This allows us to grab any file system error messages by scraping
/var/log/messages. This will make it easy for us to do error analysis
across the very large number of machines as we deploy ext4 across the
fleet.
Signed-off-by: "Theodore Ts'o" <tytso@xxxxxxx>
---
I originally wasn't going to send this patch upstream, but then I
thought that perhaps it might be useful in cases where the customer has
the file system set up with errors=continue, and there might not be any
indication that the file system contains errorrs in /var/log/message.
This way it guarantees there will be a periodic reminder that the file
system has inconsistencies in the log.
What do people think? Is this too annoying?
fs/ext4/ext4.h | 3 ++
fs/ext4/super.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 62 insertions(+), 0 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 6b96125..5d3d768 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1166,6 +1166,9 @@ struct ext4_sb_info {
/* workqueue for dio unwritten */
struct workqueue_struct *dio_unwritten_wq;
+
+ /* timer for periodic error stats printing */
+ struct timer_list s_err_report;
};
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index a94d3f5..ed00c14 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -325,6 +325,12 @@ static void __save_error_info(struct super_block *sb, const char *func,
es->s_first_error_ino = es->s_last_error_ino;
es->s_first_error_block = es->s_last_error_block;
}
+ /*
+ * Start the daily error reporting function if it hasn't been
+ * started already
+ */
+ if (!es->s_error_count)
+ mod_timer(&EXT4_SB(sb)->s_err_report, jiffies + 24*60*60*HZ);
es->s_error_count = cpu_to_le32(le32_to_cpu(es->s_error_count) + 1);
}
@@ -2480,6 +2486,53 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly)
return 1;
}
+/*
+ * This function is called once a day if we have errors logged
+ * on the file system
+ */
+static void print_daily_error_info(unsigned long arg)
+{
+ struct super_block *sb = (struct super_block *) arg;
+ struct ext4_sb_info *sbi;
+ struct ext4_super_block *es;
+
+ sbi = EXT4_SB(sb);
+ es = sbi->s_es;
+
+ if (es->s_error_count)
+ ext4_msg(sb, KERN_NOTICE, "error count: %u",
+ le32_to_cpu(es->s_error_count));
+ if (es->s_first_error_time) {
+ printk(KERN_NOTICE "EXT4-fs (%s): initial error at %u: %.*s:%d",
+ sb->s_id, le32_to_cpu(es->s_first_error_time),
+ (int) sizeof(es->s_first_error_func),
+ es->s_first_error_func,
+ le32_to_cpu(es->s_first_error_line));
+ if (es->s_first_error_ino)
+ printk(": inode %u",
+ le32_to_cpu(es->s_first_error_ino));
+ if (es->s_first_error_block)
+ printk(": block %llu", (unsigned long long)
+ le64_to_cpu(es->s_first_error_block));
+ printk("\n");
+ }
+ if (es->s_last_error_time) {
+ printk(KERN_NOTICE "EXT4-fs (%s): last error at %u: %.*s:%d",
+ sb->s_id, le32_to_cpu(es->s_last_error_time),
+ (int) sizeof(es->s_last_error_func),
+ es->s_last_error_func,
+ le32_to_cpu(es->s_last_error_line));
+ if (es->s_last_error_ino)
+ printk(": inode %u",
+ le32_to_cpu(es->s_last_error_ino));
+ if (es->s_last_error_block)
+ printk(": block %llu", (unsigned long long)
+ le64_to_cpu(es->s_last_error_block));
+ printk("\n");
+ }
+ mod_timer(&sbi->s_err_report, jiffies + 24*60*60*HZ); /* Once a day */
+}
+
static int ext4_fill_super(struct super_block *sb, void *data, int silent)
__releases(kernel_lock)
__acquires(kernel_lock)
@@ -3083,6 +3136,12 @@ no_journal:
ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. "
"Opts: %s", descr, orig_data);
+ init_timer(&sbi->s_err_report);
+ sbi->s_err_report.function = print_daily_error_info;
+ sbi->s_err_report.data = (unsigned long) sb;
+ if (es->s_error_count)
+ mod_timer(&sbi->s_err_report, jiffies + 300*HZ); /* 5 minutes */
+
lock_kernel();
kfree(orig_data);
return 0;
--
1.7.0.4
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
