[Bugs] [Bug 1408809] [Perf] : significant Performance regression seen with disperse volume when compared with 3.1.3

[bugzilla at redhat.com]

https://bugzilla.redhat.com/show_bug.cgi?id=1408809

Pranith Kumar K <pkarampu at redhat.com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |pkarampu at redhat.com



--- Comment #8 from Pranith Kumar K <pkarampu at redhat.com> ---
recursive dir creation

./ec-create.sh && gluster v profile ec2 start && cd /mnt/ec2 && for i in
{1..100}; do mkdir $i && cd $i; done && gluster v profile ec2 info

v3.8.8
Interval 0 Stats:
 %-latency   Avg-latency   Min-Latency   Max-Latency   No. of calls         Fop
 ---------   -----------   -----------   -----------   ------------        ----
      0.00       0.00 us       0.00 us       0.00 us              2  RELEASEDIR
      0.04      30.50 us      29.00 us      32.00 us              2      STATFS
      6.30      86.02 us      46.00 us     146.00 us            100    SETXATTR
      7.08      96.61 us      41.00 us     296.00 us            100     SETATTR
      8.49     115.90 us      70.00 us     215.00 us            100     XATTROP
     12.67      34.58 us      16.00 us     259.00 us            500     INODELK
     31.15     138.93 us      52.00 us     642.00 us            306      LOOKUP
     34.27     467.70 us     266.00 us    1190.00 us            100       MKDIR

Master
Interval 0 Stats:
 %-latency   Avg-latency   Min-Latency   Max-Latency   No. of calls         Fop
 ---------   -----------   -----------   -----------   ------------        ----
      0.00       0.00 us       0.00 us       0.00 us              1  RELEASEDIR
      0.02      24.00 us      24.00 us      24.00 us              1      STATFS
      6.12      84.02 us      48.00 us     158.00 us            100    SETXATTR
      6.73      92.41 us      46.00 us     215.00 us            100     SETATTR
     12.39      34.02 us      16.00 us     640.00 us            500     INODELK
     15.24     104.61 us      55.00 us     236.00 us            200     XATTROP
     27.91     125.20 us      48.00 us     331.00 us            306      LOOKUP
     31.58     433.43 us     241.00 us     938.00 us            100       MKDIR

With Modified idea of Xavi:
Interval 0 Stats:
 %-latency   Avg-latency   Min-Latency   Max-Latency   No. of calls         Fop
 ---------   -----------   -----------   -----------   ------------        ----
      0.10      72.50 us      24.00 us     121.00 us              2      STATFS
      4.87      73.98 us      37.00 us     230.00 us            100     XATTROP
      6.75     102.38 us      59.00 us     220.00 us            100    SETXATTR
      7.36     111.63 us      53.00 us     305.00 us            100     SETATTR
     13.68      41.53 us      17.00 us     284.00 us            500     INODELK
     33.54     509.02 us     280.00 us    1080.00 us            100       MKDIR
     33.70     167.15 us      51.00 us    3137.00 us            306      LOOKUP


Xattrops are the ones we are worried about as you can see, it came back to 100
like it was before :-).

-- 
You are receiving this mail because:
You are on the CC list for the bug.
Unsubscribe from this bug https://bugzilla.redhat.com/token.cgi?t=ywIIbPmDs5&a=cc_unsubscribe