# HG changeset patch
# User Maxim Dounin <mdounin@mdounin.ru>
# Date 1633526031 -10800
# Wed Oct 06 16:13:51 2021 +0300
# Node ID ac42b4b31026ec24345331e9bd5c38ac4b6e7502
# Parent bfad703459b4e2416548ac66f548e96c2197d9cc
Changed ngx_chain_update_chains() to test tag first (ticket #2248).

Without this change, aio used with HTTP/2 can result in connection hang,
as observed with "aio threads; aio_write on;" and proxying (ticket #2248).

The problem is that HTTP/2 updates buffers outside of the output filters
(notably, marks them as sent), and then posts a write event to call
output filters. If a filter does not call the next one for some reason
(for example, because of an AIO operation in progress), this might
result in a state when the owner of a buffer already called
ngx_chain_update_chains() and can reuse the buffer, the same buffer
is still sitting in the busy chain of some other filter.

In the particular case a buffer was sitting in output chain's ctx->busy,
and was reused by even pipe. Output chain's ctx->busy was permanently
blocked by it, and this resulted in connection hang.

Fix is to change ngx_chain_update_chains() to skip buffers from other
modules unconditionally, without trying to wait for these buffers to
become empty.

diff --git a/src/core/ngx_buf.c b/src/core/ngx_buf.c
--- a/src/core/ngx_buf.c
+++ b/src/core/ngx_buf.c
@@ -203,16 +203,16 @@ ngx_chain_update_chains(ngx_pool_t *p, n
while (*busy) {
cl = *busy;

- if (ngx_buf_size(cl->buf) != 0) {
- break;
- }
-
if (cl->buf->tag != tag) {
*busy = cl->next;
ngx_free_chain(p, cl);
continue;
}

+ if (ngx_buf_size(cl->buf) != 0) {
+ break;
+ }
+
cl->buf->pos = cl->buf->start;
cl->buf->last = cl->buf->start;


_______________________________________________
nginx-devel mailing list
nginx-devel@nginx.org
http://mailman.nginx.org/mailman/listinfo/nginx-devel