Re: 10K vs 15k rpm for analytics

From: Pierre C
Subject: Re: 10K vs 15k rpm for analytics
Date: ,
Msg-id: op.u8zmftmjeorkce@localhost
(view: Whole thread, Raw)
In response to: Re: 10K vs 15k rpm for analytics  (Yeb Havinga)
List: pgsql-performance

Tree view

10K vs 15k rpm for analytics  (Francisco Reyes, )
 Re: 10K vs 15k rpm for analytics  (Yeb Havinga, )
  Re: 10K vs 15k rpm for analytics  (Greg Smith, )
   Re: 10K vs 15k rpm for analytics  (Yeb Havinga, )
    Re: 10K vs 15k rpm for analytics  ("Pierre C", )
  Re: 10K vs 15k rpm for analytics  (Dave Crooke, )
  Re: 10K vs 15k rpm for analytics  (Scott Marlowe, )
   Re: 10K vs 15k rpm for analytics  (Yeb Havinga, )
 Re: 10K vs 15k rpm for analytics  (Scott Marlowe, )
 Re: 10K vs 15k rpm for analytics  (, )
  Re: 10K vs 15k rpm for analytics  (Scott Marlowe, )
   Re: 10K vs 15k rpm for analytics  (Greg Smith, )
    Re: 10K vs 15k rpm for analytics  (Scott Marlowe, )
     Re: 10K vs 15k rpm for analytics  (Greg Smith, )
      Re: 10K vs 15k rpm for analytics  (Scott Marlowe, )
       Re: 10K vs 15k rpm for analytics  (Greg Smith, )
 Re: 10K vs 15k rpm for analytics  (Francisco Reyes, )
  Re: 10K vs 15k rpm for analytics  (Greg Smith, )
  Re: 10K vs 15k rpm for analytics  (Yeb Havinga, )
 Re: 10K vs 15k rpm for analytics  (Francisco Reyes, )
  Re: 10K vs 15k rpm for analytics  (Scott Marlowe, )
   Re: 10K vs 15k rpm for analytics  (, )
    Re: 10K vs 15k rpm for analytics  (Scott Carey, )
     Re: 10K vs 15k rpm for analytics  (Greg Smith, )
      Re: 10K vs 15k rpm for analytics  ("Pierre C", )
       Re: 10K vs 15k rpm for analytics  ("Ing. Marcos Ortiz Valmaseda", )
       Re: 10K vs 15k rpm for analytics  (, )
       Re: 10K vs 15k rpm for analytics  ("Kevin Grittner", )
       Re: 10K vs 15k rpm for analytics  (Michael Stone, )
      Re: 10K vs 15k rpm for analytics  (Scott Carey, )
       Re: 10K vs 15k rpm for analytics  (Scott Carey, )
       Re: 10K vs 15k rpm for analytics  (Greg Smith, )
 Re: 10K vs 15k rpm for analytics  (Francisco Reyes, )
  Re: 10K vs 15k rpm for analytics  (Scott Carey, )
 Re: 10K vs 15k rpm for analytics  (Francisco Reyes, )
 Re: 10K vs 15k rpm for analytics  (Francisco Reyes, )
 Re: 10K vs 15k rpm for analytics  (Francisco Reyes, )
 Re: 10K vs 15k rpm for analytics  (Francisco Reyes, )
 Re: 10K vs 15k rpm for analytics  (Francisco Reyes, )
 Re: 10K vs 15k rpm for analytics  (Greg Smith, )
  Re: 10K vs 15k rpm for analytics  (Scott Marlowe, )
 Re: 10K vs 15k rpm for analytics  (Francisco Reyes, )
  Re: 10K vs 15k rpm for analytics  (Scott Marlowe, )
  Re: 10K vs 15k rpm for analytics  (Greg Smith, )
 Re: 10K vs 15k rpm for analytics  (Francisco Reyes, )
  Re: 10K vs 15k rpm for analytics  (Yeb Havinga, )
 Re: 10K vs 15k rpm for analytics  (Scott Marlowe, )

>>> With 24 drives it'll probably be the controller that is the limiting
>>> factor of bandwidth. Our HP SAN controller with 28 15K drives delivers
>>> 170MB/s at maximum with raid 0 and about 155MB/s with raid 1+0.

I get about 150-200 MB/s on .... a linux software RAID of 3 cheap Samsung
SATA 1TB drives (which is my home multimedia server)...
IOPS would be of course horrendous, that's RAID-5, but that's not the
point here.

For raw sequential throughput, dumb drives with dumb software raid can be
pretty fast, IF each drive has a dedicated channel (SATA ensures this) and
the controller is on a fast PCIexpress (in my case, chipset SATA
controller).

I don't suggest you use software RAID with cheap consumer drives, just
that any expensive setup that doesn't deliver MUCH more performance that
is useful to you (ie in your case sequential IO) maybe isn't worth the
extra price... There are many bottlenecks...


pgsql-performance by date:

From: "Pierre C"
Date:
Subject: Re: 10K vs 15k rpm for analytics
From: Francisco Reyes
Date:
Subject: Re: 10K vs 15k rpm for analytics