From 63e03724b51e7315a66a3f1fee6cb8b4a16dc8cc Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Mon, 4 Jul 2011 13:40:17 -0400 Subject: perf script: Add drop monitor script A while back I created the dropmonitor protocol, which allowed users to get reports of dropped frames communicated to them via a netlink socket. While useful, several people have now asked that I integrate the ability to do drop monitoring with perf, so they don't have to run additional tools. This patch adds a drop monitor script to the perf suite, and provides the same output that the netlink socket does. Cc: Ingo Molnar Cc: Paul Mackerras Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1309801217-22450-1-git-send-email-nhorman@tuxdriver.com Signed-off-by: Neil Horman Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/net_dropmonitor.py | 72 ++++++++++++++++++++++++++++ 1 file changed, 72 insertions(+) create mode 100755 tools/perf/scripts/python/net_dropmonitor.py (limited to 'tools/perf/scripts/python/net_dropmonitor.py') diff --git a/tools/perf/scripts/python/net_dropmonitor.py b/tools/perf/scripts/python/net_dropmonitor.py new file mode 100755 index 000000000000..a4ffc9500023 --- /dev/null +++ b/tools/perf/scripts/python/net_dropmonitor.py @@ -0,0 +1,72 @@ +# Monitor the system for dropped packets and proudce a report of drop locations and counts + +import os +import sys + +sys.path.append(os.environ['PERF_EXEC_PATH'] + \ + '/scripts/python/Perf-Trace-Util/lib/Perf/Trace') + +from perf_trace_context import * +from Core import * +from Util import * + +drop_log = {} +kallsyms = [] + +def get_kallsyms_table(): + global kallsyms + try: + f = open("/proc/kallsyms", "r") + linecount = 0 + for line in f: + linecount = linecount+1 + f.seek(0) + except: + return + + + j = 0 + for line in f: + loc = int(line.split()[0], 16) + name = line.split()[2] + j = j +1 + if ((j % 100) == 0): + print "\r" + str(j) + "/" + str(linecount), + kallsyms.append({ 'loc': loc, 'name' : name}) + + print "\r" + str(j) + "/" + str(linecount) + kallsyms.sort() + return + +def get_sym(sloc): + loc = int(sloc) + for i in kallsyms: + if (i['loc'] >= loc): + return (i['name'], i['loc']-loc) + return (None, 0) + +def print_drop_table(): + print "%25s %25s %25s" % ("LOCATION", "OFFSET", "COUNT") + for i in drop_log.keys(): + (sym, off) = get_sym(i) + if sym == None: + sym = i + print "%25s %25s %25s" % (sym, off, drop_log[i]) + + +def trace_begin(): + print "Starting trace (Ctrl-C to dump results)" + +def trace_end(): + print "Gathering kallsyms data" + get_kallsyms_table() + print_drop_table() + +# called from perf, when it finds a correspoinding event +def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, + skbaddr, protocol, location): + slocation = str(location) + try: + drop_log[slocation] = drop_log[slocation] + 1 + except: + drop_log[slocation] = 1 -- cgit v1.2.3 From 140c3c6a2bcd2c31e2f7f5a8d59689724776c8e5 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 20 May 2013 14:44:43 +0000 Subject: perf: net_dropmonitor: Fix trace parameter order This works much better if we don't treat protocol numbers as addresses. Cc: stable@vger.kernel.org Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- tools/perf/scripts/python/net_dropmonitor.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/scripts/python/net_dropmonitor.py') diff --git a/tools/perf/scripts/python/net_dropmonitor.py b/tools/perf/scripts/python/net_dropmonitor.py index a4ffc9500023..adbfbf030576 100755 --- a/tools/perf/scripts/python/net_dropmonitor.py +++ b/tools/perf/scripts/python/net_dropmonitor.py @@ -64,7 +64,7 @@ def trace_end(): # called from perf, when it finds a correspoinding event def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, - skbaddr, protocol, location): + skbaddr, location, protocol): slocation = str(location) try: drop_log[slocation] = drop_log[slocation] + 1 -- cgit v1.2.3 From 5a1e99dd2028e00998d42029be86835d8ef4a46e Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 20 May 2013 14:45:26 +0000 Subject: perf: net_dropmonitor: Fix symbol-relative addresses The comparison between traced and symbol addresses is backwards: if the traced address doesn't exactly match a symbol (which we don't expect it to), we'll show the next symbol and the offset to it, whereas we should show the previous symbol and the offset from it. Cc: stable@vger.kernel.org Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- tools/perf/scripts/python/net_dropmonitor.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'tools/perf/scripts/python/net_dropmonitor.py') diff --git a/tools/perf/scripts/python/net_dropmonitor.py b/tools/perf/scripts/python/net_dropmonitor.py index adbfbf030576..4c1160560917 100755 --- a/tools/perf/scripts/python/net_dropmonitor.py +++ b/tools/perf/scripts/python/net_dropmonitor.py @@ -40,9 +40,9 @@ def get_kallsyms_table(): def get_sym(sloc): loc = int(sloc) - for i in kallsyms: - if (i['loc'] >= loc): - return (i['name'], i['loc']-loc) + for i in kallsyms[::-1]: + if loc >= i['loc']: + return (i['name'], loc - i['loc']) return (None, 0) def print_drop_table(): -- cgit v1.2.3 From 326017c757e387007c6629797d7ae22fd33c1317 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 20 May 2013 14:45:34 +0000 Subject: perf: net_dropmonitor: Do not assume ordering of dictionaries The sort order of dictionaries in Python is undocumented. Use tuples instead, which are documented to be lexically ordered. Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- tools/perf/scripts/python/net_dropmonitor.py | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'tools/perf/scripts/python/net_dropmonitor.py') diff --git a/tools/perf/scripts/python/net_dropmonitor.py b/tools/perf/scripts/python/net_dropmonitor.py index 4c1160560917..6acdc82ef47f 100755 --- a/tools/perf/scripts/python/net_dropmonitor.py +++ b/tools/perf/scripts/python/net_dropmonitor.py @@ -32,7 +32,7 @@ def get_kallsyms_table(): j = j +1 if ((j % 100) == 0): print "\r" + str(j) + "/" + str(linecount), - kallsyms.append({ 'loc': loc, 'name' : name}) + kallsyms.append((loc, name)) print "\r" + str(j) + "/" + str(linecount) kallsyms.sort() @@ -40,9 +40,9 @@ def get_kallsyms_table(): def get_sym(sloc): loc = int(sloc) - for i in kallsyms[::-1]: - if loc >= i['loc']: - return (i['name'], loc - i['loc']) + for symloc, name in kallsyms[::-1]: + if loc >= symloc: + return (name, loc - symloc) return (None, 0) def print_drop_table(): -- cgit v1.2.3 From 0ce58bae851dc3728af1c0b83905cd6b4565417a Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 20 May 2013 14:45:42 +0000 Subject: perf: net_dropmonitor: Use bisection in symbol lookup Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- tools/perf/scripts/python/net_dropmonitor.py | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) (limited to 'tools/perf/scripts/python/net_dropmonitor.py') diff --git a/tools/perf/scripts/python/net_dropmonitor.py b/tools/perf/scripts/python/net_dropmonitor.py index 6acdc82ef47f..32fcee05c0f6 100755 --- a/tools/perf/scripts/python/net_dropmonitor.py +++ b/tools/perf/scripts/python/net_dropmonitor.py @@ -40,10 +40,24 @@ def get_kallsyms_table(): def get_sym(sloc): loc = int(sloc) - for symloc, name in kallsyms[::-1]: - if loc >= symloc: - return (name, loc - symloc) - return (None, 0) + + # Invariant: kallsyms[i][0] <= loc for all 0 <= i <= start + # kallsyms[i][0] > loc for all end <= i < len(kallsyms) + start, end = -1, len(kallsyms) + while end != start + 1: + pivot = (start + end) // 2 + if loc < kallsyms[pivot][0]: + end = pivot + else: + start = pivot + + # Now (start == -1 or kallsyms[start][0] <= loc) + # and (start == len(kallsyms) - 1 or loc < kallsyms[start + 1][0]) + if start >= 0: + symloc, name = kallsyms[start] + return (name, loc - symloc) + else: + return (None, 0) def print_drop_table(): print "%25s %25s %25s" % ("LOCATION", "OFFSET", "COUNT") -- cgit v1.2.3 From 6b75c7357c947dd9fd8482b3395664a9b7385ed5 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 20 May 2013 14:45:57 +0000 Subject: perf: net_dropmonitor: Remove progress indicator We can read /proc/kallsyms in a fraction of a second, so why waste a further fraction of a second showing progress? Signed-off-by: Ben Hutchings Signed-off-by: David S. Miller --- tools/perf/scripts/python/net_dropmonitor.py | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) (limited to 'tools/perf/scripts/python/net_dropmonitor.py') diff --git a/tools/perf/scripts/python/net_dropmonitor.py b/tools/perf/scripts/python/net_dropmonitor.py index 32fcee05c0f6..b5740599aabd 100755 --- a/tools/perf/scripts/python/net_dropmonitor.py +++ b/tools/perf/scripts/python/net_dropmonitor.py @@ -15,28 +15,17 @@ kallsyms = [] def get_kallsyms_table(): global kallsyms + try: f = open("/proc/kallsyms", "r") - linecount = 0 - for line in f: - linecount = linecount+1 - f.seek(0) except: return - - j = 0 for line in f: loc = int(line.split()[0], 16) name = line.split()[2] - j = j +1 - if ((j % 100) == 0): - print "\r" + str(j) + "/" + str(linecount), kallsyms.append((loc, name)) - - print "\r" + str(j) + "/" + str(linecount) kallsyms.sort() - return def get_sym(sloc): loc = int(sloc) -- cgit v1.2.3 From 0f5f5bcd112292f14b75750dde7461463bb1c7bb Mon Sep 17 00:00:00 2001 From: Joseph Schuchart Date: Thu, 10 Jul 2014 13:50:51 +0200 Subject: perf script: Add callchain to generic and tracepoint events This provides valuable information for tracing performance problems. Since this change alters the interface for the python scripts, also adjust the script generation and the provided scripts. Signed-off-by: Joseph Schuchart Acked-by: Thomas Ilsche Cc: Ingo Molnar Cc: Jiri Olsa Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Thomas Ilsche Link: http://lkml.kernel.org/r/53BE7E1B.10503@tu-dresden.de Signed-off-by: Arnaldo Carvalho de Melo --- .../python/Perf-Trace-Util/lib/Perf/Trace/Core.py | 3 +- tools/perf/scripts/python/check-perf-trace.py | 4 +- .../perf/scripts/python/failed-syscalls-by-pid.py | 2 +- tools/perf/scripts/python/futex-contention.py | 4 +- tools/perf/scripts/python/net_dropmonitor.py | 2 +- tools/perf/scripts/python/netdev-times.py | 26 ++--- tools/perf/scripts/python/sched-migration.py | 41 ++++---- tools/perf/scripts/python/sctop.py | 2 +- tools/perf/scripts/python/syscall-counts-by-pid.py | 2 +- tools/perf/scripts/python/syscall-counts.py | 2 +- .../util/scripting-engines/trace-event-python.c | 106 ++++++++++++++++++++- 11 files changed, 146 insertions(+), 48 deletions(-) (limited to 'tools/perf/scripts/python/net_dropmonitor.py') diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py index de7211e4fa47..38dfb720fb6f 100644 --- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py +++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py @@ -107,12 +107,13 @@ def taskState(state): class EventHeaders: def __init__(self, common_cpu, common_secs, common_nsecs, - common_pid, common_comm): + common_pid, common_comm, common_callchain): self.cpu = common_cpu self.secs = common_secs self.nsecs = common_nsecs self.pid = common_pid self.comm = common_comm + self.callchain = common_callchain def ts(self): return (self.secs * (10 ** 9)) + self.nsecs diff --git a/tools/perf/scripts/python/check-perf-trace.py b/tools/perf/scripts/python/check-perf-trace.py index 4647a7694cf6..334599c6032c 100644 --- a/tools/perf/scripts/python/check-perf-trace.py +++ b/tools/perf/scripts/python/check-perf-trace.py @@ -27,7 +27,7 @@ def trace_end(): def irq__softirq_entry(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - vec): + common_callchain, vec): print_header(event_name, common_cpu, common_secs, common_nsecs, common_pid, common_comm) @@ -38,7 +38,7 @@ def irq__softirq_entry(event_name, context, common_cpu, def kmem__kmalloc(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - call_site, ptr, bytes_req, bytes_alloc, + common_callchain, call_site, ptr, bytes_req, bytes_alloc, gfp_flags): print_header(event_name, common_cpu, common_secs, common_nsecs, common_pid, common_comm) diff --git a/tools/perf/scripts/python/failed-syscalls-by-pid.py b/tools/perf/scripts/python/failed-syscalls-by-pid.py index 266a8364bce5..cafeff3d74db 100644 --- a/tools/perf/scripts/python/failed-syscalls-by-pid.py +++ b/tools/perf/scripts/python/failed-syscalls-by-pid.py @@ -39,7 +39,7 @@ def trace_end(): def raw_syscalls__sys_exit(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - id, ret): + common_callchain, id, ret): if (for_comm and common_comm != for_comm) or \ (for_pid and common_pid != for_pid ): return diff --git a/tools/perf/scripts/python/futex-contention.py b/tools/perf/scripts/python/futex-contention.py index 11e70a388d41..0f5cf437b602 100644 --- a/tools/perf/scripts/python/futex-contention.py +++ b/tools/perf/scripts/python/futex-contention.py @@ -21,7 +21,7 @@ thread_blocktime = {} lock_waits = {} # long-lived stats on (tid,lock) blockage elapsed time process_names = {} # long-lived pid-to-execname mapping -def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm, +def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm, callchain, nr, uaddr, op, val, utime, uaddr2, val3): cmd = op & FUTEX_CMD_MASK if cmd != FUTEX_WAIT: @@ -31,7 +31,7 @@ def syscalls__sys_enter_futex(event, ctxt, cpu, s, ns, tid, comm, thread_thislock[tid] = uaddr thread_blocktime[tid] = nsecs(s, ns) -def syscalls__sys_exit_futex(event, ctxt, cpu, s, ns, tid, comm, +def syscalls__sys_exit_futex(event, ctxt, cpu, s, ns, tid, comm, callchain, nr, ret): if thread_blocktime.has_key(tid): elapsed = nsecs(s, ns) - thread_blocktime[tid] diff --git a/tools/perf/scripts/python/net_dropmonitor.py b/tools/perf/scripts/python/net_dropmonitor.py index b5740599aabd..0b6ce8c253e8 100755 --- a/tools/perf/scripts/python/net_dropmonitor.py +++ b/tools/perf/scripts/python/net_dropmonitor.py @@ -66,7 +66,7 @@ def trace_end(): print_drop_table() # called from perf, when it finds a correspoinding event -def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, +def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, location, protocol): slocation = str(location) try: diff --git a/tools/perf/scripts/python/netdev-times.py b/tools/perf/scripts/python/netdev-times.py index 9aa0a32972e8..4d21ef2d601d 100644 --- a/tools/perf/scripts/python/netdev-times.py +++ b/tools/perf/scripts/python/netdev-times.py @@ -224,75 +224,75 @@ def trace_end(): (len(rx_skb_list), of_count_rx_skb_list) # called from perf, when it finds a correspoinding event -def irq__softirq_entry(name, context, cpu, sec, nsec, pid, comm, vec): +def irq__softirq_entry(name, context, cpu, sec, nsec, pid, comm, callchain, vec): if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX": return event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec) all_event_list.append(event_info) -def irq__softirq_exit(name, context, cpu, sec, nsec, pid, comm, vec): +def irq__softirq_exit(name, context, cpu, sec, nsec, pid, comm, callchain, vec): if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX": return event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec) all_event_list.append(event_info) -def irq__softirq_raise(name, context, cpu, sec, nsec, pid, comm, vec): +def irq__softirq_raise(name, context, cpu, sec, nsec, pid, comm, callchain, vec): if symbol_str("irq__softirq_entry", "vec", vec) != "NET_RX": return event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, vec) all_event_list.append(event_info) def irq__irq_handler_entry(name, context, cpu, sec, nsec, pid, comm, - irq, irq_name): + callchain, irq, irq_name): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, irq, irq_name) all_event_list.append(event_info) -def irq__irq_handler_exit(name, context, cpu, sec, nsec, pid, comm, irq, ret): +def irq__irq_handler_exit(name, context, cpu, sec, nsec, pid, comm, callchain, irq, ret): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, irq, ret) all_event_list.append(event_info) -def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, napi, dev_name): +def napi__napi_poll(name, context, cpu, sec, nsec, pid, comm, callchain, napi, dev_name): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, napi, dev_name) all_event_list.append(event_info) -def net__netif_receive_skb(name, context, cpu, sec, nsec, pid, comm, skbaddr, +def net__netif_receive_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, skblen, dev_name): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr, skblen, dev_name) all_event_list.append(event_info) -def net__netif_rx(name, context, cpu, sec, nsec, pid, comm, skbaddr, +def net__netif_rx(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, skblen, dev_name): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr, skblen, dev_name) all_event_list.append(event_info) -def net__net_dev_queue(name, context, cpu, sec, nsec, pid, comm, +def net__net_dev_queue(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, skblen, dev_name): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr, skblen, dev_name) all_event_list.append(event_info) -def net__net_dev_xmit(name, context, cpu, sec, nsec, pid, comm, +def net__net_dev_xmit(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, skblen, rc, dev_name): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr, skblen, rc ,dev_name) all_event_list.append(event_info) -def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, +def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, protocol, location): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr, protocol, location) all_event_list.append(event_info) -def skb__consume_skb(name, context, cpu, sec, nsec, pid, comm, skbaddr): +def skb__consume_skb(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr) all_event_list.append(event_info) -def skb__skb_copy_datagram_iovec(name, context, cpu, sec, nsec, pid, comm, +def skb__skb_copy_datagram_iovec(name, context, cpu, sec, nsec, pid, comm, callchain, skbaddr, skblen): event_info = (name, context, cpu, nsecs(sec, nsec), pid, comm, skbaddr, skblen) diff --git a/tools/perf/scripts/python/sched-migration.py b/tools/perf/scripts/python/sched-migration.py index 74d55ec08aed..de66cb3b72c9 100644 --- a/tools/perf/scripts/python/sched-migration.py +++ b/tools/perf/scripts/python/sched-migration.py @@ -369,93 +369,92 @@ def trace_end(): def sched__sched_stat_runtime(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, runtime, vruntime): + common_callchain, comm, pid, runtime, vruntime): pass def sched__sched_stat_iowait(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, delay): + common_callchain, comm, pid, delay): pass def sched__sched_stat_sleep(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, delay): + common_callchain, comm, pid, delay): pass def sched__sched_stat_wait(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, delay): + common_callchain, comm, pid, delay): pass def sched__sched_process_fork(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - parent_comm, parent_pid, child_comm, child_pid): + common_callchain, parent_comm, parent_pid, child_comm, child_pid): pass def sched__sched_process_wait(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio): + common_callchain, comm, pid, prio): pass def sched__sched_process_exit(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio): + common_callchain, comm, pid, prio): pass def sched__sched_process_free(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio): + common_callchain, comm, pid, prio): pass def sched__sched_migrate_task(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio, orig_cpu, + common_callchain, comm, pid, prio, orig_cpu, dest_cpu): headers = EventHeaders(common_cpu, common_secs, common_nsecs, - common_pid, common_comm) + common_pid, common_comm, common_callchain) parser.migrate(headers, pid, prio, orig_cpu, dest_cpu) def sched__sched_switch(event_name, context, common_cpu, - common_secs, common_nsecs, common_pid, common_comm, + common_secs, common_nsecs, common_pid, common_comm, common_callchain, prev_comm, prev_pid, prev_prio, prev_state, next_comm, next_pid, next_prio): headers = EventHeaders(common_cpu, common_secs, common_nsecs, - common_pid, common_comm) + common_pid, common_comm, common_callchain) parser.sched_switch(headers, prev_comm, prev_pid, prev_prio, prev_state, next_comm, next_pid, next_prio) def sched__sched_wakeup_new(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio, success, + common_callchain, comm, pid, prio, success, target_cpu): headers = EventHeaders(common_cpu, common_secs, common_nsecs, - common_pid, common_comm) + common_pid, common_comm, common_callchain) parser.wake_up(headers, comm, pid, success, target_cpu, 1) def sched__sched_wakeup(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio, success, + common_callchain, comm, pid, prio, success, target_cpu): headers = EventHeaders(common_cpu, common_secs, common_nsecs, - common_pid, common_comm) + common_pid, common_comm, common_callchain) parser.wake_up(headers, comm, pid, success, target_cpu, 0) def sched__sched_wait_task(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid, prio): + common_callchain, comm, pid, prio): pass def sched__sched_kthread_stop_ret(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - ret): + common_callchain, ret): pass def sched__sched_kthread_stop(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - comm, pid): + common_callchain, comm, pid): pass -def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs, - common_pid, common_comm): +def trace_unhandled(event_name, context, event_fields_dict): pass diff --git a/tools/perf/scripts/python/sctop.py b/tools/perf/scripts/python/sctop.py index c9f3058b7dd4..61621b93affb 100644 --- a/tools/perf/scripts/python/sctop.py +++ b/tools/perf/scripts/python/sctop.py @@ -44,7 +44,7 @@ def trace_begin(): def raw_syscalls__sys_enter(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - id, args): + common_callchain, id, args): if for_comm is not None: if common_comm != for_comm: return diff --git a/tools/perf/scripts/python/syscall-counts-by-pid.py b/tools/perf/scripts/python/syscall-counts-by-pid.py index cf2054c529c9..daf314cc5dd3 100644 --- a/tools/perf/scripts/python/syscall-counts-by-pid.py +++ b/tools/perf/scripts/python/syscall-counts-by-pid.py @@ -38,7 +38,7 @@ def trace_end(): def raw_syscalls__sys_enter(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - id, args): + common_callchain, id, args): if (for_comm and common_comm != for_comm) or \ (for_pid and common_pid != for_pid ): diff --git a/tools/perf/scripts/python/syscall-counts.py b/tools/perf/scripts/python/syscall-counts.py index 92b29381bd39..e66a7730aeb5 100644 --- a/tools/perf/scripts/python/syscall-counts.py +++ b/tools/perf/scripts/python/syscall-counts.py @@ -35,7 +35,7 @@ def trace_end(): def raw_syscalls__sys_enter(event_name, context, common_cpu, common_secs, common_nsecs, common_pid, common_comm, - id, args): + common_callchain, id, args): if for_comm is not None: if common_comm != for_comm: return diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index b6c1a69f2b18..cf65404472cb 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -32,6 +32,7 @@ #include "../event.h" #include "../thread.h" #include "../trace-event.h" +#include "../machine.h" PyMODINIT_FUNC initperf_trace_context(void); @@ -278,12 +279,90 @@ static PyObject *get_field_numeric_entry(struct event_format *event, return obj; } + +static PyObject *python_process_callchain(struct perf_sample *sample, + struct perf_evsel *evsel, + struct addr_location *al) +{ + PyObject *pylist; + + pylist = PyList_New(0); + if (!pylist) + Py_FatalError("couldn't create Python list"); + + if (!symbol_conf.use_callchain || !sample->callchain) + goto exit; + + if (machine__resolve_callchain(al->machine, evsel, al->thread, + sample, NULL, NULL, + PERF_MAX_STACK_DEPTH) != 0) { + pr_err("Failed to resolve callchain. Skipping\n"); + goto exit; + } + callchain_cursor_commit(&callchain_cursor); + + + while (1) { + PyObject *pyelem; + struct callchain_cursor_node *node; + node = callchain_cursor_current(&callchain_cursor); + if (!node) + break; + + pyelem = PyDict_New(); + if (!pyelem) + Py_FatalError("couldn't create Python dictionary"); + + + pydict_set_item_string_decref(pyelem, "ip", + PyLong_FromUnsignedLongLong(node->ip)); + + if (node->sym) { + PyObject *pysym = PyDict_New(); + if (!pysym) + Py_FatalError("couldn't create Python dictionary"); + pydict_set_item_string_decref(pysym, "start", + PyLong_FromUnsignedLongLong(node->sym->start)); + pydict_set_item_string_decref(pysym, "end", + PyLong_FromUnsignedLongLong(node->sym->end)); + pydict_set_item_string_decref(pysym, "binding", + PyInt_FromLong(node->sym->binding)); + pydict_set_item_string_decref(pysym, "name", + PyString_FromStringAndSize(node->sym->name, + node->sym->namelen)); + pydict_set_item_string_decref(pyelem, "sym", pysym); + } + + if (node->map) { + struct map *map = node->map; + const char *dsoname = "[unknown]"; + if (map && map->dso && (map->dso->name || map->dso->long_name)) { + if (symbol_conf.show_kernel_path && map->dso->long_name) + dsoname = map->dso->long_name; + else if (map->dso->name) + dsoname = map->dso->name; + } + pydict_set_item_string_decref(pyelem, "dso", + PyString_FromString(dsoname)); + } + + callchain_cursor_advance(&callchain_cursor); + PyList_Append(pylist, pyelem); + Py_DECREF(pyelem); + } + +exit: + return pylist; +} + + static void python_process_tracepoint(struct perf_sample *sample, struct perf_evsel *evsel, struct thread *thread, struct addr_location *al) { - PyObject *handler, *retval, *context, *t, *obj, *dict = NULL; + PyObject *handler, *retval, *context, *t, *obj, *callchain; + PyObject *dict = NULL; static char handler_name[256]; struct format_field *field; unsigned long s, ns; @@ -326,18 +405,23 @@ static void python_process_tracepoint(struct perf_sample *sample, PyTuple_SetItem(t, n++, PyString_FromString(handler_name)); PyTuple_SetItem(t, n++, context); + /* ip unwinding */ + callchain = python_process_callchain(sample, evsel, al); + if (handler) { PyTuple_SetItem(t, n++, PyInt_FromLong(cpu)); PyTuple_SetItem(t, n++, PyInt_FromLong(s)); PyTuple_SetItem(t, n++, PyInt_FromLong(ns)); PyTuple_SetItem(t, n++, PyInt_FromLong(pid)); PyTuple_SetItem(t, n++, PyString_FromString(comm)); + PyTuple_SetItem(t, n++, callchain); } else { pydict_set_item_string_decref(dict, "common_cpu", PyInt_FromLong(cpu)); pydict_set_item_string_decref(dict, "common_s", PyInt_FromLong(s)); pydict_set_item_string_decref(dict, "common_ns", PyInt_FromLong(ns)); pydict_set_item_string_decref(dict, "common_pid", PyInt_FromLong(pid)); pydict_set_item_string_decref(dict, "common_comm", PyString_FromString(comm)); + pydict_set_item_string_decref(dict, "common_callchain", callchain); } for (field = event->format.fields; field; field = field->next) { if (field->flags & FIELD_IS_STRING) { @@ -357,6 +441,7 @@ static void python_process_tracepoint(struct perf_sample *sample, pydict_set_item_string_decref(dict, field->name, obj); } + if (!handler) PyTuple_SetItem(t, n++, dict); @@ -388,7 +473,7 @@ static void python_process_general_event(struct perf_sample *sample, struct thread *thread, struct addr_location *al) { - PyObject *handler, *retval, *t, *dict; + PyObject *handler, *retval, *t, *dict, *callchain; static char handler_name[64]; unsigned n = 0; @@ -428,6 +513,10 @@ static void python_process_general_event(struct perf_sample *sample, PyString_FromString(al->sym->name)); } + /* ip unwinding */ + callchain = python_process_callchain(sample, evsel, al); + pydict_set_item_string_decref(dict, "callchain", callchain); + PyTuple_SetItem(t, n++, dict); if (_PyTuple_Resize(&t, n) == -1) Py_FatalError("error resizing Python tuple"); @@ -624,6 +713,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "common_nsecs, "); fprintf(ofp, "common_pid, "); fprintf(ofp, "common_comm,\n\t"); + fprintf(ofp, "common_callchain, "); not_first = 0; count = 0; @@ -667,7 +757,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "%%u"); } - fprintf(ofp, "\\n\" %% \\\n\t\t("); + fprintf(ofp, "\" %% \\\n\t\t("); not_first = 0; count = 0; @@ -703,7 +793,15 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) fprintf(ofp, "%s", f->name); } - fprintf(ofp, "),\n\n"); + fprintf(ofp, ")\n\n"); + + fprintf(ofp, "\t\tfor node in common_callchain:"); + fprintf(ofp, "\n\t\t\tif 'sym' in node:"); + fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])"); + fprintf(ofp, "\n\t\t\telse:"); + fprintf(ofp, "\n\t\t\t\tprint \"\t[%%x]\" %% (node['ip'])\n\n"); + fprintf(ofp, "\t\tprint \"\\n\"\n\n"); + } fprintf(ofp, "def trace_unhandled(event_name, context, " -- cgit v1.2.3