[ Jens/James, This is a rather old rate limt patch but never gets picked up in upstream, so I am resending it here as v3, with some minor changes so it is directly applicable to the current linux-2.6.git tree. I don't have that many LUNs that the original issue was reported but the patch was already reviewed and acked in the past, I did retest w/ stress I/O on 4 LUNs I have right now.
Original thread can be found at: http://comments.gmane.org/gmane.linux.scsi/73497 http://www.open-fcoe.org/patchwork/patch/2436/ Can you please pull this patch in? it's been hanging there for a long time. Original patch description is below. thanks, yi ] When performing a cable pull test w/ active stress I/O using fio over a dual port Intel 82599 FCoE CNA, w/ 256LUNs on one port and about 32LUNs on the other, it is observed that the system becomes not usable due to scsi-ml being busy printing the error messages for all the failing commands. I don't believe this problem is specific to FCoE and these commands are anyway failing due to link being down (DID_NO_CONNECT), just rate-limit the messages here to solve this issue. v2->v1: use __ratelimit() as Tomas Henzl mentioned as the proper way for rate-limit per function. However, in this case, the failed i/o gets to blk_end_request_err() and then blk_update_request(), which also has to be rate-limited, as added in the v2 of this patch. v3-v2: resolved conflict to apply on current 3.6-rc3 upstream tip. Signed-off-by: Yi Zou <yi....@intel.com> Cc: www.Open-FCoE.org <devel@open-fcoe.org> Cc: Tomas Henzl <the...@redhat.com> Cc: <linux-s...@vger.kernel.org> --- block/blk-core.c | 8 +++++--- drivers/scsi/scsi_lib.c | 5 ++++- 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index 4b4dbdf..ee3cb3a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2254,9 +2254,11 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) error_type = "I/O"; break; } - printk(KERN_ERR "end_request: %s error, dev %s, sector %llu\n", - error_type, req->rq_disk ? req->rq_disk->disk_name : "?", - (unsigned long long)blk_rq_pos(req)); + printk_ratelimited(KERN_ERR "end_request: %s error, dev %s, sector %llu\n", + error_type, req->rq_disk ? + req->rq_disk->disk_name : "?", + (unsigned long long)blk_rq_pos(req)); + } blk_account_io_completion(req, nr_bytes); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index ffd7773..d784e68 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -20,6 +20,7 @@ #include <linux/delay.h> #include <linux/hardirq.h> #include <linux/scatterlist.h> +#include <linux/ratelimit.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> @@ -768,6 +769,8 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) enum {ACTION_FAIL, ACTION_REPREP, ACTION_RETRY, ACTION_DELAYED_RETRY} action; char *description = NULL; + static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); if (result) { sense_valid = scsi_command_normalize_sense(cmd, &sshdr); @@ -958,7 +961,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) case ACTION_FAIL: /* Give up and fail the remainder of the request */ scsi_release_buffers(cmd); - if (!(req->cmd_flags & REQ_QUIET)) { + if (!(req->cmd_flags & REQ_QUIET) && __ratelimit(&rs)) { if (description) scmd_printk(KERN_INFO, cmd, "%s\n", description); _______________________________________________ devel mailing list devel@open-fcoe.org https://lists.open-fcoe.org/mailman/listinfo/devel
