any system information like io stats? btw, "worker_connections 768", is this enough ? maybe you can try a bigger limitby zls - Nginx Mailing List - English
Use gdb attaching to the running worker, and provide the backstrace information?by zls - Nginx Mailing List - English
We've found the problem and sent email to "igor@sysoev.ru", but got no answers. It's caused in ngx_http_upstream_process_header. If r->cache->header_start is bigger than u->conf->buffer_size, u->buffer.last will be bigger than u->buffer.end, and the response header will be written to invalid memory for this buffer. But the written memory may be valid for this procesby zls - Nginx Mailing List - English
Still got core files from a clean nginx # ./sbin/nginx -V nginx: nginx version: nginx/1.0.4 nginx: TLS SNI support disabled nginx: configure arguments: --with-pcre=/search/zls/nginx/pcre-8.12 --with-http_stub_status_module --with-http_ssl_module --with-debug --prefix=/usr/local/nginx --with-http_realip_module -rw------- 1 nobody nobody 1.2G Jun 12 15:02 core.25256 -rw------- 1 nobody noby zls - Nginx Mailing List - English
We'll try it. Thanks`by zls - Nginx Mailing List - English
Our nginx -V outputs: nginx: nginx version: nginx/1.0.0 nginx: built by gcc 4.1.2 20080704 (Red Hat 4.1.2-48) nginx: TLS SNI support disabled nginx: configure arguments: --with-pcre=/home/ashtray/build_nginx/pcre-8.12 --add-module=/home/ashtray/build_nginx/ngx_cache_purge-1.2 --with-http_stub_status_module --with-http_ssl_module --with-debug --prefix=/usr/local/nginx --with-http_realip_modulby zls - Nginx Mailing List - English
feature not enabled on redhat by default because of no -pthread on testing? checking for POSIX semaphores /tmp/cc2q2SHU.o: In function `main': /search/zls/nginx/server_traffic/nginx-1.0.2.zls/objs/autotest.c:8: undefined reference to `sem_init' /search/zls/nginx/server_traffic/nginx-1.0.2.zls/objs/autotest.c:9: undefined reference to `sem_destroy' collect2: ld return 1by zls - Nginx Mailing List - English