Re: [PATCH] ceph: abort osd requests on force umount

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



"Yan, Zheng" <zyan@xxxxxxxxxx> writes:

> this avoid force umount getting stuck at ceph_osdc_sync()
>
> Signed-off-by: "Yan, Zheng" <zyan@xxxxxxxxxx>
> ---
>  fs/ceph/super.c                 |  1 +
>  include/linux/ceph/osd_client.h |  5 ++++-
>  net/ceph/osd_client.c           | 43 ++++++++++++++++++++++++++++++++++++-----
>  3 files changed, 43 insertions(+), 6 deletions(-)
>
> diff --git a/fs/ceph/super.c b/fs/ceph/super.c
> index 3c1155803444..40664e13cc0f 100644
> --- a/fs/ceph/super.c
> +++ b/fs/ceph/super.c
> @@ -793,6 +793,7 @@ static void ceph_umount_begin(struct super_block *sb)
>  	if (!fsc)
>  		return;
>  	fsc->mount_state = CEPH_MOUNT_SHUTDOWN;
> +	ceph_osdc_abort_requests(&fsc->client->osdc, -EIO);
>  	ceph_mdsc_force_umount(fsc->mdsc);
>  	return;
>  }
> diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
> index b73dd7ebe585..f61736963236 100644
> --- a/include/linux/ceph/osd_client.h
> +++ b/include/linux/ceph/osd_client.h
> @@ -347,6 +347,7 @@ struct ceph_osd_client {
>  	struct rb_root         linger_map_checks;
>  	atomic_t               num_requests;
>  	atomic_t               num_homeless;
> +	int		       abort_code;
>  	struct delayed_work    timeout_work;
>  	struct delayed_work    osds_timeout_work;
>  #ifdef CONFIG_DEBUG_FS
> @@ -377,7 +378,9 @@ extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc,
>  				   struct ceph_msg *msg);
>  extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc,
>  				 struct ceph_msg *msg);
> -void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb);
> +extern void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32);

nit: Why did you drop the arg name 'eb'?

> +extern void ceph_osdc_abort_requests(struct ceph_osd_client *osdc, +
> int err_code);
>  
>  extern void osd_req_op_init(struct ceph_osd_request *osd_req,
>  			    unsigned int which, u16 opcode, u32 flags);
> diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
> index 08b5fc1f90cc..959af0e165ba 100644
> --- a/net/ceph/osd_client.c
> +++ b/net/ceph/osd_client.c
> @@ -2165,9 +2165,9 @@ static void __submit_request(struct ceph_osd_request *req, bool wrlocked)
>  	struct ceph_osd_client *osdc = req->r_osdc;
>  	struct ceph_osd *osd;
>  	enum calc_target_result ct_res;
> +	bool abort_code = 0;

This should be an int, not a bool.

Cheers,
-- 
Luis

>  	bool need_send = false; bool promoted = false; - bool need_abort
> = false;
>  
>  	WARN_ON(req->r_tid);
>  	dout("%s req %p wrlocked %d\n", __func__, req, wrlocked);
> @@ -2183,7 +2183,9 @@ static void __submit_request(struct ceph_osd_request *req, bool wrlocked)
>  		goto promote;
>  	}
>  
> -	if (osdc->osdmap->epoch < osdc->epoch_barrier) {
> +	if (osdc->abort_code) {
> +		abort_code = osdc->abort_code;
> +	} else if (osdc->osdmap->epoch < osdc->epoch_barrier) {
>  		dout("req %p epoch %u barrier %u\n", req, osdc->osdmap->epoch,
>  		     osdc->epoch_barrier);
>  		req->r_t.paused = true;
> @@ -2208,7 +2210,7 @@ static void __submit_request(struct ceph_osd_request *req, bool wrlocked)
>  		req->r_t.paused = true;
>  		maybe_request_map(osdc);
>  		if (req->r_abort_on_full)
> -			need_abort = true;
> +			abort_code = -ENOSPC;
>  	} else if (!osd_homeless(osd)) {
>  		need_send = true;
>  	} else {
> @@ -2225,8 +2227,8 @@ static void __submit_request(struct ceph_osd_request *req, bool wrlocked)
>  	link_request(osd, req);
>  	if (need_send)
>  		send_request(req);
> -	else if (need_abort)
> -		complete_request(req, -ENOSPC);
> +	else if (abort_code)
> +		complete_request(req, abort_code);
>  	mutex_unlock(&osd->lock);
>  
>  	if (ct_res == CALC_TARGET_POOL_DNE)
> @@ -2366,6 +2368,37 @@ void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb)
>  }
>  EXPORT_SYMBOL(ceph_osdc_update_epoch_barrier);
>  
> +void ceph_osdc_abort_requests(struct ceph_osd_client *osdc, int err_code)
> +{
> +	struct rb_node *n, *m;
> +	struct ceph_osd *osd;
> +	struct ceph_osd_request *req;
> +
> +	dout("%s err_code %d\n", __func__, err_code);
> +
> +	down_write(&osdc->lock);
> +	osdc->abort_code = err_code;
> +
> +	for (n = rb_first(&osdc->osds); n; n = rb_next(n)) {
> +		osd = rb_entry(n, struct ceph_osd, o_node);
> +		m = rb_first(&osd->o_requests);
> +		while (m) {
> +			req = rb_entry(m, struct ceph_osd_request, r_node);
> +			m = rb_next(m);
> +			abort_request(req, err_code);
> +		}
> +	}
> +
> +	m = rb_first(&osdc->homeless_osd.o_requests);
> +	while (m) {
> +		req = rb_entry(m, struct ceph_osd_request, r_node);
> +		m = rb_next(m);
> +		abort_request(req, err_code);
> +	}
> +	up_write(&osdc->lock);
> +}
> +EXPORT_SYMBOL(ceph_osdc_abort_requests);
> +
>  /*
>   * Drop all pending requests that are stalled waiting on a full condition to
>   * clear, and complete them with ENOSPC as the return code. Set the
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html



[Index of Archives]     [CEPH Users]     [Ceph Large]     [Information on CEPH]     [Linux BTRFS]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux