lustre/ptlrpc: re-enqueue ptlrpcd worker
osc_extent_wait can be stuck in scenario like this: 1) thread-1 held an active extent 2) thread-2 called flush cache, and marked this extent as "urgent" and "sync_wait" 3) thread-3 wants to write to the same extent, osc_extent_find will get "conflict" because this extent is "sync_wait", so it starts to wait... 4) cl_writeback_work has been scheduled by thread-4 to write some other extents, it has sent RPCs but not returned yet. 5) thread-1 finished his work, and called osc_extent_release()-> osc_io_unplug_async()->ptlrpcd_queue_work(), but found cl_writeback_work is still running, so it's ignored (-EBUSY) 6) thread-3 is stuck because nobody will wake him up. This patch allows ptlrpcd_work to be rescheduled, so it will not miss request anymore Signed-off-by: Liang Zhen <liang.zhen@intel.com> Reviewed-on: http://review.whamcloud.com/8922 Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-4509 Reviewed-by: Jinshan Xiong <jinshan.xiong@intel.com> Reviewed-by: Bobi Jam <bobijam@gmail.com> Reviewed-by: Oleg Drokin <oleg.drokin@intel.com> Signed-off-by: Oleg Drokin <oleg.drokin@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
parent
15c50ccc3c
commit
82a373aec0
|
@ -48,6 +48,7 @@
|
|||
#include "ptlrpc_internal.h"
|
||||
|
||||
static int ptlrpc_send_new_req(struct ptlrpc_request *req);
|
||||
static int ptlrpcd_check_work(struct ptlrpc_request *req);
|
||||
|
||||
/**
|
||||
* Initialize passed in client structure \a cl.
|
||||
|
@ -1779,6 +1780,10 @@ interpret:
|
|||
|
||||
ptlrpc_req_interpret(env, req, req->rq_status);
|
||||
|
||||
if (ptlrpcd_check_work(req)) {
|
||||
atomic_dec(&set->set_remaining);
|
||||
continue;
|
||||
}
|
||||
ptlrpc_rqphase_move(req, RQ_PHASE_COMPLETE);
|
||||
|
||||
CDEBUG(req->rq_reqmsg != NULL ? D_RPCTRACE : 0,
|
||||
|
@ -2952,22 +2957,50 @@ EXPORT_SYMBOL(ptlrpc_sample_next_xid);
|
|||
* have delay before it really runs by ptlrpcd thread.
|
||||
*/
|
||||
struct ptlrpc_work_async_args {
|
||||
__u64 magic;
|
||||
int (*cb)(const struct lu_env *, void *);
|
||||
void *cbdata;
|
||||
};
|
||||
|
||||
#define PTLRPC_WORK_MAGIC 0x6655436b676f4f44ULL /* magic code */
|
||||
static void ptlrpcd_add_work_req(struct ptlrpc_request *req)
|
||||
{
|
||||
/* re-initialize the req */
|
||||
req->rq_timeout = obd_timeout;
|
||||
req->rq_sent = cfs_time_current_sec();
|
||||
req->rq_deadline = req->rq_sent + req->rq_timeout;
|
||||
req->rq_reply_deadline = req->rq_deadline;
|
||||
req->rq_phase = RQ_PHASE_INTERPRET;
|
||||
req->rq_next_phase = RQ_PHASE_COMPLETE;
|
||||
req->rq_xid = ptlrpc_next_xid();
|
||||
req->rq_import_generation = req->rq_import->imp_generation;
|
||||
|
||||
ptlrpcd_add_req(req, PDL_POLICY_ROUND, -1);
|
||||
}
|
||||
|
||||
static int work_interpreter(const struct lu_env *env,
|
||||
struct ptlrpc_request *req, void *data, int rc)
|
||||
{
|
||||
struct ptlrpc_work_async_args *arg = data;
|
||||
|
||||
LASSERT(arg->magic == PTLRPC_WORK_MAGIC);
|
||||
LASSERT(ptlrpcd_check_work(req));
|
||||
LASSERT(arg->cb != NULL);
|
||||
|
||||
return arg->cb(env, arg->cbdata);
|
||||
rc = arg->cb(env, arg->cbdata);
|
||||
|
||||
list_del_init(&req->rq_set_chain);
|
||||
req->rq_set = NULL;
|
||||
|
||||
if (atomic_dec_return(&req->rq_refcount) > 1) {
|
||||
atomic_set(&req->rq_refcount, 2);
|
||||
ptlrpcd_add_work_req(req);
|
||||
}
|
||||
return rc;
|
||||
}
|
||||
|
||||
static int worker_format;
|
||||
|
||||
static int ptlrpcd_check_work(struct ptlrpc_request *req)
|
||||
{
|
||||
return req->rq_pill.rc_fmt == (void *)&worker_format;
|
||||
}
|
||||
|
||||
/**
|
||||
|
@ -3000,6 +3033,7 @@ void *ptlrpcd_alloc_work(struct obd_import *imp,
|
|||
req->rq_receiving_reply = 0;
|
||||
req->rq_must_unlink = 0;
|
||||
req->rq_no_delay = req->rq_no_resend = 1;
|
||||
req->rq_pill.rc_fmt = (void *)&worker_format;
|
||||
|
||||
spin_lock_init(&req->rq_lock);
|
||||
INIT_LIST_HEAD(&req->rq_list);
|
||||
|
@ -3013,7 +3047,6 @@ void *ptlrpcd_alloc_work(struct obd_import *imp,
|
|||
|
||||
CLASSERT(sizeof(*args) <= sizeof(req->rq_async_args));
|
||||
args = ptlrpc_req_async_args(req);
|
||||
args->magic = PTLRPC_WORK_MAGIC;
|
||||
args->cb = cb;
|
||||
args->cbdata = cbdata;
|
||||
|
||||
|
@ -3043,25 +3076,8 @@ int ptlrpcd_queue_work(void *handler)
|
|||
* req as opaque data. - Jinshan
|
||||
*/
|
||||
LASSERT(atomic_read(&req->rq_refcount) > 0);
|
||||
if (atomic_read(&req->rq_refcount) > 1)
|
||||
return -EBUSY;
|
||||
|
||||
if (atomic_inc_return(&req->rq_refcount) > 2) { /* race */
|
||||
atomic_dec(&req->rq_refcount);
|
||||
return -EBUSY;
|
||||
}
|
||||
|
||||
/* re-initialize the req */
|
||||
req->rq_timeout = obd_timeout;
|
||||
req->rq_sent = cfs_time_current_sec();
|
||||
req->rq_deadline = req->rq_sent + req->rq_timeout;
|
||||
req->rq_reply_deadline = req->rq_deadline;
|
||||
req->rq_phase = RQ_PHASE_INTERPRET;
|
||||
req->rq_next_phase = RQ_PHASE_COMPLETE;
|
||||
req->rq_xid = ptlrpc_next_xid();
|
||||
req->rq_import_generation = req->rq_import->imp_generation;
|
||||
|
||||
ptlrpcd_add_req(req, PDL_POLICY_ROUND, -1);
|
||||
if (atomic_inc_return(&req->rq_refcount) == 2)
|
||||
ptlrpcd_add_work_req(req);
|
||||
return 0;
|
||||
}
|
||||
EXPORT_SYMBOL(ptlrpcd_queue_work);
|
||||
|
|
Loading…
Reference in New Issue