1656913 – qcow2 cache is too small

RHEL Engineering is moving the tracking of its product development work on RHEL 6 through RHEL 9 to Red Hat Jira (issues.redhat.com). If you're a Red Hat customer, please continue to file support cases via the Red Hat customer portal. If you're not, please head to the "RHEL project" in Red Hat Jira and file new tickets here. Individual Bugzilla bugs in the statuses "NEW", "ASSIGNED", and "POST" are being migrated throughout September 2023. Bugs of Red Hat partners with an assigned Engineering Partner Manager (EPM) are migrated in late September as per pre-agreed dates. Bugs against components "kernel", "kernel-rt", and "kpatch" are only migrated if still in "NEW" or "ASSIGNED". If you cannot log in to RH Jira, please consult article #7032570. That failing, please send an e-mail to the RH Jira admins at rh-issues@redhat.com to troubleshoot your issue as a user management inquiry. The email creates a ServiceNow ticket with Red Hat. Individual Bugzilla bugs that are migrated will be moved to status "CLOSED", resolution "MIGRATED", and set with "MigratedToJIRA" in "Keywords". The link to the successor Jira issue will be found under "Links", have a little "two-footprint" icon next to it, and direct you to the "RHEL project" in Red Hat Jira (issue links are of type "https://issues.redhat.com/browse/RHEL-XXXX", where "X" is a digit). This same link will be available in a blue banner at the top of the page informing you that that bug has been migrated.

Bug 1656913 - qcow2 cache is too small

Summary: qcow2 cache is too small

Keywords:
Status:	CLOSED ERRATA
Alias:	None
Product:	Red Hat Enterprise Linux 7
Classification:	Red Hat
Component:	qemu-kvm-rhev
Sub Component:
Version:	7.6
Hardware:	Unspecified
OS:	Unspecified
Priority:	unspecified
Severity:	unspecified
Target Milestone:	rc
Target Release:	---
Assignee:	Kevin Wolf
QA Contact:	Tingting Mao
Docs Contact:
URL:
Whiteboard:
Depends On:	1656507
Blocks:
TreeView+	depends on / blocked

Reported:	2018-12-06 16:17 UTC by Kevin Wolf
Modified:	2019-08-22 09:21 UTC (History)
CC List:	7 users (show)
Fixed In Version:	qemu-kvm-rhev-2.12.0-24.el7
Doc Type:	If docs needed, set a value
Doc Text:
Clone Of:	1656507
Environment:
Last Closed:	2019-08-22 09:19:58 UTC
Target Upstream Version:
Embargoed:

Attachments	(Terms of Use)

Links
System	ID	Private	Priority	Status	Summary	Last Updated
Red Hat Product Errata	RHSA-2019:2553	0	None	None	None	2019-08-22 09:21:28 UTC

Description Kevin Wolf 2018-12-06 16:17:29 UTC

+++ This bug was initially created as a clone of Bug #1656507 +++

The qcow2 metadata cache is too small for some use cases (covering only a 8 GB region for random I/O). Originally, the idea was that management tools would set the cache size options, but this has never happened. Upstream recently switched to a more intelligent default at the QEMU level that can make a big difference.


The difference is easily demonstrated:

1. Create an image that is noticeably larger than 8G (with 64k clusters)
   $ qemu-img create -f qcow2 /tmp/test.qcow2 32G

2. Initialise the image with some data
   $ qemu-img bench -w -c 1000 -S 512M /tmp/test.qcow2

3. Benchmark reads with 512 MB steps between each request:
   $ qemu-img bench -c 1000000 -S 512M /tmp/test.qcow2


On RHEL qemu-kvm (qcow2):

$ qemu-img bench -c 1000000 -S 512M /tmp/test.qcow2
Sending 1000000 read requests, 4096 bytes each, 64 in parallel (starting at offset 0, step size 536870912)
Run completed in 20.913 seconds.


On RHEL qemu-kvm (raw):

$ qemu-img bench -c 1000000 -S 512M /tmp/test.raw 
Sending 1000000 read requests, 4096 bytes each, 64 in parallel (starting at offset 0, step size 536870912)
Run completed in 2.572 seconds.


On upstream qemu (qcow2):
$ qemu-img bench -c 1000000 -S 512M /tmp/test.qcow2
Sending 1000000 read requests, 4096 bytes each, 64 in parallel (starting at offset 0, step size 536870912)
Run completed in 1.571 seconds.


The difference should also be very visible in fio, with random I/O across a 32 GB image.

Comment 2 Miroslav Rezanina 2019-02-26 11:24:49 UTC

Fix included in qemu-kvm-rhev-2.12.0-24.el7

Comment 4 Tingting Mao 2019-02-28 09:21:00 UTC

Tried to verify this bug as below.


Scenario 1

1. Do test in host with latest qemu packages.
# qemu-img --version
qemu-img version 2.12.0 (qemu-kvm-rhev-2.12.0-24.el7)
Copyright (c) 2003-2017 Fabrice Bellard and the QEMU Project developers

# qemu-img create -f qcow2 test.qcow2 30G
Formatting 'test.qcow2', fmt=qcow2 size=32212254720 cluster_size=65536 lazy_refcounts=off refcount_bits=16

# qemu-img bench -w -c 1000 -S 512M test.qcow2
Sending 1000 write requests, 4096 bytes each, 64 in parallel (starting at offset 0, step size 536870912)

# qemu-img bench -c 1000000 -S 512M test.qcow2
Sending 1000000 read requests, 4096 bytes each, 64 in parallel (starting at offset 0, step size 536870912)
Run completed in 2.879 seconds. ----------------------------- Improved!!!


2. Do test in host with older qemu packages
# qemu-img --version
qemu-img version 2.12.0 (qemu-kvm-rhev-2.12.0-23.el7)
Copyright (c) 2003-2017 Fabrice Bellard and the QEMU Project developers

# qemu-img bench -c 1000000 -S 512M test.qcow2
Sending 1000000 read requests, 4096 bytes each, 64 in parallel (starting at offset 0, step size 536870912)
Run completed in 34.924 seconds.

Comment 5 Tingting Mao 2019-03-05 07:53:22 UTC

Tried to verify this issue with Scenario 2 steps:


Steps:

1. Mount tmpfs 
# mount tmpfs tmpfs_dir/ -t tmpfs -o size=50G

2. Create qcow2 data disk on tmpfs:
# qemu-img create -f qcow2 data.qcow2 35G
Formatting 'data.qcow2', fmt=qcow2 size=37580963840 cluster_size=65536 lazy_refcounts=off refcount_bits=16
# df -T data.qcow2
Filesystem     Type  1K-blocks  Used Available Use% Mounted on
tmpfs          tmpfs  52428800   196  52428604   1% /home/test/tmpfs_dir

3. Boot guest with the data disk
# /usr/libexec/qemu-kvm \
        -name 'guest-rhel7.6' \
        -machine pc \
        -nodefaults \
        -vga qxl \
        -device virtio-blk-pci,id=virtio_blk_pci0,drive=my_file,bus=pci.0,addr=05,bootindex=0 \
        -blockdev driver=raw,cache.direct=off,cache.no-flush=on,node-name=my_file,file.driver=file,file.filename=base.img \
        -device virtio-blk-pci,id=virtio_blk_pci1,drive=my_file1,bus=pci.0,addr=06 \
        -blockdev driver=qcow2,cache.direct=off,cache.no-flush=off,node-name=my_file1,file.driver=file,file.filename=/home/test/tmpfs_dir/data.qcow2 \
        -vnc :0 \
        -monitor stdio \
        -m 4096 \
        -smp 8 \
        -device virtio-net-pci,mac=9a:b5:b6:b1:b2:b3,id=idMmq1jH,vectors=4,netdev=idxgXAlm,bus=pci.0,addr=0x9  \
        -netdev tap,id=idxgXAlm \
        -chardev socket,id=qmp_id_qmpmonitor1,path=/var/tmp/timao/monitor-qmpmonitor1-20180220-094308-h9I6hRsI,server,nowait \
        -mon chardev=qmp_id_qmpmonitor1,mode=control  \

4. Allocated ‘0’ to the data disk before i/o test
# dd if=/dev/zero of=/dev/vdb
dd: writing to ‘/dev/vdb’: No space left on device
73400321+0 records in
73400320+0 records out
37580963840 bytes (38 GB) copied, 585.097 s, 64.2 MB/s

5. Compare i/o performance

In ‘qemu-kvm-rhev-2.12.0-24.el7’

# fio --filename=/dev/vdb --direct=1 --rw=randread --bs=8K --name=my_test --iodepth=1 --ioengine=libaio --size=30G
my_test: (g=0): rw=randread, bs=(R) 8192B-8192B, (W) 8192B-8192B, (T) 8192B-8192B, ioengine=libaio, iodepth=1
fio-3.1
Starting 1 process
Jobs: 1 (f=1): [r(1)][100.0%][r=43.5MiB/s,w=0KiB/s][r=5567,w=0 IOPS][eta 00m:00s]
my_test: (groupid=0, jobs=1): err= 0: pid=4130: Tue Mar  5 01:00:45 2019
   read: IOPS=6618, BW=51.7MiB/s (54.2MB/s)(30.0GiB/594095msec)
    slat (usec): min=7, max=236, avg=10.87, stdev= 4.69
    clat (usec): min=15, max=215180, avg=133.66, stdev=1669.06
     lat (usec): min=40, max=215191, avg=146.06, stdev=1669.36
    clat percentiles (usec):
     |  1.00th=[   38],  5.00th=[   47], 10.00th=[   48], 20.00th=[   51],
     | 30.00th=[   55], 40.00th=[   58], 50.00th=[   62], 60.00th=[   69],
     | 70.00th=[   86], 80.00th=[  116], 90.00th=[  178], 95.00th=[  208],
     | 99.00th=[  289], 99.50th=[  326], 99.90th=[ 6259], 99.95th=[26608],
     | 99.99th=[90702]
   bw (  KiB/s): min=  816, max=122512, per=99.99%, avg=52944.09, stdev=13019.07, samples=1188
   iops        : min=  102, max=15314, avg=6617.98, stdev=1627.38, samples=1188
  lat (usec)   : 20=0.01%, 50=17.47%, 100=58.40%, 250=21.86%, 500=1.86%
  lat (usec)   : 750=0.01%, 1000=0.01%
  lat (msec)   : 2=0.07%, 4=0.12%, 10=0.13%, 20=0.01%, 50=0.02%
  lat (msec)   : 100=0.02%, 250=0.01%
  cpu          : usr=4.75%, sys=12.23%, ctx=3932193, majf=0, minf=32
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     submit    : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     complete  : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     issued rwt: total=3932160,0,0, short=0,0,0, dropped=0,0,0
     latency   : target=0, window=0, percentile=100.00%, depth=1

Run status group 0 (all jobs):
   READ: bw=51.7MiB/s (54.2MB/s), 51.7MiB/s-51.7MiB/s (54.2MB/s-54.2MB/s), io=30.0GiB (32.2GB), run=594095-594095msec

Disk stats (read/write):
  vdb: ios=3930673/0, merge=0/0, ticks=533479/0, in_queue=532555, util=89.73%

# fio --filename=/dev/vdb --direct=1 --rw=randwrite --bs=8K --name=my_test --iodepth=1 --ioengine=libaio --size=30G
my_test: (g=0): rw=randwrite, bs=(R) 8192B-8192B, (W) 8192B-8192B, (T) 8192B-8192B, ioengine=libaio, iodepth=1
fio-3.1
Starting 1 process
Jobs: 1 (f=1): [w(1)][100.0%][r=0KiB/s,w=45.6MiB/s][r=0,w=5836 IOPS][eta 00m:00s]
my_test: (groupid=0, jobs=1): err= 0: pid=4154: Tue Mar  5 01:11:24 2019
  write: IOPS=6519, BW=50.9MiB/s (53.4MB/s)(30.0GiB/603165msec)
    slat (nsec): min=7870, max=93628, avg=11305.07, stdev=4788.60
    clat (usec): min=8, max=255313, avg=135.47, stdev=1673.93
     lat (usec): min=38, max=255323, avg=148.28, stdev=1674.25
    clat percentiles (usec):
     |  1.00th=[   38],  5.00th=[   47], 10.00th=[   48], 20.00th=[   51],
     | 30.00th=[   55], 40.00th=[   57], 50.00th=[   62], 60.00th=[   69],
     | 70.00th=[   86], 80.00th=[  117], 90.00th=[  176], 95.00th=[  206],
     | 99.00th=[  293], 99.50th=[  330], 99.90th=[ 6325], 99.95th=[28443],
     | 99.99th=[89654]
   bw (  KiB/s): min=10960, max=130352, per=99.96%, avg=52134.71, stdev=12311.13, samples=1206
   iops        : min= 1370, max=16294, avg=6516.80, stdev=1538.89, samples=1206
  lat (usec)   : 10=0.01%, 20=0.01%, 50=18.58%, 100=56.74%, 250=22.34%
  lat (usec)   : 500=1.92%, 750=0.01%, 1000=0.01%
  lat (msec)   : 2=0.07%, 4=0.12%, 10=0.14%, 20=0.01%, 50=0.03%
  lat (msec)   : 100=0.03%, 250=0.01%, 500=0.01%
  cpu          : usr=5.01%, sys=11.81%, ctx=3932203, majf=0, minf=27
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     submit    : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     complete  : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     issued rwt: total=0,3932160,0, short=0,0,0, dropped=0,0,0
     latency   : target=0, window=0, percentile=100.00%, depth=1

Run status group 0 (all jobs):
  WRITE: bw=50.9MiB/s (53.4MB/s), 50.9MiB/s-50.9MiB/s (53.4MB/s-53.4MB/s), io=30.0GiB (32.2GB), run=603165-603165msec

Disk stats (read/write):
  vdb: ios=42/3931609, merge=0/0, ticks=9/542410, in_queue=541453, util=89.87%


# fio --filename=/dev/vdb --direct=1 --rw=randrw --bs=8K --name=my_test --iodepth=1 --ioengine=libaio --size=30G
my_test: (g=0): rw=randrw, bs=(R) 8192B-8192B, (W) 8192B-8192B, (T) 8192B-8192B, ioengine=libaio, iodepth=1
fio-3.1
Starting 1 process
Jobs: 1 (f=1): [m(1)][100.0%][r=23.0MiB/s,w=24.0MiB/s][r=3069,w=3074 IOPS][eta 00m:00s]
my_test: (groupid=0, jobs=1): err= 0: pid=4165: Tue Mar  5 01:21:38 2019
   read: IOPS=3300, BW=25.8MiB/s (27.0MB/s)(15.0GiB/596094msec)
    slat (nsec): min=7583, max=74855, avg=10906.44, stdev=4881.25
    clat (usec): min=8, max=239129, avg=132.62, stdev=1696.87
     lat (usec): min=40, max=239148, avg=145.10, stdev=1697.19
    clat percentiles (usec):
     |  1.00th=[   37],  5.00th=[   44], 10.00th=[   46], 20.00th=[   48],
     | 30.00th=[   51], 40.00th=[   53], 50.00th=[   57], 60.00th=[   63],
     | 70.00th=[   76], 80.00th=[   97], 90.00th=[  174], 95.00th=[  196],
     | 99.00th=[  277], 99.50th=[  693], 99.90th=[ 6456], 99.95th=[30540],
     | 99.99th=[89654]
   bw (  KiB/s): min= 6944, max=64208, per=99.97%, avg=26392.41, stdev=6280.53, samples=1192
   iops        : min=  868, max= 8026, avg=3299.01, stdev=785.06, samples=1192
  write: IOPS=3296, BW=25.8MiB/s (27.0MB/s)(14.0GiB/596094msec)
    slat (nsec): min=7672, max=81491, avg=11840.27, stdev=4942.73
    clat (usec): min=25, max=231637, avg=134.17, stdev=1701.12
     lat (usec): min=38, max=231667, avg=147.59, stdev=1701.45
    clat percentiles (usec):
     |  1.00th=[   37],  5.00th=[   45], 10.00th=[   46], 20.00th=[   49],
     | 30.00th=[   52], 40.00th=[   55], 50.00th=[   58], 60.00th=[   64],
     | 70.00th=[   78], 80.00th=[   99], 90.00th=[  176], 95.00th=[  198],
     | 99.00th=[  281], 99.50th=[  553], 99.90th=[ 6587], 99.95th=[32637],
     | 99.99th=[90702]
   bw (  KiB/s): min= 7712, max=63104, per=99.97%, avg=26363.52, stdev=6265.38, samples=1192
   iops        : min=  964, max= 7888, avg=3295.39, stdev=783.17, samples=1192
  lat (usec)   : 10=0.01%, 20=0.01%, 50=25.81%, 100=54.93%, 250=17.48%
  lat (usec)   : 500=1.27%, 750=0.01%, 1000=0.01%
  lat (msec)   : 2=0.08%, 4=0.15%, 10=0.17%, 20=0.01%, 50=0.03%
  lat (msec)   : 100=0.03%, 250=0.01%
  cpu          : usr=5.38%, sys=12.32%, ctx=3932192, majf=0, minf=28
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     submit    : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     complete  : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     issued rwt: total=1967169,1964991,0, short=0,0,0, dropped=0,0,0
     latency   : target=0, window=0, percentile=100.00%, depth=1

Run status group 0 (all jobs):
   READ: bw=25.8MiB/s (27.0MB/s), 25.8MiB/s-25.8MiB/s (27.0MB/s-27.0MB/s), io=15.0GiB (16.1GB), run=596094-596094msec
  WRITE: bw=25.8MiB/s (27.0MB/s), 25.8MiB/s-25.8MiB/s (27.0MB/s-27.0MB/s), io=14.0GiB (16.1GB), run=596094-596094msec

Disk stats (read/write):
  vdb: ios=1966019/1963801, merge=0/0, ticks=262610/266141, in_queue=527877, util=88.71%


In ‘qemu-kvm-rhev-2.12.0-18.el7’

# fio --filename=/dev/vdb --direct=1 --rw=randrw --bs=8K --name=my_test --iodepth=1 --ioengine=libaio --size=30G
my_test: (g=0): rw=randrw, bs=(R) 8192B-8192B, (W) 8192B-8192B, (T) 8192B-8192B, ioengine=libaio, iodepth=1
fio-3.1
Starting 1 process
Jobs: 1 (f=1): [m(1)][99.9%][r=23.6MiB/s,w=23.0MiB/s][r=3020,w=2946 IOPS][eta 00m:01s]
my_test: (groupid=0, jobs=1): err= 0: pid=4138: Tue Mar  5 01:45:04 2019
   read: IOPS=2444, BW=19.1MiB/s (20.0MB/s)(15.0GiB/804710msec)
    slat (nsec): min=7940, max=93459, avg=12149.58, stdev=5559.17
    clat (usec): min=18, max=280789, avg=184.51, stdev=1795.43
     lat (usec): min=43, max=280799, avg=198.36, stdev=1795.77
    clat percentiles (usec):
     |  1.00th=[   47],  5.00th=[   57], 10.00th=[   66], 20.00th=[   86],
     | 30.00th=[  101], 40.00th=[  110], 50.00th=[  117], 60.00th=[  126],
     | 70.00th=[  145], 80.00th=[  180], 90.00th=[  233], 95.00th=[  269],
     | 99.00th=[  351], 99.50th=[  404], 99.90th=[ 6325], 99.95th=[27395],
     | 99.99th=[96994]
   bw (  KiB/s): min=  256, max=38672, per=99.97%, avg=19549.83, stdev=5403.15, samples=1609
   iops        : min=   32, max= 4834, avg=2443.70, stdev=675.39, samples=1609
  write: IOPS=2441, BW=19.1MiB/s (20.0MB/s)(14.0GiB/804710msec)
    slat (usec): min=8, max=106, avg=13.01, stdev= 5.63
    clat (usec): min=27, max=380480, avg=184.82, stdev=1763.46
     lat (usec): min=44, max=380518, avg=199.53, stdev=1763.79
    clat percentiles (usec):
     |  1.00th=[   48],  5.00th=[   58], 10.00th=[   67], 20.00th=[   88],
     | 30.00th=[  102], 40.00th=[  111], 50.00th=[  118], 60.00th=[  128],
     | 70.00th=[  147], 80.00th=[  182], 90.00th=[  235], 95.00th=[  269],
     | 99.00th=[  351], 99.50th=[  404], 99.90th=[ 6325], 99.95th=[26870],
     | 99.99th=[95945]
   bw (  KiB/s): min=  320, max=39280, per=99.97%, avg=19527.94, stdev=5399.53, samples=1609
   iops        : min=   40, max= 4910, avg=2440.96, stdev=674.94, samples=1609
  lat (usec)   : 20=0.01%, 50=2.17%, 100=26.66%, 250=64.23%, 500=6.50%
  lat (usec)   : 750=0.01%, 1000=0.01%
  lat (msec)   : 2=0.07%, 4=0.13%, 10=0.15%, 20=0.01%, 50=0.02%
  lat (msec)   : 100=0.02%, 250=0.01%, 500=0.01%
  cpu          : usr=4.50%, sys=9.77%, ctx=3932203, majf=0, minf=28
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     submit    : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     complete  : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     issued rwt: total=1967169,1964991,0, short=0,0,0, dropped=0,0,0
     latency   : target=0, window=0, percentile=100.00%, depth=1

Run status group 0 (all jobs):
   READ: bw=19.1MiB/s (20.0MB/s), 19.1MiB/s-19.1MiB/s (20.0MB/s-20.0MB/s), io=15.0GiB (16.1GB), run=804710-804710msec
  WRITE: bw=19.1MiB/s (20.0MB/s), 19.1MiB/s-19.1MiB/s (20.0MB/s-20.0MB/s), io=14.0GiB (16.1GB), run=804710-804710msec

Disk stats (read/write):
  vdb: ios=1966547/1964354, merge=0/0, ticks=367448/367390, in_queue=733713, util=91.26%


# fio --filename=/dev/vdb --direct=1 --rw=randwrite --bs=8K --name=my_test --iodepth=1 --ioengine=libaio --size=30G
my_test: (g=0): rw=randwrite, bs=(R) 8192B-8192B, (W) 8192B-8192B, (T) 8192B-8192B, ioengine=libaio, iodepth=1
fio-3.1
Starting 1 process
Jobs: 1 (f=1): [w(1)][100.0%][r=0KiB/s,w=38.2MiB/s][r=0,w=4888 IOPS][eta 00m:00s]
my_test: (groupid=0, jobs=1): err= 0: pid=4152: Tue Mar  5 01:59:07 2019
  write: IOPS=4848, BW=37.9MiB/s (39.7MB/s)(30.0GiB/811059msec)
    slat (usec): min=7, max=146, avg=12.40, stdev= 5.57
    clat (usec): min=24, max=246605, avg=186.42, stdev=1708.14
     lat (usec): min=42, max=246615, avg=200.55, stdev=1708.51
    clat percentiles (usec):
     |  1.00th=[   47],  5.00th=[   56], 10.00th=[   67], 20.00th=[   87],
     | 30.00th=[  101], 40.00th=[  110], 50.00th=[  117], 60.00th=[  127],
     | 70.00th=[  145], 80.00th=[  182], 90.00th=[  233], 95.00th=[  269],
     | 99.00th=[  355], 99.50th=[  429], 99.90th=[ 6521], 99.95th=[32637],
     | 99.99th=[90702]
   bw (  KiB/s): min= 5344, max=83200, per=99.99%, avg=38782.54, stdev=10403.23, samples=1622
   iops        : min=  668, max=10400, avg=4847.79, stdev=1300.41, samples=1622
  lat (usec)   : 50=2.55%, 100=27.00%, 250=63.57%, 500=6.40%, 750=0.02%
  lat (usec)   : 1000=0.01%
  lat (msec)   : 2=0.08%, 4=0.14%, 10=0.17%, 20=0.01%, 50=0.03%
  lat (msec)   : 100=0.03%, 250=0.01%
  cpu          : usr=4.20%, sys=9.98%, ctx=3932200, majf=0, minf=27
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     submit    : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     complete  : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     issued rwt: total=0,3932160,0, short=0,0,0, dropped=0,0,0
     latency   : target=0, window=0, percentile=100.00%, depth=1

Run status group 0 (all jobs):
  WRITE: bw=37.9MiB/s (39.7MB/s), 37.9MiB/s-37.9MiB/s (39.7MB/s-39.7MB/s), io=30.0GiB (32.2GB), run=811059-811059msec

Disk stats (read/write):
  vdb: ios=40/3929926, merge=0/0, ticks=8/740943, in_queue=739759, util=91.32%

# fio --filename=/dev/vdb --direct=1 --rw=randread --bs=8K --name=my_test --iodepth=1 --ioengine=libaio --size=30G
my_test: (g=0): rw=randread, bs=(R) 8192B-8192B, (W) 8192B-8192B, (T) 8192B-8192B, ioengine=libaio, iodepth=1
fio-3.1
Starting 1 process
Jobs: 1 (f=1): [r(1)][100.0%][r=47.9MiB/s,w=0KiB/s][r=6130,w=0 IOPS][eta 00m:00s]
my_test: (groupid=0, jobs=1): err= 0: pid=4158: Tue Mar  5 02:12:23 2019
   read: IOPS=5058, BW=39.5MiB/s (41.4MB/s)(30.0GiB/777271msec)
    slat (usec): min=7, max=277, avg=11.75, stdev= 5.30
    clat (usec): min=15, max=260765, avg=178.85, stdev=1747.29
     lat (usec): min=41, max=260775, avg=192.28, stdev=1747.63
    clat percentiles (usec):
     |  1.00th=[   40],  5.00th=[   51], 10.00th=[   62], 20.00th=[   73],
     | 30.00th=[   91], 40.00th=[  104], 50.00th=[  113], 60.00th=[  123],
     | 70.00th=[  139], 80.00th=[  174], 90.00th=[  225], 95.00th=[  262],
     | 99.00th=[  347], 99.50th=[  408], 99.90th=[ 6456], 99.95th=[30016],
     | 99.99th=[91751]
   bw (  KiB/s): min=  384, max=93520, per=99.99%, avg=40468.07, stdev=12033.41, samples=1554
   iops        : min=   48, max=11690, avg=5058.47, stdev=1504.18, samples=1554
  lat (usec)   : 20=0.01%, 50=4.80%, 100=32.18%, 250=56.92%, 500=5.63%
  lat (usec)   : 750=0.01%, 1000=0.01%
  lat (msec)   : 2=0.07%, 4=0.13%, 10=0.16%, 20=0.01%, 50=0.03%
  lat (msec)   : 100=0.03%, 250=0.01%, 500=0.01%
  cpu          : usr=4.17%, sys=9.89%, ctx=3932194, majf=0, minf=32
  IO depths    : 1=100.0%, 2=0.0%, 4=0.0%, 8=0.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     submit    : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     complete  : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     issued rwt: total=3932160,0,0, short=0,0,0, dropped=0,0,0
     latency   : target=0, window=0, percentile=100.00%, depth=1

Run status group 0 (all jobs):
   READ: bw=39.5MiB/s (41.4MB/s), 39.5MiB/s-39.5MiB/s (41.4MB/s-41.4MB/s), io=30.0GiB (32.2GB), run=777271-777271msec

Disk stats (read/write):
  vdb: ios=3930526/0, merge=0/0, ticks=710623/0, in_queue=709498, util=91.39%

Comment 11 errata-xmlrpc 2019-08-22 09:19:58 UTC

Since the problem described in this bug report should be
resolved in a recent advisory, it has been closed with a
resolution of ERRATA.

For information on the advisory, and where to find the updated
files, follow the link below.

If the solution does not work for you, open a new bug report.

https://access.redhat.com/errata/RHSA-2019:2553

Note You need to log in before you can comment on or make changes to this bug.