tools/kvm_stat: Add command line switch '-L' to log to file

To integrate with logrotate, we have a signal handler that will re-open
the logfile.
Assuming we have a systemd unit file with
     ExecStart=kvm_stat -dtc -s 10 -L /var/log/kvm_stat.csv
     ExecReload=/bin/kill -HUP $MAINPID
and a logrotate config featuring
     postrotate
        /bin/systemctl reload kvm_stat.service
     endscript
Then the overall flow will look like this:
(1) systemd starts kvm_stat, logging to A.
(2) At some point, logrotate runs, moving A to B.
    kvm_stat continues to write to B at this point.
(3) After rotating, logrotate restarts the kvm_stat unit via systemctl.
(4) The kvm_stat unit sends a SIGHUP to kvm_stat, finally making it
    switch over to writing to A again.
Note that in order to keep the structure of the cvs output in tact, we
make sure to, in contrast to the standard log format, only write the
header once at the beginning of a file. This implies that the header is
suppressed when appending to an existing file. Unlike with the standard
format, where we append to an existing file by starting out with a
header.

Signed-off-by: Stefan Raspl <raspl@de.ibm.com>
Message-Id: <20200402085705.61155-3-raspl@linux.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

2 files changed, 68 insertions, 13 deletions

diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat
index d6cced4e1ef4..d199a3694be8 100755
--- a/tools/kvm/kvm_stat/kvm_stat
+++ b/tools/kvm/kvm_stat/kvm_stat
@@ -32,6 +32,7 @@ import resource
 import struct
 import re
 import subprocess
+import signal
 from collections import defaultdict, namedtuple
 from functools import reduce
 from datetime import datetime
@@ -228,6 +229,8 @@ IOCTL_NUMBERS = {
     'RESET':       0x00002403,
 }
 
+signal_received = False
+
 ENCODING = locale.getpreferredencoding(False)
 TRACE_FILTER = re.compile(r'^[^\(]*$')
 
@@ -1523,26 +1526,64 @@ class CSVFormat(object):
 
 def log(stats, opts, frmt, keys):
     """Prints statistics as reiterating key block, multiple value blocks."""
+    global signal_received
     line = 0
     banner_repeat = 20
-    banner_printed = False
-
+    f = None
+
+    def do_banner(opts):
+        nonlocal f
+        if opts.log_to_file:
+            if not f:
+                try:
+                     f = open(opts.log_to_file, 'a')
+                except (IOError, OSError):
+                    sys.exit("Error: Could not open file: %s" %
+                             opts.log_to_file)
+                if isinstance(frmt, CSVFormat) and f.tell() != 0:
+                    return
+        print(frmt.get_banner(), file=f or sys.stdout)
+
+    def do_statline(opts, values):
+        statline = datetime.now().strftime("%Y-%m-%d %H:%M:%S") + \
+                   frmt.get_statline(keys, values)
+        print(statline, file=f or sys.stdout)
+
+    do_banner(opts)
+    banner_printed = True
     while True:
         try:
             time.sleep(opts.set_delay)
-            if line % banner_repeat == 0 and not banner_printed:
-                print(frmt.get_banner())
+            if signal_received:
+                banner_printed = True
+                line = 0
+                f.close()
+                do_banner(opts)
+                signal_received = False
+            if (line % banner_repeat == 0 and not banner_printed and
+                not (opts.log_to_file and isinstance(frmt, CSVFormat))):
+                do_banner(opts)
                 banner_printed = True
             values = stats.get()
             if (not opts.skip_zero_records or
                 any(values[k].delta != 0 for k in keys)):
-                print(datetime.now().strftime("%Y-%m-%d %H:%M:%S") +
-                      frmt.get_statline(keys, values))
+                do_statline(opts, values)
                 line += 1
                 banner_printed = False
         except KeyboardInterrupt:
             break
 
+    if opts.log_to_file:
+        f.close()
+
+
+def handle_signal(sig, frame):
+    global signal_received
+
+    signal_received = True
+
+    return
+
 
 def is_delay_valid(delay):
     """Verify delay is in valid value range."""
@@ -1615,7 +1656,7 @@ Press any other key to refresh statistics immediately.
     argparser.add_argument('-c', '--csv',
                            action='store_true',
                            default=False,
-                           help='log in csv format - requires option -l/--log',
+                           help='log in csv format - requires option -l/-L',
                            )
     argparser.add_argument('-d', '--debugfs',
                            action='store_true',
@@ -1643,6 +1684,11 @@ Press any other key to refresh statistics immediately.
                            default=False,
                            help='run in logging mode (like vmstat)',
                            )
+    argparser.add_argument('-L', '--log-to-file',
+                           type=str,
+                           metavar='FILE',
+                           help="like '--log', but logging to a file"
+                           )
     argparser.add_argument('-p', '--pid',
                            type=int,
                            default=0,
@@ -1666,10 +1712,10 @@ Press any other key to refresh statistics immediately.
                            help='omit records with all zeros in logging mode',
                            )
     options = argparser.parse_args()
-    if options.csv and not options.log:
+    if options.csv and not (options.log or options.log_to_file):
         sys.exit('Error: Option -c/--csv requires -l/--log')
-    if options.skip_zero_records and not options.log:
-        sys.exit('Error: Option -z/--skip-zero-records requires -l/--log')
+    if options.skip_zero_records and not (options.log or options.log_to_file):
+        sys.exit('Error: Option -z/--skip-zero-records requires -l/-L')
     try:
         # verify that we were passed a valid regex up front
         re.compile(options.fields)
@@ -1749,7 +1795,9 @@ def main():
         sys.stdout.write('  ' + '\n  '.join(sorted(set(event_list))) + '\n')
         sys.exit(0)
 
-    if options.log:
+    if options.log or options.log_to_file:
+        if options.log_to_file:
+            signal.signal(signal.SIGHUP, handle_signal)
         keys = sorted(stats.get().keys())
         if options.csv:
             frmt = CSVFormat(keys)
diff --git a/tools/kvm/kvm_stat/kvm_stat.txt b/tools/kvm/kvm_stat/kvm_stat.txt
index 24296dccc00a..feaf46451e83 100644
--- a/tools/kvm/kvm_stat/kvm_stat.txt
+++ b/tools/kvm/kvm_stat/kvm_stat.txt
@@ -65,8 +65,10 @@ OPTIONS
 	run in batch mode for one second
 
 -c::
---csv=<file>::
-        log in csv format - requires option -l/--log
+--csv::
+        log in csv format. Requires option -l/--log or -L/--log-to-file.
+        When used with option -L/--log-to-file, the header is only ever
+        written to start of file to preserve the format.
 
 -d::
 --debugfs::
@@ -92,6 +94,11 @@ OPTIONS
 --log::
         run in logging mode (like vmstat)
 
+
+-L<file>::
+--log-to-file=<file>::
+        like -l/--log, but logging to a file. Appends to existing files.
+
 -p<pid>::
 --pid=<pid>::
 	limit statistics to one virtual machine (pid)