Two 2023 self-test reports (one co-signed by the Institute of Information Engineering, Chinese Academy of Sciences) describe a dedicated capture appliance, hardware model MESA-NF-3100 (2U, Xeon E5-2640V4, 256GB RAM, dual XL710 10GbE NICs, 8Gbps/device and 20-27Gbps/cluster), whose mirror-capture driver is started via `systemctl start mrzpd` (mrzcpd) alongside the sapp process, feeding a downstream 'nirvana_server' component.
设备名称:MESA-NF-3100 规格:2U CPU:E5-2640V4 10CORES2.4G 内存:256G ... 通过systemctl start mrzpd查看驱动状态确保驱动运行正常,执行命令monit_stream -lHs ... 通过ps -aHx | grep sapp查看程序运行状态
Related findings
An internal TSG operations/troubleshooting manual lays out TSG's full traffic pipeline (NIC -> mrzcpd/marsio capture driver -> sapp DPI engine -> firewall/proxy(KNI->TFE)/active-defense/WAN-NAT policy branches) and shows engineers using maat_redis_tool to pull the live Redis-synced blocking policy tables (TSG_SECURITY_COMPILE, TSG_OBJ_IP_ADDR, TSG_OBJ_APP_ID) and filter them by numeric policy/object ID to debug why a block rule isn't firing.
The same SAPP manual documents mrzcpd's inline (串联) packet-re-injection subcomponent mrtunnat, configured at /opt/mrzcpd/etc/mrtunnat.conf: use_recent_tunnel=1 allows it to inject a packet with no prior session record, and use_link_info_table=1 makes it validate outer MAC, link_id, link_dir, and inner MAC against a live link-state table at /run/mrzcpd/mrmonit.tunnat before re-injecting a censor-forged packet onto the correct physical link.
An internal SAPP platform training/reference manual (marked "Geedge Networks Confidential And Proprietary") gives SAPP's full name as "Stream Analyse Process Platform" and documents its three-tier plugin architecture (platform / protocol-parsing / business layers, each loaded via dlopen), inline and mirror deployment modes at a stated 10-40 Gbps per box, tunnel-protocol support (GRE/MPLS/IPIP/IPv6-over-IPv4/Teredo), and the MESA_kill_tcp() plugin API that forges and sends RST packets to sever a monitored TCP connection, with the manual noting it was "originally used in mirror mode to send RST packets to block a TCP connection" and auto-retries until the connection is confirmed dead.
A June 2021 internal report measures a live in-network TLS-interception pilot: one sapp instance ingests raw ciphertext via mrzcpd while a second ingests plaintext from a "third-party decryption platform" over a Unix domain socket, and one hour of production traffic on a live front-end (10.187.0.2) shows the decryption platform successfully produced plaintext for 4.85% of raw traffic bytes and 7.4% of all port-443 TCP connections, with an average end-to-end decrypt latency of 1741ms (median 460ms, up to 6000ms) between first ciphertext byte and the resulting plaintext HTTP GET.
sapp's internal architecture guide documents three deployment topologies (mirror/passive-tap, inline, dual-arm transparent) and four distinct methods for injecting blocking packets back onto the wire, including a MAC-in-MAC scheme that extracts device/link IDs from mirrored traffic's source MAC field to route an injected packet to the correct physically separate inline device over VXLAN when multiple injection points exist.
The same operations manual's troubleshooting section confirms the blocking system operationally injects forged RST and "spoofed" (欺骗) packets onto mirrored/passive-tap links via network devices — validated by test-injecting a packet via tcpreplay to an external VPS and confirming arrival with tcpdump — runs the sapp process under supervisor scripts with live status/config-version files (TF_maat.status, RESTART.log), and distinguishes a national "GF" system from separate provincial-gateway ("省口") deployments when localizing which egress point a given block should have taken effect at.