192
EMC Symmetrix DMX-3 Product Guide
Data Integrity, Availability, and Protection
Read operations
with mirroring
During read operations, if the data is not available in global memory,
the Symmetrix system reads the data from the volume chosen for best
system performance. Performance algorithms within the Enginuity
operating environment track path busy information, as well as
actuator location, and which sector is currently under the disk head
in each device.
Symmetrix performance algorithms for read operations choose the
best volume in the mirrored pair based upon three service policies
used to balance system performance:
◆ Interleave Service Policy — Shares the read operations of the
mirrored pair by reading tracks from both disk drives in an
alternating method, a number of tracks from M1, and a number of
tracks from M2. Interleave is designed to achieve maximum
throughput.
◆ Split Service Policy — Differs from Interleave because read
operations are assigned to either the M1 or the M2 logical volume,
but not both. Split is designed to minimize head movement.
◆ Dynamic Mirror Service Policy (DMSP) — Utilizes both
Interleave and Split for maximum throughput and minimal head
movement. DMSP adjusts each logical volume dynamically based
on access patterns detected. This is the default mode within the
Enginuity operating system.
Error recovery with
mirroring
In the unlikely event that one volume in the mirrored pair fails, the
Symmetrix system automatically uses the other volume without
interruption of data availability. The Symmetrix system notifies the
host operating system of the error and EMC Customer Support
Center through the call-home feature. The EMC Product Support
Engineer (PSE) then begins the diagnostic process and, if necessary,
dispatches a Customer Engineer (CE) to the customer site. Once the
suspect disk drive is nondisruptively replaced, the Symmetrix system
reestablishes the mirrored pair and automatically resynchronizes the
data with the new disk. During the data resynchronization process,
the Symmetrix system gives priority to host I/O requests over the
copy process to minimize the impact on performance. All new writes
take place to both devices. The time it takes to resynchronize the
mirrored pair depends on the I/O activity to the volume, the disk
drive, and the disk capacity.
To Next Page
Loading...
Need help?
General
