Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754773AbYCIWr0 (ORCPT ); Sun, 9 Mar 2008 18:47:26 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752677AbYCIWrT (ORCPT ); Sun, 9 Mar 2008 18:47:19 -0400 Received: from hancock.steeleye.com ([71.30.118.248]:46497 "EHLO hancock.sc.steeleye.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1751002AbYCIWrS (ORCPT ); Sun, 9 Mar 2008 18:47:18 -0400 Message-ID: <47D468F0.8000506@steeleye.com> Date: Sun, 09 Mar 2008 18:47:12 -0400 From: Paul Clements User-Agent: Swiftdove 2.0.0.9 (X11/20071116) MIME-Version: 1.0 To: Andrew Morton CC: linux-kernel@vger.kernel.org, nbd-general@lists.sourceforge.net, Laurent Vivier Subject: [PATCH 1/1] NBD: allow nbd to be used locally Content-Type: multipart/mixed; boundary="------------010108040009030105060703" Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 7540 Lines: 271 This is a multi-part message in MIME format. --------------010108040009030105060703 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit This patch allows a Network Block Device to be mounted locally (nbd-client to nbd-server over 127.0.0.1). It creates a kthread to avoid the deadlock described in NBD tools documentation. So, if nbd-client hangs waiting for pages, the kblockd thread can continue its work and free pages. I have tested the patch to verify that it avoids the hang that occurs when writing to a localhost nbd connection. I have also tested to verify that no performance degradation results from the additional thread and queue. Patch originally from Laurent Vivier. Thanks, Paul --------------010108040009030105060703 Content-Type: text/x-patch; name="nbd_local.diff" Content-Transfer-Encoding: 7bit Content-Disposition: inline; filename="nbd_local.diff" This patch allows Network Block Device to be mounted locally (nbd-client to nbd-server over 127.0.0.1). It creates a kthread to avoid the deadlock described in NBD tools documentation. So, if nbd-client hangs waiting for pages, the kblockd thread can continue its work and free pages. I have tested the patch to verify that it avoids the hang that always occurs when writing to a localhost nbd connection. I have also tested to verify that no performance degradation results from the additional thread and queue. Patch originally from Laurent Vivier. Thanks, Paul Signed-Off-By: Paul Clements Signed-off-by: Laurent Vivier --- ./drivers/block/nbd.c.deadline 2008-02-09 08:55:27.000000000 -0500 +++ ./drivers/block/nbd.c 2008-02-09 09:08:11.000000000 -0500 @@ -29,6 +29,7 @@ #include #include #include +#include #include #include @@ -434,6 +435,85 @@ static void nbd_clear_que(struct nbd_dev } +static void nbd_handle_req(struct nbd_device *lo, struct request *req) +{ + if (!blk_fs_request(req)) + goto error_out; + + nbd_cmd(req) = NBD_CMD_READ; + if (rq_data_dir(req) == WRITE) { + nbd_cmd(req) = NBD_CMD_WRITE; + if (lo->flags & NBD_READ_ONLY) { + printk(KERN_ERR "%s: Write on read-only\n", + lo->disk->disk_name); + goto error_out; + } + } + + req->errors = 0; + + mutex_lock(&lo->tx_lock); + if (unlikely(!lo->sock)) { + mutex_unlock(&lo->tx_lock); + printk(KERN_ERR "%s: Attempted send on closed socket\n", + lo->disk->disk_name); + req->errors++; + nbd_end_request(req); + return; + } + + lo->active_req = req; + + if (nbd_send_req(lo, req) != 0) { + printk(KERN_ERR "%s: Request send failed\n", + lo->disk->disk_name); + req->errors++; + nbd_end_request(req); + } else { + spin_lock(&lo->queue_lock); + list_add(&req->queuelist, &lo->queue_head); + spin_unlock(&lo->queue_lock); + } + + lo->active_req = NULL; + mutex_unlock(&lo->tx_lock); + wake_up_all(&lo->active_wq); + + return; + +error_out: + req->errors++; + nbd_end_request(req); +} + +static int nbd_thread(void *data) +{ + struct nbd_device *lo = data; + struct request *req; + + set_user_nice(current, -20); + while (!kthread_should_stop() || !list_empty(&lo->waiting_queue)) { + /* wait for something to do */ + wait_event_interruptible(lo->waiting_wq, + kthread_should_stop() || + !list_empty(&lo->waiting_queue)); + + /* extract request */ + if (list_empty(&lo->waiting_queue)) + continue; + + spin_lock_irq(&lo->queue_lock); + req = list_entry(lo->waiting_queue.next, struct request, + queuelist); + list_del_init(&req->queuelist); + spin_unlock_irq(&lo->queue_lock); + + /* handle request */ + nbd_handle_req(lo, req); + } + return 0; +} + /* * We always wait for result of write, for now. It would be nice to make it optional * in future @@ -449,65 +529,23 @@ static void do_nbd_request(struct reques struct nbd_device *lo; blkdev_dequeue_request(req); + + spin_unlock_irq(q->queue_lock); + dprintk(DBG_BLKDEV, "%s: request %p: dequeued (flags=%x)\n", req->rq_disk->disk_name, req, req->cmd_type); - if (!blk_fs_request(req)) - goto error_out; - lo = req->rq_disk->private_data; BUG_ON(lo->magic != LO_MAGIC); - nbd_cmd(req) = NBD_CMD_READ; - if (rq_data_dir(req) == WRITE) { - nbd_cmd(req) = NBD_CMD_WRITE; - if (lo->flags & NBD_READ_ONLY) { - printk(KERN_ERR "%s: Write on read-only\n", - lo->disk->disk_name); - goto error_out; - } - } - - req->errors = 0; - spin_unlock_irq(q->queue_lock); - - mutex_lock(&lo->tx_lock); - if (unlikely(!lo->sock)) { - mutex_unlock(&lo->tx_lock); - printk(KERN_ERR "%s: Attempted send on closed socket\n", - lo->disk->disk_name); - req->errors++; - nbd_end_request(req); - spin_lock_irq(q->queue_lock); - continue; - } + spin_lock_irq(&lo->queue_lock); + list_add_tail(&req->queuelist, &lo->waiting_queue); + spin_unlock_irq(&lo->queue_lock); - lo->active_req = req; - - if (nbd_send_req(lo, req) != 0) { - printk(KERN_ERR "%s: Request send failed\n", - lo->disk->disk_name); - req->errors++; - nbd_end_request(req); - } else { - spin_lock(&lo->queue_lock); - list_add(&req->queuelist, &lo->queue_head); - spin_unlock(&lo->queue_lock); - } - - lo->active_req = NULL; - mutex_unlock(&lo->tx_lock); - wake_up_all(&lo->active_wq); + wake_up(&lo->waiting_wq); spin_lock_irq(q->queue_lock); - continue; - -error_out: - req->errors++; - spin_unlock(q->queue_lock); - nbd_end_request(req); - spin_lock(q->queue_lock); } } @@ -517,6 +555,7 @@ static int nbd_ioctl(struct inode *inode struct nbd_device *lo = inode->i_bdev->bd_disk->private_data; int error; struct request sreq ; + struct task_struct *thread; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -599,7 +638,12 @@ static int nbd_ioctl(struct inode *inode case NBD_DO_IT: if (!lo->file) return -EINVAL; + thread = kthread_create(nbd_thread, lo, lo->disk->disk_name); + if (IS_ERR(thread)) + return PTR_ERR(thread); + wake_up_process(thread); error = nbd_do_it(lo); + kthread_stop(thread); if (error) return error; sock_shutdown(lo, 1); @@ -688,10 +732,12 @@ static int __init nbd_init(void) nbd_dev[i].file = NULL; nbd_dev[i].magic = LO_MAGIC; nbd_dev[i].flags = 0; + INIT_LIST_HEAD(&nbd_dev[i].waiting_queue); spin_lock_init(&nbd_dev[i].queue_lock); INIT_LIST_HEAD(&nbd_dev[i].queue_head); mutex_init(&nbd_dev[i].tx_lock); init_waitqueue_head(&nbd_dev[i].active_wq); + init_waitqueue_head(&nbd_dev[i].waiting_wq); nbd_dev[i].blksize = 1024; nbd_dev[i].bytesize = 0; disk->major = NBD_MAJOR; --- ./include/linux/nbd.h.max_nbd_killed 2008-02-07 16:46:13.000000000 -0500 +++ ./include/linux/nbd.h 2008-02-09 09:05:18.000000000 -0500 @@ -56,9 +56,11 @@ struct nbd_device { int magic; spinlock_t queue_lock; - struct list_head queue_head;/* Requests are added here... */ + struct list_head queue_head; /* Requests waiting result */ struct request *active_req; wait_queue_head_t active_wq; + struct list_head waiting_queue; /* Requests to be sent */ + wait_queue_head_t waiting_wq; struct mutex tx_lock; struct gendisk *disk; --------------010108040009030105060703-- -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/