From 6c177e28eafe09afcb4a9823d0addd568b202418 Mon Sep 17 00:00:00 2001 From: Yao Qi Date: Thu, 24 Oct 2013 09:28:33 +0800 Subject: [PATCH] Send qXfer:traceframe-info:read when traceframe is selected. When I do 'si', I find many 'qXfer:traceframe-info:read' packets are sent, which is not necessary. It slows down the single step. (gdb) si Sending packet: $qTStatus#49...Packet received: T0;tnotrun:0;tframes:0;tcreated:0;tfree:500000;tsize:500000;circular:0;disconn:0;starttime:0;stoptime:0;username:;notes:: Sending packet: $Z0,80483c7,1#b4...Packet received: OK Sending packet: $Z0,4ce5b6b0,1#6e...Packet received: OK Sending packet: $QPassSignals:e;10;14;17;1a;1b;1c;21;24;25;2c;4c;#5f...Packet received: OK Sending packet: $vCont;s:p1b15.1b15;c#20...Packet received: T0505:44efffbf;04:44efffbf;08:d1830408;thread:p1b15.1b15;core:3; Sending packet: $qXfer:traceframe-info:read::0,fff#0b...Packet received: E01 Sending packet: $mbfffef40,40#c0...Packet received: d183040878efffbf2e840408030000000000a040030000000500000070efffbf07000000010000004984040807000000030000000500000000000000b396e84c Sending packet: $qXfer:traceframe-info:read::0,fff#0b...Packet received: E01 Sending packet: $qXfer:traceframe-info:read::0,fff#0b...Packet received: E01 Sending packet: $qXfer:traceframe-info:read::0,fff#0b...Packet received: E01 Sending packet: $z0,80483c7,1#d4...Packet received: OK Sending packet: $z0,4ce5b6b0,1#8e...Packet received: OK Sending packet: $qXfer:traceframe-info:read::0,fff#0b...Packet received: E01 Sending packet: $qXfer:traceframe-info:read::0,fff#0b...Packet received: E01 Sending packet: $qXfer:traceframe-info:read::0,fff#0b...Packet received: E01 Sending packet: $qXfer:traceframe-info:read::0,fff#0b...Packet received: E01 Sending packet: $qXfer:traceframe-info:read::0,fff#0b...Packet received: E01 Sending packet: $qXfer:traceframe-info:read::0,fff#0b...Packet received: E01 This problem was introduced by this patch (https://sourceware.org/ml/gdb-patches/2013-04/msg00000.html), in which get_traceframe_number is not checked before calling traceframe_available_memory. This patch moves the check to remote_traceframe_info, say, if GDB doesn't have traceframe selected, GDB doesn't need to send qXfer:traceframe-info:read packets. With this patch applied, there is no qXfer:traceframe-info:read sent out and single step is speed up a little bit. Here is the experiment I did: Num of single step Original Patched single-step cpu_time 10000 8.08 7.57 single-step cpu_time 20000 16.23 14.23 single-step cpu_time 30000 24.19 21.59 single-step cpu_time 40000 32.49 28.0 single-step wall_time 10000 14.1974210739 13.2641420364 single-step wall_time 20000 28.5278921127 25.0541369915 single-step wall_time 30000 42.5864038467 38.0038759708 single-step wall_time 40000 57.2107698917 49.2350611687 single-step vmsize 10000 16128 16388 single-step vmsize 20000 16128 16388 single-step vmsize 30000 16260 16520 single-step vmsize 40000 16444 16704 The patch is tested on x86_64-linux. gdb: 2013-10-24 Yao Qi * remote.c (remote_traceframe_info): Return early if traceframe is not selected. --- gdb/ChangeLog | 5 +++++ gdb/remote.c | 5 +++++ 2 files changed, 10 insertions(+) diff --git a/gdb/ChangeLog b/gdb/ChangeLog index d7c044b9602..ec491c55efa 100644 --- a/gdb/ChangeLog +++ b/gdb/ChangeLog @@ -1,3 +1,8 @@ +2013-10-25 Yao Qi + + * remote.c (remote_traceframe_info): Return early if + traceframe is not selected. + 2013-10-25 Yao Qi * tracepoint.c (traceframe_fun): Remove. diff --git a/gdb/remote.c b/gdb/remote.c index 7d8a4deb77a..7bd9b2a3b4c 100644 --- a/gdb/remote.c +++ b/gdb/remote.c @@ -11157,6 +11157,11 @@ remote_traceframe_info (void) { char *text; + /* If current traceframe is not selected, don't bother the remote + stub. */ + if (get_traceframe_number () < 0) + return NULL; + text = target_read_stralloc (¤t_target, TARGET_OBJECT_TRACEFRAME_INFO, NULL); if (text != NULL) -- 2.30.2