UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

IB/iser: Use internal polling budget to avoid possible live-lock 

We need a way to guarentee that we don't stay in soft-IRQ context for
too long.  We might starve other pending CQ tasklets or worse lock
against application trying to issue IO on the running CPU.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Ariel Nahum <arieln@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
This commit is contained in:
Sagi Grimberg 2014-10-01 14:02:08 +03:00 committed by Roland Dreier
parent bf17554035
commit 183cfa434e
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
drivers/infiniband/ulp/iser/iser_verbs.c
View File

@ -42,6 +42,8 @@
#define ISER_MAX_RX_CQ_LEN (ISER_QP_MAX_RECV_DTOS * ISCSI_ISER_MAX_CONN)
#define ISER_MAX_TX_CQ_LEN (ISER_QP_MAX_REQ_DTOS * ISCSI_ISER_MAX_CONN)
static int iser_cq_poll_limit = 512;
static void iser_cq_tasklet_fn(unsigned long data);
static void iser_cq_callback(struct ib_cq *cq, void *cq_context);
static int iser_drain_tx_cq(struct iser_comp *comp);
@ -1248,6 +1250,8 @@ static void iser_cq_tasklet_fn(unsigned long data)
completed_rx++;
if (!(completed_rx & 63))
completed_tx += iser_drain_tx_cq(comp);
if (completed_rx >= iser_cq_poll_limit)
break;
}
/* #warning "it is assumed here that arming CQ only once its empty" *
* " would not cause interrupts to be missed" */