Understanding Storage Performance .pdf
Original filename: Understanding Storage Performance.pdf
Author: Wangjiaxin (Jacky, Dorado)
This PDF 1.7 document has been generated by WPS 文字 / , and has been sent on pdf-archive.com on 30/11/2018 at 11:41, from IP address 45.35.x.x.
The current document download page has been viewed 102 times.
File size: 204 KB (2 pages).
Privacy: public file
Download original PDF file
Understanding Storage Performance
Excellent performance is an everlasting pursuit for storage system vendors. Vendors use
different performance parameters to promote product performance, such as 100% cache
hit ratio (maximum IOPS), 256 KB I/O bandwidth, and 100% write latency. All vendors
want you to believe that they can provide the highest performance and can easily handle
business pressure during peak hours. You may want to know how to identify all-flash
arrays that truly have high performance from amongst a huge number of potentially
SPC, the most commonly used third-party platform for evaluating SAN storage
Test standards (especially SPC-1 tests for random IOPS effectiveness) proposed by the
Storage Performance Council (SPC) are commonly used as a reference for measuring
SAN storage product performance in the industry. Mainstream vendors such as EMC,
NetApp, Dell, HPE, HDS, Huawei, IBM, and Fujitsu have participated in SPC tests and
used the results to promote their product performance and cost-effective features. This
makes SPC-1 a well-known indicator for measuring the performance of products from
The test specifications of SPC-1 are both strict and fair. Its test program prevents
deliberate data value manipulation and its test models are similar to mainstream
transaction workloads, meaning SPC-1 can be reliably used as a reference to reflect
performance in real-life environments.
Service type: For production services, the SPC provides the SPC-1 benchmark test guide.
For data analysis services, the SPC provides the SPC-2 benchmark test guide.
Mixed service workload: In the SPC-1 test, multiple service workloads are used for
concurrency testing to verify response times of storage systems in mixed service
scenarios. The main indicators include different data types (text, binary, and sparse),
different block sizes (8 KB to 128 KB), and different read/write ratios, such as sequential
reads and writes or random reads and writes.
SPC-1 testing model
Varying service pressure: The SPC increases and decreases dynamic workload behaviors
to test the storage performance of varying service pressure. Specifically, the SPC starts
tests from the peak value before gradually decreasing and then increasing service
pressure. The SPC then simulates two service peaks as shown in the following figure.
SPEC, the most commonly used third-party platform for evaluating NAS storage
Founded in 1988, the Standard Performance Evaluation Corporation (SPEC) is a global
and authoritative application performance testing organization, designed to formulate a
series of application performance evaluation standards. SPEC is a third-party
organization that consists of dozens of prestigious and influential universities, research
institutes, and IT enterprises.
SPEC uses the latest SPEC SFS®2014 standard performance evaluation benchmark to
test file server throughput and response times, and provides a standard measurement
method for comparing the storage performance of devices from different vendors in
specific application scenarios. This benchmark uses software to establish swbuild
scenarios and tests NAS performance when handling metadata-intensive workloads. NAS
products from multiple brands, including Huawei and NetApp, have released the
performance evaluation results obtained in this scenario.