs_lock);
+}
+
+static int ocfs2_filecheck_sysfs_del(const char *devname)
+{
+	struct ocfs2_filecheck_sysfs_entry *p;
+
+	spin_lock(&ocfs2_filecheck_sysfs_lock);
+	list_for_each_entry(p, &ocfs2_filecheck_sysfs_list, fs_list) {
+		if (!strcmp(p->fs_sb->s_id, devname)) {
+			list_del(&p->fs_list);
+			spin_unlock(&ocfs2_filecheck_sysfs_lock);
+			ocfs2_filecheck_sysfs_free(p);
+			return 0;
+		}
+	}
+	spin_unlock(&ocfs2_filecheck_sysfs_lock);
+	return 1;
+}
+
+static void
+ocfs2_filecheck_sysfs_put(struct ocfs2_filecheck_sysfs_entry *entry)
+{
+	if (atomic_dec_and_test(&entry->fs_count))
+		wake_up_atomic_t(&entry->fs_count);
+}
+
+static struct ocfs2_filecheck_sysfs_entry *
+ocfs2_filecheck_sysfs_get(const char *devname)
+{
+	struct ocfs2_filecheck_sysfs_entry *p = NULL;
+
+	spin_lock(&ocfs2_filecheck_sysfs_lock);
+	list_for_each_entry(p, &ocfs2_filecheck_sysfs_list, fs_list) {
+		if (!strcmp(p->fs_sb->s_id, devname)) {
+			atomic_inc(&p->fs_count);
+			spin_unlock(&ocfs2_filecheck_sysfs_lock);
+			return p;
+		}
+	}
+	spin_unlock(&ocfs2_filecheck_sysfs_lock);
+	return NULL;
+}
+
+int ocfs2_filecheck_create_sysfs(struct super_block *sb)
+{
+	int ret = 0;
+	struct kset *ocfs2_filecheck_kset = NULL;
+	struct ocfs2_filecheck *fcheck = NULL;
+	struct ocfs2_filecheck_sysfs_entry *entry = NULL;
+	struct attribute **attrs = NULL;
+	struct attribute_group attrgp;
+
+	if (!ocfs2_kset)
+		return -ENOMEM;
+
+	attrs = kmalloc(sizeof(struct attribute *) * 2, GFP_NOFS);
+	if (!attrs) {
+		ret = -ENOMEM;
+		goto error;
+	} else {
+		attrs[0] = &ocfs2_attr_filecheck.attr;
+		attrs[1] = NULL;
+		memset(&attrgp, 0, sizeof(attrgp));
+		attrgp.attrs = attrs;
+	}
+
+	fcheck = kmalloc(sizeof(struct ocfs2_filecheck), GFP_NOFS);
+	if (!fcheck) {
+		ret = -ENOMEM;
+		goto error;
+	} else {
+		INIT_LIST_HEAD(&fcheck->fc_head);
+		spin_lock_init(&fcheck->fc_lock);
+		fcheck->fc_max = OCFS2_FILECHECK_MINSIZE;
+		fcheck->fc_size = 0;
+		fcheck->fc_done = 0;
+	}
+
+	if (strlen(sb->s_id) <= 0) {
+		mlog(ML_ERROR,
+		"Cannot get device basename when create filecheck sysfs\n");
+		ret = -ENODEV;
+		goto error;
+	}
+
+	ocfs2_filecheck_kset = kset_create_and_add(sb->s_id, NULL,
+						&ocfs2_kset->kobj);
+	if (!ocfs2_filecheck_kset) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	ret = sysfs_create_group(&ocfs2_filecheck_kset->kobj, &attrgp);
+	if (ret)
+		goto error;
+
+	entry = kmalloc(sizeof(struct ocfs2_filecheck_sysfs_entry), GFP_NOFS);
+	if (!entry) {
+		ret = -ENOMEM;
+		goto error;
+	} else {
+		atomic_set(&entry->fs_count, 1);
+		entry->fs_sb = sb;
+		entry->fs_kset = ocfs2_filecheck_kset;
+		entry->fs_fcheck = fcheck;
+		ocfs2_filecheck_sysfs_add(entry);
+	}
+
+	kfree(attrs);
+	return 0;
+
+error:
+	kfree(attrs);
+	kfree(entry);
+	kfree(fcheck);
+	kset_unregister(ocfs2_filecheck_kset);
+	return ret;
+}
+
+int ocfs2_filecheck_remove_sysfs(struct super_block *sb)
+{
+	return ocfs2_filecheck_sysfs_del(sb->s_id);
+}
+
+static int
+ocfs2_filecheck_erase_entries(struct ocfs2_filecheck_sysfs_entry *ent,
+				unsigned int count);
+static int
+ocfs2_filecheck_adjust_max(struct ocfs2_filecheck_sysfs_entry *ent,
+				unsigned int len)
+{
+	int ret;
+
+	if ((len < OCFS2_FILECHECK_MINSIZE) || (len > OCFS2_FILECHECK_MAXSIZE))
+		return -EINVAL;
+
+	spin_lock(&ent->fs_fcheck->fc_lock);
+	if (len < (ent->fs_fcheck->fc_size - ent->fs_fcheck->fc_done)) {
+		mlog(ML_ERROR,
+		"Cannot set online file check maximum entry number "
+		"to %u due to too much pending entries(%u)\n",
+		len, ent->fs_fcheck->fc_size - ent->fs_fcheck->fc_done);
+		ret = -EBUSY;
+	} else {
+		if (len < ent->fs_fcheck->fc_size)
+			BUG_ON(!ocfs2_filecheck_erase_entries(ent,
+				ent->fs_fcheck->fc_size - len));
+
+		ent->fs_fcheck->fc_max = len;
+		ret = 0;
+	}
+	spin_unlock(&ent->fs_fcheck->fc_lock);
+
+	return ret;
+}
+
+#define OCFS2_FILECHECK_ARGS_LEN	32
+static int
+ocfs2_filecheck_args_get_long(const char *buf, size_t count,
+				unsigned long *val)
+{
+	char buffer[OCFS2_FILECHECK_ARGS_LEN];
+
+	if (count < 1)
+		return 1;
+
+	memcpy(buffer, buf, count);
+	buffer[count] = '\0';
+
+	if (kstrtoul(buffer, 0, val))
+		return 1;
+
+	return 0;
+}
+
+static int
+ocfs2_filecheck_args_parse(const char *buf, size_t count,
+				struct ocfs2_filecheck_args *args)
+{
+	unsigned long val = 0;
+
+	/* too short/long args length */
+	if ((count < 5) || (count > OCFS2_FILECHECK_ARGS_LEN))
+		return 1;
+
+	if (!strncasecmp(buf, "FIX ", 4)) {
+		if (ocfs2_filecheck_args_get_long(buf + 4, count - 4, &val))
+			return 1;
+
+		args->fa_type = OCFS2_FILECHECK_TYPE_FIX;
+		args->fa_ino = val;
+		return 0;
+	} else if ((count > 6) && !strncasecmp(buf, "CHECK ", 6)) {
+		if (ocfs2_filecheck_args_get_long(buf + 6, count - 6, &val))
+			return 1;
+
+		args->fa_type = OCFS2_FILECHECK_TYPE_CHK;
+		args->fa_ino = val;
+		return 0;
+	} else if (!strncasecmp(buf, "SET ", 4)) {
+		if (ocfs2_filecheck_args_get_long(buf + 4, count - 4, &val))
+			return 1;
+
+		args->fa_type = OCFS2_FILECHECK_TYPE_SET;
+		args->fa_len = (unsigned int)val;
+		return 0;
+	} else { /* invalid args */
+		return 1;
+	}
+}
+
+static ssize_t ocfs2_filecheck_show(struct kobject *kobj,
+					struct kobj_attribute *attr,
+					char *buf)
+{
+
+	ssize_t ret = 0, total = 0, remain = PAGE_SIZE;
+	struct ocfs2_filecheck_entry *p;
+	struct ocfs2_filecheck_sysfs_entry *ent;
+
+	ent = ocfs2_filecheck_sysfs_get(kobj->name);
+	if (!ent) {
+		mlog(ML_ERROR,
+		"Cannot get the corresponding entry via device basename %s\n",
+		kobj->name);
+		return -ENODEV;
+	}
+
+	spin_lock(&ent->fs_fcheck->fc_lock);
+	ret = snprintf(buf, remain, "INO\t\tTYPE\tDONE\tERROR\n");
+	total += ret;
+	remain -= ret;
+
+	list_for_each_entry(p, &ent->fs_fcheck->fc_head, fe_list) {
+		ret = snprintf(buf + total, remain, "%lu\t\t%u\t%u\t%s\n",
+			p->fe_ino, p->fe_type, p->fe_done,
+			ocfs2_filecheck_error(p->fe_status));
+		if (ret < 0) {
+			total = ret;
+			break;
+		}
+		if (ret == remain) {
+			/* snprintf() didn't fit */
+			total = -E2BIG;
+			break;
+		}
+		total += ret;
+		remain -= ret;
+	}
+	spin_unlock(&ent->fs_fcheck->fc_lock);
+
+	ocfs2_filecheck_sysfs_put(ent);
+	return total;
+}
+
+static int
+ocfs2_filecheck_erase_entry(struct ocfs2_filecheck_sysfs_entry *ent)
+{
+	struct ocfs2_filecheck_entry *p;
+
+	list_for_each_entry(p, &ent->fs_fcheck->fc_head, fe_list) {
+		if (p->fe_done) {
+			list_del(&p->fe_list);
+			kfree(p);
+			ent->fs_fcheck->fc_size--;
+			ent->fs_fcheck->fc_done--;
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+static int
+ocfs2_filecheck_erase_entries(struct ocfs2_filecheck_sysfs_entry *ent,
+				unsigned int count)
+{
+	unsigned int i = 0;
+	unsigned int ret = 0;
+
+	while (i++ < count) {
+		if (ocfs2_filecheck_erase_entry(ent))
+			ret++;
+		else
+			break;
+	}
+
+	return (ret == count ? 1 : 0);
+}
+
+static void
+ocfs2_filecheck_done_entry(struct ocfs2_filecheck_sysfs_entry *ent,
+				struct ocfs2_filecheck_entry *entry)
+{
+	entry->fe_done = 1;
+	spin_lock(&ent->fs_fcheck->fc_lock);
+	ent->fs_fcheck->fc_done++;
+	spin_unlock(&ent->fs_fcheck->fc_lock);
+}
+
+static unsigned short
+ocfs2_filecheck_handle(struct super_block *sb,
+				unsigned long ino, unsigned int flags)
+{
+	unsigned short ret = OCFS2_FILECHECK_ERR_SUCCESS;
+	struct inode *inode = NULL;
+	int rc;
+
+	inode = ocfs2_iget(OCFS2_SB(sb), ino, flags, 0);
+	if (IS_ERR(inode)) {
+		rc = (int)(-(long)inode);
+		if (rc >= OCFS2_FILECHECK_ERR_START &&
+			rc < OCFS2_FILECHECK_ERR_END)
+			ret = rc;
+		else
+			ret = OCFS2_FILECHECK_ERR_FAILED;
+	} else
+		iput(inode);
+
+	return ret;
+}
+
+static void
+ocfs2_filecheck_handle_entry(struct ocfs2_filecheck_sysfs_entry *ent,
+				struct ocfs2_filecheck_entry *entry)
+{
+	if (entry->fe_type == OCFS2_FILECHECK_TYPE_CHK)
+		entry->fe_status = ocfs2_filecheck_handle(ent->fs_sb,
+				entry->fe_ino, OCFS2_FI_FLAG_FILECHECK_CHK);
+	else if (entry->fe_type == OCFS2_FILECHECK_TYPE_FIX)
+		entry->fe_status = ocfs2_filecheck_handle(ent->fs_sb,
+				entry->fe_ino, OCFS2_FI_FLAG_FILECHECK_FIX);
+	else
+		entry->fe_status = OCFS2_FILECHECK_ERR_UNSUPPORTED;
+
+	ocfs2_filecheck_done_entry(ent, entry);
+}
+
+static ssize_t ocfs2_filecheck_store(struct kobject *kobj,
+				struct kobj_attribute *attr,
+				const char *buf, size_t count)
+{
+	struct ocfs2_filecheck_args args;
+	struct ocfs2_filecheck_entry *entry = NULL;
+	struct ocfs2_filecheck_sysfs_entry *ent;
+	ssize_t ret = 0;
+
+	if (count == 0)
+		return count;
+
+	if (ocfs2_filecheck_args_parse(buf, count, &args)) {
+		mlog(ML_ERROR, "Invalid arguments for online file check\n");
+		return -EINVAL;
+	}
+
+	ent = ocfs2_filecheck_sysfs_get(kobj->name);
+	if (!ent) {
+		mlog(ML_ERROR,
+		"Cannot get the corresponding entry via device basename %s\n",
+		kobj->name);
+		return -ENODEV;
+	}
+
+	if (args.fa_type == OCFS2_FILECHECK_TYPE_SET) {
+		ret = ocfs2_filecheck_adjust_max(ent, args.fa_len);
+		ocfs2_filecheck_sysfs_put(ent);
+		return (!ret ? count : ret);
+	}
+
+	spin_lock(&ent->fs_fcheck->fc_lock);
+	if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) &&
+		(ent->fs_fcheck->fc_done == 0)) {
+		mlog(ML_ERROR,
+		"Online file check queue(%u) is full\n",
+		ent->fs_fcheck->fc_max);
+		ret = -EBUSY;
+	} else {
+		if ((ent->fs_fcheck->fc_size >= ent->fs_fcheck->fc_max) &&
+			(ent->fs_fcheck->fc_done > 0)) {
+			/* Delete the oldest entry which was done,
+			 * make sure the entry size in list does
+			 * not exceed maximum value
+			 */
+			BUG_ON(!ocfs2_filecheck_erase_entry(ent));
+		}
+
+		entry = kmalloc(sizeof(struct ocfs2_filecheck_entry), GFP_NOFS);
+		if (entry) {
+			entry->fe_ino = args.fa_ino;
+			entry->fe_type = args.fa_type;
+			entry->fe_done = 0;
+			entry->fe_status = OCFS2_FILECHECK_ERR_INPROGRESS;
+			list_add_tail(&entry->fe_list,
+					&ent->fs_fcheck->fc_head);
+
+			ent->fs_fcheck->fc_size++;
+			ret = count;
+		} else {
+			ret = -ENOMEM;
+		}
+	}
+	spin_unlock(&ent->fs_fcheck->fc_lock);
+
+	if (entry)
+		ocfs2_filecheck_handle_entry(ent, entry);
+
+	ocfs2_filecheck_sysfs_put(ent);
+	return ret;
+}
diff --git a/fs/ocfs2/filecheck.h b/fs/ocfs2/filecheck.h
new file mode 100644
index 0000000..5ec331b
--- /dev/null
+++ b/fs/ocfs2/filecheck.h
@@ -0,0 +1,48 @@
+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * filecheck.h
+ *
+ * Online file check.
+ *
+ * Copyright (C) 2015 Novell.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License as published by the Free Software Foundation, version 2.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+
+#ifndef FILECHECK_H
+#define FILECHECK_H
+
+#include <linux/types.h>
+#include <linux/list.h>
+
+
+/* File check errno */
+enum {
+	OCFS2_FILECHECK_ERR_SUCCESS = 0,	/* Success */
+	OCFS2_FILECHECK_ERR_FAILED = 1000,	/* Other failure */
+	OCFS2_FILECHECK_ERR_INPROGRESS,		/* In progress */
+	OCFS2_FILECHECK_ERR_READONLY,		/* Read only */
+	OCFS2_FILECHECK_ERR_INVALIDINO,		/* Invalid ino */
+	OCFS2_FILECHECK_ERR_BLOCKECC,		/* Block ecc */
+	OCFS2_FILECHECK_ERR_BLOCKNO,		/* Block number */
+	OCFS2_FILECHECK_ERR_VALIDFLAG,		/* Inode valid flag */
+	OCFS2_FILECHECK_ERR_GENERATION,		/* Inode generation */
+	OCFS2_FILECHECK_ERR_UNSUPPORTED		/* Unsupported */
+};
+
+#define OCFS2_FILECHECK_ERR_START	OCFS2_FILECHECK_ERR_FAILED
+#define OCFS2_FILECHECK_ERR_END		OCFS2_FILECHECK_ERR_UNSUPPORTED
+
+int ocfs2_filecheck_create_sysfs(struct super_block *sb);
+int ocfs2_filecheck_remove_sysfs(struct super_block *sb);
+
+#endif  /* FILECHECK_H */
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index 5e86b24..abd1018 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -139,6 +139,9 @@ int ocfs2_drop_inode(struct inode *inode);
 /* Flags for ocfs2_iget() */
 #define OCFS2_FI_FLAG_SYSFILE		0x1
 #define OCFS2_FI_FLAG_ORPHAN_RECOVERY	0x2
+#define OCFS2_FI_FLAG_FILECHECK_CHK	0x4
+#define OCFS2_FI_FLAG_FILECHECK_FIX	0x8
+
 struct inode *ocfs2_ilookup(struct super_block *sb, u64 feoff);
 struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 feoff, unsigned flags,
 			 int sysfile_type);
-- 
2.1.2

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]

#1258293 — Re: [Ocfs2-devel] [PATCH v2 0/4] Add online file check feature

Hi Gang,

thank you for implementing this. I would like to understand this better 
on where and how it helps ... would you mind sharing couple 
examples(real scenarios).

Thanks,
--Srini


On 10/27/2015 11:25 PM, Gang He wrote:
> When there are errors in the ocfs2 filesystem,
> they are usually accompanied by the inode number which caused the error.
> This inode number would be the input to fixing the file.
> One of these options could be considered:
> A file in the sys filesytem which would accept inode numbers.
> This could be used to communication back what has to be fixed or is fixed.
> You could write:
> $# echo "CHECK <inode>" > /sys/fs/ocfs2/devname/filecheck
> or
> $# echo "FIX <inode>" > /sys/fs/ocfs2/devname/filecheck
>
> Compare with first version, I use strncasecmp instead of double strncmp
> functions. Second, update the source file contribution vendor.
>
> Gang He (4):
>    ocfs2: export ocfs2_kset for online file check
>    ocfs2: sysfile interfaces for online file check
>    ocfs2: create/remove sysfile for online file check
>    ocfs2: check/fix inode block for online file check
>
>   fs/ocfs2/Makefile      |   3 +-
>   fs/ocfs2/filecheck.c   | 566 +++++++++++++++++++++++++++++++++++++++++++++++++
>   fs/ocfs2/filecheck.h   |  48 +++++
>   fs/ocfs2/inode.c       | 196 ++++++++++++++++-
>   fs/ocfs2/inode.h       |   3 +
>   fs/ocfs2/ocfs2_trace.h |   2 +
>   fs/ocfs2/stackglue.c   |   3 +-
>   fs/ocfs2/stackglue.h   |   2 +
>   fs/ocfs2/super.c       |   5 +
>   9 files changed, 820 insertions(+), 8 deletions(-)
>   create mode 100644 fs/ocfs2/filecheck.c
>   create mode 100644 fs/ocfs2/filecheck.h
>

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]

#1258572 — Re: [Ocfs2-devel] [PATCH v2 0/4] Add online file check feature

Hello Srini,

There is a doc about ocfs2 online file check.

OCFS2 online file check
-----------------------

This document will describe OCFS2 online file check feature.

Introduction
============
OCFS2 is often used in high-availaibility systems. However, OCFS2 usually
converts the filesystem to read-only on errors. This may not be necessary, since
turning the filesystem read-only would affect other running processes as well,
decreasing availability. Then, a mount option (errors=continue) was introduced,
which would return the EIO to the calling process and terminate furhter
processing so that the filesystem is not corrupted further. So,the filesystem is
not converted to read-only, and the problematic file's inode number is reported
in the kernel log so that the user can try to check/fix this file via online
filecheck feature.

Scope
=====
This effort is to check/fix small issues which may hinder day-to-day operations
of a cluster filesystem by turning the filesystem read-only. The scope of
checking/fixing is at the file level, initially for regular files and eventually
to all files (including system files) of the filesystem.

In case of directory to file links is incorrect, the directory inode is
reported as erroneous.

This feature is not suited for extravagant checks which involve dependency of
other components of the filesystem, such as but not limited to, checking if the
bits for file blocks in the allocation has been set. In case of such an error,
the offline fsck should/would be recommended.

Finally, such an operation/feature should not be automated lest the filesystem
may end up with more damage than before the repair attempt. So, this has to
be performed using user interaction and consent.

User interface
==============
When there are errors in the OCFS2 filesystem, they are usually accompanied
by the inode number which caused the error. This inode number would be the
input to check/fix the file.

There is a sysfs file for each OCFS2 file system mounting:

  /sys/fs/ocfs2/<devname>/filecheck

Here, <devname> indicates the name of OCFS2 volumn device which has been already
mounted. The file above would accept inode numbers. This could be used to
communicate with kernel space, tell which file(inode number) will be checked or
fixed. Currently, three operations are supported, which includes checking
inode, fixing inode and setting the size of result record history.

1. If you want to know what error exactly happened to <inode> before fixing, do

  # echo "CHECK <inode>" > /sys/fs/ocfs2/<devname>/filecheck
  # cat /sys/fs/ocfs2/<devname>/filecheck

The output is like this:
  INO		TYPE		DONE		ERROR
39502		0		1		GENERATION

<INO> lists the inode numbers.
<TYPE> is what kind of operation you've done, 0 for inode check,1 for inode fix.
<DONE> 	indicates whether the operation has been finished.
<ERROR> says what kind of errors was found. For the details, please refer to the
file linux/fs/ocfs2/filecheck.h.

2. If you determine to fix this inode, do

  # echo "FIX <inode>" > /sys/fs/ocfs2/<devname>/filecheck
  # cat /sys/fs/ocfs2/<devname>/filecheck

The output is like this:
  INO		TYPE		DONE		ERROR
39502		1		1		SUCCESS

This time, the <ERROR> column indicates whether this fix is successful or not.

3. The record cache is used to store the history of check/fix result. Its
defalut size is 10, and can be adjust between the range of 10 ~ 100. You can
adjust the size like this:

  # echo "SET <size>" > /sys/fs/ocfs2/<devname>/filecheck

Fixing stuff
============
On receivng the inode, the filesystem would read the inode and the
file metadata. In case of errors, the filesystem would fix the errors
and report the problems it fixed in the kernel log. As a precautionary measure,
the inode must first be checked for errors before performing a final fix.

The inode and the fix history will be maintained temporarily in a
small linked list buffer which would contain the last (N) inodes
fixed/checked, along with the logs of what errors were reported/fixed.

Thanks
Gang


>>> 
> Hi Gang,
> 
> thank you for implementing this. I would like to understand this better 
> on where and how it helps ... would you mind sharing couple 
> examples(real scenarios).
> 
> Thanks,
> --Srini
> 
> 
> On 10/27/2015 11:25 PM, Gang He wrote:
>> When there are errors in the ocfs2 filesystem,
>> they are usually accompanied by the inode number which caused the error.
>> This inode number would be the input to fixing the file.
>> One of these options could be considered:
>> A file in the sys filesytem which would accept inode numbers.
>> This could be used to communication back what has to be fixed or is fixed.
>> You could write:
>> $# echo "CHECK <inode>" > /sys/fs/ocfs2/devname/filecheck
>> or
>> $# echo "FIX <inode>" > /sys/fs/ocfs2/devname/filecheck
>>
>> Compare with first version, I use strncasecmp instead of double strncmp
>> functions. Second, update the source file contribution vendor.
>>
>> Gang He (4):
>>    ocfs2: export ocfs2_kset for online file check
>>    ocfs2: sysfile interfaces for online file check
>>    ocfs2: create/remove sysfile for online file check
>>    ocfs2: check/fix inode block for online file check
>>
>>   fs/ocfs2/Makefile      |   3 +-
>>   fs/ocfs2/filecheck.c   | 566 
> +++++++++++++++++++++++++++++++++++++++++++++++++
>>   fs/ocfs2/filecheck.h   |  48 +++++
>>   fs/ocfs2/inode.c       | 196 ++++++++++++++++-
>>   fs/ocfs2/inode.h       |   3 +
>>   fs/ocfs2/ocfs2_trace.h |   2 +
>>   fs/ocfs2/stackglue.c   |   3 +-
>>   fs/ocfs2/stackglue.h   |   2 +
>>   fs/ocfs2/super.c       |   5 +
>>   9 files changed, 820 insertions(+), 8 deletions(-)
>>   create mode 100644 fs/ocfs2/filecheck.c
>>   create mode 100644 fs/ocfs2/filecheck.h
>>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]

#1258618 — Re: [Ocfs2-devel] [PATCH v2 0/4] Add online file check feature

Hi Gang,

thanks for pointing to explanation of the feature.

What I am curious about is ... what were the real cases that you came 
across prompted this change and how this change would help in that case.

Thanks,
--Srini


On 10/28/2015 09:44 PM, Gang He wrote:
> Hello Srini,
>
> There is a doc about ocfs2 online file check.
>
> OCFS2 online file check
> -----------------------
>
> This document will describe OCFS2 online file check feature.
>
> Introduction
> ============
> OCFS2 is often used in high-availaibility systems. However, OCFS2 usually
> converts the filesystem to read-only on errors. This may not be necessary, since
> turning the filesystem read-only would affect other running processes as well,
> decreasing availability. Then, a mount option (errors=continue) was introduced,
> which would return the EIO to the calling process and terminate furhter
> processing so that the filesystem is not corrupted further. So,the filesystem is
> not converted to read-only, and the problematic file's inode number is reported
> in the kernel log so that the user can try to check/fix this file via online
> filecheck feature.
>
> Scope
> =====
> This effort is to check/fix small issues which may hinder day-to-day operations
> of a cluster filesystem by turning the filesystem read-only. The scope of
> checking/fixing is at the file level, initially for regular files and eventually
> to all files (including system files) of the filesystem.
>
> In case of directory to file links is incorrect, the directory inode is
> reported as erroneous.
>
> This feature is not suited for extravagant checks which involve dependency of
> other components of the filesystem, such as but not limited to, checking if the
> bits for file blocks in the allocation has been set. In case of such an error,
> the offline fsck should/would be recommended.
>
> Finally, such an operation/feature should not be automated lest the filesystem
> may end up with more damage than before the repair attempt. So, this has to
> be performed using user interaction and consent.
>
> User interface
> ==============
> When there are errors in the OCFS2 filesystem, they are usually accompanied
> by the inode number which caused the error. This inode number would be the
> input to check/fix the file.
>
> There is a sysfs file for each OCFS2 file system mounting:
>
>    /sys/fs/ocfs2/<devname>/filecheck
>
> Here, <devname> indicates the name of OCFS2 volumn device which has been already
> mounted. The file above would accept inode numbers. This could be used to
> communicate with kernel space, tell which file(inode number) will be checked or
> fixed. Currently, three operations are supported, which includes checking
> inode, fixing inode and setting the size of result record history.
>
> 1. If you want to know what error exactly happened to <inode> before fixing, do
>
>    # echo "CHECK <inode>" > /sys/fs/ocfs2/<devname>/filecheck
>    # cat /sys/fs/ocfs2/<devname>/filecheck
>
> The output is like this:
>    INO		TYPE		DONE		ERROR
> 39502		0		1		GENERATION
>
> <INO> lists the inode numbers.
> <TYPE> is what kind of operation you've done, 0 for inode check,1 for inode fix.
> <DONE> 	indicates whether the operation has been finished.
> <ERROR> says what kind of errors was found. For the details, please refer to the
> file linux/fs/ocfs2/filecheck.h.
>
> 2. If you determine to fix this inode, do
>
>    # echo "FIX <inode>" > /sys/fs/ocfs2/<devname>/filecheck
>    # cat /sys/fs/ocfs2/<devname>/filecheck
>
> The output is like this:
>    INO		TYPE		DONE		ERROR
> 39502		1		1		SUCCESS
>
> This time, the <ERROR> column indicates whether this fix is successful or not.
>
> 3. The record cache is used to store the history of check/fix result. Its
> defalut size is 10, and can be adjust between the range of 10 ~ 100. You can
> adjust the size like this:
>
>    # echo "SET <size>" > /sys/fs/ocfs2/<devname>/filecheck
>
> Fixing stuff
> ============
> On receivng the inode, the filesystem would read the inode and the
> file metadata. In case of errors, the filesystem would fix the errors
> and report the problems it fixed in the kernel log. As a precautionary measure,
> the inode must first be checked for errors before performing a final fix.
>
> The inode and the fix history will be maintained temporarily in a
> small linked list buffer which would contain the last (N) inodes
> fixed/checked, along with the logs of what errors were reported/fixed.
>
> Thanks
> Gang
>
>
>> Hi Gang,
>>
>> thank you for implementing this. I would like to understand this better
>> on where and how it helps ... would you mind sharing couple
>> examples(real scenarios).
>>
>> Thanks,
>> --Srini
>>
>>
>> On 10/27/2015 11:25 PM, Gang He wrote:
>>> When there are errors in the ocfs2 filesystem,
>>> they are usually accompanied by the inode number which caused the error.
>>> This inode number would be the input to fixing the file.
>>> One of these options could be considered:
>>> A file in the sys filesytem which would accept inode numbers.
>>> This could be used to communication back what has to be fixed or is fixed.
>>> You could write:
>>> $# echo "CHECK <inode>" > /sys/fs/ocfs2/devname/filecheck
>>> or
>>> $# echo "FIX <inode>" > /sys/fs/ocfs2/devname/filecheck
>>>
>>> Compare with first version, I use strncasecmp instead of double strncmp
>>> functions. Second, update the source file contribution vendor.
>>>
>>> Gang He (4):
>>>     ocfs2: export ocfs2_kset for online file check
>>>     ocfs2: sysfile interfaces for online file check
>>>     ocfs2: create/remove sysfile for online file check
>>>     ocfs2: check/fix inode block for online file check
>>>
>>>    fs/ocfs2/Makefile      |   3 +-
>>>    fs/ocfs2/filecheck.c   | 566
>> +++++++++++++++++++++++++++++++++++++++++++++++++
>>>    fs/ocfs2/filecheck.h   |  48 +++++
>>>    fs/ocfs2/inode.c       | 196 ++++++++++++++++-
>>>    fs/ocfs2/inode.h       |   3 +
>>>    fs/ocfs2/ocfs2_trace.h |   2 +
>>>    fs/ocfs2/stackglue.c   |   3 +-
>>>    fs/ocfs2/stackglue.h   |   2 +
>>>    fs/ocfs2/super.c       |   5 +
>>>    9 files changed, 820 insertions(+), 8 deletions(-)
>>>    create mode 100644 fs/ocfs2/filecheck.c
>>>    create mode 100644 fs/ocfs2/filecheck.h
>>>

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [next] | [standalone]

#1258646 — Re: [Ocfs2-devel] [PATCH v2 0/4] Add online file check feature

Hello Srini,

The real cases are that we try to fix some independent issues without turning the file system off-line (error=continue was introduced).
You know, the online file check feature is used for fixing some independent or light meta-data block corruption, e.g. inode block, file extent block, dir entry block, etc.
These corruptions are usually like checksum error, blk number inconsistency, etc. 

Thanks
Gang  


-- 
<The HTML signature 'New Signature' does not contain any text>


>>> 
> Hi Gang,
> 
> thanks for pointing to explanation of the feature.
> 
> What I am curious about is ... what were the real cases that you came 
> across prompted this change and how this change would help in that case.
> 
> Thanks,
> --Srini
> 
> 
> On 10/28/2015 09:44 PM, Gang He wrote:
>> Hello Srini,
>>
>> There is a doc about ocfs2 online file check.
>>
>> OCFS2 online file check
>> -----------------------
>>
>> This document will describe OCFS2 online file check feature.
>>
>> Introduction
>> ============
>> OCFS2 is often used in high-availaibility systems. However, OCFS2 usually
>> converts the filesystem to read-only on errors. This may not be necessary, 
> since
>> turning the filesystem read-only would affect other running processes as 
> well,
>> decreasing availability. Then, a mount option (errors=continue) was 
> introduced,
>> which would return the EIO to the calling process and terminate furhter
>> processing so that the filesystem is not corrupted further. So,the 
> filesystem is
>> not converted to read-only, and the problematic file's inode number is 
> reported
>> in the kernel log so that the user can try to check/fix this file via online
>> filecheck feature.
>>
>> Scope
>> =====
>> This effort is to check/fix small issues which may hinder day-to-day 
> operations
>> of a cluster filesystem by turning the filesystem read-only. The scope of
>> checking/fixing is at the file level, initially for regular files and 
> eventually
>> to all files (including system files) of the filesystem.
>>
>> In case of directory to file links is incorrect, the directory inode is
>> reported as erroneous.
>>
>> This feature is not suited for extravagant checks which involve dependency 
> of
>> other components of the filesystem, such as but not limited to, checking if 
> the
>> bits for file blocks in the allocation has been set. In case of such an 
> error,
>> the offline fsck should/would be recommended.
>>
>> Finally, such an operation/feature should not be automated lest the 
> filesystem
>> may end up with more damage than before the repair attempt. So, this has to
>> be performed using user interaction and consent.
>>
>> User interface
>> ==============
>> When there are errors in the OCFS2 filesystem, they are usually accompanied
>> by the inode number which caused the error. This inode number would be the
>> input to check/fix the file.
>>
>> There is a sysfs file for each OCFS2 file system mounting:
>>
>>    /sys/fs/ocfs2/<devname>/filecheck
>>
>> Here, <devname> indicates the name of OCFS2 volumn device which has been 
> already
>> mounted. The file above would accept inode numbers. This could be used to
>> communicate with kernel space, tell which file(inode number) will be checked 
> or
>> fixed. Currently, three operations are supported, which includes checking
>> inode, fixing inode and setting the size of result record history.
>>
>> 1. If you want to know what error exactly happened to <inode> before fixing, 
> do
>>
>>    # echo "CHECK <inode>" > /sys/fs/ocfs2/<devname>/filecheck
>>    # cat /sys/fs/ocfs2/<devname>/filecheck
>>
>> The output is like this:
>>    INO		TYPE		DONE		ERROR
>> 39502		0		1		GENERATION
>>
>> <INO> lists the inode numbers.
>> <TYPE> is what kind of operation you've done, 0 for inode check,1 for inode 
> fix.
>> <DONE> 	indicates whether the operation has been finished.
>> <ERROR> says what kind of errors was found. For the details, please refer to 
> the
>> file linux/fs/ocfs2/filecheck.h.
>>
>> 2. If you determine to fix this inode, do
>>
>>    # echo "FIX <inode>" > /sys/fs/ocfs2/<devname>/filecheck
>>    # cat /sys/fs/ocfs2/<devname>/filecheck
>>
>> The output is like this:
>>    INO		TYPE		DONE		ERROR
>> 39502		1		1		SUCCESS
>>
>> This time, the <ERROR> column indicates whether this fix is successful or not.
>>
>> 3. The record cache is used to store the history of check/fix result. Its
>> defalut size is 10, and can be adjust between the range of 10 ~ 100. You can
>> adjust the size like this:
>>
>>    # echo "SET <size>" > /sys/fs/ocfs2/<devname>/filecheck
>>
>> Fixing stuff
>> ============
>> On receivng the inode, the filesystem would read the inode and the
>> file metadata. In case of errors, the filesystem would fix the errors
>> and report the problems it fixed in the kernel log. As a precautionary 
> measure,
>> the inode must first be checked for errors before performing a final fix.
>>
>> The inode and the fix history will be maintained temporarily in a
>> small linked list buffer which would contain the last (N) inodes
>> fixed/checked, along with the logs of what errors were reported/fixed.
>>
>> Thanks
>> Gang
>>
>>
>>> Hi Gang,
>>>
>>> thank you for implementing this. I would like to understand this better
>>> on where and how it helps ... would you mind sharing couple
>>> examples(real scenarios).
>>>
>>> Thanks,
>>> --Srini
>>>
>>>
>>> On 10/27/2015 11:25 PM, Gang He wrote:
>>>> When there are errors in the ocfs2 filesystem,
>>>> they are usually accompanied by the inode number which caused the error.
>>>> This inode number would be the input to fixing the file.
>>>> One of these options could be considered:
>>>> A file in the sys filesytem which would accept inode numbers.
>>>> This could be used to communication back what has to be fixed or is fixed.
>>>> You could write:
>>>> $# echo "CHECK <inode>" > /sys/fs/ocfs2/devname/filecheck
>>>> or
>>>> $# echo "FIX <inode>" > /sys/fs/ocfs2/devname/filecheck
>>>>
>>>> Compare with first version, I use strncasecmp instead of double strncmp
>>>> functions. Second, update the source file contribution vendor.
>>>>
>>>> Gang He (4):
>>>>     ocfs2: export ocfs2_kset for online file check
>>>>     ocfs2: sysfile interfaces for online file check
>>>>     ocfs2: create/remove sysfile for online file check
>>>>     ocfs2: check/fix inode block for online file check
>>>>
>>>>    fs/ocfs2/Makefile      |   3 +-
>>>>    fs/ocfs2/filecheck.c   | 566
>>> +++++++++++++++++++++++++++++++++++++++++++++++++
>>>>    fs/ocfs2/filecheck.h   |  48 +++++
>>>>    fs/ocfs2/inode.c       | 196 ++++++++++++++++-
>>>>    fs/ocfs2/inode.h       |   3 +
>>>>    fs/ocfs2/ocfs2_trace.h |   2 +
>>>>    fs/ocfs2/stackglue.c   |   3 +-
>>>>    fs/ocfs2/stackglue.h   |   2 +
>>>>    fs/ocfs2/super.c       |   5 +
>>>>    9 files changed, 820 insertions(+), 8 deletions(-)
>>>>    create mode 100644 fs/ocfs2/filecheck.c
>>>>    create mode 100644 fs/ocfs2/filecheck.h
>>>>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web