From patchwork Tue Sep 29 10:47:29 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Hannes Reinecke X-Patchwork-Id: 7285181 Return-Path: X-Original-To: patchwork-linux-scsi@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork2.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.136]) by patchwork2.web.kernel.org (Postfix) with ESMTP id 1CCB2BEEA4 for ; Tue, 29 Sep 2015 10:48:47 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id 8F84D206CC for ; Tue, 29 Sep 2015 10:48:45 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id B2902206D9 for ; Tue, 29 Sep 2015 10:48:43 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934692AbbI2Ksj (ORCPT ); Tue, 29 Sep 2015 06:48:39 -0400 Received: from mx2.suse.de ([195.135.220.15]:42015 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S934666AbbI2KsF (ORCPT ); Tue, 29 Sep 2015 06:48:05 -0400 X-Virus-Scanned: by amavisd-new at test-mx.suse.de Received: from relay2.suse.de (charybdis-ext.suse.de [195.135.220.254]) by mx2.suse.de (Postfix) with ESMTP id EDC5175039; Tue, 29 Sep 2015 10:47:48 +0000 (UTC) From: Hannes Reinecke To: James Bottomley Cc: linux-scsi@vger.kernel.org, Christoph Hellwig , Bart van Assche , Ewan Milne , "Martin K. Petersen" , Hannes Reinecke Subject: [PATCH 27/36] scsi_dh_alua: Use workqueue for RTPG Date: Tue, 29 Sep 2015 12:47:29 +0200 Message-Id: <1443523658-87622-28-git-send-email-hare@suse.de> X-Mailer: git-send-email 1.8.5.6 In-Reply-To: <1443523658-87622-1-git-send-email-hare@suse.de> References: <1443523658-87622-1-git-send-email-hare@suse.de> Sender: linux-scsi-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-scsi@vger.kernel.org X-Spam-Status: No, score=-6.9 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_HI, T_RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=unavailable version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP The current ALUA device_handler has two drawbacks: - We're sending a 'SET TARGET PORT GROUP' command to every LUN, disregarding the fact that several LUNs might be in a port group and will be automatically switched whenever _any_ LUN within that port group receives the command. - Whenever a LUN is in 'transitioning' mode we cannot block I/O to that LUN, instead the controller has to abort the command. This leads to increased traffic across the wire and heavy load on the controller during switchover. With this patch the RTPG handling is moved to a per-portgroup workqueue. This reduces the number of 'REPORT TARGET PORT GROUP' and 'SET TARGET PORT GROUPS' sent to the controller as we're sending them now per port group, and not per device as previously. It also allows us to block I/O to any LUN / port group found to be in 'transitioning' ALUA mode, as the workqueue item will be requeued until the controller moves out of transitioning. Signed-off-by: Hannes Reinecke --- drivers/scsi/device_handler/scsi_dh_alua.c | 327 +++++++++++++++++++++++------ 1 file changed, 267 insertions(+), 60 deletions(-) diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index 4113b76..1b7153f 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -59,13 +59,23 @@ #define ALUA_RTPG_SIZE 128 #define ALUA_FAILOVER_TIMEOUT 60 #define ALUA_FAILOVER_RETRIES 5 +#define ALUA_RTPG_DELAY_MSECS 5 /* device handler flags */ -#define ALUA_OPTIMIZE_STPG 1 -#define ALUA_RTPG_EXT_HDR_UNSUPP 2 +#define ALUA_OPTIMIZE_STPG 0x01 +#define ALUA_RTPG_EXT_HDR_UNSUPP 0x02 +/* State machine flags */ +#define ALUA_PG_RUN_RTPG 0x10 +#define ALUA_PG_RUN_STPG 0x20 +#define ALUA_PG_RUNNING 0x40 + +static uint optimize_stpg; +module_param(optimize_stpg, uint, S_IRUGO|S_IWUSR); +MODULE_PARM_DESC(optimize_stpg, "Allow use of a non-optimized path, rather than sending a STPG, when implicit TPGS is supported (0=No,1=Yes). Default is 0."); static LIST_HEAD(port_group_list); static DEFINE_SPINLOCK(port_group_lock); +static struct workqueue_struct *kaluad_wq; struct alua_port_group { struct kref kref; @@ -78,12 +88,25 @@ struct alua_port_group { int pref; unsigned flags; /* used for optimizing STPG */ unsigned char transition_tmo; + unsigned long expiry; + unsigned long interval; + struct delayed_work rtpg_work; + spinlock_t lock; + struct list_head rtpg_list; + struct scsi_device *rtpg_sdev; }; struct alua_dh_data { struct alua_port_group *pg; int rel_port; + spinlock_t pg_lock; struct scsi_device *sdev; + int init_error; + struct mutex init_mutex; +}; + +struct alua_queue_data { + struct list_head entry; activate_complete callback_fn; void *callback_data; }; @@ -91,8 +114,10 @@ struct alua_dh_data { #define ALUA_POLICY_SWITCH_CURRENT 0 #define ALUA_POLICY_SWITCH_ALL 1 -static int alua_rtpg(struct scsi_device *, struct alua_port_group *); -static char print_alua_state(int); +static void alua_rtpg_work(struct work_struct *work); +static void alua_rtpg_queue(struct alua_port_group *pg, + struct scsi_device *sdev, + struct alua_queue_data *qdata); static void release_port_group(struct kref *kref) { @@ -103,6 +128,7 @@ static void release_port_group(struct kref *kref) spin_lock(&port_group_lock); list_del(&pg->node); spin_unlock(&port_group_lock); + WARN_ON(pg->rtpg_sdev); kfree(pg); } @@ -168,7 +194,7 @@ static int submit_stpg(struct scsi_device *sdev, int group_id, struct alua_port_group *alua_lookup_pg(char *id_str, size_t id_size, int group_id) { - struct alua_port_group *pg = NULL; + struct alua_port_group *pg; list_for_each_entry(pg, &port_group_list, node) { if (pg->group_id != group_id) @@ -218,18 +244,26 @@ struct alua_port_group *alua_get_pg(struct scsi_device *sdev, pg->group_id = group_id; pg->tpgs = tpgs; pg->state = TPGS_STATE_OPTIMIZED; + if (optimize_stpg) + pg->flags |= ALUA_OPTIMIZE_STPG; kref_init(&pg->kref); + INIT_DELAYED_WORK(&pg->rtpg_work, alua_rtpg_work); + INIT_LIST_HEAD(&pg->rtpg_list); + INIT_LIST_HEAD(&pg->node); + spin_lock_init(&pg->lock); /* Re-check list again to catch concurrent updates */ spin_lock(&port_group_lock); tmp_pg = alua_lookup_pg(id_str, id_size, group_id); if (tmp_pg) { spin_unlock(&port_group_lock); - kfree(pg); - return tmp_pg; + kref_put(&pg->kref, release_port_group); + pg = tmp_pg; + tmp_pg = NULL; + } else { + list_add(&pg->node, &port_group_list); + spin_unlock(&port_group_lock); } - list_add(&pg->node, &port_group_list); - spin_unlock(&port_group_lock); return pg; } @@ -293,7 +327,7 @@ static int alua_check_tpgs(struct scsi_device *sdev) * Extract the relative target port and the target port group * descriptor from the list of identificators. * - * Returns 0 or SCSI_DH_ error code on failure. + * Returns the target port group id or -1 on failure */ static int alua_check_vpd(struct scsi_device *sdev, struct alua_dh_data *h, int tpgs) @@ -301,6 +335,8 @@ static int alua_check_vpd(struct scsi_device *sdev, struct alua_dh_data *h, int rel_port = -1, group_id; char id_str[256]; int id_size; + struct alua_port_group *pg = NULL, *old_pg = NULL; + bool pg_found = false; group_id = scsi_vpd_tpg_id(sdev, &rel_port); if (group_id < 0) { @@ -332,11 +368,37 @@ static int alua_check_vpd(struct scsi_device *sdev, struct alua_dh_data *h, "rel port %02x\n", ALUA_DH_NAME, id_str, group_id, h->rel_port); - h->pg = alua_get_pg(sdev, group_id, tpgs, id_str, id_size); - if (!h->pg) + pg = alua_get_pg(sdev, group_id, tpgs, id_str, id_size); + if (!pg) return SCSI_DH_NOMEM; - return alua_rtpg(sdev, h->pg); + /* Check for existing port_group references */ + spin_lock(&h->pg_lock); + if (h->pg) { + old_pg = pg; + /* port_group has changed. Update to new port group */ + if (h->pg != pg) { + old_pg = h->pg; + rcu_assign_pointer(h->pg, pg); + h->pg->expiry = 0; + pg_found = true; + } + } else { + rcu_assign_pointer(h->pg, pg); + pg_found = true; + } + alua_rtpg_queue(h->pg, sdev, NULL); + spin_unlock(&h->pg_lock); + + if (pg_found) + synchronize_rcu(); + if (old_pg) { + if (old_pg->rtpg_sdev) + flush_delayed_work(&old_pg->rtpg_work); + kref_put(&old_pg->kref, release_port_group); + } + + return SCSI_DH_OK; } static char print_alua_state(int state) @@ -430,14 +492,15 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) int len, k, off, valid_states = 0, bufflen = ALUA_RTPG_SIZE; unsigned char *ucp, *buff; unsigned err, retval; - unsigned long expiry, interval = 0; unsigned int tpg_desc_tbl_off; unsigned char orig_transition_tmo; - if (!pg->transition_tmo) - expiry = round_jiffies_up(jiffies + ALUA_FAILOVER_TIMEOUT * HZ); - else - expiry = round_jiffies_up(jiffies + pg->transition_tmo * HZ); + if (!pg->expiry) { + if (!pg->transition_tmo) + pg->expiry = round_jiffies_up(jiffies + ALUA_FAILOVER_TIMEOUT * HZ); + else + pg->expiry = round_jiffies_up(jiffies + pg->transition_tmo * HZ); + } buff = kzalloc(bufflen, GFP_KERNEL); if (!buff) @@ -480,16 +543,18 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) err = SCSI_DH_RETRY; else if (sense_hdr.sense_key == UNIT_ATTENTION) err = SCSI_DH_RETRY; - if (err == SCSI_DH_RETRY && time_before(jiffies, expiry)) { + if (err == SCSI_DH_RETRY && + pg->expiry != 0 && time_before(jiffies, pg->expiry)) { sdev_printk(KERN_ERR, sdev, "%s: rtpg retry\n", ALUA_DH_NAME); scsi_print_sense_hdr(sdev, ALUA_DH_NAME, &sense_hdr); - goto retry; + return err; } sdev_printk(KERN_ERR, sdev, "%s: rtpg failed\n", ALUA_DH_NAME); scsi_print_sense_hdr(sdev, ALUA_DH_NAME, &sense_hdr); kfree(buff); + pg->expiry = 0; return SCSI_DH_IO; } @@ -504,6 +569,7 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) sdev_printk(KERN_WARNING, sdev, "%s: kmalloc buffer failed\n",__func__); /* Temporary failure, bypass */ + pg->expiry = 0; return SCSI_DH_DEV_TEMP_BUSY; } goto retry; @@ -519,7 +585,7 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) sdev_printk(KERN_INFO, sdev, "%s: transition timeout set to %d seconds\n", ALUA_DH_NAME, pg->transition_tmo); - expiry = jiffies + pg->transition_tmo * HZ; + pg->expiry = jiffies + pg->transition_tmo * HZ; } if ((buff[4] & RTPG_FMT_MASK) == RTPG_FMT_EXT_HDR) @@ -553,23 +619,26 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg) switch (pg->state) { case TPGS_STATE_TRANSITIONING: - if (time_before(jiffies, expiry)) { + if (time_before(jiffies, pg->expiry)) { /* State transition, retry */ - interval += 2000; - msleep(interval); - goto retry; + pg->interval = 2; + err = SCSI_DH_RETRY; + } else { + /* Transitioning time exceeded, set port to standby */ + err = SCSI_DH_IO; + pg->state = TPGS_STATE_STANDBY; + pg->expiry = 0; } - /* Transitioning time exceeded, set port to standby */ - err = SCSI_DH_RETRY; - pg->state = TPGS_STATE_STANDBY; break; case TPGS_STATE_OFFLINE: /* Path unusable */ err = SCSI_DH_DEV_OFFLINED; + pg->expiry = 0; break; default: /* Useable path if active */ err = SCSI_DH_OK; + pg->expiry = 0; break; } kfree(buff); @@ -637,6 +706,106 @@ static unsigned alua_stpg(struct scsi_device *sdev, struct alua_port_group *pg) return SCSI_DH_RETRY; } +static void alua_rtpg_work(struct work_struct *work) +{ + struct alua_port_group *pg = + container_of(work, struct alua_port_group, rtpg_work.work); + struct scsi_device *sdev; + LIST_HEAD(qdata_list); + int err = SCSI_DH_OK; + struct alua_queue_data *qdata, *tmp; + unsigned long flags; + + spin_lock_irqsave(&pg->lock, flags); + sdev = pg->rtpg_sdev; + if (!sdev) { + WARN_ON(pg->flags & ALUA_PG_RUN_RTPG || + pg->flags & ALUA_PG_RUN_STPG); + spin_unlock_irqrestore(&pg->lock, flags); + return; + } + pg->flags |= ALUA_PG_RUNNING; + if (pg->flags & ALUA_PG_RUN_RTPG) { + spin_unlock_irqrestore(&pg->lock, flags); + err = alua_rtpg(sdev, pg); + spin_lock_irqsave(&pg->lock, flags); + if (err == SCSI_DH_RETRY) { + pg->flags &= ~ALUA_PG_RUNNING; + spin_unlock_irqrestore(&pg->lock, flags); + queue_delayed_work(kaluad_wq, &pg->rtpg_work, + pg->interval * HZ); + return; + } + pg->flags &= ~ALUA_PG_RUN_RTPG; + if (err != SCSI_DH_OK) + pg->flags &= ~ALUA_PG_RUN_STPG; + } + if (pg->flags & ALUA_PG_RUN_STPG) { + spin_unlock_irqrestore(&pg->lock, flags); + err = alua_stpg(sdev, pg); + spin_lock_irqsave(&pg->lock, flags); + pg->flags &= ~ALUA_PG_RUN_STPG; + if (err == SCSI_DH_RETRY) { + pg->flags |= ALUA_PG_RUN_RTPG; + pg->interval = 0; + pg->flags &= ~ALUA_PG_RUNNING; + spin_unlock_irqrestore(&pg->lock, flags); + queue_delayed_work(kaluad_wq, &pg->rtpg_work, + pg->interval * HZ); + return; + } + } + + list_splice_init(&pg->rtpg_list, &qdata_list); + pg->rtpg_sdev = NULL; + spin_unlock_irqrestore(&pg->lock, flags); + + list_for_each_entry_safe(qdata, tmp, &qdata_list, entry) { + list_del(&qdata->entry); + if (qdata->callback_fn) + qdata->callback_fn(qdata->callback_data, err); + kfree(qdata); + } + spin_lock_irqsave(&pg->lock, flags); + pg->flags &= ~ALUA_PG_RUNNING; + spin_unlock_irqrestore(&pg->lock, flags); + scsi_device_put(sdev); + kref_put(&pg->kref, release_port_group); +} + +static void alua_rtpg_queue(struct alua_port_group *pg, + struct scsi_device *sdev, + struct alua_queue_data *qdata) +{ + int start_queue = 0; + unsigned long flags; + + if (!pg) + return; + + spin_lock_irqsave(&pg->lock, flags); + if (qdata) { + list_add_tail(&qdata->entry, &pg->rtpg_list); + pg->flags |= ALUA_PG_RUN_STPG; + } + if (pg->rtpg_sdev == NULL) { + pg->interval = 0; + pg->flags |= ALUA_PG_RUN_RTPG; + kref_get(&pg->kref); + pg->rtpg_sdev = sdev; + scsi_device_get(sdev); + start_queue = 1; + } + spin_unlock_irqrestore(&pg->lock, flags); + + if (start_queue && + !queue_delayed_work(kaluad_wq, &pg->rtpg_work, + msecs_to_jiffies(ALUA_RTPG_DELAY_MSECS))) { + scsi_device_put(sdev); + kref_put(&pg->kref, release_port_group); + } +} + /* * alua_initialize - Initialize ALUA state * @sdev: the device to be initialized @@ -648,10 +817,12 @@ static int alua_initialize(struct scsi_device *sdev, struct alua_dh_data *h) { int err = SCSI_DH_DEV_UNSUPP, tpgs; + mutex_lock(&h->init_mutex); tpgs = alua_check_tpgs(sdev); if (tpgs != TPGS_MODE_NONE) err = alua_check_vpd(sdev, h, tpgs); - + h->init_error = err; + mutex_unlock(&h->init_mutex); return err; } @@ -671,6 +842,7 @@ static int alua_set_params(struct scsi_device *sdev, const char *params) unsigned int optimize = 0, argc; const char *p = params; int result = SCSI_DH_OK; + unsigned long flags; if ((sscanf(params, "%u", &argc) != 1) || (argc != 1)) return -EINVAL; @@ -680,22 +852,23 @@ static int alua_set_params(struct scsi_device *sdev, const char *params) if ((sscanf(p, "%u", &optimize) != 1) || (optimize > 1)) return -EINVAL; - pg = h->pg; - if (!pg) + rcu_read_lock(); + pg = rcu_dereference(h->pg); + if (!pg) { + rcu_read_unlock(); return -ENXIO; - + } + spin_lock_irqsave(&pg->lock, flags); if (optimize) pg->flags |= ALUA_OPTIMIZE_STPG; else pg->flags |= ~ALUA_OPTIMIZE_STPG; + spin_unlock_irqrestore(&pg->lock, flags); + rcu_read_unlock(); return result; } -static uint optimize_stpg; -module_param(optimize_stpg, uint, S_IRUGO|S_IWUSR); -MODULE_PARM_DESC(optimize_stpg, "Allow use of a non-optimized path, rather than sending a STPG, when implicit TPGS is supported (0=No,1=Yes). Default is 0."); - /* * alua_activate - activate a path * @sdev: device on the path to be activated @@ -711,24 +884,34 @@ static int alua_activate(struct scsi_device *sdev, { struct alua_dh_data *h = sdev->handler_data; int err = SCSI_DH_OK; + struct alua_queue_data *qdata; + struct alua_port_group *pg; - if (!h->pg) + qdata = kzalloc(sizeof(*qdata), GFP_KERNEL); + if (!qdata) { + err = SCSI_DH_RES_TEMP_UNAVAIL; goto out; + } + qdata->callback_fn = fn; + qdata->callback_data = data; - kref_get(&h->pg->kref); - - if (optimize_stpg) - h->pg->flags |= ALUA_OPTIMIZE_STPG; - - err = alua_rtpg(sdev, h->pg); - if (err != SCSI_DH_OK) { - kref_put(&h->pg->kref, release_port_group); + mutex_lock(&h->init_mutex); + rcu_read_lock(); + pg = rcu_dereference(h->pg); + if (!pg) { + rcu_read_unlock(); + kfree(qdata); + err = h->init_error; + mutex_unlock(&h->init_mutex); goto out; } - err = alua_stpg(sdev, h->pg); - if (err == SCSI_DH_RETRY) - err = alua_rtpg(sdev, h->pg); - kref_put(&h->pg->kref, release_port_group); + mutex_unlock(&h->init_mutex); + fn = NULL; + kref_get(&pg->kref); + rcu_read_unlock(); + + alua_rtpg_queue(pg, sdev, qdata); + kref_put(&pg->kref, release_port_group); out: if (fn) fn(data, err); @@ -744,14 +927,19 @@ out: static int alua_prep_fn(struct scsi_device *sdev, struct request *req) { struct alua_dh_data *h = sdev->handler_data; - int state; + struct alua_port_group *pg; + int state = TPGS_STATE_OPTIMIZED; int ret = BLKPREP_OK; - if (!h->pg) - return ret; - kref_get(&h->pg->kref); - state = h->pg->state; - kref_put(&h->pg->kref, release_port_group); + rcu_read_lock(); + pg = rcu_dereference(h->pg); + if (pg) { + state = pg->state; + /* Defer I/O while rtpg_work is active */ + if (pg->rtpg_sdev) + state = TPGS_STATE_TRANSITIONING; + } + rcu_read_unlock(); if (state == TPGS_STATE_TRANSITIONING) ret = BLKPREP_DEFER; else if (state != TPGS_STATE_OPTIMIZED && @@ -776,10 +964,13 @@ static int alua_bus_attach(struct scsi_device *sdev) h = kzalloc(sizeof(*h) , GFP_KERNEL); if (!h) return -ENOMEM; - h->pg = NULL; + spin_lock_init(&h->pg_lock); + rcu_assign_pointer(h->pg, NULL); h->rel_port = -1; + h->init_error = SCSI_DH_OK; h->sdev = sdev; + mutex_init(&h->init_mutex); err = alua_initialize(sdev, h); if (err == SCSI_DH_NOMEM) ret = -ENOMEM; @@ -800,10 +991,18 @@ failed: static void alua_bus_detach(struct scsi_device *sdev) { struct alua_dh_data *h = sdev->handler_data; + struct alua_port_group *pg; - if (h->pg) { - kref_put(&h->pg->kref, release_port_group); - h->pg = NULL; + spin_lock(&h->pg_lock); + pg = h->pg; + rcu_assign_pointer(h->pg, NULL); + h->sdev = NULL; + spin_unlock(&h->pg_lock); + if (pg) { + synchronize_rcu(); + if (pg->rtpg_sdev) + flush_delayed_work(&pg->rtpg_work); + kref_put(&pg->kref, release_port_group); } sdev->handler_data = NULL; kfree(h); @@ -824,16 +1023,24 @@ static int __init alua_init(void) { int r; + kaluad_wq = create_workqueue("kaluad_wq"); + if (!kaluad_wq) { + /* Temporary failure, bypass */ + return SCSI_DH_DEV_TEMP_BUSY; + } r = scsi_register_device_handler(&alua_dh); - if (r != 0) + if (r != 0) { printk(KERN_ERR "%s: Failed to register scsi device handler", ALUA_DH_NAME); + destroy_workqueue(kaluad_wq); + } return r; } static void __exit alua_exit(void) { scsi_unregister_device_handler(&alua_dh); + destroy_workqueue(kaluad_wq); } module_init(alua_init);