STAR/RCF resource plans

 

 

General fund

 The level of funding planned for 2008 was:

  • According to the RHIC mid-term strategic planning for 2006-2011 document, the budget for 2008 was projected to be 2140 k$ (table 7-2) with a note that and additional 2 M $ additional would be needed between FY08 and FY10 (to accommodate for network infrastructure, storage robotics and silo expansion and general infrastructure changes)
  • The budget planned for FY08 in FY07 was 2.5 M$, accounting for recovering by 0.5 M$ already present past years shortfalls
  • The current budget available is 1.7 M$ with a 1.5 M$ usable base fund.

External funds

Following previous years "outsourcing" of funds approach, an note was sent to the STAR collaboration (Subject: RCF requirements & purchase) on 3/31/2008 12:18. The pricing offered was 4.2 $/GB i.e. 4.3 k$/TB of usable space. Based on the 2007 RCF requirement learning experience (pricing was based on vendor's total space rather than usable), the price was firmed, fixed and guaranteed as "not higher than 4.2 $/GB" by the facility director Micheal Ernst at the March 27th liaison meeting.

The institutions external fund profile for 2008 is as follows:

 

STAR external funds
Institution Paying account TB requested Price
UCLA UCLA 1 4300.8
rice rice 1 4300.8
LBNL LBNL 4 17203.2
VECC BNL 1 4300.8
UKY UKY 1 4300.8
Totals 8 34406.4

Penn State university provided (late) funds for 1 TB worth.

 

*** WORK IN PROGRESS ***

Requirements 

The requirements for FY08 are determined based on 

The initial STAR requirements provided for the RHIC mid-term strategic plan can be found here

 

STAR resource requirements FY05-FY12STAR resource requirements FY05-FY12

 

The initial raw data projected was 870 TB (+310 TB).

The RAW data volume taken by STAR in FY08 (shorter run) is given by the HPSS usage (RAW COS) as showed below:


A total of 165 TB was accumulated far below expected data projections by a factor of 2. The run was however declared as meeting (to exceeding) goals comparing to the STAR initial BUR.

Some notes:

  • STAR made extensive use this year of fast triggers
     
  • Based on those numbers, we assumed that
    • The CPU requirements of 1532 kSI2k (+1071 kSI2k) would equally scale, hence a minimal requirement of +215 kSI2K should be accounted for
    • A bigger pool of distributed storage would allow for more flexibility: it would allow for re-considering multiple (if not most of) the datasets to be placed on disk in Xrootd pool + it would allow (modulo expanding beyond the 1.2 replication baseline) to better load balance the resources.
    • The distributed disk planing accounted for 365 TB of storage (1 pass production, small fraction of past results on disk). We targeted 800 TB of disk space (about twice the initial amount).

Allocations within total budgets

scenario B = scenario A + external funds

 

Experiment Parameters STAR STAR
  Senario A Senario B.
Sustained d-Au Data Rate (MB/sec) 70 70
Sustained p-p Data Rate (MB/sec) 50 50
Experiment Efficiency (d-Au) 90% 90%
Experiment Efficiency (p-p) 90% 90%
Estimated d-Au Raw Data Volume (TB) 130.8 130.8
Estimated p-p Raw Data Volume (TB) 41.5 41.5
Estimated Raw Data Volume (TB) 172.3 172.3
<d-AU Event Size> (MB) 1 1
<p-p Event Size> (MB) 0.4 0.4
Estimated Number of Raw d-Au Events 137,168,640 137,168,640
Estimated Number of Raw p-p Events 108,864,000 108,864,000
d-AU Event Reconstruction Time (sec) 9 9
p-p Event Reconstruction Time (sec) 16 16
SI2000-sec/event d-Au 5202 5202
SI2000-sec/event p-p 9248 9248
CPU Required (kSI2000-sec) 1.7E+9 1.7E+9
CRS Farm Size if take 1 Yr. (kSI2k) 54.6 54.6
CRS Farm Size if take 6 Mo. (kSI2k) 109.1 109.1
     
Estimated Derived Data Vlume (TB) 200.0 200.0
Estimated CAS Farm Size (kSI2k) 400.0 400.0
     
Total Farm Size (1 Yr. CRS) (kSI2k) 454.6 454.6
Total Farm Size (6 Mo. CRS) (kSI2k) 509.1 509.1
     
Current Central Disk  (TB) 82 82
Current Distributed Disk (TB) 527.5 527.5
Current kSI2000 1819.4 1819.4
     
Central Disk to retire (TB) 0 0
# machines to retire form CAS 0 0
# machines to retire from CRS 128 128
Distributed disk to retire (TB) 27.00 27.00
CPU to retire (kSI2k) 120.00 120.00
     
Central Disk (TB) 49.00 57.00
     
Cost of Central Disk $205,721.60 $239,308.80
Cost of Servers to support Central Disk    
     
Compensation Disk entitled (TB) 0.00 0.00
Amount (up to entitlement) (TB) 0.00 0.00
Cost of Compensation Disk $0 $0
Remaining Funds $0 $0
     
Compensation count (1U, 4 GB below) 5 5
Compensation count (1U, 8 GB below) 0 0
CPU Cost $27,500 $27,500
Distributed Disk 27.8 27.8
kSI2k 114.5 114.5
     
     
# 2U, 8 cores, 5900 GB disk, 8 GB RAM 27 27
# 2U, 8 cores, 5900 GB disk, 16 GB RAM 0 0
CPU Cost $148,500 $148,500
Distrib. Disk on new machines (TB) 153.9 153.9
kSI2k new 618.2 618.2
Total Disk (TB) 813.2 821.2
Total CPU (kSI2000) 2432.1 2432.1
Total Cost $354,222 $387,809
Outside Funds Available $0 $34,406
Funds Available $355,000 $355,000

 

Post purchase actions

BlueArc disk layout before the new storage commissioning

 

Name

File System

Path

Hard Quota

Space allocated

Available Space

BlueArc Physical storage

star_institutions_bnl

STAR-FS01

/star_institution/bnl

3.50

16.50

19.00

BA01

star_institutions_emn

STAR-FS01

/star_institution/emn

1.60

star_institutions_iucf

STAR-FS01

/star_institution/iucf

0.80

star_institutions_ksu

STAR-FS01

/star_institution/ksu

0.80

star_institutions_lbl

STAR-FS01

/star_institution/lbl

9.80

star_data03

STAR-FS02

/star_data03

1.80

17.22

19.75

star_data04

STAR-FS02

/star_data04

1.00

star_data08

STAR-FS02

/star_data08

1.00

star_data09

STAR-FS02

/star_data09

1.00

star_data16

STAR-FS02

/star_data16

1.66

star_data25

STAR-FS02

/star_data25

0.83

star_data26

STAR-FS02

/star_data26

0.84

star_data31

STAR-FS02

/star_data31

0.83

star_data36

STAR-FS02

/star_data36

1.66

star_data46

STAR-FS02

/star_data46

6.60

star_data05

STAR-FS03

/star_data05

2.24

18.51

21.40

BA02

star_data13

STAR-FS03

/star_data13

1.79

star_data34

STAR-FS03

/star_data34

1.79

star_data35

STAR-FS03

/star_data35

1.79

star_data48

STAR-FS03

/star_data48

6.40

star_data53

STAR-FS03

/star_data53

1.50

star_data54

STAR-FS03

/star_data54

1.50

star_data55

STAR-FS03

/star_data55

1.50

star_data18

STAR-FS04

/star_data18

1.00

16.86

19.45

star_data19

STAR-FS04

/star_data19

0.80

star_data20

STAR-FS04

/star_data20

0.80

star_data21

STAR-FS04

/star_data21

0.80

star_data22

STAR-FS04

/star_data22

0.80

star_data27

STAR-FS04

/star_data27

0.80

star_data47

STAR-FS04

/star_data47

6.60

star_institutions_mit

STAR-FS04

/star_institutions/mit

0.96

star_institutions_ucla

STAR-FS04

/star_institutions/ucla

1.60

star_institutions_uta

STAR-FS04

/star_institutions/uta

0.80

star_institutions_vecc

STAR-FS04

/star_institutions/vecc

0.80

star_rcf

STAR-FS04

/star_rcf

1.10

star_emc

STAR-FS05

/star_emc

?

1.042

2.05

BA4

star_grid

STAR-FS05

/star_grid

0.05

star_scr2a

STAR-FS05

/star_scr2a

?

star_scr2b

STAR-FS05

/star_scr2b

?

star_starlib

STAR-FS05

/star_starlib

0.02

star_stsg

STAR-FS05

/star_stsg

?

star_svt

STAR-FS05

/star_svt

?

star_timelapse

STAR-FS05

/star_timelapse

?

star_tof

STAR-FS05

/star_tof

?

star_tpc

STAR-FS05

/star_tpc

?

star_tpctest

STAR-FS05

/star_tpctest

?

star_trg

STAR-FS05

/star_trg

?

star_trga

STAR-FS05

/star_trga

?

star_u

STAR-FS05

/star_u

0.97

star_xtp

STAR-FS05

/star_xtp

0.002

star_data01

STAR-FS06

/star_data01

0.83

14.94

16.90

star_data02

STAR-FS06

/star_data02

0.79

star_data06

STAR-FS06

/star_data06

0.79

star_data14

STAR-FS06

/star_data14

0.89

star_data15

STAR-FS06

/star_data15

0.89

star_data38

STAR-FS06

/star_data38

1.79

star_data39

STAR-FS06

/star_data39

1.79

star_data40

STAR-FS06

/star_data40

1.79

star_data41

STAR-FS06

/star_data41

1.79

star_data43

STAR-FS06

/star_data43

1.79

star_simu

STAR-FS06

/star_simu

1.80

star_data07

STAR-FS07

/star_data07

0.89

16.40

19.15

star_data10

STAR-FS07

/star_data10

0.89

star_data12

STAR-FS07

/star_data12

0.76

star_data17

STAR-FS07

/star_data17

0.89

star_data24

STAR-FS07

/star_data24

0.89

star_data28

STAR-FS07

/star_data28

0.89

star_data29

STAR-FS07

/star_data29

0.89

star_data30

STAR-FS07

/star_data30

0.89

star_data32

STAR-FS07

/star_data32

1.75

star_data33

STAR-FS07

/star_data33

0.89

star_data37

STAR-FS07

/star_data37

1.66

star_data42

STAR-FS07

/star_data42

1.66

star_data44

STAR-FS07

/star_data44

1.79

star_data45

STAR-FS07

/star_data45

1.66


Reshape proposal

 

 

 

 

Action effect (+/- impact in TB unit)

 

Action

FS01

FS02

FS03

FS04

FS05

FS06

FS07

SATA

2008/08/15

Move/backup data25, 26, 31, 36 to SATA

 

4.56

 

 

 

 

 

-4.56

2008/08/18

Drop 25, 26, 31, 36 from FS01 and expand on SATA to 5 TB

 

 

 

 

 

 

 

-15.84

2008/08/22

Shrink 46 to 5 TB, move to SATA and make it available at 5 TB

 

6.60

 

 

 

 

 

-5.00

 

 

 

 

 

 

 

 

 

 

2008/08/19

Move institutions/ksu and institutions/iucf to FS02

1.60

-1.60

 

 

 

 

 

 

2008/08/19

Expand ksu and iucf to 2 TB

 

-0.80

 

 

 

 

 

 

2008/08/22

Move institutions/bnl to FS02

3.50

-3.50

 

 

 

 

 

 

 

Expand bnl to 4 TB

 

-0.50

 

 

 

 

 

 

 

Expand lbl by 4.2 TB (i.e. 14 TB)

-4.20

 

 

 

 

 

 

 

 

Expand emn to 2 TB 

-0.40

 

 

 

 

 

 

 

 

Expand data03 to 2.5 TB

 

-0.70

 

 

 

 

 

 

 

Expand data04 to 2 TB

 

-1.00

 

 

 

 

 

 

 

Expand data08 to 2 TB

 

-1.00

 

 

 

 

 

 

 

Expand data16 to 2 TB

 

-0.34

 

 

 

 

 

 

 

Expand data09 to 2 TB

 

-1.00

 

 

 

 

 

 

Checkpoint

 

0.50

0.72

0.00

0.00

0.00

0.00

0.00

-25.40

 

Action

FS01

FS02

FS03

FS04

FS05

FS06

FS07

SATA

2008/08/22

Shrink data 48 to 5 TB,move to SATA

 

 

6.40

 

 

 

 

-5.00

 

Expand data05 to 3 TB

 

 

-0.76

 

 

 

 

 

 

Expand 13, 34, 35, 53, 54 and 55 to 2.5 TB

 

 

-5.13

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

2008/08/22

Shrink and move data47 to SATA

 

 

 

6.60

 

 

 

-5.00

 

Move 18,19, 20, 21 to SATA

 

 

 

3.40

 

 

 

-3.40

 

Expand data18, 19, 20, 21 to 2.5 TB

 

 

 

 

 

 

 

-6.60

 

Add to FS02 a institutions/uky at 1 TB

 

 

 

-1.00

 

 

 

 

 

Add to FS02 a institutions/psu at 1 TB

 

 

 

-1.00

 

 

 

 

 

Add to FS02 a institutions/rice at 1 TB

 

 

 

-1.00

 

 

 

 

 

Expand vecc to 2 TB

 

 

 

-1.20

 

 

 

 

 

Expand ucla to 3 TB

 

 

 

-1.40

 

 

 

 

 

Expand 22 and 27 to 1.5 TB

 

 

 

-1.40

 

 

 

 

 

Expand /star/rcf to 3 TB

 

 

 

-1.90

 

 

 

 

Checkpoint

 

0.50

0.72

0.51

1.10

0.00

0.00

0.00

-45.40

 

Action

FS01

FS02

FS03

FS04

FS05

FS06

FS07

SATA

 

Free (HPSS archive) emc, src2a, src2b, stsg, timelapse, tof

 

 

 

 

0.00

 

 

 

 

Free (HPSS archive) tpc, tpctest, trg, trga

 

 

 

 

0.00

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Move 40, 41, 43 to SATA

 

 

 

 

 

5.37

 

-5.37

 

Expand 01 to 2 TB

 

 

 

 

 

-1.17

 

 

 

Expand 02 to 2 TB

 

 

 

 

 

-1.21

 

 

 

Expand star_simu to 3 TB

 

 

 

 

 

-1.20

 

 

Checkpoint

 

0.50

0.72

0.51

1.10

0.00

1.79

0.00

-50.77


 


Missing information and progress records:

  • 2008/08/14 13:44 - Answer from the RCF as per the above plan being approved (and commented it seemed easy)
    • Two caveats: ETA cannot be provided until migration starts (one test example) to get a more accurate estimate
    • While virtualmount point are swapped between one storage pool to another, there may be a fluke in access (will need infomring institutions / production disk will be handled by hard-dismount)
       
  • 2008/08/14 13:42 - Sent an Email requesting infomration regarding disk manager and/or policies for PSU, UKY and RICE - Email sent to council rep and/or designated rep on August 14th 2008
    • Answer from UKY 2008/08/14 13:56 >> Disk space manager=Renee Fatemi, policy = MIT policy
    • Answer from PSU 2008/08/15 16:07 >> Policy is standard
       
  • 2008/08/18
    • Achieved actions marked in Italic + date
    • Date in Italic are ongoing actions
    • If two dates appear, the first is the start of the action and the second the end