Date: Sat, 9 Apr 2016 12:05:24 +0000 (UTC) From: "Bjoern A. Zeeb" <bz@FreeBSD.org> To: src-committers@freebsd.org, svn-src-all@freebsd.org, svn-src-head@freebsd.org Subject: svn commit: r297742 - head/sys/netinet Message-ID: <201604091205.u39C5Oks041429@repo.freebsd.org>
next in thread | raw e-mail | index | archive | help
Author: bz Date: Sat Apr 9 12:05:23 2016 New Revision: 297742 URL: https://svnweb.freebsd.org/changeset/base/297742 Log: Mfp: r296310,r296343 It looks like as with the safety belt of DELAY() fastened (*) we can completely tear down and free all memory for TCP (after r281599). (*) in theory a few ticks should be good enough to make sure the timers are all really gone. Could we use a better matric here and check a tcbcb count as an optimization? PR: 164763 Reviewed by: gnn, emaste MFC after: 2 weeks Sponsored by: The FreeBSD Foundation Differential Revision: https://reviews.freebsd.org/D5734 Modified: head/sys/netinet/tcp_subr.c Modified: head/sys/netinet/tcp_subr.c ============================================================================== --- head/sys/netinet/tcp_subr.c Sat Apr 9 11:54:09 2016 (r297741) +++ head/sys/netinet/tcp_subr.c Sat Apr 9 12:05:23 2016 (r297742) @@ -660,7 +660,7 @@ tcp_init(void) * These have to be type stable for the benefit of the timers. */ V_tcpcb_zone = uma_zcreate("tcpcb", sizeof(struct tcpcb_mem), - NULL, NULL, NULL, NULL, UMA_ALIGN_PTR, UMA_ZONE_NOFREE); + NULL, NULL, NULL, NULL, UMA_ALIGN_PTR, 0); uma_zone_set_max(V_tcpcb_zone, maxsockets); uma_zone_set_warning(V_tcpcb_zone, "kern.ipc.maxsockets limit reached"); @@ -670,7 +670,7 @@ tcp_init(void) TUNABLE_INT_FETCH("net.inet.tcp.sack.enable", &V_tcp_do_sack); V_sack_hole_zone = uma_zcreate("sackhole", sizeof(struct sackhole), - NULL, NULL, NULL, NULL, UMA_ALIGN_PTR, UMA_ZONE_NOFREE); + NULL, NULL, NULL, NULL, UMA_ALIGN_PTR, 0); /* Skip initialization of globals for non-default instances. */ if (!IS_DEFAULT_VNET(curvnet)) @@ -737,10 +737,21 @@ tcp_destroy(void) { int error; + /* + * All our processes are gone, all our sockets should be cleaned + * up, which means, we should be past the tcp_discardcb() calls. + * Sleep to let all tcpcb timers really disappear and then cleanup. + * Timewait will cleanup its queue and will be ready to go. + * XXX-BZ In theory a few ticks should be good enough to make sure + * the timers are all really gone. We should see if we could use a + * better metric here and, e.g., check a tcbcb count as an optimization? + */ + DELAY(1000000 / hz); tcp_hc_destroy(); syncache_destroy(); tcp_tw_destroy(); in_pcbinfo_destroy(&V_tcbinfo); + /* tcp_discardcb() clears the sack_holes up. */ uma_zdestroy(V_sack_hole_zone); uma_zdestroy(V_tcpcb_zone);
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201604091205.u39C5Oks041429>