[PATCH 7/15] scsi xcopy: keep cache of failures

From: Mikulas Patocka <mpatocka@redhat.com>
To: "James E.J. Bottomley" <JBottomley@odin.com>,
	"Martin K. Petersen" <martin.petersen@oracle.com>,
	Jens Axboe <axboe@kernel.dk>, Mike Snitzer <msnitzer@redhat.com>,
	Jonathan Brassow <jbrassow@redhat.com>
Cc: dm-devel@redhat.com, linux-scsi@vger.kernel.org,
	linux-kernel@vger.kernel.org, linux-block@vger.kernel.org
Subject: [PATCH 7/15] scsi xcopy: keep cache of failures
Date: Thu, 10 Dec 2015 12:30:37 -0500 (EST)	[thread overview]
Message-ID: <alpine.LRH.2.02.1512101212220.25927@file01.intranet.prod.int.rdu2.redhat.com> (raw)
In-Reply-To: <alpine.LRH.2.02.1512101145430.25927@file01.intranet.prod.int.rdu2.redhat.com>

If xcopy between two devices fails, it is pointless to send more xcopy
command between there two devices because they take time and they will
likely also fail.

This patch keeps a cache of (source_device,destination_device) pairs where
copying failed and makes sure that no xcopy command is sooner than 30
seconds after the last failure.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>

---
 drivers/scsi/sd.c |   37 +++++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)

Index: linux-4.4-rc4/drivers/scsi/sd.c
===================================================================

--- linux-4.4-rc4.orig/drivers/scsi/sd.c	2015-12-07 16:59:09.000000000 +0100
+++ linux-4.4-rc4/drivers/scsi/sd.c	2015-12-07 16:59:12.000000000 +0100
@@ -939,6 +939,26 @@ static void sd_config_copy(struct scsi_d
 				   (logical_block_size >> 9));
 }
 
+#define SD_COPY_DISABLED_CACHE_TIME		(HZ * 30)
+#define SD_COPY_DISABLED_CACHE_HASH_BITS	6
+#define SD_COPY_DISABLED_CACHE_HASH		(1 << SD_COPY_DISABLED_CACHE_HASH_BITS)
+
+struct sd_copy_disabled_cache_entry {
+	struct scsi_device *src;
+	struct scsi_device *dst;
+	unsigned long jiffies;
+};
+
+static struct sd_copy_disabled_cache_entry sd_copy_disabled_cache[SD_COPY_DISABLED_CACHE_HASH];
+
+static struct sd_copy_disabled_cache_entry *sd_copy_disabled_cache_hash(
+	struct scsi_device *src, struct scsi_device *dst)
+{
+	return &sd_copy_disabled_cache[
+		hash_long((unsigned long)src + ((unsigned long)dst >> 1), SD_COPY_DISABLED_CACHE_HASH_BITS)
+	];
+}
+
 static int sd_setup_copy_cmnd(struct scsi_cmnd *cmd)
 {
 	struct request *rq = cmd->request;
@@ -951,6 +971,7 @@ static int sd_setup_copy_cmnd(struct scs
 	struct bio *bio = rq->bio;
 	struct page *page;
 	unsigned char *buf;
+	struct sd_copy_disabled_cache_entry *e;
 
 	dst_sdp = scsi_disk(rq->rq_disk)->device;
 	dst_queue = rq->rq_disk->queue;
@@ -970,6 +991,12 @@ static int sd_setup_copy_cmnd(struct scs
 	if (src_sdp->sector_size != dst_sdp->sector_size)
 		return BLKPREP_KILL;
 
+	/* The copy failed in the past, so do not retry it for some time */
+	e = sd_copy_disabled_cache_hash(src_sdp, dst_sdp);
+	if (unlikely(jiffies - ACCESS_ONCE(e->jiffies) < SD_COPY_DISABLED_CACHE_TIME) &&
+	    likely(ACCESS_ONCE(e->src) == src_sdp) && likely(ACCESS_ONCE(e->dst) == dst_sdp))
+		return BLKPREP_KILL;
+
 	dst_lba = blk_rq_pos(rq) >> (ilog2(dst_sdp->sector_size) - 9);
 	src_lba = bio->bi_copy->pair[0]->bi_iter.bi_sector >> (ilog2(src_sdp->sector_size) - 9);
 	nr_blocks = blk_rq_sectors(rq) >> (ilog2(dst_sdp->sector_size) - 9);
@@ -2003,6 +2030,16 @@ static int sd_done(struct scsi_cmnd *SCp
 			 */
 			case EXTENDED_COPY:
 				if ((SCpnt->cmnd[1] & 0x1f) == 0) {
+					struct sd_copy_disabled_cache_entry *e;
+					struct scsi_device *src_sdp, *dst_sdp;
+
+					dst_sdp = sdkp->device;
+					src_sdp = scsi_disk(req->bio->bi_copy->pair[0]->bi_bdev->bd_disk)->device;
+					e = sd_copy_disabled_cache_hash(src_sdp, dst_sdp);
+					ACCESS_ONCE(e->src) = src_sdp;
+					ACCESS_ONCE(e->dst) = dst_sdp;
+					ACCESS_ONCE(e->jiffies) = jiffies;
+
 					good_bytes = 0;
 					req->__data_len = blk_rq_bytes(req);
 					req->cmd_flags |= REQ_QUIET;
