[Gluster-users] Performance Issue with Webserver

[Burnash, James]

Hi Jenn,

You may not have seen the posts, but small files do not, as a general rule, do well on parallel file systems. There are numerous posts on this subject on this list concerning this subject, and the Gluster developers have devoted a good bit of energy into trying to address this, but ... this is not a general purpose file system. It is designed to be efficient with large(r) file sizes.

Throughput is (hopefully) limited by the bandwidth available - but latency comes is a factor as well in determining throughput.

Others on this list can give you much better details.

James



DISCLAIMER:
This e-mail, and any attachments thereto, is intended only for use by the addressee(s) named herein and may contain legally privileged and/or confidential information. If you are not the intended recipient of this e-mail, you are hereby notified that any dissemination, distribution or copying of this e-mail, and any attachments thereto, is strictly prohibited. If you have received this in error, please immediately notify me and permanently delete the original and any copy of any e-mail and any printout thereof. E-mail transmission cannot be guaranteed to be secure or error-free. The sender therefore does not accept liability for any errors or omissions in the contents of this message which arise as a result of e-mail transmission.
NOTICE REGARDING PRIVACY AND CONFIDENTIALITY Knight Capital Group may, at its discretion, monitor and review the content of all e-mail communications. http://www.knight.com
-----Original Message-----
From: gluster-users-bounces at gluster.org [mailto:gluster-users-bounces at gluster.org] On Behalf Of Jenn Fountain
Sent: Tuesday, May 04, 2010 1:32 PM
To: gluster-users at gluster.org
Subject: [Gluster-users] Performance Issue with Webserver

We are running our webapp on a gluster mount.  We are finding that performance is a lot slower than local disk.  We expected it to be slower but not this much slower.  So, I am looking to you for some guidance on what to do.  IE: Not run off the gluster mount or change config settings, etc.

Here are some numbers on performance:

Gluster Mount html:

Document Path:          /tmp/test.html
Document Length:        17 bytes

Concurrency Level:      1
Time taken for tests:   0.269 seconds
Complete requests:      1
Failed requests:        0
Write errors:           0
Total transferred:      302 bytes
HTML transferred:       17 bytes
Requests per second:    3.72 [#/sec] (mean)
Time per request:       268.621 [ms] (mean)
Time per request:       268.621 [ms] (mean, across all concurrent requests)
Transfer rate:          1.10 [Kbytes/sec] received

Connection Times (ms)
              min  mean[+/-sd] median   max
Connect:       16   16   0.0     16      16
Processing:   253  253   0.0    253     253
Waiting:      253  253   0.0    253     253
Total:        269  269   0.0    269     269


Local disk html:

Document Path:          /tmp2/test.html
Document Length:        16 bytes

Concurrency Level:      1
Time taken for tests:   0.035 seconds
Complete requests:      1
Failed requests:        0
Write errors:           0
Total transferred:      301 bytes
HTML transferred:       16 bytes
Requests per second:    28.24 [#/sec] (mean)
Time per request:       35.409 [ms] (mean)
Time per request:       35.409 [ms] (mean, across all concurrent requests)
Transfer rate:          8.30 [Kbytes/sec] received

Connection Times (ms)
              min  mean[+/-sd] median   max
Connect:       20   20   0.0     20      20
Processing:    16   16   0.0     16      16
Waiting:       16   16   0.0     16      16
Total:         35   35   0.0     35      35


Here is my client config:
## file auto generated by ./glusterfs-volgen (mount.vol)
# Cmd line:
# $ ./glusterfs-volgen -n live-glusterfs-001 -r 1 xxx:/.glusterfs/sb01 xxx:/.glusterfs/sb01 xxx:/.glusterfs/sb01

# RAID 1
# TRANSPORT-TYPE tcp
volume xxx-1
    type protocol/client
    option transport-type tcp
    option remote-host xxx
    option transport.socket.nodelay on
    option transport.remote-port 6996
    option remote-subvolume brick1
end-volume

volume xxx-1
    type protocol/client
    option transport-type tcp
    option remote-host xxx
    option transport.socket.nodelay on
    option transport.remote-port 6996
    option remote-subvolume brick1
end-volume

volume xxx-1
    type protocol/client
    option transport-type tcp
    option remote-host xxx
    option transport.socket.nodelay on
    option transport.remote-port 6996
    option remote-subvolume brick1
end-volume

volume mirror-0
    type cluster/replicate
    subvolumes xxx-1 xxx-1 xxx-1
end-volume

#volume writebehind
#    type performance/write-behind
#    option cache-size 4MB
#    subvolumes mirror-0
#end-volume

volume readahead
    type performance/read-ahead
    option page-count 4
    subvolumes mirror-0
    #subvolumes writebehind
end-volume

volume iocache
    type performance/io-cache
    option cache-size 1GB
    option cache-timeout 1
    subvolumes readahead
end-volume

volume quickread
    type performance/quick-read
    option cache-timeout 1
    option max-file-size 64kB
    subvolumes iocache
end-volume

volume statprefetch
    type performance/stat-prefetch
    subvolumes quickread
end-volume

volume iothreads
    type performance/io-threads
    option thread-count 16
    subvolumes statprefetch
end-volume

If you need any other information, let me know. Thank you in advance.

-Jenn





_______________________________________________
Gluster-users mailing list
Gluster-users at gluster.org
http://gluster.org/cgi-bin/mailman/listinfo/gluster-users