System and method for end to end QoS solution for data storage systems
A method, computer program product, and computer system for receiving, by a computing device, an I/O request, wherein the I/O request may include host I/O priority information. It may be determined that the I/O request is associated with a token bucket of a plurality of token buckets based upon, at least in part, the host I/O priority information. If the token bucket of the plurality of token buckets has sufficient tokens for the I/O request, the I/O request may be sent down a block stack for processing, and if the token bucket of the plurality of token buckets has insufficient tokens for the I/O request, the I/O request may be rejected.
1. A computer-implemented method comprising:
receiving, by a computing device, an I/O request, wherein the I/O request includes host I/O priority information;
determining that the I/O request is associated with a token bucket of a plurality of token buckets based upon, at least in part, the host I/O priority information; and
if the token bucket of the plurality of token buckets has sufficient tokens for the I/O request:
sending the I/O request down a block stack for processing, wherein sending the I/O request down the block stack for processing includes placing the I/O into a priority queue of a plurality of priority queues in a multi-core cache portion of the block stack, wherein the priority queue is weighted based upon the host I/O priority information of the I/O request, and
sending the I/O request for placement into a second priority queue of a second plurality of priority queues in a multi-core RAID portion of the block stack, wherein the second priority queue is weighted based upon the host I/O priority information of the I/O request; and
if the token bucket of the plurality of token buckets has insufficient tokens for the I/O request, rejecting the I/O request.
2. The computer-implemented method of claim 1 wherein the priority information is sent from host side.
3. The computer-implemented method of claim 1 wherein the priority information is encapsulated into a common protocol driver structure.
4. The computer-implemented method of claim 1 further comprising adding a token to each token bucket of the plurality of token buckets at a different rate, wherein the different rate is based upon, at least in part, a respective priority level assigned to the plurality of token buckets.
5. A computer program product residing on a non-transitory computer readable storage medium having a plurality of instructions stored thereon which, when executed across one or more processors, causes at least a portion of the one or more processors to perform operations comprising:
receiving an I/O request, wherein the I/O request includes host I/O priority information;
determining that the I/O request is associated with a token bucket of a plurality of token buckets based upon, at least in part, the host I/O priority information; and
if the token bucket of the plurality of token buckets has sufficient tokens for the I/O request;
sending the I/O request down a block stack for processing, wherein sending the I/O request down the block stack for processing includes placing the I/O into a priority queue of a plurality of priority queues in a multi-core cache portion of the block stack, wherein the priority queue is weighted based upon the host I/O priority information of the I/O request, and
sending the I/O request for placement into a second priority queue of a second plurality of priority queues in a multi-core RAID portion of the block stack, wherein the second priority queue is weighted based upon the host I/O priority information of the I/O request; and
if the token bucket of the plurality of token buckets has insufficient tokens for the I/O request, rejecting the I/O request.
6. The computer program product of claim 5 wherein the priority information is sent from host side.
7. The computer program product of claim 5 wherein the priority information is encapsulated into a common protocol driver structure.
8. The computer program product of claim 5 wherein the operations further comprise adding a token to each token bucket of the plurality of token buckets at a different rate, wherein the different rate is based upon, at least in part, a respective priority level assigned to the plurality of token buckets.
9. A computing system including one or more processors and one or more memories configured to perform operations comprising:
receiving an I/O request, wherein the I/O request includes host I/O priority information;
determining that the I/O request is associated with a token bucket of a plurality of token buckets based upon, at least in part, the host I/O priority information; and
if the token bucket of the plurality of token buckets has sufficient tokens for the I/O request;
sending the I/O request down a block stack for processing, wherein sending the I/O request down the block stack for processing includes placing the I/O into a priority queue of a plurality of priority queues in a multi-core cache portion of the block stack, wherein the priority queue is weighted based upon the host I/O priority information of the I/O request, and
sending the I/O request for placement into a second priority queue of a second plurality of priority queues in a multi-core RAID portion of the block stack, wherein the second priority queue is weighted based upon the host I/O priority information of the I/O request; and
if the token bucket of the plurality of token buckets has insufficient tokens for the I/O request, rejecting the I/O request.
10. The computing system of claim 9 wherein the priority information is sent from host side.
11. The computing system of claim 9 wherein the priority information is encapsulated into a common protocol driver structure.
12. The computing system of claim 9 wherein the operations further comprise adding a token to each token bucket of the plurality of token buckets at a different rate, wherein the different rate is based upon, at least in part, a respective priority level assigned to the plurality of token buckets.