[PATCH 37/50] mars: add new file include/linux/xio/xio_trans_logger.h

[Thomas Schoebel-Theuer]

Signed-off-by: Thomas Schoebel-Theuer <tst@xxxxxxxxxxxxxxxxxx>
---
 include/linux/xio/xio_trans_logger.h | 249 +++++++++++++++++++++++++++++++++++
 1 file changed, 249 insertions(+)
 create mode 100644 include/linux/xio/xio_trans_logger.h

diff --git a/include/linux/xio/xio_trans_logger.h b/include/linux/xio/xio_trans_logger.h
new file mode 100644
index 0000000..f499f42
--- /dev/null
+++ b/include/linux/xio/xio_trans_logger.h
@@ -0,0 +1,249 @@
+/*  (c) 2010 Thomas Schoebel-Theuer / 1&1 Internet AG */
+#ifndef XIO_TRANS_LOGGER_H
+#define XIO_TRANS_LOGGER_H
+
+#define REGION_SIZE_BITS		(PAGE_SHIFT + 4)
+#define REGION_SIZE			(1 << REGION_SIZE_BITS)
+#define LOGGER_QUEUES			4
+
+#include <linux/time.h>
+
+#include <linux/xio.h>
+#include <linux/lib_log.h>
+#include <linux/brick/lib_pairing_heap.h>
+#include <linux/brick/lib_queue.h>
+#include <linux/brick/lib_timing.h>
+
+/************************ global tuning ***********************/
+
+/* 0 = early completion of all writes
+ * 1 = early completion of non-sync
+ * 2 = late completion
+ */
+extern int trans_logger_completion_semantics;
+extern int trans_logger_do_crc;
+extern int trans_logger_mem_usage; /*  in KB */
+extern int trans_logger_max_interleave;
+extern int trans_logger_resume;
+extern int trans_logger_replay_timeout; /*  in s */
+extern atomic_t   global_mshadow_count;
+extern atomic64_t global_mshadow_used;
+
+struct writeback_group {
+	rwlock_t lock;
+	struct trans_logger_brick *leader;
+	loff_t biggest;
+	struct list_head group_anchor;
+
+	/*  tuning */
+	struct xio_limiter limiter;
+	int until_percent;
+};
+
+extern struct writeback_group global_writeback;
+
+/******************************************************************/
+
+_PAIRING_HEAP_TYPEDEF(logger, /*empty*/)
+
+struct logger_queue {
+	QUEUE_ANCHOR(logger, loff_t, logger);
+	struct trans_logger_brick *q_brick;
+	const char *q_insert_info;
+	const char *q_pushback_info;
+	const char *q_fetch_info;
+	struct banning q_banning;
+	int no_progress_count;
+	int pushback_count;
+};
+
+struct logger_head {
+	struct list_head lh_head;
+	loff_t *lh_pos;
+	struct pairing_heap_logger ph;
+};
+
+/******************************************************************/
+
+#define TL_INPUT_READ			0
+#define TL_INPUT_WRITEBACK		0
+#define TL_INPUT_LOG1			1
+#define TL_INPUT_LOG2			2
+#define TL_INPUT_NR			3
+
+struct writeback_info {
+	struct trans_logger_brick *w_brick;
+	struct logger_head w_lh;
+	loff_t w_pos;
+	int    w_len;
+	int    w_error;
+
+	struct list_head w_collect_list;   /*  list of collected orig requests */
+	struct list_head w_sub_read_list;  /*  for saving the old data before overwrite */
+	struct list_head w_sub_write_list; /*  for overwriting */
+	atomic_t w_sub_read_count;
+	atomic_t w_sub_write_count;
+	atomic_t w_sub_log_count;
+
+	/* make checkpatch.pl happy with a blank line - is this a false positive? */
+
+	void (*read_endio)(struct generic_callback *cb);
+	void (*write_endio)(struct generic_callback *cb);
+};
+
+struct trans_logger_aio_aspect {
+	GENERIC_ASPECT(aio);
+	struct trans_logger_brick *my_brick;
+	struct trans_logger_input *my_input;
+	struct trans_logger_input *log_input;
+	struct logger_head lh;
+	struct list_head hash_head;
+	struct list_head pos_head;
+	struct list_head replay_head;
+	struct list_head collect_head;
+	struct pairing_heap_logger ph;
+	struct trans_logger_aio_aspect *shadow_aio;
+	struct trans_logger_aio_aspect *orig_aio_a;
+	void  *shadow_data;
+	int    orig_rw;
+	int    wb_error;
+	bool   do_dealloc;
+	bool   do_buffered;
+	bool   is_hashed;
+	bool   is_stable;
+	bool   is_dirty;
+	bool   is_collected;
+	bool   is_fired;
+	bool   is_completed;
+	bool   is_persistent;
+	bool   is_emergency;
+	struct timespec stamp;
+	loff_t log_pos;
+	struct generic_callback cb;
+	struct writeback_info *wb;
+	struct list_head sub_list;
+	struct list_head sub_head;
+	int    total_sub_count;
+	int    alloc_len;
+	atomic_t current_sub_count;
+};
+
+struct trans_logger_hash_anchor;
+
+struct trans_logger_brick {
+	XIO_BRICK(trans_logger);
+	/*  parameters */
+	struct xio_limiter *replay_limiter;
+
+	int shadow_mem_limit; /*  max # master shadows */
+	bool replay_mode;   /*	mode of operation */
+	bool continuous_replay_mode;   /*  mode of operation */
+	bool log_reads;   /*  additionally log pre-images */
+	bool cease_logging; /*	direct IO without logging (only in case of EMERGENCY) */
+	loff_t replay_start_pos; /*  where to start replay */
+	loff_t replay_end_pos;	 /*  end of replay */
+	int new_input_nr;   /*	whereto we should switchover ASAP */
+	int replay_tolerance; /*  how many bytes to ignore at truncated logfiles */
+	/*  readonly from outside */
+	loff_t replay_current_pos;   /*  end of replay */
+	int log_input_nr;   /*	where we are currently logging to */
+	int old_input_nr;   /*	where old IO requests may be on the fly */
+	int replay_code;    /*	replay errors (if any) */
+	bool stopped_logging; /*  direct IO without logging (only in case of EMERGENCY) */
+	/*  private */
+	int disk_io_error;	   /*  replay errors from callbacks */
+	struct trans_logger_hash_anchor **hash_table;
+	struct list_head group_head;
+	loff_t old_margin;
+	spinlock_t replay_lock;
+	struct list_head replay_list;
+	struct task_struct *thread;
+
+	wait_queue_head_t worker_event;
+	wait_queue_head_t caller_event;
+	/*  statistics */
+	atomic64_t shadow_mem_used;
+	atomic_t replay_count;
+	atomic_t any_fly_count;
+	atomic_t log_fly_count;
+	atomic_t hash_count;
+	atomic_t mshadow_count;
+	atomic_t sshadow_count;
+	atomic_t outer_balance_count;
+	atomic_t inner_balance_count;
+	atomic_t sub_balance_count;
+	atomic_t wb_balance_count;
+	atomic_t total_hash_insert_count;
+	atomic_t total_hash_find_count;
+	atomic_t total_hash_extend_count;
+	atomic_t total_replay_count;
+	atomic_t total_replay_conflict_count;
+	atomic_t total_cb_count;
+	atomic_t total_read_count;
+	atomic_t total_write_count;
+	atomic_t total_flush_count;
+	atomic_t total_writeback_count;
+	atomic_t total_writeback_cluster_count;
+	atomic_t total_shortcut_count;
+	atomic_t total_mshadow_count;
+	atomic_t total_sshadow_count;
+	atomic_t total_mshadow_buffered_count;
+	atomic_t total_sshadow_buffered_count;
+	atomic_t total_round_count;
+	atomic_t total_restart_count;
+	atomic_t total_delay_count;
+
+	/*  queues */
+	struct logger_queue q_phase[LOGGER_QUEUES];
+	bool   delay_callers;
+};
+
+struct trans_logger_output {
+	XIO_OUTPUT(trans_logger);
+};
+
+#define MAX_HOST_LEN			32
+
+struct trans_logger_info {
+	/*  to be maintained / initialized from outside */
+	void (*inf_callback)(struct trans_logger_info *inf);
+	void  *inf_private;
+	char   inf_host[MAX_HOST_LEN];
+
+	int    inf_sequence;	 /*  logfile sequence number */
+
+	/*  maintained by trans_logger */
+	loff_t inf_min_pos;  /*  current replay position (both in replay mode and in logging mode) */
+	loff_t inf_max_pos;  /*  dito, indicating the "dirty" area which could be potentially "inconsistent" */
+	loff_t inf_log_pos; /*	position of transaction logging (may be ahead of replay position) */
+	struct timespec inf_min_pos_stamp; /*  when the data has been _successfully_ overwritten */
+/*  when the data has _started_ overwrite (maybe "trashed" in case of errors / aborts) */
+	struct timespec inf_max_pos_stamp;
+
+	struct timespec inf_log_pos_stamp; /*  stamp from transaction log */
+	bool inf_is_replaying;
+	bool inf_is_logging;
+};
+
+struct trans_logger_input {
+	XIO_INPUT(trans_logger);
+	/*  parameters */
+	/*  informational */
+	struct trans_logger_info inf;
+
+	/*  readonly from outside */
+	atomic_t log_obj_count;
+	atomic_t pos_count;
+	bool is_operating;
+	long long last_jiffies;
+
+	/*  private */
+	struct log_status logst;
+	struct list_head pos_list;
+	long long inf_last_jiffies;
+	struct semaphore inf_mutex;
+};
+
+XIO_TYPES(trans_logger);
+
+#endif
-- 
2.0.0

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