From: Liu Yuan <tailai.ly at taobao.com> create_cache_object() need to get a lock to avoid race with object_cache_rw(). This is to address below bug in the log: Apr 28 17:48:12 do_io_request(931) 2, 47c33f00003f80 , 1 Apr 28 17:48:12 object_cache_rw(321) 00003f80, len 4096, off 1396736 Apr 28 17:48:12 client_rx_handler(427) HEAD, fd:280 Apr 28 17:48:12 client_rx_handler(432) DATA_INIT, fd:280 Apr 28 17:48:12 client_rx_handler(470) END, fd:280 Apr 28 17:48:12 queue_request(275) 2 Apr 28 17:48:12 do_io_request(931) 2, b1f0b000003f9b , 1 Apr 28 17:48:12 object_cache_pull(423) [local] 00003f9b Apr 28 17:48:12 object_cache_pull(423) [local] 00003f9b Apr 28 17:48:12 create_cache_object(352) 00003f9b already created Apr 28 17:48:12 object_cache_rw(321) 00003f9b, len 16384, off 2940928 Apr 28 17:48:12 read_cache_object(307) size =0; count= 16384 Apr 28 17:48:12 do_io_request(956) failed: 2, b1f0b000003f9b , 1, 3 Apr 28 17:48:12 io_op_done(151) leaving sheepdog cluster Signed-off-by: Liu Yuan <tailai.ly at taobao.com> --- sheep/object_cache.c | 10 ++++++++++ 1 files changed, 10 insertions(+), 0 deletions(-) diff --git a/sheep/object_cache.c b/sheep/object_cache.c index a1b9e2a..0d00bb1 100644 --- a/sheep/object_cache.c +++ b/sheep/object_cache.c @@ -350,12 +350,22 @@ static int create_cache_object(struct object_cache *oc, uint32_t idx, void *buff ret = SD_RES_EIO; goto out; } + if (flock(fd, LOCK_EX) < 0) { + ret = SD_RES_EIO; + eprintf("%m\n"); + goto out_close; + } ret = xpwrite(fd, buffer, buf_size, 0); if (ret != buf_size) { ret = SD_RES_EIO; eprintf("failed, vid %"PRIx32", idx %"PRIx32"\n", oc->vid, idx); goto out_close; } + if (flock(fd, LOCK_UN) < 0) { + ret = SD_RES_EIO; + eprintf("%m\n"); + goto out_close; + } ret = SD_RES_SUCCESS; dprintf("%08"PRIx32" size %zu\n", idx, buf_size); -- 1.7.8.2 |