Hi, The tcp driver of tgtd is using dynamic memory allocation via malloc/valloc/free for tasks and buffer data, while the iser driver is using pre-allocated memory trunks organized by linked list. According to here(http://www.drdobbs.com/tools/memory-constraints-on-thread-performance/231300494) and here(http://stackoverflow.com/questions/470683/memory-allocation-deallocation-bottleneck), custom allocator might be better for data intensive application such as tgtd. Would custom allocators be better for tcp driver to achieve better performance in terms of latency and throughput? Any comments? Thanks Yufei -- To unsubscribe from this list: send the line "unsubscribe stgt" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
