ziomon: correct throughput calculation in ziorep_printers.cpp

During evaluation of the collected ziomon data from the system with following
multipath configuration:

$ multipath -ll
3600507630bffc3200000000000005294 dm-0 IBM,2107900
size=20G features='1 queue_if_no_path' hwhandler='1 alua' wp=rw
`-+- policy='service-time 0' prio=50 status=active
  |- 1:0:0:1083457618 sdd 8:48  active ready running
  `- 0:0:0:1083457618 sda 8:0   active ready running
3600507630bffc3200000000000005394 dm-1 IBM,2107900
size=20G features='1 queue_if_no_path' hwhandler='1 alua' wp=rw
`-+- policy='service-time 0' prio=50 status=active
  |- 1:0:0:1083457619 sdf 8:80  active ready running
  `- 0:0:0:1083457619 sdb 8:16  active ready running
3600507630bffc3200000000000005494 dm-2 IBM,2107900
size=20G features='1 queue_if_no_path' hwhandler='1 alua' wp=rw
`-+- policy='service-time 0' prio=50 status=active
  |- 1:0:0:1083457620 sdg 8:96  active ready running
  `- 0:0:0:1083457620 sdc 8:32  active ready running
3600507630bffc3200000000000005594 dm-3 IBM,2107900
size=20G features='1 queue_if_no_path' hwhandler='1 alua' wp=rw
`-+- policy='service-time 0' prio=50 status=active
  |- 1:0:0:1083457621 sdh 8:112 active ready running
  `- 0:0:0:1083457621 sde 8:64  active ready running

there were low throughput values for adapter noticed in ziorep_utilization
virtual adapter report:

$ ziorep_utilization adp_line_speed.log
...
CHP Bus-ID  |qdio util.%|queu|fail|-thp in MB/s-|I/O reqs-|
 ID            max   avg full  erc     rd    wrt   rd  wrt
2021-08-18 12:56:44
 61/0.0.1946  32.8   3.1    0    0   0.0   84.5    21 204K
12:57:04
...

there were also low values for throughput of devices noticed in
ziorep_traffic report. And were no aggregation of throughput for
different aggregation parameters provided:

$ ziorep_traffic adp_line_speed.log -i 0
       WWPN                LUN       |I/O rt MB/s|thrp in MB/s-|...
                                        min   max    avg  stdev ...
2021-08-18 12:58:24
0x500507630b09c320:0x4052409400000000   0.0 219.2  85.7  3.352K ...
0x500507630b09c320:0x4053409400000000   0.0 348.6  84.6  3.330K ...
0x500507630b09c320:0x4054409400000000   0.0 268.6  84.0  3.317K ...
0x500507630b09c320:0x4055409400000000   0.0 354.2  83.7  3.312K ...

$ ziorep_traffic adp_line_speed.log -i 0 -Cu
 Bus-ID |I/O rt MB/s|thrp in MB/s-|...
           min   max    avg  stdev ...
2021-08-18 12:58:24
0.0.1946   0.0 354.2  84.5  3.328K ...

although, iostat tool showed decent throughput values for each scsi disk, which
belongs to investigated zfcp adapter. In this example each scsi disk has
throughput more than 300MB/s, which is much larger, than 84.5MB/s
throughput for the adapter:

$ iostat -x 1
...
Device            r/s     w/s     rkB/s     wkB/s ...
dasda            0.00    0.00      0.00      0.00 ...
dasdb            0.00    0.00      0.00      0.00 ...
sda              0.00 2556.00      0.00 327168.00 ...
sdc              0.00 2554.00      0.00 326912.00 ...
sdb              0.00 2559.00      0.00 327552.00 ...
sdf              0.00 2865.00      0.00 366720.00 ...
sdd              0.00 2843.00      0.00 363904.00 ...
sdg              0.00 2845.00      0.00 364160.00 ...
sde              0.00 2471.00      0.00 315416.00 ...
sdh              0.00 2768.00      0.00 353768.00 ...
dm-0             0.00 5399.00      0.00 691072.00 ...
dm-1             0.00 5424.00      0.00 694272.00 ...
dm-2             0.00 5400.00      0.00 691200.00 ...
dm-3             0.00 5240.00      0.00 669312.00 ...

Use Frameset interval size for calculation of throughput of zfcp adapter
instead of d2c (dispatch to complete) time of request, which is used for I/O
rate calculation. Also use Frameset interval instead of total_latency.sum
(which in fact is a sum of d2c times for each repuest in specifed interval).
Use calc_avg() function for throughput calculation.

With fix applied, virtual adapter report now contains correct value for adpater
throughput for specified interval:

$ ziorep_utilization adp_line_speed.log
...
CHP Bus-ID  |qdio util.%|queu|fail|-thp in MB/s-|I/O reqs-|
 ID            max   avg full  erc     rd    wrt   rd  wrt
2021-08-18 12:56:44
 61/0.0.1946  32.8   3.1    0    0   0.0  1.336K   21 204K
...

With fix applied, traffic report now contains correct values of
throughput for each device and aggregation now works correctly:

$ ziorep_traffic adp_line_speed.log -i 0
       WWPN                LUN       |I/O rt MB/s|thrp in MB/s-|...
                                        min   max    avg  stdev ...
2021-08-18 12:58:24
0x500507630b09c320:0x4052409400000000   0.0 219.2 339.6  3.352K ...
0x500507630b09c320:0x4053409400000000   0.0 348.6 335.4  3.330K ...
0x500507630b09c320:0x4054409400000000   0.0 268.6 333.1  3.317K ...
0x500507630b09c320:0x4055409400000000   0.0 354.2 331.9  3.312K ...

$ ziorep_traffic adp_line_speed.log -i 0 -Cu
 Bus-ID |I/O rt MB/s|thrp in MB/s-|...
           min   max    avg  stdev ...
2021-08-18 12:58:24
0.0.1946   0.0 354.2 1.340K 3.328K ...

Signed-off-by: Fedor Loshakov <loshakov@linux.ibm.com>
Reviewed-by: Benjamin Block <bblock@linux.ibm.com>
Signed-off-by: Jan Höppner <hoeppner@linux.ibm.com>
This commit is contained in:
Fedor Loshakov
2021-08-17 10:47:08 +02:00
committed by Jan Höppner
parent 895dc80580
commit f8331a4b8e
2 changed files with 42 additions and 21 deletions

View File

@@ -3,7 +3,7 @@
*
* Utility classes to print framsets
*
* Copyright IBM Corp. 2008, 2017
* Copyright IBM Corp. 2008, 2021
*
* s390-tools is free software; you can redistribute it and/or modify
* it under the terms of the MIT license. See LICENSE for details.
@@ -478,21 +478,22 @@ void VirtAdapterPrinter::print_failures(FILE *fp, const struct ioerr_cnt *cnt)
}
void VirtAdapterPrinter::print_throughput(FILE *fp,
const struct blkiomon_stat *stat)
const struct blkiomon_stat *stat,
const __u64 interval)
{
double tmp;
if (!stat || stat->d2c_r.num <= 0 || stat->size_r.num <= 0)
if (!stat || interval == 0 || stat->size_r.num <= 0)
tmp = 0;
else
tmp = stat->size_r.sum/(double)stat->d2c_r.sum;
tmp = calc_avg(stat->size_r.sum, interval);
print_delimiter(fp);
print_abbrev_num(fp, tmp);
if (!stat || stat->d2c_w.num <= 0 || stat->size_w.num <= 0)
if (!stat || interval == 0 || stat->size_w.num <= 0)
tmp = 0;
else
tmp = stat->size_w.sum/(double)stat->d2c_w.sum;
tmp = calc_avg(stat->size_w.sum, interval);
print_delimiter(fp);
print_abbrev_num(fp, tmp);
}
@@ -536,6 +537,12 @@ int VirtAdapterPrinter::print_frame(FILE *fp,
const struct blkiomon_stat *blk_stat;
const struct zfcpdd_dstat *zfcp_stat;
/**
* Receive Frameset interval and convert it
* from seconds to microseconds
*/
__u64 interval = frameset.get_duration() * 1000000;
list<__u32> devnos;
devnos = ((StagedDeviceFilter*)&dev_filt)->get_filter_devnos();
@@ -557,7 +564,7 @@ int VirtAdapterPrinter::print_frame(FILE *fp,
print_queue_fill(fp, zfcp_stat, util);
print_queue_full(fp, util);
print_failures(fp, ioerr);
print_throughput(fp, blk_stat);
print_throughput(fp, blk_stat, interval);
print_num_requests(fp, blk_stat);
if (lrc) {
fprintf(stderr, "%s: Did not find matching data in"
@@ -810,6 +817,12 @@ int TrafficPrinter::print_frame(FILE *fp, const Frameset &frameset,
const struct zfcpdd_dstat *zfcp_stat = NULL;
const AggregationCollapser *agg_col;
/**
* Receive Frameset interval and convert it
* from seconds to microseconds
*/
__u64 interval = frameset.get_duration() * 1000000;
switch (m_agg_crit) {
case none:
get_device_list(lst_32, dev_filt);
@@ -847,7 +860,7 @@ int TrafficPrinter::print_frame(FILE *fp, const Frameset &frameset,
blk_stat = frameset.get_blkiomon_stat_by_wwpn(*i);
zfcp_stat = frameset.get_zfcpdd_stat_by_wwpn(*i);
print_device_wwpn(fp, *i);
print_data_row(fp, blk_stat, zfcp_stat);
print_data_row(fp, blk_stat, zfcp_stat, interval);
}
}
else if (m_agg_crit == all) {
@@ -856,7 +869,7 @@ int TrafficPrinter::print_frame(FILE *fp, const Frameset &frameset,
blk_stat = frameset.get_first_blkiomon_stat();
zfcp_stat = frameset.get_first_zfcpdd_stat();
print_device_all(fp);
print_data_row(fp, blk_stat, zfcp_stat);
print_data_row(fp, blk_stat, zfcp_stat, interval);
}
else {
for (list<__u32>::const_iterator i = lst_32.begin();
@@ -894,7 +907,7 @@ int TrafficPrinter::print_frame(FILE *fp, const Frameset &frameset,
}
if (rc )
return -1;
print_data_row(fp, blk_stat, zfcp_stat);
print_data_row(fp, blk_stat, zfcp_stat, interval);
}
}
@@ -930,7 +943,8 @@ void SummaryTrafficPrinter::print_topline(FILE *fp)
}
void SummaryTrafficPrinter::print_throughput(FILE *fp, const struct blkiomon_stat *stat)
void SummaryTrafficPrinter::print_throughput(FILE *fp, const struct blkiomon_stat *stat,
const __u64 interval)
{
struct minmax thrp_data, total_size, total_latency;
double tmp;
@@ -968,7 +982,7 @@ void SummaryTrafficPrinter::print_throughput(FILE *fp, const struct blkiomon_sta
tmp = 0;
if (stat && total_size.sum > 0)
tmp = calc_avg(total_size.sum, total_latency.sum);
tmp = calc_avg(total_size.sum, interval);
print_delimiter(fp);
print_abbrev_num(fp, tmp);
@@ -1101,14 +1115,15 @@ void SummaryTrafficPrinter::print_fabric_latency(FILE *fp, const struct zfcpdd_d
void SummaryTrafficPrinter::print_data_row(FILE *fp,
const struct blkiomon_stat *blk_stat,
const struct zfcpdd_dstat *zfcp_stat)
const struct zfcpdd_dstat *zfcp_stat,
const __u64 interval)
{
if (!blk_stat)
blk_stat = get_empty_blkiomon_stat();
if (!zfcp_stat)
zfcp_stat = get_empty_zfcpdd_dstat();
print_throughput(fp, blk_stat);
print_throughput(fp, blk_stat, interval);
print_request_stats(fp, blk_stat);
print_io_subsystem_latency(fp, blk_stat);
print_channel_latency(fp, zfcp_stat);
@@ -1177,7 +1192,8 @@ void DetailedTrafficPrinter::print_topline(FILE *fp)
void DetailedTrafficPrinter::print_data_row(FILE *fp,
const struct blkiomon_stat *blk_stat,
const struct zfcpdd_dstat *zfcp_stat)
const struct zfcpdd_dstat *zfcp_stat,
const __u64 interval __attribute__ ((unused)))
{
if (!blk_stat)
blk_stat = get_empty_blkiomon_stat();

View File

@@ -3,7 +3,7 @@
*
* Utility classes to print framsets
*
* Copyright IBM Corp. 2008, 2017
* Copyright IBM Corp. 2008, 2021
*
* s390-tools is free software; you can redistribute it and/or modify
* it under the terms of the MIT license. See LICENSE for details.
@@ -128,7 +128,8 @@ private:
const struct adapter_utilization *res);
void print_queue_full(FILE *fp, const struct adapter_utilization *res);
void print_failures(FILE *fp, const struct ioerr_cnt *cnt);
void print_throughput(FILE *fp, const struct blkiomon_stat *stat);
void print_throughput(FILE *fp, const struct blkiomon_stat *stat,
const __u64 interval);
void print_num_requests(FILE *fp, const struct blkiomon_stat *stat);
};
@@ -147,7 +148,8 @@ protected:
* Print the actual row, excluding the first column */
virtual void print_data_row(FILE *fp,
const struct blkiomon_stat *blk_stat,
const struct zfcpdd_dstat *zfcp_stat) = 0;
const struct zfcpdd_dstat *zfcp_stat,
const __u64 interval) = 0;
void print_topline_prefix1(FILE *fp);
void print_topline_prefix2(FILE *fp);
@@ -185,8 +187,10 @@ public:
private:
virtual void print_data_row(FILE *fp,
const struct blkiomon_stat *blk_stat,
const struct zfcpdd_dstat *zfcp_stat);
void print_throughput(FILE *fp, const struct blkiomon_stat *stat);
const struct zfcpdd_dstat *zfcp_stat,
const __u64 interval);
void print_throughput(FILE *fp, const struct blkiomon_stat *stat,
const __u64 interval);
void print_request_stats(FILE *fp, const struct blkiomon_stat *stat);
void print_io_subsystem_latency(FILE *fp, const struct blkiomon_stat *stat);
void print_channel_latency(FILE *fp, const struct zfcpdd_dstat *stat);
@@ -207,7 +211,8 @@ public:
private:
virtual void print_data_row(FILE *fp,
const struct blkiomon_stat *blk_stat,
const struct zfcpdd_dstat *zfcp_stat);
const struct zfcpdd_dstat *zfcp_stat,
const __u64 interval);
void print_histogram_io_reqs(FILE *fp,
const struct blkiomon_stat *stat);
void print_histogram_io_subs_lat(FILE *fp,