From: Fan Yong <fan.yong@xxxxxxxxx> The commit d099fdd6 replaced the "rq_xid" with "rq_mbits" as the matchbits of bulk data transferring. To be interoperable with old servers, it introduced the new connection flag: OBD_CONNECT_BULK_MBITS. If the server does not support such feature, then the "rq_xid" would be set the same value as "rq_mbits". Unfortunately, it forgot to handle multiple bulk operations, for example 4MB IO. If the new client wants to make 4MB IO with old server, it may send a small "rq_xid" to the old server, as to the old server will regard it as an 1MB IO or 2MB IO. So the data transfer will not complete because of only part of data transferred. Then the client will timeout failure and retry again and again. Test-Parameters: alwaysuploadlogs testlist=sanity envdefinitions=ONLY=224c ossjob=lustre-b2_7_fe mdsjob=lustre-b2_7_fe ossbuildno=95 mdsbuildno=95 mdsdistro=el6.7 ossdistro=el6.7 Signed-off-by: Fan Yong <fan.yong@xxxxxxxxx> Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-6808 Reviewed-on: http://review.whamcloud.com/22373 Tested-by: Jenkins Reviewed-by: Jinshan Xiong <jinshan.xiong@xxxxxxxxx> Tested-by: Maloo <hpdd-maloo@xxxxxxxxx> Reviewed-by: Bobi Jam <bobijam@xxxxxxxxxxx> Reviewed-by: Liang Zhen <liang.zhen@xxxxxxxxx> Reviewed-by: Oleg Drokin <oleg.drokin@xxxxxxxxx> Signed-off-by: Tyson Whitehead <twhitehead@xxxxxxxxx> --- drivers/staging/lustre/lustre/ptlrpc/client.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/staging/lustre/lustre/ptlrpc/client.c b/drivers/staging/lustre/lustre/ptlrpc/client.c index 6466974a43e7..0f9db5526ba5 100644 --- a/drivers/staging/lustre/lustre/ptlrpc/client.c +++ b/drivers/staging/lustre/lustre/ptlrpc/client.c @@ -3123,8 +3123,7 @@ void ptlrpc_set_bulk_mbits(struct ptlrpc_request *req) } else { /* needs to generate a new matchbits for resend */ u64 old_mbits = req->rq_mbits; - if ((bd->bd_import->imp_connect_data.ocd_connect_flags & - OBD_CONNECT_BULK_MBITS)) { + if (OCD_HAS_FLAG(&bd->bd_import->imp_connect_data, BULK_MBITS)){ req->rq_mbits = ptlrpc_next_xid(); } else { /* old version transfers rq_xid to peer as matchbits */ @@ -3145,6 +3144,11 @@ void ptlrpc_set_bulk_mbits(struct ptlrpc_request *req) * see LU-1431 */ req->rq_mbits += DIV_ROUND_UP(bd->bd_iov_count, LNET_MAX_IOV) - 1; + + /* Set rq_xid as rq_mbits to indicate the final bulk for the old + * server which does not support OBD_CONNECT_BULK_MBITS. LU-6808 */ + if (!OCD_HAS_FLAG(&bd->bd_import->imp_connect_data, BULK_MBITS)) + req->rq_xid = req->rq_mbits; } /** -- 2.14.0 _______________________________________________ devel mailing list devel@xxxxxxxxxxxxxxxxxxxxxx http://driverdev.linuxdriverproject.org/mailman/listinfo/driverdev-devel
